WO2020075771A1

WO2020075771A1 - Planning device, planning method, and planning program

Info

Publication number: WO2020075771A1
Application number: PCT/JP2019/039878
Authority: WO
Inventors: 豪秀奈木野
Original assignee: 旭化成株式会社
Priority date: 2018-10-12
Filing date: 2019-10-09
Publication date: 2020-04-16
Also published as: JPWO2020075771A1; JP7157815B2

Abstract

When hydrogen is frequently transported to hydrogen stations to prevent shortages of hydrogen at the hydrogen stations, hydrogen supply costs may increase. Provided is a planning device that comprises: an operation prediction part that uses an operation prediction model to generate an operation prediction for each of a plurality of hydrogen generation devices that generate hydrogen; a demand prediction part that uses a demand prediction model to generate a hydrogen demand prediction for each of a plurality of hydrogen stations; and a transport planning part that, on the basis of transport planning factors that include the operation predictions for the plurality of hydrogen generation devices and the demand predictions for the plurality of hydrogen stations, uses a transport planning model to generate a transport plan for transporting hydrogen that has been generated by the plurality of hydrogen generation devices to the plurality of hydrogen stations.

Description

Planning device, planning method, and planning program

The present invention relates to a planning device, a planning method, and a planning program.

Conventionally, hydrogen generators that generate hydrogen by electrolyzing water have been known. The hydrogen generated by the hydrogen generator is transported to a plurality of hydrogen stations and consumed.

Issues to be solved

-If hydrogen is frequently transported to the hydrogen station so that the hydrogen station does not run short of hydrogen, the hydrogen supply cost may increase.

General disclosure

In order to solve the above problems, a planning device is provided in the first aspect of the present invention. The planning device may include an operation prediction unit that generates an operation prediction of each of the plurality of hydrogen generation devices that generate hydrogen using an operation prediction model. The planning device may include a demand prediction unit that generates a hydrogen demand forecast at each of the plurality of hydrogen stations using a demand forecast model. The planning device uses the transportation planning model to make a transportation plan for transporting the hydrogen generated by the multiple hydrogen generators to the multiple hydrogen stations, using the transportation planning model to predict the operation of each of the multiple hydrogen generators and each of the multiple hydrogen stations. A transportation planning unit that generates the transportation planning factor based on the transportation planning factor may be included.

Further, the planning device may include a power generation amount prediction unit that generates a power generation amount prediction of renewable energy for each of a plurality of renewable energy power generation facilities using a power generation amount prediction model. The operation prediction unit may generate the operation prediction of each of the plurality of hydrogen generators that use renewable energy, based on the power generation amount prediction of each of the plurality of renewable energy power generation facilities. The planning device may further include an electricity price prediction unit that generates an electricity price prediction of the renewable energy using the electricity price prediction model. The operation prediction unit may generate the operation prediction of each of the plurality of hydrogen generators based on the operation prediction factors including the electricity rate prediction. The electricity rate prediction model is at least one of electricity rate, power demand, power supply, renewable energy power generation, weather information, and power generation prediction of renewable energy by the power generation prediction unit before the prediction target period. The electricity price forecast of the renewable energy may be calculated based on the electricity rate prediction factors including one. The planning apparatus may include an electricity price prediction model updating unit that updates the electricity price prediction model by learning using the actual value of the electricity price. The operation prediction factor is the operation amount of the plurality of hydrogen generators, the storage amount of hydrogen in the plurality of hydrogen storage devices that store hydrogen generated by the plurality of hydrogen generation devices, and the plurality of hydrogen storage devices before the prediction target period. At least one of the hydrogen transportation amount, the hydrogen demand amount at each of the plurality of hydrogen stations, and the electricity price forecast for the forecast period. The planning device may include an operation prediction model updating unit that updates the operation prediction model by learning using the actual values of the operation amounts of the plurality of hydrogen generation devices.

Also, the planning device may include a consumption prediction unit that generates a hydrogen consumption prediction at each of a plurality of hydrogen stations using a consumption prediction model. The demand forecasting unit may forecast hydrogen demand at each of the plurality of hydrogen stations based on a demand forecast factor including a hydrogen consumption forecast at each hydrogen station. The consumption forecast model is supplied from each of the plurality of hydrogen stations, the demand amount of hydrogen at each of the plurality of hydrogen stations, the hydrogen consumption at each of the plurality of hydrogen stations, the weather information, and the plurality of hydrogen stations before the forecast period. The hydrogen consumption prediction of the plurality of hydrogen stations during the prediction target period may be calculated based on the consumption prediction factor that further includes at least one of the factors related to the hydrogen usage amount of the service provided using hydrogen. The planning apparatus may include a consumption prediction model updating unit that updates the consumption prediction model by learning using the actual value of the amount of hydrogen consumed at each of the plurality of hydrogen stations. The demand forecasting model is based on a demand forecasting factor further including at least one of hydrogen demand at each of the plurality of hydrogen stations and hydrogen consumption at each of the plurality of hydrogen stations before the forecast period. A hydrogen demand forecast may be calculated for each of the plurality of hydrogen stations during the forecast period. The planning device may further include a demand prediction model updating unit that updates the demand prediction model by learning using the actual value of the demanded amount of hydrogen at each of the plurality of hydrogen stations.

In addition, the planning device may include a storage amount prediction unit that generates a storage amount prediction of hydrogen in each of the plurality of hydrogen storage devices that stores hydrogen generated by the plurality of hydrogen generation devices, using a storage amount prediction model. . The transportation planning unit uses a transportation planning model to predict a hydrogen storage amount in each of the plurality of hydrogen storage devices and each of the plurality of hydrogen storage devices by using the transportation planning model. It may be generated based on the transportation planning factors that are further included. The storage amount prediction model is a storage amount of hydrogen of the plurality of hydrogen storage devices in the prediction target period, the operating amount of the plurality of hydrogen generators before the prediction target period, the storage amount of hydrogen in the plurality of hydrogen storage device, May be predicted based on a storage amount prediction factor including at least one of the transport amount of hydrogen from the hydrogen storage device, the demand amount of hydrogen at each of the plurality of hydrogen stations, and the operation prediction of the plurality of hydrogen generation devices. The planning device may include a storage amount prediction model updating unit that updates the storage amount prediction model by learning using the actual values of the hydrogen storage amounts of the plurality of hydrogen storage devices. The transportation planning factor is at least the operating amount of each of the plurality of hydrogen generators, the storage amount of hydrogen in each of the plurality of hydrogen storage devices, and the demand amount of hydrogen in each of the plurality of hydrogen stations before the prediction target period. May include one.

In addition, the planning device includes a plurality of hydrogen generators, a plurality of hydrogen storage devices, a transportation means between each of the plurality of hydrogen storage devices and each of the plurality of hydrogen stations, and a production of a cooperation system including the plurality of hydrogen stations. A transportation plan model updating unit that updates the transportation plan model by learning based on an evaluation index that evaluates the property may be provided. The evaluation index may be based on at least one of operating costs, sales, and profits of the cooperation system, and cost per unit amount of hydrogen supplied by the cooperation system. The planning device uses the transportation prediction model based on the transportation prediction factor including at least one of the operation prediction of each of the plurality of hydrogen generators and the hydrogen demand prediction of each of the plurality of hydrogen stations to use the transportation prediction model. A transport predictor may be provided that generates a transport forecast that is a forecast of a transport plan for transporting hydrogen between the device and the plurality of hydrogen stations. The planning device uses the operation planning model to generate an operation plan for each of the plurality of hydrogen generators based on the operation planning factors including the hydrogen transport prediction between the plurality of hydrogen generators and the plurality of hydrogen stations. An operation planning unit may be provided. The planning apparatus may include an operation plan model updating unit that updates the operation plan model by learning based on the evaluation index.

In addition, the planning device uses the storage planning model to calculate the hydrogen storage plan in each of the plurality of hydrogen storage devices that store hydrogen generated by the plurality of hydrogen generation devices, using the storage planning model. A storage planning unit may be provided that generates based on a storage planning factor including an operation prediction of the apparatus and a hydrogen transportation prediction between the plurality of hydrogen generation apparatuses and the plurality of hydrogen stations. The planning apparatus may further include a storage plan model updating unit that updates the storage plan model by learning based on the evaluation index.

In the second aspect of the present invention, a planning device is provided. The planning device may include a demand prediction unit that generates a hydrogen demand forecast at each of the plurality of hydrogen stations using a demand forecast model. The planning device uses the transport prediction model based on the transport prediction factor including the hydrogen demand forecast at each of the multiple hydrogen stations to generate hydrogen between the multiple hydrogen generators that generate hydrogen and between the multiple hydrogen stations. A transportation prediction unit that generates a transportation prediction that is a prediction of a transportation plan to be transported may be provided. The planning device uses the operation planning model to generate an operation plan for each of the plurality of hydrogen generators based on the operation planning factors including the hydrogen transport prediction between the plurality of hydrogen generators and the plurality of hydrogen stations. An operation planning unit may be provided.

In the third aspect of the present invention, a planning method is provided. The planning method may include a step of generating an operation prediction of each of the plurality of hydrogen generation devices that generate hydrogen using an operation prediction model. The planning method may include the step of generating a demand forecast of hydrogen at each of the plurality of hydrogen stations using a demand forecast model. The planning method is to use a transportation planning model to create a transportation plan for transporting hydrogen generated by multiple hydrogen generators to multiple hydrogen stations. May be generated based on transportation planning factors including the demand forecast of

In the fourth aspect of the present invention, a planning program is provided. The planning program is executed by a computer and causes the computer to function as an operation prediction unit that generates an operation prediction of each of a plurality of hydrogen generation devices that generate hydrogen using an operation prediction model. The planning program is executed by a computer and causes the computer to function as a demand prediction unit that generates a hydrogen demand forecast at each of a plurality of hydrogen stations using a demand forecast model. The planning program is executed by the computer, and the transportation plan for transporting the hydrogen generated by the plurality of hydrogen generators to the plurality of hydrogen stations is used by the computer to operate each of the plurality of hydrogen generators. It functions as a transportation planning unit that generates based on transportation planning factors including forecasts and demand forecasts for each of a plurality of hydrogen stations.

In the fifth aspect of the present invention, a planning method is provided. The planning method may include the step of generating a demand forecast of hydrogen at each of the plurality of hydrogen stations using a demand forecast model. The planning method uses a transport prediction model based on a transport prediction factor including a hydrogen demand forecast at each of the plurality of hydrogen stations to generate hydrogen between the plurality of hydrogen generators that generate hydrogen and the plurality of hydrogen stations. The method may include generating a transportation forecast that is a forecast of a transportation plan to transport. The planning method uses an operation plan model to generate an operation plan for each of the plurality of hydrogen generators based on an operation plan factor including transportation prediction of hydrogen between the plurality of hydrogen generators and the plurality of hydrogen stations. Stages may be provided.

In the sixth aspect of the present invention, a planning program is provided. The planning program is executed by a computer and causes the computer to function as a demand prediction unit that generates a hydrogen demand forecast at each of a plurality of hydrogen stations using a demand forecast model. The planning program is executed by a computer, and the computer is configured to generate a plurality of hydrogen generators and a plurality of hydrogen generators that generate hydrogen by using a transportation prediction model based on a transportation prediction factor including a hydrogen demand prediction at each of the plurality of hydrogen stations. It functions as a transport prediction unit that generates a transport forecast that is a forecast of a transport plan for transporting hydrogen between the hydrogen stations of the above. The planning program is executed by a computer, and the computer uses the operation planning model based on the operation planning factors including the hydrogen transportation prediction between the plurality of hydrogen generating apparatuses and the plurality of hydrogen stations. It functions as an operation planning unit that generates each operation plan of each.

The summary of the invention described above does not enumerate all necessary features of the invention. Further, a sub-combination of these feature groups can also be an invention.

1 shows a system 10 according to this embodiment. The structural example of the planning apparatus 70 which concerns on this embodiment is shown. The detailed structural example of the prediction part 120 of the planning device 70 of this embodiment is shown. The detailed structural example of the planning part 130 of the planning device 70 of this embodiment is shown. An example of the flow of the planning device 70 according to the present embodiment is shown. 1 illustrates an example computer 1900 in which aspects of the present embodiment may be embodied in whole or in part.

Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. In addition, not all of the combinations of features described in the embodiments are essential to the solving means of the invention.

FIG. 1 shows a system 10 according to this embodiment. The system 10 produces | generates the plan for satisfying the demand of the hydrogen station 60, and supplies the hydrogen produced | generated by the hydrogen generator to the hydrogen station according to the said plan. The system 10 includes a plurality of renewable energy power generation facilities 20, a plurality of hydrogen generators 30, a plurality of hydrogen storage devices 40, a plurality of transportation means 50, a plurality of hydrogen stations 60, and a planning device 70. .

The plurality of renewable energy power generation facilities 20 are respectively connected to the hydrogen generation device 30 via the power transmission grid of the electric power system 80 or not. For example, the renewable energy

power generation facilities

20a and 20b are connected to the

hydrogen generators

30a and 30b, respectively, without passing through the power grid, and the renewable energy

power generation facilities

20c and 20d are connected to the hydrogen via the power grid of the power grid 80. The

generators

30c and 30d are respectively connected. The plurality of renewable energy power generation facilities 20 are facilities that generate electricity using renewable energy such as wind power, sunlight, heat, geothermal power, hydraulic power, and / or biomass. The plurality of renewable energy power generation facilities 20 supply generated power to the hydrogen generation device 30 at the connection destination. Further, the plurality of renewable energy power generation facilities 20 may sell the generated power to the power grid 80.

Here, the electric power system 80 supplies electric power to a large number of consumers via a power transmission network from, for example, one or a plurality of power plants that perform nuclear power generation, thermal power generation, and / or power generation using renewable energy. System. In the electric power system 80, for example, depending on the amount of power generation and the amount of demand, the electricity charge (for example, the power sale charge and the power purchase charge) can change every predetermined time, every day, every month, or the like.

The plurality of hydrogen generators 30 are connected to the hydrogen storage device 40, respectively. The hydrogen generator 30 is, for example, a device that generates hydrogen by electrolysis using electric energy. The hydrogen generator 30 may operate according to the plan generated by the planning device 70. The hydrogen generator 30 operates by being supplied with power from the renewable energy power generation facility 20 and / or the power grid 80.

The plurality of hydrogen storage devices 40 may be, for example, tanks that store hydrogen generated by the hydrogen generation device 30. The hydrogen storage device 40d may be directly connected to the hydrogen station 60 and supply the stored hydrogen to the hydrogen station 60 via a pipe or the like. In addition, the plurality of hydrogen storage devices 40 may be connected to one hydrogen generation device 30.

The plurality of transportation means 50 are, for example, a trailer that stores and carries compressed hydrogen in a tank or the like, and a vehicle that pulls the trailer. The plurality of transportation means 50 transports hydrogen between each of the plurality of hydrogen storage devices 40 and each of the plurality of hydrogen stations 60.

The plurality of hydrogen stations 60 is, for example, a facility that supplies hydrogen to a consumption means 90 such as a fuel cell vehicle that consumes hydrogen as fuel. The hydrogen station 60 may have a storage facility for compressing and storing the hydrogen transported by the transportation means 50.

The planning device 70 includes at least one of the plurality of renewable energy power generation facilities 20, the plurality of hydrogen generators 30, the plurality of hydrogen storage devices 40, the plurality of transportation means 50, and the plurality of hydrogen stations 60, or at least one of the at least one. It may be connected to a management device or the like owned by the business operator. The planning device 70 generates and outputs a plan for operating a plurality of devices in the system 10 in cooperation.

The planning device 70 may be a computer such as a personal computer, a tablet computer, a smartphone, a workstation, a server computer, or a general-purpose computer, or may be a computer system in which a plurality of computers are connected. The planning device 70 may generate a plan or the like by processing in a CPU, a GPU (Graphics Processing Unit), and / or a TPU (Tensor Processing Unit) of a computer. Further, the planning device 70 may perform various processes on the cloud provided by the server computer.

FIG. 2 shows a configuration example of the planning device 70 according to this embodiment. The planning device 70 includes an acquisition unit 100, a storage unit 110, a prediction unit 120, a planning unit 130, and an output unit 140.

Here, one or more management devices 150 in FIG. 2 are connected to the planning device 70 via a network or the like. The one or more management devices 150 include at least one of the plurality of renewable energy power generation facilities 20, the plurality of hydrogen generators 30, the plurality of hydrogen storage devices 40, the plurality of transportation means 50, and the plurality of hydrogen stations 60. It may be a device or a device owned by the at least one business operator. The one or more management devices 150 are at least one of the plurality of renewable energy power generation facilities 20, the plurality of hydrogen generators 30, the plurality of hydrogen storage devices 40, the plurality of transportation means 50, and the plurality of hydrogen stations 60. Various data may be acquired from the above and supplied to the planning apparatus 70. One or a plurality of management apparatuses 150 may supply the data input by the user of the management apparatus 150 to the planning apparatus 70. The one or more management devices 150 may control the devices in the system 10 according to the plan received from the planning device 70. The one or more management apparatuses 150 may display the plan or the like received from the planning apparatus 70.

The acquisition unit 100 may be connected to the management device 150 and the storage unit 110, and may acquire data used for learning from the management device 150. The acquisition unit 100 may acquire and update the information for each predetermined period. The acquisition unit 100 may acquire the information at almost the same or different periods and add or update the information, respectively, depending on the information to be acquired. Further, the acquisition unit 100 may be connected to a network or the like and acquire data via the network. When at least a part of the data to be acquired is stored in an external database or the like, the acquisition unit 100 may access the database or the like and acquire the data. The acquisition unit 100 supplies the acquired data to the storage unit 110.

The storage unit 110 is connected to the prediction unit 120 and the planning unit 130, and stores the data acquired by the acquisition unit 100. The storage unit 110 may store data processed by the planning device 70. The storage unit 110 may store intermediate data, calculation results, parameters, and the like that are calculated or used by the planning apparatus 70 in the process of generating a plan. In addition, the storage unit 110 may supply the stored data to the request source in response to a request from each component in the planning device 70.

The prediction unit 120 is connected to the planning unit 130, and generates a prediction result including at least one of an operation prediction, a demand prediction, a consumption prediction, a power generation amount prediction, an electricity price prediction, a storage amount prediction, and a transportation prediction. The prediction unit 120 generates one or a plurality of learning models, learns and updates the learning model, and generates a prediction result based on the updated learning model. The prediction unit 120 supplies the prediction result to the storage unit 110 or the planning unit 130.

Here, the operation prediction is the operation amount of each of the plurality of hydrogen generation devices 30 that generate hydrogen in the future prediction period (for example, the operation rate of the hydrogen generation device 30, the operation period, the cumulative hydrogen generation amount, or the unit). The amount of hydrogen produced per hour) may be included. The demand forecast may include at least one of the cumulative demand of hydrogen at each of the plurality of hydrogen stations 60 and the demand of hydrogen for each hour, day, or month in the future forecast period. The consumption prediction may include at least one of a cumulative hydrogen consumption amount in each of the plurality of hydrogen stations 60 and a hydrogen consumption amount per hour, day, or month in a future prediction period.

Here, the demand amount is, for example, a required amount of hydrogen in the hydrogen station 60, and a predetermined buffer amount is supplied to the consuming means 90 so that the hydrogen storage amount in the hydrogen station 60 does not become zero. It may be the amount of hydrogen added to the amount. Further, the consumption amount may be the supply amount of hydrogen to the consumption means 90 in the hydrogen station 60.

The power generation amount prediction includes at least one of the cumulative amount of power generation of renewable energy and the amount of power generation of each hour, day, or month for each of the plurality of renewable energy power generation facilities 20 in the prediction period. Good. The electricity price forecast is a renewable energy that is supplied from the renewable energy power generation facility 20 to the hydrogen generator 30 through the power transmission grid of the power grid 80 or directly without the grid during the prediction period. It may include the electricity rate (power selling rate or power purchasing rate) of the power generated by. In addition, when the electric power system 80 purchases the electric power from the renewable energy power generation facility 20, the charge for the electric power to be purchased by the hydrogen generator 30 via the power transmission network of the electric power system 80 is renewable. It may be included in the electricity bill for energy.

The storage amount prediction indicates the storage amount of hydrogen (for example, the ratio of the storage amount to the maximum possible storage amount) in each of the plurality of hydrogen storage devices 40 that stores the hydrogen generated by the plurality of hydrogen generation devices 30 in the prediction period. May be included. The transportation forecast is a forecast of a transportation plan for transporting hydrogen between the plurality of hydrogen generators 30 and the plurality of hydrogen stations 60 in the prediction period.

The planning unit 130 is connected to the output unit 140 and generates planning data including at least one of a transportation plan, an operation plan, and a storage plan. The planning unit 130 generates one or a plurality of learning models, learns and updates the learning model, and generates planning data based on the updated learning model. The planning unit 130 supplies the generated planning data to the storage unit 110 and the output unit 140.

Here, the transportation plan includes a transportation route of each transportation means 50, a transportation distance of each transportation means 50, and a transportation distance of each transportation means 50 between the plurality of hydrogen generators 30 and the plurality of hydrogen stations 60 in the planning period. A plan may be included that specifies at least one of a transportation time, a transportation cost for each transportation means 50, a number of transportation means 50, and a type of each transportation means 50. The operation plan may include a plan that specifies at least one of the operation rate, the hydrogen generation amount, the operation period, and the operation time zone of each of the plurality of hydrogen generation devices 30 in the plan target period. The storage plan is a time-dependent change in the storage amount of hydrogen in each of the plurality of hydrogen storage devices 40 that store hydrogen generated by the plurality of hydrogen generation devices 30, the minimum storage amount of hydrogen, and the maximum storage amount of hydrogen in the planning period. A plan may be included that specifies at least one of the reserves.

The output unit 140 is connected to the management device 150 and outputs plan data to the management device 150.

According to the planning device 70 of the present embodiment described above, it is possible to reduce the supply cost by generating an appropriate plan based on the model updated by learning and supplying hydrogen according to the plan.

FIG. 3 shows a detailed configuration example of the prediction unit 120 of the planning device 70 of this embodiment. The prediction unit 120 includes an operation prediction model generation unit 200, an operation prediction model update unit 210, and an operation prediction unit 220, and generates the operation prediction of each of the hydrogen generation devices 30 that generate hydrogen. The prediction unit 120 includes a demand prediction model generation unit 230, a demand prediction model update unit 240, and a demand prediction unit 250, and generates a hydrogen demand prediction at each of the plurality of hydrogen stations 60. The prediction unit 120 includes a power generation prediction model generation unit 260, a power generation prediction model update unit 270, and a power generation prediction unit 280, and generates renewable energy for each of the plurality of renewable energy power generation facilities 20. Generate a quantity forecast.

The prediction unit 120 includes an electricity price prediction model generation unit 290, an electricity price prediction model update unit 300, and an electricity price prediction unit 310, and generates an electricity price prediction of renewable energy. The prediction unit 120 includes a consumption prediction model generation unit 320, a consumption prediction model update unit 330, and a consumption prediction unit 340, and generates a hydrogen consumption prediction at each of the plurality of hydrogen stations 60. The prediction unit 120 includes a storage amount prediction model generation unit 350, a storage amount prediction model update unit 360, and a storage amount prediction unit 370, and stores a plurality of hydrogen storage units that store the hydrogen generated by the plurality of hydrogen generation devices 30. Generate hydrogen storage forecasts in each of the devices 40. The prediction unit 120 includes a transportation prediction model generation unit 380, a transportation prediction model update unit 390, and a transportation prediction unit 400, and transports hydrogen between the plurality of hydrogen generation devices 30 and the plurality of hydrogen stations 60. Generate transport forecasts, which are forecasts for the plan.

Here, the storage unit 110 stores prediction factors including an operation prediction factor, a demand prediction factor, a power generation amount prediction factor, an electricity rate prediction factor, a consumption prediction factor, a storage amount prediction factor, and a transportation prediction factor.

The operation prediction factor may include information on the operation of the hydrogen generator 30. The operation prediction factor is the operation amount of the plurality of hydrogen generation devices 30, the storage amount of hydrogen in the plurality of hydrogen storage devices 40 that stores the hydrogen generated by the plurality of hydrogen generation devices 30, and the plurality of hydrogens before the prediction target period. At least one of the transportation amount of hydrogen from the storage device 40, the demand amount of hydrogen at each of the plurality of hydrogen stations 60, the demand forecast for the prediction target period, and the electricity charge forecast for the prediction target period may be included. The operation predicting factor includes the power generation amount of the renewable energy power generation facility 20 connected to the hydrogen generator 30 and the hydrogen generation efficiency of the hydrogen generator 30 (for example, per unit power or per unit time) before the prediction target period. At least one of the generation amount of hydrogen) and the power generation amount prediction in the prediction target period of the renewable energy power generation facility 20 connected to the hydrogen generation device 30 may be further included. Further, the operation prediction factor may include virtual data calculated from the physical model of the hydrogen generator 30.

The demand forecasting factor may include information about the demanded amount of hydrogen at the hydrogen station 60. The demand prediction factor is at least the hydrogen consumption amount at each hydrogen station 60, the hydrogen demand amount at each of the plurality of hydrogen stations 60, and the hydrogen consumption forecast at each of the plurality of hydrogen stations 60 before the prediction target period. May include one. The demand forecasting factor is the number of consumption means 90 using the hydrogen station 60 before the forecast target period, weather information (for example, weather information before the forecast target period, or weather forecast for the forecast target period), and operation. It may further include at least one of the operation predictions of the prediction target period by the prediction unit 220. The weather information may include at least one of wind speed, wind direction, sunny, rain, temperature, wave height, sunshine duration, and the like.

The power generation amount prediction factor may include information on the power generation amount of the renewable energy power generation facility 20. The power generation amount prediction factor is the power generation amount (for example, power generation efficiency) of each renewable energy power generation facility 20, the power supply amount of each renewable energy power generation facility 20, and each renewable energy power generation facility 20 before the prediction target period. May include at least one of the amount of electric power purchased or the amount of electric power sold, and the selling price or purchasing price of each renewable energy power generation facility 20. The power generation amount prediction factor is the type of the renewable energy power generation facility 20 (for example, the type of renewable energy used for power generation), weather information (for example, weather information before the prediction target period, or weather prediction for the prediction target period). ), And at least one of the usage periods of the renewable energy power generation facility 20. Further, the power generation amount prediction factor may include virtual data calculated from the physical model of the renewable energy power generation facility 20.

The electricity price prediction factor may include information related to the electricity price when the hydrogen generator 30 purchases electricity. The electricity rate predictor is an electricity rate, a power demand, a power supply, a renewable energy generation amount, weather information (for example, weather information before the forecast period, or weather in the forecast period before the forecast period). Prediction), and at least one of the power generation amount prediction of the renewable energy in the prediction target period by the power generation amount prediction unit 280.

The consumption predictor may include information regarding the consumption of hydrogen at the hydrogen station 60. The consumption prediction factor is a hydrogen demand amount at each of the plurality of hydrogen stations 60 before the prediction target period, a hydrogen consumption amount at each of the plurality of hydrogen stations 60, and weather information (for example, the weather before the prediction target period). Information, or weather forecast for the forecast target period), and at least one of the factors related to the hydrogen usage amount of the service provided by using the hydrogen supplied from each of the plurality of hydrogen stations 60. Factors relating to the amount of hydrogen used for the services provided by using the hydrogen supplied from each of the plurality of hydrogen stations 60 include, for example, operation information of the fuel cell bus, which is the consuming means 90, and each of the plurality of hydrogen stations 60. It may include at least one of the number of consuming means 90 to be used and the supply amount of hydrogen to each consuming means 90 in the hydrogen station 60.

The storage amount prediction factor may include information about the storage amount of hydrogen in the hydrogen storage device 40. The storage amount prediction factor includes the operating amount of the plurality of hydrogen generation devices 30, the storage amount of hydrogen in the plurality of hydrogen storage devices 40, the transport amount of hydrogen from the plurality of hydrogen storage devices 40, and At least one of the demanded amount of hydrogen in each of the hydrogen stations 60 and the operation prediction of the plurality of hydrogen generators 30 during the prediction target period may be included. The storage amount prediction factor is at least one of the transportable amount of hydrogen in each transportation means 50, the number of times hydrogen is supplied from the hydrogen storage device 40 to the transportation means 50, and the hydrogen supply date and time from the hydrogen storage device 40 to the transportation means 50. May be included.

The transportation predictor may include information on transportation of hydrogen between the plurality of hydrogen generators 30 and the plurality of hydrogen stations 60. The transportation prediction factor may include at least one of an operation prediction of each of the plurality of hydrogen generators 30 and a hydrogen demand prediction of each of the plurality of hydrogen stations 60. The transportation prediction factor is the date and time of hydrogen supply to the hydrogen station 60 by the transportation means 50 before the prediction target period, the number of times of hydrogen supply to the hydrogen station 60 by the transportation means 50, the number of transportation means 50, the type of each transportation means 50, At least one of the transportable amount of hydrogen of each transportation means 50, the transportation cost of each transportation means 50, the transportation time of each transportation means 50, the available time zone of the plurality of transportation means 50, and the arrangement of the plurality of transportation means 50. May include one.

At least one of the operation forecasting factor, the demand forecasting factor, the power generation forecasting factor, the electricity price forecasting factor, the consumption forecasting factor, the storage amount forecasting factor, and the transport forecasting factor may be time-series information at approximately fixed time intervals. At least one of the operation predictor, the demand predictor, the power generation predictor, the electricity rate predictor, the consumption predictor, the storage predictor, and the transport predictor may be added or updated over time. At least one of the operation predicting factor, the demand predicting factor, the power generation predicting factor, the electricity rate predicting factor, the consumption predicting factor, the storage predicting factor, and the transport predicting factor are prediction results generated by the planning device 70, and plan data. May be further included. Further, at least one of the operation predicting factor, the demand predicting factor, the power generation predicting factor, the electricity rate predicting factor, the consumption predicting factor, the storage predicting factor, and the transport predicting factor is supplied from an external database or the management device 150. The information acquired by the acquisition unit 100 may be included.

The operation prediction model generation unit 200 is connected to the storage unit 110 and the operation prediction model update unit 210. The operation prediction model generation unit 200 generates an operation prediction model that generates an operation prediction of the hydrogen generator 30 based on the operation prediction factor. The operation prediction model generation unit 200 may generate an operation prediction model by a process called pre-learning or off-line learning using information past the prediction target period.

The operation prediction model generation unit 200 generates an operation prediction model using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, and hidden Markov model. If, for example, a model having LSTM (Long short-term memory), RNN (Recurrent Neural Network), and other memory is used as the operation prediction model, the operation of the hydrogen generator 30 is predicted from the time series of factors. You can also do it. The operation prediction model generation unit 200 supplies the generated operation prediction model to the operation prediction model update unit 210.

The operation prediction model updating unit 210 is connected to the storage unit 110 and the operation prediction unit 220. The operation prediction model updating unit 210 updates the operation prediction model by learning using learning data including the actual values of the operation amounts of the plurality of hydrogen generation devices 30. The operation prediction model updating unit 210 may update to a new operation prediction model by learning, for example, at each predetermined update period. Instead of this, the operation prediction model updating unit 210 sets the operation prediction model according to various conditions such as learning a predetermined number of times, or an error difference due to learning falling below a predetermined threshold value. You may update.

The operation prediction model updating unit 210 may learn the operation prediction model by a process called adaptive learning or online learning. The operation prediction model updating unit 210 learns the operation prediction model by executing reinforcement learning using an arbitrary machine learning model as an identification model, for example. By performing such machine learning, the operation prediction model updating unit 210 predicts the operation amount and the like of the hydrogen generator 30 according to the operation prediction factor with the accuracy according to the model to which the operation prediction factor is input. You will be able to.

It is desirable that the operation prediction model updating unit 210 learn by further using information that is later in time than the information of the operation prediction factor used by the operation prediction model generation unit 200 to generate the operation prediction model. The operation prediction model updating unit 210 may update the operation prediction model by learning, for example, based on the value of the operation prediction factor in the past period and the actual value of the operation amount of the hydrogen generator 30 after the past period. The operation prediction model updating unit 210 learns the operation prediction model using the information of the operation prediction factors updated by the actual operation of the hydrogen generator 30. The operation prediction model updating unit 210 may perform learning of the operation prediction model in response to the update of the operation prediction factor information. The operation prediction model update unit 210 may execute learning one or more times during the update period. The operation prediction model updating unit 210 supplies the updated operation prediction model to the operation prediction unit 220.

The operation prediction unit 220 is connected to the storage unit 110. The operation prediction unit 220 generates an operation prediction of each of the hydrogen generation devices 30 that generate hydrogen using an operation prediction model. The operation prediction unit 220 may generate an operation prediction of each of the plurality of hydrogen generation devices 30 that use renewable energy, based on each power generation amount prediction of each of the plurality of renewable energy power generation facilities 20.

Here, the hydrogen generator 30, which uses renewable energy, is connected to the renewable energy power generation facility 20 via a power transmission network of the power system 80, and is supplied with power via the power transmission network, for example. Alternatively, the hydrogen generation device 30 may be directly connected to the renewable energy power generation facility 20 without a power grid of the power system 80 and supplied with power from the renewable energy power generation facility 20.

Further, the operation prediction unit 220 may generate the operation prediction of each of the plurality of hydrogen generation devices 30 based on the operation prediction factors including the electricity price prediction. The operation prediction unit 220 can generate a highly accurate operation prediction for the hydrogen generator 30 that operates according to the fluctuating electricity rate by using the electricity rate prediction for the estimation.

The operation prediction unit 220 predicts the operation of the hydrogen generation device 30 in the predetermined period in the future, for example, for each predetermined period. The operation prediction unit 220 may predict the operation amount of the hydrogen generator 30 using the operation prediction model and the information of the operation prediction factor. The operation prediction unit 220 predicts the operation of the hydrogen generator 30, for example, by applying the information of the operation prediction factor in the period immediately before the period to be predicted to the operation prediction model. The operation prediction unit 220 supplies the prediction result to the storage unit 110, and stores it as at least one of a transportation prediction factor, a storage amount prediction factor, a transportation planning factor, and a storage planning factor, for example. In addition, the operation prediction unit 220 may directly supply the prediction result to another configuration of the prediction unit 120 or the planning unit 130.

The demand forecast model generation unit 230 is connected to the storage unit 110 and the demand forecast model update unit 240. The demand prediction model generation unit 230 generates a demand prediction model that generates a hydrogen demand prediction at the hydrogen station 60 based on the demand prediction factor. The demand forecasting model is based on a demand forecasting factor including at least one of the demanded amount of hydrogen in each of the plurality of hydrogen stations 60 and the consumed amount of hydrogen in each of the plurality of hydrogen stations 60 before the forecast period. The model may be a model for calculating the demand forecast of hydrogen for each of the plurality of hydrogen stations 60 in the prediction target period.

The demand prediction model generation unit 230 may generate a demand prediction model by a process called pre-learning or offline learning using information past the prediction target period. The demand prediction model generation unit 230 generates a demand prediction model by using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, hidden Markov model, or the like. Further, for example, if a model having memory such as LSTM, RNN, and the like is used as the demand prediction model, the demand amount of hydrogen at the hydrogen station 60 can be predicted from the time series of factors. The demand forecast model generation unit 230 supplies the generated demand forecast model to the demand forecast model update unit 240.

The demand forecast model update unit 240 is connected to the storage unit 110 and the demand forecast unit 250. The demand prediction model updating unit 240 updates the demand prediction model by learning using learning data including the actual value of the demanded amount of hydrogen in each of the plurality of hydrogen stations 60. The demand forecast model update unit 240 may update the new demand forecast model by learning, for example, at each predetermined update period. Instead of this, the demand prediction model update unit 240 sets the demand prediction model according to various conditions such as learning a predetermined number of times, or an error difference due to learning falling below a predetermined threshold value. You may update.

The demand forecast model updating unit 240 may learn the demand forecast model by a process called adaptive learning or online learning. The demand prediction model updating unit 240 learns the demand prediction model by executing reinforcement learning using, for example, an arbitrary machine learning model as an identification model. By performing such machine learning, the demand prediction model updating unit 240 receives the demand prediction factor as an input and predicts the demand amount of the hydrogen station 60 or the like according to the demand prediction factor with accuracy according to the model to be applied. Will be able to.

It is desirable that the demand forecast model update unit 240 further learns by further using information that is later in time than the information of the demand forecast factor used by the demand forecast model generation unit 230 to generate the demand forecast model. The demand prediction model updating unit 240 may update the demand prediction model by learning, for example, based on the value of the demand prediction factor in the past period and the actual value of the demand amount of the hydrogen station 60 after the past period. The demand forecast model updating unit 240 learns the demand forecast model using the information of the demand forecast factor updated by the actual hydrogen demand. The demand prediction model updating unit 240 may execute the learning of the demand prediction model in response to the update of the information of the demand prediction factor. The demand prediction model updating unit 240 may execute learning one or more times during the update period. The demand forecast model updating unit 240 supplies the updated demand forecast model to the demand forecasting unit 250.

The demand prediction unit 250 is connected to the storage unit 110. The demand prediction unit 250 generates a hydrogen demand prediction for each of the plurality of hydrogen stations 60 using a demand prediction model. The demand prediction unit 250 may predict the demand forecast of hydrogen at each of the plurality of hydrogen stations 60 based on a demand forecast factor including a hydrogen consumption forecast at each hydrogen station 60.

The demand prediction unit 250 predicts, for example, for every predetermined period, the hydrogen demand amount of the hydrogen station 60 in the future for the predetermined period. The demand prediction unit 250 may predict the demanded amount of hydrogen at the hydrogen station 60 using the demand prediction model and the information of the demand prediction factor. The demand prediction unit 250 predicts the demand quantity of the hydrogen station 60 by applying the information of the demand prediction factor in the period immediately before the period to be predicted to the demand prediction model, for example. The demand prediction unit 250 supplies the prediction result to the storage unit 110, and stores it as at least one of a transportation prediction factor and a transportation planning factor, for example. Further, the demand prediction unit 250 may directly supply the prediction result to another configuration of the prediction unit 120 or the planning unit 130.

The power generation amount prediction model generation unit 260 is connected to the storage unit 110 and the power generation amount prediction model update unit 270. The power generation amount prediction model generation unit 260 generates a power generation amount prediction model that generates a power generation amount prediction of renewable energy for each of the plurality of renewable energy power generation facilities 20 based on a power generation amount prediction factor. The power generation prediction model is a model for calculating the power generation prediction of renewable energy for each of the plurality of renewable energy power generation facilities 20 in the prediction target period based on the power generation prediction factor before the prediction target period. Good.

The power generation amount prediction model generation unit 260 may generate a power generation amount prediction model by a process called pre-learning or off-line learning using information past the prediction target period. The power generation amount prediction model generation unit 260 generates a power generation amount prediction model by using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, hidden Markov model, or the like. In addition, for example, if a model having a memory such as LSTM, RNN, and the like is used as the power generation prediction model, the power generation of the renewable energy power generation facility 20 can be predicted from the time series of factors. The power generation amount prediction model generation unit 260 supplies the generated power generation amount prediction model to the power generation amount prediction model update unit 270.

The power generation amount prediction model update unit 270 is connected to the storage unit 110 and the power generation amount prediction unit 280. The power generation amount prediction model updating unit 270 updates the power generation amount prediction model by learning using learning data including the actual value of the power generation amount in each of the plurality of renewable energy power generation facilities 20. The power generation amount prediction model update unit 270 may update the power generation amount prediction model with a new power generation amount prediction model by learning for each predetermined update period. Instead of this, the power generation amount prediction model updating unit 270 predicts the power generation amount according to various conditions, such as learning a predetermined number of times, or an error difference due to learning falling below a predetermined threshold value. The model may be updated.

The power generation prediction model updating unit 270 may learn the power generation prediction model by a process called adaptive learning or online learning. The power generation amount prediction model updating unit 270 learns the power generation amount prediction model by executing reinforcement learning using, for example, an arbitrary machine learning model as the identification model. By performing such machine learning, the power generation amount prediction model updating unit 270 receives the power generation amount prediction factor as an input and applies the power generation amount of the renewable energy power generation facility 20 according to the power generation amount prediction factor to the model to be applied. It becomes possible to make predictions according to the accuracy.

It is desirable that the power generation prediction model updating unit 270 further learns by further using information that is later in time than the information of the power generation prediction factor used by the power generation prediction model generation unit 260 to generate the power generation prediction model. The power generation amount prediction model updating unit 270 learns the power generation amount prediction model based on, for example, the value of the power generation amount prediction factor in the past period and the actual value of the power generation amount of the renewable energy power generation facility 20 after the past period. You may update. The power generation amount prediction model update unit 270 learns the power generation amount prediction model using the information of the power generation amount prediction factor updated by the actual power generation of the renewable energy power generation facility 20. The power generation amount prediction model updating unit 270 may execute learning of the power generation amount prediction model in response to the information of the power generation amount prediction factor being updated. The power generation prediction model updating unit 270 may execute learning one or more times during the update period. The power generation amount prediction model updating unit 270 supplies the updated power generation amount prediction model to the power generation amount prediction unit 280.

The power generation amount prediction unit 280 is connected to the storage unit 110. The power generation amount prediction unit 280 generates a power generation amount prediction of renewable energy for each of the plurality of renewable energy power generation facilities 20 using a power generation amount prediction model.

The power generation amount prediction unit 280 predicts, for example, for each predetermined period, the power generation amount of the renewable energy power generation facility 20 in the predetermined period in the future. The power generation amount prediction unit 280 may predict the power generation amount of the renewable energy power generation facility 20 using the power generation amount prediction model and the information of the power generation amount prediction factor. The power generation amount prediction unit 280 predicts the power generation amount of the renewable energy power generation facility 20 by applying the information of the power generation amount prediction factor in the period immediately before the period to be predicted to the power generation amount prediction model, for example. The power generation amount prediction unit 280 supplies the prediction result to the storage unit 110 and stores it as at least one of an electricity rate prediction factor and an operation prediction factor, for example. In addition, the power generation amount prediction unit 280 may directly supply the prediction result to another configuration of the prediction unit 120 or the planning unit 130.

The electricity price prediction model generation unit 290 is connected to the storage unit 110 and the electricity price prediction model update unit 300. The electricity rate prediction model generation unit 290 generates an electricity rate prediction model that generates an electricity rate prediction of renewable energy based on the electricity rate prediction factor before the prediction target period.

The electricity price prediction model generation unit 290 may generate an electricity price prediction model by a process called pre-learning or offline learning using information past the prediction target period. The electricity price prediction model generation unit 290 generates an electricity price prediction model using, for example, regression analysis, Bayesian inference, a neural network, a Gaussian mixture model, a hidden Markov model, or the like. In addition, if an LSTM, RNN, or other model having memory is used as the electricity price prediction model, the electricity price of the renewable energy can be predicted from the time series of the factors. The electricity charge prediction model generation unit 290 supplies the generated electricity charge prediction model to the electricity charge prediction model update unit 300.

The electricity charge prediction model updating unit 300 is connected to the storage unit 110 and the electricity charge prediction unit 310. The electricity price prediction model updating unit 300 may update the electricity price prediction model by learning using the learning data including the actual value of the electricity price. The electricity price prediction model updating unit 300 may update a new electricity price prediction model by learning for each predetermined update period. Instead of this, the electricity price prediction model update unit 300 predicts the electricity price according to various conditions such as learning a predetermined number of times, or an error difference due to learning falling below a predetermined threshold value. The model may be updated.

The electricity price prediction model updating unit 300 may learn the electricity price prediction model by a process called adaptive learning or online learning. The electricity charge prediction model updating unit 300 learns the electricity charge prediction model by executing reinforcement learning using an arbitrary machine learning model as an identification model, for example. By performing such machine learning, the electricity price prediction model updating unit 300 receives the electricity price prediction factor as an input, and generates the electricity price of the renewable energy according to the electricity price prediction factor with accuracy according to the applied model. Be able to predict.

It is desirable that the electricity price prediction model update unit 300 further learns by further using information that is later in time than the information of the electricity price prediction factor used by the electricity price prediction model generation unit 290 to generate the electricity price prediction model. The electricity price prediction model updating unit 300 may update the electricity price prediction model by learning, for example, based on the value of the electricity price prediction factor in the past period and the actual value of the electricity price after the past period. The electricity price prediction model updating unit 300 learns the electricity price prediction model using the information of the electricity price prediction factor updated by the transition of the actual electricity price. The electricity charge prediction model updating unit 300 may execute the learning of the electricity charge prediction model in response to the update of the information of the electricity charge prediction factor. The electricity price prediction model update unit 300 may perform learning one or more times during the update period. The electricity charge prediction model updating unit 300 supplies the updated electricity charge prediction model to the electricity charge prediction unit 310.

The electricity price prediction unit 310 is connected to the storage unit 110. The electricity bill prediction unit 310 uses the electricity bill prediction model to generate an electricity bill prediction for renewable energy.

The electricity price prediction unit 310 predicts, for example, for each predetermined period, the future electricity price in the predetermined period. The electricity charge prediction unit 310 may predict the electricity charge of the renewable energy using the electricity charge prediction model and the information of the electricity charge prediction factor. The electricity charge prediction unit 310 predicts the electricity charge by applying, for example, the information of the electricity charge prediction factor in the period immediately before the period to be predicted to the electricity charge prediction model. The electricity price prediction unit 310 supplies the prediction result to the storage unit 110, and stores it as at least one of an operation prediction factor and an operation plan factor, for example. In addition, the electricity price prediction unit 310 may directly supply the prediction result to another configuration of the prediction unit 120 or the planning unit 130.

The consumption prediction model generation unit 320 is connected to the storage unit 110 and the consumption prediction model update unit 330. The consumption prediction model generation unit 320 generates a consumption prediction model that calculates a hydrogen consumption prediction of the plurality of hydrogen stations 60 during the prediction target period based on the consumption prediction factor before the prediction target period.

The consumption prediction model generation unit 320 may generate a consumption prediction model by a process called pre-learning or offline learning using information past the prediction target period. The consumption prediction model generation unit 320 generates a consumption prediction model using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, hidden Markov model, or the like. Further, for example, if a model having a memory such as LSTM, RNN, and the like is used as the consumption prediction model, it is possible to predict the hydrogen consumption at the hydrogen station 60 from the time series of the factors. The consumption prediction model generation unit 320 supplies the generated consumption prediction model to the consumption prediction model update unit 330.

The consumption prediction model updating unit 330 is connected to the storage unit 110 and the consumption prediction unit 340. The consumption prediction model update unit 330 may update the consumption prediction model by learning using learning data including the actual value of the amount of hydrogen consumed in each of the plurality of hydrogen stations 60. The consumption prediction model updating unit 330 may update the new consumption prediction model by learning, for example, for each predetermined update period. Instead of this, the consumption prediction model update unit 330 sets the consumption prediction model according to various conditions such as learning a predetermined number of times or an error difference due to learning falling below a predetermined threshold value. You may update.

The consumption prediction model updating unit 330 may learn the consumption prediction model by a process called adaptive learning or online learning. The consumption prediction model update unit 330 learns the consumption prediction model by executing reinforcement learning using, for example, an arbitrary machine learning model as an identification model. By performing such machine learning, the consumption prediction model updating unit 330 predicts the consumption amount of hydrogen in the hydrogen station 60 according to the consumption prediction factor with the accuracy according to the model to which the consumption prediction factor is input. You will be able to.

It is desirable that the consumption prediction model update unit 330 learn by further using information that is later in time than the information of the consumption prediction factor used by the consumption prediction model generation unit 320 to generate the consumption prediction model. The consumption prediction model updating unit 330 may update the consumption prediction model by learning, for example, based on the value of the consumption prediction factor in the past period and the actual value such as the hydrogen consumption amount after the past period. The consumption prediction model updating unit 330 learns the consumption prediction model using the information of the consumption prediction factor updated by the transition of the actual hydrogen consumption amount. The consumption prediction model update unit 330 may perform learning of the consumption prediction model in response to the information on the consumption prediction factor being updated. The consumption prediction model update unit 330 may perform learning one or more times during the update period. The consumption prediction model update unit 330 supplies the updated consumption prediction model to the consumption prediction unit 340.

The consumption prediction unit 340 is connected to the storage unit 110. The consumption prediction unit 340 generates a hydrogen consumption prediction in each of the plurality of hydrogen stations 60 using a consumption prediction model.

The consumption prediction unit 340 predicts, for example, for every predetermined period, hydrogen consumption in the hydrogen station 60 in the predetermined period in the future. The consumption prediction unit 340 may predict the consumption of hydrogen at the hydrogen station 60 using the consumption prediction model and the information of the consumption prediction factor. For example, the consumption prediction unit 340 applies the information of the consumption prediction factor in the period immediately before the period to be predicted to the consumption prediction model to predict the hydrogen consumption amount in the hydrogen station 60. The consumption prediction unit 340 supplies the prediction result to the storage unit 110 and stores it as, for example, a demand prediction factor. Moreover, the consumption prediction unit 340 may directly supply the prediction result to another configuration of the prediction unit 120 or the planning unit 130.

The storage amount prediction model generation unit 350 is connected to the storage unit 110 and the storage amount prediction model update unit 360. The storage amount prediction model generation unit 350 generates a storage amount prediction model that calculates the storage amount prediction based on the storage amount prediction factor. The storage amount prediction model may be a model that predicts the storage amount of hydrogen in the plurality of hydrogen storage devices 40 in the prediction target period based on the storage amount prediction factor before the prediction target period.

The storage amount prediction model generation unit 350 may generate a storage amount prediction model by a process called pre-learning or off-line learning using information past the prediction target period. The storage amount prediction model generation unit 350 generates a storage amount prediction model using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, hidden Markov model, and the like. Further, if a model having memory such as LSTM, RNN, and the like is used as the storage amount prediction model, the storage amount of the hydrogen storage device 40 can be predicted from the time series of the factors. The storage amount prediction model generation unit 350 supplies the generated storage amount prediction model to the storage amount prediction model update unit 360.

The storage amount prediction model update unit 360 is connected to the storage unit 110 and the storage amount prediction unit 370. The storage amount prediction model updating unit 360 may update the storage amount prediction model by learning using learning data including the actual values of the hydrogen storage amounts of the plurality of hydrogen storage devices 40. The storage amount prediction model updating unit 360 may update the storage amount prediction model by learning, for example, at each predetermined update period. Instead of this, the storage amount prediction model update unit 360 predicts the storage amount according to various conditions such as that learning is performed a predetermined number of times, or that an error difference due to learning is below a predetermined threshold value. The model may be updated.

The storage amount prediction model updating unit 360 may learn the storage amount prediction model by a process called adaptive learning or online learning. The storage amount prediction model updating unit 360 learns the storage amount prediction model by executing reinforcement learning using, for example, an arbitrary machine learning model as an identification model. By performing such machine learning, the storage amount prediction model updating unit 360 receives the storage amount prediction factor as an input, and stores the hydrogen storage amount of the hydrogen storage device 40 according to the storage amount prediction factor according to the applied model. It becomes possible to predict with high accuracy.

It is desirable that the storage amount prediction model update unit 360 further learns by further using information that is later in time than the information of the storage amount prediction factor used by the storage amount prediction model generation unit 350 to generate the storage amount prediction model. The storage amount prediction model updating unit 360 learns the storage amount prediction model based on, for example, the value of the storage amount prediction factor in the past period and the actual value of the hydrogen storage amount of the hydrogen storage device 40 after the past period. You may update. The storage amount prediction model updating unit 360 learns the storage amount prediction model using the information of the storage amount prediction factor updated by the transition of the actual storage amount of hydrogen. The storage amount prediction model updating unit 360 may execute the learning of the storage amount prediction model in response to the information of the storage amount prediction factor being updated. The storage amount prediction model update unit 360 may execute learning one or more times during the update period. The storage amount prediction model update unit 360 supplies the updated storage amount prediction model to the storage amount prediction unit 370.

The storage amount prediction unit 370 is connected to the storage unit 110. The storage amount prediction unit 370 generates a hydrogen storage amount prediction in each of the plurality of hydrogen storage devices 40 that stores hydrogen generated by the plurality of hydrogen generation devices 30, using the updated storage amount prediction model.

The storage amount prediction unit 370 predicts the storage amount of hydrogen in the hydrogen storage device 40 in the future for the predetermined period, for example, for each predetermined period. The storage amount prediction unit 370 may predict the storage amount of hydrogen in the hydrogen storage device 40 using the storage amount prediction model and the information on the storage amount prediction factor. The storage amount prediction unit 370 predicts the storage amount of hydrogen of the hydrogen storage device 40, for example, by applying the information of the storage amount prediction factor in the period immediately before the period to be predicted to the storage amount prediction model. The storage amount prediction unit 370 supplies the prediction result to the storage unit 110 and stores it as at least one of a transportation planning factor and a storage planning factor, for example. In addition, the storage amount prediction unit 370 may directly supply the prediction result to another configuration of the prediction unit 120 or the planning unit 130.

The transportation prediction model generation unit 380 is connected to the storage unit 110 and the transportation prediction model update unit 390. The transportation prediction model generation unit 380 predicts a transportation plan for transporting hydrogen between the plurality of hydrogen generation devices 30 and the plurality of hydrogen stations 60 during the prediction target period based on the transport prediction factor before the prediction target period. Generate a transport forecasting model that produces a transport forecast that is

The transportation prediction model generation unit 380 may generate a transportation prediction model by a process called pre-learning or off-line learning using information past the prediction target period. The transportation prediction model generation unit 380 generates a transportation prediction model using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, hidden Markov model, or the like. Moreover, if a model having a memory such as LSTM, RNN, and the like is used as the transportation prediction model, the transportation plan can be predicted from a time series of factors. The transportation prediction model generation unit 380 supplies the generated transportation prediction model to the transportation prediction model updating unit 390.

The transportation prediction model updating unit 390 is connected to the storage unit 110 and the transportation prediction unit 400. The transportation prediction model updating unit 390 updates the transportation prediction model by learning using learning data including the actual value of the transportation plan (for example, the actual value of the executed transportation plan or the actually executed transportation). Good. The transportation prediction model updating unit 390 may update the transportation prediction model by learning, for example, in each predetermined updating period. Instead of this, the transportation prediction model updating unit 390 sets the transportation prediction model in accordance with various conditions such as learning a predetermined number of times or an error difference due to learning falling below a predetermined threshold value. You may update.

The transportation prediction model updating unit 390 may learn the transportation prediction model by a process called adaptive learning or online learning. The transportation prediction model updating unit 390 learns the transportation prediction model by executing reinforcement learning using an arbitrary machine learning model as an identification model, for example. By performing such machine learning, the transportation prediction model update unit 390 can predict the transportation plan according to the transportation prediction factor with the accuracy according to the applied model by inputting the transportation prediction factor. Become.

It is desirable that the transportation prediction model update unit 390 further learns by further using information that is later in time than the information of the transportation prediction factor used by the transportation prediction model generation unit 380 to generate the transportation prediction model. The transportation prediction model updating unit 390 may update the transportation prediction model by learning, for example, based on the value of the transportation prediction factor in the past period and the actual value of the transportation plan after the past period. The transportation prediction model update unit 390 learns the transportation prediction model using the information of the transportation prediction factor updated by the actual implementation of the transportation plan. The transportation prediction model updating unit 390 may execute learning of the transportation prediction model in response to the information of the transportation prediction factor being updated. The transportation prediction model update unit 390 may perform learning one or more times during the update period. The transportation prediction model updating unit 390 supplies the updated transportation prediction model to the transportation prediction unit 400.

The transportation prediction unit 400 is connected to the storage unit 110. The transportation prediction unit 400 uses a transportation prediction model based on the transportation prediction factor to generate a transportation prediction that is a prediction of a transportation plan that transports hydrogen between the plurality of hydrogen generation devices 30 and the plurality of hydrogen stations 60. .

The transportation prediction unit 400 predicts a transportation plan in the predetermined period in the future, for example, for each predetermined period. The transportation prediction unit 400 may predict the transportation plan using the transportation prediction model and the information of the transportation prediction factor. The transportation prediction unit 400 predicts a transportation plan by applying, for example, the information of the transportation prediction factor in the period immediately before the period to be predicted to the transportation prediction model. The transportation prediction unit 400 supplies the prediction result to the storage unit 110, and stores it as at least one of the operation planning factor and the storage planning factor, for example. In addition, the transportation prediction unit 400 may directly supply the prediction result to another configuration of the prediction unit 120 or the planning unit 130.

FIG. 4 shows a detailed configuration example of the planning unit 130 of the planning device 70 of this embodiment. The planning unit 130 includes a transportation plan model generation unit 410, a transportation plan model updating unit 420, and a transportation planning unit 430, and transports hydrogen generated by the plurality of hydrogen generation devices 30 to the plurality of hydrogen stations 60. Generate a transportation plan. The planning unit 130 includes an operation plan model generation unit 440, an operation plan model update unit 450, and an operation plan unit 460, and generates an operation plan for each of the hydrogen generation devices 30. The planning unit 130 includes a storage plan model generating unit 470, a storage plan model updating unit 480, and a storage planning unit 490, and generates a hydrogen storage plan for each of the plurality of hydrogen storage devices 40.

Here, the storage unit 110 stores planning factors including a transportation planning factor, an operation planning factor, and a storage planning factor.

The transportation plan factor may include information on a transportation plan for transporting hydrogen generated by the plurality of hydrogen generators 30 to the plurality of hydrogen stations 60. The transportation planning factor includes at least one of an operation prediction of each of the plurality of hydrogen generators 30, a storage amount prediction of hydrogen in each of the plurality of hydrogen storage devices 40, and a demand prediction of each of the plurality of hydrogen stations 60. Good. The transportation planning factor is the operating amount of each of the plurality of hydrogen generators 30, the storage amount of hydrogen in each of the plurality of hydrogen storage devices 40, and the demand of hydrogen in each of the plurality of hydrogen stations 60 before the prediction target period. It may further comprise at least one of the amounts. Transportation planning factors may include transportation predictors. The transportation planning factor is at least one of the type of transportation means 50, the number of transportation means 50, the transportation cost of each transportation means 50, the arrangement of each transportation means 50, and the transportable amount of hydrogen of each transportation means 50. May be included.

The operation plan factor may include information on the operation of the plurality of hydrogen generators 30. The operation plan factor includes a hydrogen transportation prediction between the plurality of hydrogen generators 30 and the plurality of hydrogen stations 60. The operation plan factor may include an operation prediction factor. The operation plan factor is an identifier of the hydrogen generator 30 and the renewable energy power generation facility 20 that supplies power to the hydrogen generation device 30, the type of renewable energy used by the renewable energy power generation facility 20 for power generation, and the renewable energy power generation facility. It may include at least one of 20 power generation amounts, power generation amount predictions, electricity prices for renewable energy, electricity price forecasts, and operation forecasts.

The storage plan factor may include information regarding the storage amount of hydrogen in the plurality of hydrogen storage devices 40. The storage plan factor is the operation prediction of the corresponding hydrogen generation device 30 (the hydrogen generation device 30 connected to the hydrogen storage device 40 corresponding to the storage plan factor) among the plurality of hydrogen generation devices 30, and the plurality of hydrogen generation devices 30. And hydrogen transport predictions between the plurality of hydrogen stations 60. The storage planning factor may include a storage amount prediction factor. The storage plan factor is, for example, the type of each hydrogen storage device 40, the maximum amount of hydrogen that can be stored in each hydrogen storage device 40, and information on the hydrogen generation device 30 corresponding to each hydrogen storage device 40 (for the hydrogen generation device 30). At least one of the number of connections, hydrogen generation efficiency, operating rate, and / or operating time).

At least one of the transportation planning factor, the operation planning factor, and the storage planning factor may be time-series information at approximately fixed time intervals. At least one of a transportation planning factor, an operation planning factor, and a storage planning factor may be added or updated over time, respectively. At least one of the transportation planning factor, the operation planning factor, and the storage planning factor may include at least one of the prediction result generated by the planning device 70 and the planning data. Further, at least one of the transportation planning factor, the operation planning factor, and the storage planning factor may be supplied from an external database or the management device 150, and may include the information acquired by the acquisition unit 100.

The transportation plan model generation unit 410 is connected to the storage unit 110 and the transportation plan model updating unit 420. The transportation plan model generation unit 410 transports hydrogen between each of the plurality of hydrogen storage devices 40 and each of the plurality of hydrogen stations 60 during the planning period based on the transportation planning factor before the planning period. Generate transportation planning model.

The transportation plan model generation unit 410 may generate the transportation plan model by a process called pre-learning or off-line learning using information past the planned period. The transportation plan model generation unit 410 generates a transportation plan model using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, hidden Markov model, or the like. Further, if a transport plan model such as an LSTM, an RNN, or another model having a memory is used, the transport plan can be generated from a time series of factors. The transportation plan model generation unit 410 supplies the generated transportation plan model to the transportation plan model updating unit 420.

The transportation plan model updating unit 420 is connected to the storage unit 110 and the transportation planning unit 430. The transportation plan model updating unit 420 includes a plurality of hydrogen generators 30, a plurality of hydrogen storage devices 40, a transportation means 50 between each of the plurality of hydrogen storage devices 40 and each of the plurality of hydrogen stations 60, and a plurality of hydrogens. The transportation planning model is updated by learning based on the evaluation index for evaluating the productivity of the cooperation system including the station 60.

Here, the evaluation index may be based on at least one of the operating cost, sales, and profit of the cooperation system, and the cost per unit amount of hydrogen supplied by the cooperation system. The evaluation index may be calculated by each model updating unit of the planning device 70, or may be supplied to the planning device 70 from an external device. The evaluation index may be calculated by an objective function, for example. As an example, the evaluation index is calculated by an objective function of a weighted sum obtained by weighting the operating costs, sales, and profits of the cooperation system, and the cost per unit amount of hydrogen supplied by the cooperation system. May be done.

The transportation plan model updating unit 420 may update a new transportation plan model by learning, for example, at each predetermined updating period. Instead, the transportation plan model updating unit 420 has learned a predetermined number of times, that the error difference due to learning has fallen below a predetermined threshold value, or the evaluation index is maximum, minimum, or predetermined. The transportation planning model may be updated according to various conditions such as being within the specified range.

The transportation plan model updating unit 420 may learn the transportation plan model by a process called adaptive learning or online learning. The transportation plan model updating unit 420 learns the transportation plan model by executing reinforcement learning using an arbitrary machine learning model as an identification model, for example. By carrying out such machine learning, the transportation plan model updating unit 420 can generate a transportation plan according to the transportation plan factor with the accuracy according to the applied model by inputting the transportation plan factor. Become.

It is desirable that the transportation plan model update unit 420 further learns by further using information that is later in time than the information of the transportation plan factor used by the transportation plan model generation unit 410 to generate the transportation plan model. The transportation plan model updating unit 420 may update the transportation plan model by learning, for example, based on the value of the transportation plan factor in the past period and the evaluation index of the transportation plan after the past period. The transportation plan model updating unit 420 learns the transportation plan model using the evaluation index calculated according to the actual implementation of the transportation plan. The transportation plan model updating unit 420 may perform learning of the transportation plan model according to the calculation of the evaluation index. The transportation plan model update unit 420 may perform learning one or more times during the update period. The transportation planning model updating unit 420 supplies the updated transportation planning model to the transportation planning unit 430.

The transportation planning unit 430 is connected to the storage unit 110 and the output unit 140. The transportation planning unit 430 generates a transportation plan that transports the hydrogen generated by the plurality of hydrogen generators 30 to the plurality of hydrogen stations 60, using the transportation planning model, based on the transportation planning factor.

The transportation planning unit 430, for example, for each predetermined period, generates a transportation plan for the future predetermined period. The transportation planning unit 430 may generate a transportation plan using the transportation planning model and the information on the transportation planning factors. The transportation planning unit 430 applies, for example, the information of the transportation planning factor in the period immediately before the period to be planned to the transportation planning model to generate the transportation plan. The transportation planning unit 430 supplies the planning data of the transportation plan to the storage unit 110 and stores it as a planning factor, for example. In addition, the transportation planning unit 430 may directly supply the planning data to other components of the prediction unit 120 and / or the planning unit 130.

The operation plan model generation unit 440 is connected to the storage unit 110 and the operation plan model update unit 450. The operation plan model generation unit 440 generates an operation plan model that generates an operation plan for each of the plurality of hydrogen generators 30 during the planning period based on the operation planning factors before the planning period.

The operation plan model generation unit 440 may generate an operation plan model by a process called pre-learning or offline learning using the information in the past of the plan target period. The operation plan model generation unit 440 generates an operation plan model using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, hidden Markov model, and the like. Further, if, for example, an LSTM, RNN, or other model having memory is used as the operation plan model, the operation plan can be generated from the time series of factors. The operation plan model generation unit 440 supplies the generated operation plan model to the operation plan model update unit 450.

The operation plan model updating unit 450 is connected to the storage unit 110 and the operation planning unit 460. The operation plan model updating unit 450 updates the operation plan model by learning based on the evaluation index for evaluating the productivity of the cooperation system. The operation plan model updating unit 450 may update a new operation plan model by learning, for example, in each predetermined update period. Instead, the operation plan model updating unit 450 has learned a predetermined number of times, that the error difference due to learning has fallen below a predetermined threshold value, or the evaluation index is maximum, minimum, or predetermined. The operation plan model may be updated according to various conditions such as being within the specified range.

The operation plan model updating unit 450 may learn the operation plan model by a process called adaptive learning or online learning. The operation plan model updating unit 450 learns the operation plan model by executing reinforcement learning using, for example, an arbitrary machine learning model as an identification model. By performing such machine learning, the operation plan model updating unit 450 can generate an operation plan according to the operation plan factor with the accuracy according to the applied model by inputting the operation plan factor. Become.

It is desirable that the operation plan model update unit 450 further learns by further using information that is later in time than the information of the operation plan factor used by the operation plan model generation unit 440 to generate the operation plan model. The operation plan model updating unit 450 may update the operation plan model by learning, for example, based on the value of the operation plan factor in the past period and the evaluation index of the operation plan after the past period. The operation plan model updating unit 450 learns the operation plan model using the evaluation index calculated according to the actual execution of the operation plan. The operation plan model updating unit 450 may execute learning of the operation plan model according to the calculation of the evaluation index. The operation plan model updating unit 450 may execute learning one or more times during the update period. The operation plan model updating unit 450 supplies the updated operation plan model to the operation planning unit 460.

The operation planning unit 460 is connected to the storage unit 110 and the output unit 140. The operation planning unit 460 generates an operation plan for each of the plurality of hydrogen generators 30 using the operation plan model based on the operation plan factor.

The operation planning unit 460, for example, generates an operation plan for the future predetermined period for each predetermined period. The operation plan unit 460 may generate an operation plan using the operation plan model and the information on the operation plan factors. The operation planning unit 460 applies, for example, the information of the operation plan factors in the period immediately before the period to be planned to the operation plan model to generate the operation plan. The operation planning unit 460 supplies the plan data of the operation plan to the storage unit 110 and stores it as a planning factor, for example. In addition, the operation planning unit 460 may directly supply the planning data to other components of the prediction unit 120 and / or the planning unit 130.

The storage plan model generation unit 470 is connected to the storage unit 110 and the storage plan model update unit 480. The storage plan model generation unit 470 determines the hydrogen in each of the plurality of hydrogen storage devices 40 that stores the hydrogen generated by the plurality of hydrogen generation devices 30 during the planning target period based on the storage planning factor before the planning target period. Generate a storage plan model to generate the storage plan of the.

The storage plan model generation unit 470 may generate a storage plan model by a process called pre-learning or off-line learning, using information past the planning period. The storage plan model generation unit 470 generates a storage plan model using, for example, regression analysis, Bayesian inference, neural network, Gaussian mixture model, hidden Markov model, and the like. Further, if a storage plan model, for example, an LSTM, RNN, or other model having memory is used, the storage plan can be generated from a time series of factors. The storage plan model generation unit 470 supplies the generated storage plan model to the storage plan model update unit 480.

The storage plan model updating unit 480 is connected to the storage unit 110 and the storage planning unit 490. The storage plan model updating unit 480 updates the storage plan model by learning based on the evaluation index for evaluating the productivity of the cooperation system. The storage plan model updating unit 480 may update a new storage plan model by learning, for example, at each predetermined update period. Instead of this, the storage plan model updating unit 480 learns a predetermined number of times, the error difference due to learning is below a predetermined threshold value, or the evaluation index is maximum, minimum, or predetermined. The storage plan model may be updated according to various conditions such as being within the specified range.

The storage plan model updating unit 480 may learn the storage plan model by a process called adaptive learning or online learning. The storage plan model updating unit 480 learns the storage plan model by executing reinforcement learning using an arbitrary machine learning model as an identification model, for example. By performing such machine learning, the storage plan model updating unit 480 can generate a storage plan according to the storage plan factor with the accuracy according to the applied model by inputting the storage plan factor. Become.

It is desirable that the storage plan model updating unit 480 further learns by further using information that is later in time than the storage plan factor information used by the storage plan model generating unit 470 to generate the storage plan model. The storage plan model updating unit 480 may update the storage plan model by learning, for example, based on the value of the storage plan factor in the past period and the evaluation index of the storage plan after the past period. The storage plan model updating unit 480 may learn the storage plan model using the evaluation index calculated according to the actual implementation of the storage plan. The storage plan model updating unit 480 may execute the storage plan model learning according to the calculation of the evaluation index. The storage plan model updating unit 480 may execute learning one or more times during the update period. The storage plan model updating unit 480 supplies the updated storage plan model to the storage planning unit 490.

The storage planning unit 490 is connected to the storage unit 110 and the output unit 140. The storage planning unit 490 uses the updated storage planning model based on the storage planning factor to set the hydrogen storage plan in each of the plurality of hydrogen storage devices 40 that stores the hydrogen generated by the plurality of hydrogen generation devices 30. To generate.

The storage planning unit 490 generates, for example, for each predetermined period, a storage plan for the future predetermined period. The storage planning unit 490 may generate a storage plan using the storage planning model and the information on the storage planning factors. The storage planning unit 490 applies, for example, the information of the storage planning factor in the period immediately before the period to be planned to the storage planning model to generate the storage plan. The storage planning unit 490 supplies the plan data of the storage plan to the storage unit 110 and stores it as a planning factor, for example. In addition, the storage planning unit 490 may directly supply the planning data to the prediction unit 120 and / or other components of the planning unit 130.

The planning device 70 according to the present embodiment described above can generate an efficient plan for supplying hydrogen at low cost in the cooperative system from hydrogen generation to consumption by using the model generated by learning. . The operation of the planning device 70 will be described below.

FIG. 5 shows an example of the flow of the planning device 70 according to this embodiment.

The acquisition unit 100 acquires information on a predictive factor and a plan factor that are past trends (S510). The acquisition unit 100 acquires, for example, information on the prediction factor and the design factor from time t0 to time t1. The acquisition unit 100 causes the storage unit 110 to store the acquired information about the prediction factor and the design factor. Further, the acquisition unit 100 may directly supply the information of the prediction factor and the planning factor to the prediction unit 120 and the planning unit 130.

Next, the prediction unit 120 and the planning unit 130 generate a learning model (S520). The prediction unit 120 and the planning unit 130 generate a learning model based on the values of the prediction factor and the planning factor in the period from time t0 to time t1. For example, the operation prediction model generation unit 200 uses the value of the operation prediction factor in the period from time t0 to time t1 to generate the operation prediction model. The demand prediction model generation unit 230 generates a demand prediction model using the value of the demand prediction factor in the period from time t0 to time t1. The power generation amount prediction model generation unit 260 generates a power generation amount prediction model using the value of the power generation amount prediction factor in the period from time t0 to time t1. The electricity charge prediction model generation unit 290 generates an electricity charge prediction model using the value of the electricity charge prediction factor in the period from time t0 to time t1. The consumption prediction model generation unit 320 generates a consumption prediction model using the value of the consumption prediction factor in the period from time t0 to time t1. The storage amount prediction model generation unit 350 generates a storage amount prediction model using the value of the storage amount prediction factor in the period from time t0 to time t1. The transportation prediction model generation unit 380 generates a transportation prediction model using the value of the transportation prediction factor in the period from time t0 to time t1.

The transportation plan model generation unit 410 also generates a transportation plan model using the values of the transportation plan factor in the period from time t0 to time t1. The operation plan model generation unit 440 uses the value of the operation plan factor in the period from time t0 to time t1 to generate the operation plan model. The storage plan model generation unit 470 uses the value of the storage plan factor in the period from time t0 to time t1 to generate the storage plan model.

Further, the prediction unit 120 and the planning unit 130 are based on the physical model of the target device such as the hydrogen generation device 30, the renewable energy power generation facility 20, the hydrogen storage device 40, the transportation means 50, the hydrogen station 60, or the consumption means 90. A model may be generated by using virtual data as prediction data and comparing the prediction data with actual data acquired in the past operation of the target apparatus. For example, the prediction unit 120 and the planning unit 130 enhance the error between the prediction data and the target data derived from the past actual data so that the error is a minimum error (for example, 0) or less than a predetermined value. Perform training to generate a model.

As an example, the prediction unit 120 and the planning unit 130 set the period of M days in the period from time t0 to time t1 as a virtual prediction period or planning period. The M days may be, for example, a period of several days or a dozen days, one or several weeks. Then, the prediction unit 120 and the planning unit 130 predict the prediction period in the period from the time t0 to the time t1 or the prediction result or the plan data based on the value of the factor of the period before the planning period or the planning period, and the prediction period. Alternatively, reinforcement learning is performed so that the error between the actual data and the virtual data in the planning period is minimized.

The generation of the learning model by the predicting unit 120 and the planning unit 130 may be executed before the planning device 70 acquires the actual data of the target device as the target device operates.

Next, the prediction unit 120 and the planning unit 130 adaptively learn the generated learning model (S530). Here, the acquisition unit 100 may further acquire information on each factor. The acquisition unit 100 acquires information on each factor from time t2 to time t3, for example. Further, the planning device 70 may calculate the evaluation index or acquire the evaluation index from an external device or the like. In addition, the prediction unit 120 and the planning unit 130 may generate information on each factor from time t2 to time t3, for example. The period from time t2 to time t3 is the period after the period from time t0 to time t1. The prediction unit 120 and the planning unit 130 may perform adaptive learning using the information of each new factor and / or the evaluation index.

For example, the operation prediction model updating unit 210 adaptively learns the operation prediction model based on the value of the operation prediction factor. The operation prediction model updating unit 210 may adaptively learn the operation prediction model using the operation status of the hydrogen generator 30 in the period from time t2 to time t3. The operation prediction model updating unit 210 uses the operation prediction model to predict the operation amount of the hydrogen generator 30 in the period from time t2 to time t3, and the obtained result is the hydrogen generator in the period from time t2 to time t3. Reinforcement learning may be performed so as to match the operation status of 30.

The operation prediction model updating unit 210, for example, sets a period of M days in a period from time t2 to time t3 as a virtual prediction period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. As an example, the operation prediction model updating unit 210 determines that the error between the prediction result of the prediction period based on the value of the operation prediction factor in the period before the prediction period in the period from time t2 to time t3 and the actual data in the prediction period is , Minimum error (for example, 0) or reinforcement learning is performed so as to be less than a predetermined value.

For example, the demand forecast model updating unit 240 adaptively learns the demand forecast model based on the value of the demand forecast factor. The demand prediction model updating unit 240 may adaptively learn the demand prediction model using the demanded amount of hydrogen at each hydrogen station 60 in the period from time t2 to time t3. The demand forecast model updating unit 240 predicts the demand amount of hydrogen at the hydrogen station 60 during the period from time t2 to time t3 using the demand forecast model, and the obtained hydrogen station 60 during the period from time t2 to time t3. Reinforcement learning may be performed so as to match the demand amount of hydrogen in.

The demand prediction model update unit 240, for example, sets the period of M days in the period from time t2 to time t3 as a virtual prediction period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. As an example, the demand prediction model updating unit 240 determines that the error between the prediction result of the prediction period based on the value of the demand prediction factor in the period before the prediction period in the period from time t2 to time t3 and the actual data in the prediction period is , Minimum error (for example, 0) or reinforcement learning is performed so as to be less than a predetermined value.

For example, the power generation prediction model updating unit 270 adaptively learns the power generation prediction model based on the value of the power generation prediction factor. The power generation amount prediction model updating unit 270 may adaptively learn the power generation amount prediction model using the power generation amount of the renewable energy in each renewable energy power generation facility 20 in the period from time t2 to time t3. The power generation amount prediction model update unit 270 predicts the power generation amount in the renewable energy power generation facility 20 in the period from time t2 to time t3 using the power generation amount prediction model, and the result is obtained in the acquired period from time t2 to time t3. Reinforcement learning may be performed so as to match the amount of power generation in the renewable energy power generation facility 20.

As an example, the power generation amount prediction model updating unit 270 sets the period of M days in the period from time t2 to time t3 as a virtual prediction period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. As an example, the power generation amount prediction model updating unit 270 determines that the error between the prediction result of the prediction period based on the value of the power generation amount prediction factor in the period before the prediction period from time t2 to time t3 and the actual data of the prediction period is , Minimum error (for example, 0) or reinforcement learning is performed so as to be less than a predetermined value.

For example, the electricity price prediction model updating unit 300 adaptively learns the electricity price prediction model based on the value of the electricity price prediction factor. The electricity price prediction model updating unit 300 may adaptively learn the electricity price prediction model using the electricity price of the renewable energy in the period from time t2 to time t3. The electricity price prediction model update unit 300 predicts the electricity price of the renewable energy during the period from time t2 to time t3 using the electricity price prediction model, and the result of the obtained renewable energy during the period from time t2 to time t3 Reinforcement learning may be performed so as to match the electricity bill.

The electricity price prediction model updating unit 300, for example, sets the period of M days in the period from time t2 to time t3 as a virtual prediction period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. As an example, the electricity price prediction model updating unit 300 calculates the prediction result of the prediction period based on the value of the electricity price prediction factor in the period before the prediction period in the period from time t2 to time t3, and the actual data of the prediction period. Reinforcement learning is performed so that the error becomes the minimum error (for example, 0) or less than a predetermined value.

For example, the consumption prediction model updating unit 330 adaptively learns the consumption prediction model based on the value of the consumption prediction factor. The consumption prediction model updating unit 330 may adaptively learn the consumption prediction model using the hydrogen consumption amount in each hydrogen station 60 in the period from time t2 to time t3. The consumption prediction model update unit 330 uses the consumption prediction model to predict the amount of hydrogen consumed at the hydrogen station 60 in the period from time t2 to time t3, and the obtained result is the hydrogen station in the period from time t2 to time t3. Reinforcement learning may be performed so as to match the hydrogen consumption amount in 60.

As an example, the consumption prediction model update unit 330 sets the period of M days in the period from time t2 to time t3 as a virtual prediction period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. As an example, the consumption prediction model update unit 330 determines that the error between the prediction result of the prediction period based on the value of the consumption prediction factor in the period before the prediction period in the period from time t2 to time t3 and the actual data in the prediction period is , Minimum error (for example, 0) or reinforcement learning is performed so as to be less than a predetermined value.

For example, the storage amount prediction model updating unit 360 adaptively learns the storage amount prediction model based on the value of the storage amount prediction factor. The storage amount prediction model updating unit 360 may adaptively learn the storage amount prediction model using the storage amount of hydrogen of each hydrogen storage device 40 in the period from time t2 to time t3. The storage amount prediction model updating unit 360 predicts the storage amount of hydrogen of the hydrogen storage device 40 during the period from time t2 to time t3 using the storage amount prediction model, and obtains the result of the estimation during the period from time t2 to time t3. Reinforcement learning may be performed so as to match the hydrogen storage amount of the hydrogen storage device 40.

The storage amount prediction model updating unit 360, for example, sets the period of M days in the period from time t2 to time t3 as a virtual prediction period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. As one example, the storage amount prediction model updating unit 360 calculates the prediction result of the prediction period based on the value of the storage amount prediction factor in the period before the prediction period in the period from time t2 to time t3, and the actual data of the prediction period. Reinforcement learning is performed so that the error becomes the minimum error (for example, 0) or less than a predetermined value.

For example, the transportation prediction model updating unit 390 adaptively learns the transportation prediction model based on the value of the transportation prediction factor. The transportation prediction model updating unit 390 applies the transportation prediction model using the actual values of the transportation plan for transporting hydrogen between the plurality of hydrogen generators 30 and the plurality of hydrogen stations 60 in the period from time t2 to time t3. You may learn. The transportation prediction model updating unit 390 uses the transportation prediction model to predict the transportation plan in the period from time t2 to time t3, and the result matches the acquired transportation plan (or transportation record) in the period from time t2 to time t3. Reinforcement learning may be done.

As an example, the transportation prediction model updating unit 390 sets the period of M days in the period from time t2 to time t3 as a virtual prediction period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. As an example, the transportation prediction model updating unit 390 determines that the error between the prediction result of the prediction period based on the value of the transport prediction factor in the period before the period from time t2 to time t3 and the actual data in the prediction period is the minimum error. (For example, 0) or reinforcement learning is performed so as to be less than a predetermined value.

Further, the transportation plan model updating unit 420 may adaptively learn the transportation plan model based on the evaluation index for evaluating the productivity of the cooperation system. For example, the transportation plan model updating unit 420 may learn the transportation plan model using the learning data including the evaluation index in the period from time t2 to time t3. The transportation plan model updating unit 420 has a minimum (for example, 0), maximum, or a predetermined range of the evaluation index value for the transportation plan generated using the transportation plan model from the time t2 to the time t3. Reinforcement learning may be performed so that

As an example, the transportation plan model updating unit 420 sets the period of M days in the period from time t2 to time t3 as a virtual planning period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. Then, the transportation plan model updating unit 420, for the transportation plan in the planning period based on the value of the transportation planning factor in the period before the planning period from time t2 to time t3, indicates the evaluation index of the transportation plan executed in the planning period. Reinforcement learning may be performed so that the value is the minimum (for example, 0), the maximum, or within a predetermined range.

Further, the operation plan model updating unit 450 may adaptively learn the operation plan model based on the evaluation index for evaluating the productivity of the cooperation system. For example, the operation plan model updating unit 450 may learn the operation plan model using the learning data including the evaluation index in the period from time t2 to time t3. The operation plan model updating unit 450 has a minimum (for example, 0), maximum, or a predetermined range of the evaluation index value for the operation plan generated from the time t2 to the time t3 using the operation plan model. Reinforcement learning may be performed so that

As an example, the operation plan model updating unit 450 sets the period of M days in the period from time t2 to time t3 as a virtual planning period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. Then, the operation plan model updating unit 450, for the operation plan of the plan period based on the value of the operation plan factor of the period before the plan period from time t2 to time t3, the evaluation index of the operation plan executed in the plan period. Reinforcement learning may be performed so that the value is the minimum (for example, 0), the maximum, or within a predetermined range.

Further, the storage plan model updating unit 480 may adaptively learn the storage plan model based on the evaluation index for evaluating the productivity of the cooperation system. For example, the storage plan model updating unit 480 may learn the storage plan model using learning data including the evaluation index in the period from time t2 to time t3. The storage plan model updating unit 480 determines that the value of the evaluation index is minimum (for example, 0), maximum, or within a predetermined range for the storage plan generated using the storage plan model from time t2 to time t3. Reinforcement learning may be performed so that

The storage plan model updating unit 480, for example, sets the period of M days in the period from time t2 to time t3 as a virtual planning period. The M days may be, for example, a period of several days or ten and several days, one or several weeks, one or several months, one or several years. Then, the storage plan model update unit 480 determines the evaluation index of the storage plan executed in the plan period for the storage plan in the plan period based on the value of the storage plan factor in the period before the plan period from time t2 to time t3. Reinforcement learning may be performed so that the value is the minimum (for example, 0), the maximum, or within a predetermined range.

Note that the prediction periods in the respective components of the prediction unit 120 may be different periods or the same period. The planning period in each configuration of the planning unit 130 may be a different period or the same period. Further, the prediction period and the planning period may be different periods or the same period.

Further, the transportation plan model updating unit 420, the operation plan model updating unit 450, and the storage plan model updating unit 480 may learn a plurality of planning models according to one evaluation index. The transportation plan model update unit 420, the operation plan model update unit 450, and the storage plan model update unit 480 calculate the evaluation index with one objective function for two or more of the transportation plan, the operation plan, and the storage plan, for example. Then, the plurality of planning models may be reinforced and learned so that the value of the evaluation index is the minimum (for example, 0), the maximum, or within a predetermined range.

Next, the prediction unit 120 and the planning unit 130 update the learned learning model (S540). The prediction unit 120 and the planning unit 130 may update the learning model every predetermined time. For example, the prediction unit 120 and the planning unit 130 start adaptive learning, continue the adaptive learning for the initial update period required for updating, and then perform the first update of the learning model, and thereafter, at regular intervals. Repeat the update. Here, the initial update period is preferably longer than the planned period of the plan to be generated. Moreover, the fixed period of repeating the update may be several hours, ten and several hours, one day, several tens of hours, or several days. The prediction unit 120 and the planning unit 130 may update the learning model in different update periods or the same update period.

Next, the prediction unit 120 generates a prediction result using the learning model (S550). For example, the operation prediction unit 220 predicts the operation amount of the hydrogen generator 30 from time t4 to time t5 using the updated operation prediction model and the value of the operation prediction factor. The period from time t4 to time t5 is a period after the period from time t2 to time t3, and may be a future period at the prediction time point. As an example, the operation prediction unit 220 calculates the value of the operation prediction factor for N days acquired by the acquisition unit 100 in the initial update period and / or the value of the operation prediction factor including the prediction result generated by the prediction unit 120 as the operation prediction. Apply to the model to predict operating capacity in N days after the initial renewal period. The operation prediction unit 220 may supply the generated operation prediction to the storage unit 110 and store it therein.

For example, the demand prediction unit 250 predicts the demand (for example, demand amount) of hydrogen at the hydrogen station 60 from time t4 to time t5 using the updated demand prediction model and the value of the demand prediction factor. As an example, the demand prediction unit 250 calculates the value of the operation prediction factor for N days acquired by the acquisition unit 100 in the initial update period and / or the value of the operation prediction factor including the prediction result generated by the prediction unit 120 as the demand prediction. Apply to the model to predict demand for N days after the initial update period. The demand prediction unit 250 may supply the generated demand prediction to the storage unit 110 and store it therein.

For example, the power generation amount prediction unit 280 predicts the power generation amount of the renewable energy power generation facility 20 from time t4 to time t5 using the updated power generation amount prediction model and the value of the power generation amount prediction factor. As an example, the power generation amount prediction unit 280 sets the value of the power generation amount prediction factor for N days acquired by the acquisition unit 100 in the initial update period and / or the value of the power generation amount prediction factor including the prediction result generated by the prediction unit 120. , Is applied to a power generation prediction model to predict power generation in N days after the initial update period. The power generation amount prediction unit 280 may supply the generated power generation amount prediction to the storage unit 110 and store it therein.

For example, the electricity price prediction unit 310 predicts the electricity price of the renewable energy from the time t4 to the time t5 by using the updated electricity price prediction model and the value of the electricity price prediction factor. As an example, the electricity charge prediction unit 310 may obtain the value of the electricity charge prediction factor for N days acquired by the acquisition unit 100 during the initial update period and / or the value of the electricity charge prediction factor including the prediction result generated by the prediction unit 120. , It is applied to the electricity rate prediction model to forecast the electricity rate in N days after the initial renewal period. The electricity bill prediction unit 310 may supply the generated electricity bill prediction to the storage unit 110 to store the electricity bill prediction.

For example, the consumption prediction unit 340 predicts the amount of hydrogen consumed at the hydrogen station 60 from time t4 to time t5 using the updated values of the consumption prediction model and the consumption prediction factor. As an example, the consumption prediction unit 340 applies the value of the consumption prediction factor for N days acquired by the acquisition unit 100 and / or the value of the consumption prediction factor generated by the prediction unit 120 to the consumption prediction model in the initial update period. And predict the consumption in N days after the initial renewal period. The consumption prediction unit 340 may supply the generated consumption prediction to the storage unit 110 and store it therein.

For example, the storage amount prediction unit 370 uses the updated storage amount prediction model and the value of the storage amount prediction factor to predict the storage amount of hydrogen in the hydrogen storage device 40 from time t4 to time t5. As an example, the storage amount prediction unit 370 displays the value of the storage amount prediction factor for N days acquired by the acquisition unit 100 in the initial update period and / or the value of the storage amount prediction factor including the prediction result generated by the prediction unit 120. , It is applied to the storage amount prediction model to predict the storage amount in N days after the initial renewal period. The storage amount prediction unit 370 may supply the generated storage amount prediction to the storage unit 110 and store it therein.

For example, the transportation prediction unit 400 uses the updated transportation prediction model and transportation prediction factor values to plan transportation of hydrogen between the plurality of hydrogen generators 30 and the plurality of hydrogen stations 60 from time t4 to time t5. Predict. As an example, the transportation prediction unit 400 applies the value of the transportation prediction factor for N days acquired by the acquisition unit 100 during the initial update period and / or the value of the transportation prediction factor generated by the prediction unit 120 to the transportation prediction model. And forecast the transportation plan in N days after the initial renewal period. The transportation prediction unit 400 may supply the generated transportation prediction to the storage unit 110 to store the transportation prediction.

The planning unit 130 uses the updated learning model to generate a plan (S560). For example, the transportation planning unit 430 may apply the value of the transportation planning factor including the prediction result generated by the prediction unit 120 to the updated transportation planning model to generate the transportation plan from time t4 to time t5. As an example, the transportation planning unit 430 sets the value of the transportation planning factor for N days acquired by the acquisition unit 100 during the initial update period and / or the value of the transportation prediction factor including the prediction result generated by the prediction unit 120 to the transportation planning unit 430. Apply to the model to generate a transportation plan for N days after the initial update period.

Also, the transportation planning unit 430 may generate a transportation plan for each of the plurality of transportation means 50. When the plurality of transportation means 50 are substantially the same, the transportation planning unit 430 may respectively generate substantially the same transportation plans. Further, the transportation planning unit 430 may generate different transportation plans for each of the plurality of transportation means 50 including different types of transportation means 50, transportation means 50 of different transportation cost, or a combination thereof.

In this case, the transportation plan model generation unit 410 may generate a plurality of transportation plan models corresponding to each transportation means 50 or each combination of a plurality of transportation means 50. Further, the transportation plan model updating unit 420 may learn each of the plurality of transportation plan models and update each.

For example, the operation plan unit 460 may apply the value of the operation plan factor including the prediction result generated by the prediction unit 120 to the updated operation plan model to generate the operation plan from time t4 to time t5. As an example, the operation planning unit 460 sets the value of the operation plan factor for N days acquired by the acquisition unit 100 in the initial update period and / or the value of the operation prediction factor including the prediction result generated by the prediction unit 120 to the operation plan. Apply to the model to generate a work plan for N days after the initial update period.

Further, the operation planning unit 460 may generate an operation plan for each of the plurality of hydrogen generators 30. The operation planning unit 460 may generate substantially the same operation plans when the plurality of hydrogen generation devices 30 are substantially the same. In addition, the operation planning unit 460 generates different operation plans corresponding to different types of hydrogen generators 30, hydrogen generators 30 having different hydrogen generation costs, or a plurality of hydrogen generators 30 including a combination thereof. You can do it.

In this case, the operation plan model generation unit 440 may generate a plurality of operation plan models corresponding to each hydrogen generation device 30 or each combination of a plurality of hydrogen generation devices 30. Further, the operation plan model updating unit 450 may each learn a plurality of operation plan models and update each.

For example, the storage planning unit 490 may apply the value of the storage planning factor including the prediction result generated by the prediction unit 120 to the updated storage planning model to generate the storage plan from time t4 to time t5. As an example, the storage planning unit 490 sets the value of the storage planning factor for the N days acquired by the acquisition unit 100 in the initial update period and / or the value of the storage prediction factor including the prediction result generated by the prediction unit 120 to the storage plan. Apply to the model to generate a storage plan for N days after the initial renewal period.

Further, the storage planning unit 490 may generate a storage plan for each of the plurality of hydrogen storage devices 40. When the plurality of hydrogen storage devices 40 and / or the hydrogen generation devices 30 connected to the hydrogen storage devices 40 are substantially the same, the storage planning unit 490 may respectively generate substantially the same storage plans. In addition, when the hydrogen storage device 40 and / or the hydrogen generation device 30 connected to the hydrogen storage device 40 are of different types, the storage planning unit 490 corresponds to each of the plurality of hydrogen storage devices 40 and stores different hydrogen. A plan may be generated.

In this case, the storage plan model generation unit 470 may generate a plurality of storage plan models corresponding to each hydrogen storage device 40 or each combination of a plurality of hydrogen storage devices 40. Further, the storage plan model updating unit 480 may learn each of the plurality of storage plan models and update each of them.

The output unit 140 outputs the plan generated by the planning unit 130 (S570). Accordingly, each business operator of the system 10 that supplies hydrogen can operate and control each configuration of the system 10 according to the plan received by the management device 150.

After the plan is output by the planner 70 or after the period from time t4 to time t5 has elapsed (S580: No), the process returns to S530 and the planner 70 adaptively learns the learning model. In this case, the acquisition unit 100 sequentially acquires information on factors that change due to the operation of the target device during the period from the time t4 to the time t5, and sequentially stores the information in the storage unit 110. That is, the planning apparatus 70 includes the information of the period from the time t4 to the time t5 in the past information, and sets the target period as a period after the period from the time t4 to the time t5.

Then, the planning device 70 repeats the adaptive learning of the model, updates the model according to the lapse of a certain period, and generates and outputs the plan. As described above, the planning apparatus 70 according to the present embodiment can continuously output the plan while updating the learning model by repeating the generation of the plan for the target period and the operation of the system 10 during the target period.

In the above operation flow of the planning device 70, an example has been described in which the planning device 70 is operated in time series in the order of time t0 to t5. Here, each period may be a temporally continuous period.

The planning device 70 according to the present embodiment can predict the operation of each component in the system 10 by learning and create a plan that can efficiently supply hydrogen at low cost.

The planning device 70 includes an operation plan model generation unit 440, an operation plan model update unit 450, an operation plan unit 460, a storage plan model generation unit 470, a storage plan model update unit 480, and a storage plan unit 490. In this case, the planning device 70 may generate a transportation plan. Further, the planning device 70 includes a transportation plan model generating unit 410, a transportation planning model updating unit 420, a transportation planning unit 430, a storage planning model generating unit 470, a storage planning model updating unit 480, and a storage planning unit 490. May not be included, and in this case, the planning apparatus 70 may generate the operation plan.

Further, the planning device 70 may not have at least one configuration of the prediction unit 120, and in this case, the plan may be generated using the prediction result supplied from the external device. In addition, the planning apparatus 70 proposes an operation plan that proposes to increase or decrease the number of hydrogen generators 30 in the system 10, a transportation plan that proposes to increase or decrease the transportation means 50 in the system 10, and hydrogen storage in the system 10. A storage plan may be created that suggests increasing or decreasing the number of devices 40.

Further, the timings of generation of prediction results in the plurality of configurations of the prediction unit 120 may be different or may be the same. The timing of generating the plan data in the plurality of configurations of the planning unit 130 may be different or may be the same.

Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where a block is (1) a stage of a process in which an operation is performed or (2) an apparatus responsible for performing an operation. Section may be represented. Specific steps and sections are implemented by dedicated circuitry, programmable circuitry provided with computer readable instructions stored on a computer readable medium, and / or a processor provided with computer readable instructions stored on a computer readable medium. You may Dedicated circuits may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuits include memory elements such as logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, field programmable gate arrays (FPGA), programmable logic arrays (PLA), and the like. Reconfigurable hardware circuitry may be included, including, and the like.

Computer-readable media may include any tangible device capable of storing instructions executed by a suitable device, such that computer-readable media having instructions stored therein are designated by flowcharts or block diagrams. A product will be provided that includes instructions that can be executed to create a means for performing the operations. Examples of computer readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable media include floppy disks, diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), Electrically Erasable Programmable Read Only Memory (EEPROM), Static Random Access Memory (SRAM), Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD), Blu-Ray (RTM) Disc, Memory Stick, Integrated Circuit cards and the like may be included.

Computer readable instructions include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state set data, or object oriented programming such as Smalltalk, JAVA, C ++, etc. Language, Python, and any source or object code written in any combination of one or more programming languages, including conventional procedural programming languages such as the "C" programming language or similar programming languages. May be included.

Computer-readable instructions are provided to a processor or programmable circuit of a general purpose computer, a special purpose computer, or other programmable data processing device, locally or in a wide area network (WAN) such as a local area network (LAN), the Internet, or the like. Computer readable instructions may be executed to create a means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like.

FIG. 6 illustrates an example computer 1900 in which multiple aspects of the present invention may be embodied in whole or in part. The program installed in the computer 1900 can cause the computer 1900 to perform an operation associated with an apparatus according to an embodiment of the present invention or one or more sections of the apparatus, or the operation or the one or more sections. Sections may be executed and / or computer 1900 may perform processes or stages of processes according to embodiments of the invention. Such programs may be executed by CPU 2000 to cause computer 1900 to perform certain operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

The computer 1900 according to this embodiment is connected to the host controller 2082 by an input / output controller 2084 and a CPU peripheral part having a CPU 2000, a RAM 2020, a graphic controller 2075, and a display device 2080, which are mutually connected by a host controller 2082. An input / output unit having a communication interface 2030, a hard disk drive 2040, and a DVD drive 2060, a ROM 2010 connected to the input / output controller 2084, a flash memory drive 2050, and a legacy input / output unit having an input / output chip 2070. .

The host controller 2082 connects the RAM 2020 with the CPU 2000 and the graphic controller 2075 that access the RAM 2020 at a high transfer rate. The CPU 2000 operates based on the programs stored in the ROM 2010 and the RAM 2020, and controls each unit. The graphic controller 2075 acquires image data generated by the CPU 2000 or the like on a frame buffer provided in the RAM 2020 and displays it on the display device 2080. Instead of this, the graphic controller 2075 may internally include a frame buffer that stores image data generated by the CPU 2000 or the like.

The input / output controller 2084 connects the host controller 2082 to the communication interface 2030, hard disk drive 2040, and DVD drive 2060, which are relatively high-speed input / output devices. The communication interface 2030 communicates with other devices via a network by wire or wirelessly. Further, the communication interface functions as hardware that performs communication. The hard disk drive 2040 stores programs and data used by the CPU 2000 in the computer 1900. The DVD drive 2060 reads a program or data from the DVD 2095 and provides it to the hard disk drive 2040 via the RAM 2020.

Further, the ROM 2010, the flash memory drive 2050, and the relatively low-speed input / output device of the input / output chip 2070 are connected to the input / output controller 2084. The ROM 2010 stores a boot program executed by the computer 1900 at startup, and / or a program dependent on the hardware of the computer 1900. The flash memory drive 2050 reads a program or data from the flash memory 2090 and provides it to the hard disk drive 2040 via the RAM 2020. The input / output chip 2070 connects the flash memory drive 2050 to the input / output controller 2084, and inputs / outputs various input / output devices via, for example, a parallel port, a serial port, a keyboard port, a mouse port, or the like. Connect to controller 2084.

The program provided to the hard disk drive 2040 via the RAM 2020 is stored in a recording medium such as a flash memory 2090, a DVD 2095, or an IC card and provided by the user. The program is read from the recording medium, installed in the hard disk drive 2040 in the computer 1900 via the RAM 2020, and executed by the CPU 2000. The information processing described in these programs is read by the computer 1900, and causes the software and the various types of hardware resources described above to cooperate with each other. An apparatus or method may be configured by implementing the operation or processing of information according to the use of the computer 1900.

As an example, when communication is performed between the computer 1900 and an external device or the like, the CPU 2000 executes the communication program loaded on the RAM 2020, and based on the processing content described in the communication program, the communication interface. Instructing 2030 to perform communication processing. Under the control of the CPU 2000, the communication interface 2030 reads out the transmission data stored in the transmission buffer area or the like provided on the storage device such as the RAM 2020, the hard disk drive 2040, the flash memory 2090, or the DVD 2095 and transmits it to the network. Alternatively, the received data received from the network is written to the receiving buffer area or the like provided on the storage device. As described above, the communication interface 2030 may transfer the transmission / reception data to / from the storage device by the DMA (Direct Memory Access) method. Instead, the CPU 2000 transfers the storage device or the communication interface 2030 of the transfer source. The transmission / reception data may be transferred by reading the data from the device and writing the data to the transfer destination communication interface 2030 or the storage device.

In addition, the CPU 2000 DMAs all or necessary portions from files or databases stored in an external storage device such as a hard disk drive 2040, a DVD drive 2060 (DVD2095), a flash memory drive 2050 (flash memory 2090). The data is read into the RAM 2020 by transfer or the like, and various processing is performed on the data in the RAM 2020. Then, the CPU 2000 writes the processed data back to the external storage device by DMA transfer or the like. In such a process, the RAM 2020 can be regarded as temporarily holding the contents of the external storage device, and thus in the present embodiment, the RAM 2020 and the external storage device are collectively referred to as a memory, a storage unit, a storage device, or the like.

Various types of information such as various types of programs, data, tables, and databases according to the present embodiment are stored in such a storage device and are subject to information processing. Note that the CPU 2000 can also hold part of the RAM 2020 in the cache memory and read / write on the cache memory. Even in such a form, the cache memory plays a part of the function of the RAM 2020. Therefore, in the present embodiment, the cache memory is also included in the RAM 2020, the memory, and / or the storage device unless otherwise indicated. To do.

Further, the CPU 2000 performs various operations specified in the instruction sequence of the program on the data read from the RAM 2020, including various calculations, information processing, condition determination, information search / replacement, and the like. Process and write back to the RAM 2020. For example, in the case of performing the condition determination, the CPU 2000 determines whether or not the various variables shown in the present embodiment satisfy a condition such as being larger, smaller, above, below, or equal to other variables or constants. If the condition is satisfied (or not satisfied), a branch is made to a different instruction sequence or a subroutine is called.

Also, the CPU 2000 can search for information stored in a file or database in the storage device. For example, when a plurality of entries in which the attribute values of the second attribute are associated with the attribute values of the first attribute are stored in the storage device, the CPU 2000 determines that the entries of the plurality of entries stored in the storage device are stored. Corresponding to the first attribute satisfying a predetermined condition by searching the entry in which the attribute value of the first attribute matches the specified condition and reading the attribute value of the second attribute stored in the entry. The attribute value of the obtained second attribute can be obtained.

Also, when a plurality of elements are listed in the description of the embodiment, elements other than the listed elements may be used. For example, when it is described that "X executes Y using A, B and C", X may execute Y by using D in addition to A, B and C.

Although the present invention has been described using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is apparent to those skilled in the art that various changes or improvements can be made to the above embodiment. It is apparent from the description of the appended claims that embodiments with such changes or improvements can be included in the technical scope of the present invention.

The execution order of each processing such as operation, procedure, step, and step in the apparatus, system, program, and method shown in the claims, the description, and the drawings is particularly “before” or “before”. It should be noted that they can be realized in any order as long as the output of the previous process is not used in the subsequent process. For the convenience of description in the claims, the description, and the operation flow in the drawings, it is essential that the operation is performed in this order even if the description is made using “first”, “next”, and the like for convenience. is not.

10 system 20 renewable energy power generation facility 30 hydrogen generator 40 hydrogen storage device 50 transportation means 60 hydrogen station 70 planning device 80 electric power system 90 consumption means 100 acquisition unit 110 storage unit 120 prediction unit 130 planning unit 140 output unit 150 management device 200 Operation prediction model generation unit 210 Operation prediction model update unit 220 Operation prediction unit 230 Demand prediction model generation unit 240 Demand prediction model update unit 250 Demand prediction unit 260 Power generation prediction model generation unit 270 Power generation prediction model update unit 280 Power generation prediction unit 290 Electricity charge prediction model generation unit 300 Electricity charge prediction model update unit 310 Electricity charge prediction unit 320 Consumption prediction model generation unit 330 Consumption prediction model update unit 340 Consumption prediction unit 350 Storage amount prediction model generation unit 360 Storage amount prediction model update unit 370 Storage amount forecast 380 Transport Prediction Model Generation Unit 390 Transport Prediction Model Update Unit 400 Transport Prediction Unit 410 Transport Plan Model Generation Unit 420 Transport Plan Model Update Unit 430 Transport Planning Unit 440 Operation Plan Model Generation Unit 450 Operation Plan Model Update Unit 460 Operation Planning Unit 470 Storage plan model generation unit 480 Storage plan model update unit 490 Storage plan unit 1900 Computer 2000 CPU
2010 ROM
2020 RAM
2030 communication interface 2040 hard disk drive 2050 flash memory drive 2060 DVD drive 2070 input / output chip 2075 graphic controller 2080 display device 2082 host controller 2084 input / output controller 2090 flash memory 2095 DVD

Claims

An operation prediction unit that generates an operation prediction of each of a plurality of hydrogen generation devices that generate hydrogen using an operation prediction model,
A demand forecasting unit that generates a demand forecast for hydrogen at each of a plurality of hydrogen stations using a demand forecasting model,
A transportation plan for transporting hydrogen generated by the plurality of hydrogen generators to the plurality of hydrogen stations, using a transportation plan model, an operation prediction of each of the plurality of hydrogen generators and each of the plurality of hydrogen stations. And a transportation planning unit which is generated based on a transportation planning factor including the demand forecast of the vehicle.
For each of the plurality of renewable energy power generation facilities, further comprises a power generation amount prediction unit that generates a power generation amount prediction of renewable energy using a power generation amount prediction model,
The plan according to claim 1, wherein the operation prediction unit generates an operation prediction of each of the plurality of hydrogen generators that use renewable energy based on a power generation amount prediction of each of the plurality of renewable energy power generation facilities. apparatus.
And further comprising an electricity price prediction unit that generates an electricity price prediction for renewable energy using the electricity price prediction model,
The planning device according to claim 2, wherein the operation prediction unit generates an operation prediction of each of the plurality of hydrogen generation devices based on an operation prediction factor including the electricity price prediction.
The electricity price prediction model is an electricity price, a power demand, a power supply, a renewable energy power generation amount, weather information, and a power generation amount prediction amount of the renewable energy by the power generation amount prediction unit before the prediction target period. The planning apparatus according to claim 3, wherein the electricity price forecast of the renewable energy is calculated based on the electricity rate prediction factor including at least one.
The planning apparatus according to claim 3 or 4, further comprising an electricity price prediction model updating unit that updates the electricity price prediction model by learning using the actual value of the electricity price.
The operation predicting factor is, before the prediction target period, the operating amount of the plurality of hydrogen generators, the storage amount of hydrogen in the plurality of hydrogen storage devices that store hydrogen generated by the plurality of hydrogen generators, the plurality of 6. The method according to claim 3, further comprising at least one of a transport amount of hydrogen from the hydrogen storage device, a demand amount of hydrogen at each of the plurality of hydrogen stations, and the electricity price forecast for the forecast target period. Planning device according to paragraph.
The planning device according to any one of claims 1 to 6, further comprising an operation prediction model updating unit that updates the operation prediction model by learning using actual values of the operation amounts of the plurality of hydrogen generation devices.
A hydrogen consumption prediction in each of the plurality of hydrogen stations, further comprising a consumption prediction unit that generates using a consumption prediction model,
The said demand estimation part estimates the demand forecast of hydrogen in each of these hydrogen stations based on the demand forecast factor containing the hydrogen consumption forecast in each hydrogen station. Planning equipment.
The consumption prediction model is, before the prediction target period, the hydrogen demand in each of the plurality of hydrogen stations, the hydrogen consumption in each of the plurality of hydrogen stations, weather information, and each of the plurality of hydrogen stations A hydrogen consumption prediction of the plurality of hydrogen stations during the prediction target period based on a consumption prediction factor further including at least one factor related to the hydrogen usage amount of the service provided by using the hydrogen supplied from The planning device according to claim 8, which calculates.
The planning apparatus according to claim 9, further comprising a consumption prediction model updating unit that updates the consumption prediction model by learning using actual values of hydrogen consumption at each of the plurality of hydrogen stations.
The demand forecast model further includes at least one of a demand amount of hydrogen at each of the plurality of hydrogen stations and a hydrogen consumption amount at each of the plurality of hydrogen stations before the forecast target period. The planning device according to claim 9 or 10, which calculates a hydrogen demand forecast for each of the plurality of hydrogen stations in the forecast target period based on a factor.
The plan according to any one of claims 1 to 11, further comprising: a demand prediction model updating unit that updates the demand prediction model by learning using actual values of the demanded amount of hydrogen at each of the plurality of hydrogen stations. apparatus.
The storage amount prediction of hydrogen in each of the plurality of hydrogen storage devices that store hydrogen generated by the plurality of hydrogen generation devices, further comprising a storage amount prediction unit that uses a storage amount prediction model,
The transportation planning unit uses a transportation planning model to calculate a hydrogen transportation plan between each of the plurality of hydrogen storage apparatuses and each of the plurality of hydrogen stations. The planning device according to any one of claims 1 to 12, wherein the planning device is generated based on the transportation planning factor that further includes a storage amount prediction of.
The storage amount prediction model, the storage amount of hydrogen of the plurality of hydrogen storage device in the prediction target period, before the prediction target period, the operating amount of the plurality of hydrogen generators, hydrogen in the plurality of hydrogen storage devices Storage amount, a transport amount of hydrogen from the plurality of hydrogen storage devices, a demand amount of hydrogen at each of the plurality of hydrogen stations, and a storage amount prediction factor including at least one of operation predictions of the plurality of hydrogen generation devices The planning device according to claim 13, wherein the planning is performed based on the above.
The planning device according to claim 13 or 14, further comprising a storage amount prediction model updating unit that updates the storage amount prediction model by learning using actual values of the hydrogen storage amounts of the plurality of hydrogen storage devices.
The transportation planning factor is the operating amount of each of the plurality of hydrogen generators, the storage amount of hydrogen in each of the plurality of hydrogen storage devices, and the amount of hydrogen in each of the plurality of hydrogen stations before the prediction target period. 16. The planning device according to claim 13, further comprising at least one of demand amounts.
Productivity of the plurality of hydrogen generators, the plurality of hydrogen storage devices, a transportation means between each of the plurality of hydrogen storage devices and each of the plurality of hydrogen stations, and a cooperation system including the plurality of hydrogen stations The planning apparatus according to any one of claims 13 to 15, further comprising a transportation plan model updating unit that updates the transportation planning model by learning based on an evaluation index that evaluates.
18. The planning apparatus according to claim 17, wherein the evaluation index is based on at least one of an operating cost, sales, and profit of the cooperation system, and a cost per unit amount of hydrogen supplied by the cooperation system.
The plurality of hydrogen generators are used by using a transport prediction model based on a transport prediction factor including at least one of an operation forecast of each of the plurality of hydrogen generators and a hydrogen demand forecast at each of the plurality of hydrogen stations. The planning apparatus according to any one of claims 1 to 18, further comprising: a transportation prediction unit that generates a transportation prediction that is a transportation planning prediction for transporting hydrogen between the plurality of hydrogen stations.
An operation of generating an operation plan of each of the plurality of hydrogen generators using an operation plan model based on an operation plan factor including transportation prediction of hydrogen between the plurality of hydrogen generators and the plurality of hydrogen stations. The planning device according to claim 19, further comprising a planning unit.
21. The planning apparatus according to claim 20, which is dependent on claim 17 or 18, further comprising an operation plan model updating unit that updates the operation plan model by learning based on the evaluation index.
A storage plan of hydrogen in each of the plurality of hydrogen storage devices that store the hydrogen generated by the plurality of hydrogen generation devices, using a storage planning model, the operation prediction of the corresponding hydrogen generation device of the plurality of hydrogen generation device 22. and a storage planning unit for generating hydrogen based on a storage planning factor including a transportation prediction of hydrogen between the plurality of hydrogen generators and the plurality of hydrogen stations. 22. Planning equipment.
23. The planning apparatus according to claim 22, which is dependent on claim 17 or 18, further comprising a storage plan model updating unit that updates the storage plan model by learning based on the evaluation index.
A demand forecasting unit that generates a demand forecast for hydrogen at each of a plurality of hydrogen stations using a demand forecasting model,
A transportation prediction model is used to transport hydrogen between a plurality of hydrogen generators that generate hydrogen and the plurality of hydrogen stations based on a transportation prediction factor including a hydrogen demand prediction at each of the plurality of hydrogen stations. A transportation forecasting unit that generates a transportation forecast that is a forecast of a transportation plan;
An operation of generating an operation plan of each of the plurality of hydrogen generators using an operation plan model based on an operation plan factor including transportation prediction of hydrogen between the plurality of hydrogen generators and the plurality of hydrogen stations. A planning device having a planning section.
A step of generating an operation prediction of each of a plurality of hydrogen generators that generate hydrogen using an operation prediction model;
Generating a demand forecast for hydrogen at each of the plurality of hydrogen stations using a demand forecast model;
A transportation plan for transporting hydrogen generated by the plurality of hydrogen generators to the plurality of hydrogen stations, using a transportation plan model, an operation prediction of each of the plurality of hydrogen generators and each of the plurality of hydrogen stations. And a step of generating the transportation plan factor including a demand forecast of the vehicle.
Executed by a computer,
An operation prediction unit that generates an operation prediction of each of a plurality of hydrogen generation devices that generate hydrogen using an operation prediction model,
A demand forecasting unit that generates a demand forecast for hydrogen at each of a plurality of hydrogen stations using a demand forecasting model,
A transportation plan for transporting hydrogen generated by the plurality of hydrogen generators to the plurality of hydrogen stations, using a transportation plan model, an operation prediction of each of the plurality of hydrogen generators and each of the plurality of hydrogen stations. A planning program that functions as a transportation planning section that is generated based on transportation planning factors including the demand forecast of
Generating a demand forecast for hydrogen at each of the plurality of hydrogen stations using a demand forecast model;
A transportation prediction model is used to transport hydrogen between a plurality of hydrogen generators that generate hydrogen and the plurality of hydrogen stations based on a transportation prediction factor including a hydrogen demand prediction at each of the plurality of hydrogen stations. Generating a transportation forecast that is a forecast of the transportation plan;
Generating an operation plan for each of the plurality of hydrogen generators using an operation plan model based on an operation plan factor that includes transportation prediction of hydrogen between the plurality of hydrogen generators and the plurality of hydrogen stations. And a planning method comprising.
Executed by a computer,
A demand forecasting unit that generates a demand forecast for hydrogen at each of a plurality of hydrogen stations using a demand forecasting model,
A transportation prediction model is used to transport hydrogen between a plurality of hydrogen generators that generate hydrogen and the plurality of hydrogen stations based on a transportation prediction factor that includes a hydrogen demand prediction at each of the plurality of hydrogen stations. A transportation forecasting unit that generates a transportation forecast that is a forecast of a transportation plan;
An operation of generating an operation plan of each of the plurality of hydrogen generators using an operation plan model based on an operation plan factor including transportation prediction of hydrogen between the plurality of hydrogen generators and the plurality of hydrogen stations. A planning program that functions as a planning department.