CN116826796A - Demand control method, device and charge storage system - Google Patents
Demand control method, device and charge storage system Download PDFInfo
- Publication number
- CN116826796A CN116826796A CN202310651145.7A CN202310651145A CN116826796A CN 116826796 A CN116826796 A CN 116826796A CN 202310651145 A CN202310651145 A CN 202310651145A CN 116826796 A CN116826796 A CN 116826796A
- Authority
- CN
- China
- Prior art keywords
- load
- storage system
- charge
- energy storage
- user side
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000004146 energy storage Methods 0.000 claims abstract description 121
- 230000005611 electricity Effects 0.000 claims abstract description 114
- 230000008859 change Effects 0.000 claims abstract description 66
- 238000004422 calculation algorithm Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 15
- 230000002787 reinforcement Effects 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 230000009471 action Effects 0.000 claims description 10
- 238000010248 power generation Methods 0.000 claims description 9
- 238000011478 gradient descent method Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 description 11
- 238000007599 discharging Methods 0.000 description 11
- 230000001276 controlling effect Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 6
- 239000003795 chemical substances by application Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000003190 augmentative effect Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
- H02J3/144—Demand-response operation of the power transmission or distribution network
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
- H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
- H02J2310/58—The condition being electrical
- H02J2310/60—Limiting power consumption in the network or in one section of the network, e.g. load shedding or peak shaving
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a demand control method and device and a charge storage system, and belongs to the technical field of power control. The method is applied to a charge storage system, the charge storage system comprises a user side and an energy storage system, the charge storage system is connected with a power grid, and the method comprises the following steps: acquiring a historical electricity load of a user; based on the historical power utilization load, determining a load change trend of a user side in the next power utilization period; determining an energy storage charge-discharge power value corresponding to a next power utilization period based on a target demand value of a user side, a current power utilization load and a load change trend; and controlling the charge and discharge power of the energy storage system based on the energy storage charge and discharge power value. According to the method, the load change trend of the next electricity utilization period is determined through the historical electricity utilization load, the current load state and the future load trend of the charge storage system are synthesized, the reasonable energy storage charge-discharge power value is calculated, the charge-discharge behavior of the energy storage system is controlled, the demand of the charge storage system can be effectively reduced, and the purpose of saving electricity charge is achieved.
Description
Technical Field
The application belongs to the technical field of power control, and particularly relates to a demand control method, a demand control device and a charge storage system.
Background
Currently, most enterprises adopt a charging mode of two electricity prices. The two electricity generation prices are a system in which a basic electricity price corresponding to a capacity and an electricity price corresponding to an electricity consumption are combined to determine an electricity price. The basic electricity price is based on the transformer capacity or the maximum demand (the maximum value of average load of 15 minutes or 30 minutes in one month) of the enterprise as the basis for calculating the electricity price. The industrial enterprise can contract with the power supply department to determine the limit (i.e. contract demand), and the basic electric charge is fixedly charged each month, and the basic electric charge is additionally charged when the basic electric charge exceeds the limit; the basic electricity fee may also be charged in accordance with the actual maximum monthly demand (i.e., maximum demand).
In a charge storage system comprising an energy storage system and a user side load, an enterprise can achieve the purpose of saving electricity charge by controlling charge and discharge behaviors of the energy storage system and utilizing energy storage of the energy storage system.
The existing energy storage regulation and control scheme is divided into two types: firstly, acquiring real-time user load, and giving out energy storage real-time power through a certain rule, wherein the method is only suitable for a load storage system with higher capability of processing real-time data, and cannot guarantee that the load average value in the time granularity does not exceed a target demand value for a strategy with larger regulation and control time granularity; secondly, a load value with a time granularity is predicted through a certain prediction algorithm, and then energy storage real-time power is given out according to the predicted load value and a certain rule.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a demand control method, a demand control device and a charge storage system, which integrate the current load state and the future load trend, calculate reasonable energy storage charge-discharge power values to control the charge-discharge behavior of energy storage, effectively reduce the demand and save the electric charge.
In a first aspect, the present application provides a demand control method, the method being applied to a charge storage system, the charge storage system including a user side and an energy storage system, the charge storage system being connected to a power grid, the method comprising:
acquiring the historical electricity load of the user side;
based on the historical electricity load, determining a load change trend of the user side in the next electricity utilization period;
determining an energy storage charge-discharge power value corresponding to the next electricity utilization period based on the target demand value of the user side, the current electricity utilization load and the load change trend;
and controlling the charge and discharge power of the energy storage system based on the energy storage charge and discharge power value.
According to the demand control method, the load change trend of the next electricity utilization period is determined through the historical electricity utilization load, the current load state and the future load trend of the charge storage system are synthesized, the reasonable energy storage charge-discharge power value is calculated, the charge-discharge behavior of the energy storage system is controlled, the demand of the charge storage system can be effectively reduced, and the purpose of saving electricity charge is achieved.
According to one embodiment of the present application, the determining, based on the historical electricity load, a load change trend of the user side in a next electricity utilization period includes:
inputting the historical electricity load to a target prediction model, and obtaining the load change trend of the next electricity period output by the target prediction model;
the target prediction model is obtained through training of a supervised learning algorithm or a prediction algorithm based on historical load data samples of the load storage system.
According to one embodiment of the application, the target prediction model is a long-short-term memory neural network, and the long-short-term memory neural network is trained by a random gradient descent method.
According to an embodiment of the present application, the determining the stored energy charge-discharge power value corresponding to the next electricity utilization period based on the target demand value of the user side, the current electricity utilization load and the load variation trend includes:
inputting the target demand value, the current power consumption load and the load change trend into a target decision model to obtain the energy storage charge-discharge power value corresponding to the next power consumption period output by the target decision model;
The target decision model is obtained through training of a deep reinforcement learning algorithm based on a historical load data sample, a load change trend sample and a demand value sample of the load storage system.
According to one embodiment of the application, in the training process of the deep reinforcement learning algorithm, the input state of the target decision model comprises a user side load, an energy storage charge quantity, a demand value and a load trend, and the input action of the target decision model comprises energy storage charging and discharging power.
According to one embodiment of the application, the target decision model is a multi-layer perceptron neural network trained by an actor commentary algorithm.
According to one embodiment of the present application, the obtaining the historical electricity load of the user side includes:
and acquiring a historical load sequence of the user side in a historical electricity utilization period.
In a second aspect, the present application provides a demand control device, the device being applied to a charge storage system, the charge storage system comprising a user side and an energy storage system, the charge storage system being connected to a power grid, the device comprising:
the acquisition module is used for acquiring the historical electricity load of the user side;
The first processing module is used for determining the load change trend of the user side in the next power utilization period based on the historical power utilization load;
the second processing module is used for determining an energy storage charge-discharge power value corresponding to the next power utilization period based on the target demand value of the user side, the current power utilization load and the load change trend;
and the control module is used for controlling the charge and discharge power of the energy storage system based on the energy storage charge and discharge power value.
According to the demand control device, the load change trend of the next electricity utilization period is determined through the historical electricity utilization load, the current load state and the future load trend of the charge storage system are synthesized, the reasonable energy storage charge-discharge power value is calculated, the charge-discharge behavior of the energy storage system is controlled, the demand of the charge storage system can be effectively reduced, and the purpose of saving electricity charge is achieved.
In a third aspect, the present application provides a charge storage system connected to a power grid, the charge storage system comprising:
the system comprises a user side and an energy storage system, wherein the user side is connected with the energy storage system;
and the controller is connected with the user side and the energy storage system and is used for executing the demand control method in the first aspect.
According to one embodiment of the present application, further comprising:
and the power generation side is connected with the user side.
In a fourth aspect, the present application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the demand control method according to the first aspect as described above when executing the computer program.
In a fifth aspect, the present application provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a demand control method as described in the first aspect above.
In a sixth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements a demand control method as described in the first aspect above.
Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a schematic flow chart of a demand control method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a demand control device according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a charge storage system according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions of the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which are obtained by a person skilled in the art based on the embodiments of the present application, fall within the scope of protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
In the related art, there are two ways to perform energy storage regulation:
firstly, acquiring a real-time user load, and giving out energy storage real-time power through a certain rule, wherein the method is only suitable for a charge storage system with higher capability of processing real-time data, and cannot guarantee that the average value of the load in the time granularity does not exceed a target demand value for a strategy with larger regulation time granularity (such as issuing a charge and discharge power instruction once in 15 minutes);
secondly, a load value with a time granularity is predicted through a certain prediction algorithm, and then energy storage real-time power is given out according to the predicted load value and a certain rule.
The energy storage regulation and control effects of the two modes are poor, and the purpose of saving the required electricity charge cannot be achieved.
The method for controlling the demand, the demand control device, the load storage system, the electronic device and the readable storage medium provided by the embodiment of the application are described in detail below through specific embodiments and application scenes thereof with reference to the accompanying drawings.
The demand control device method can be applied to the terminal, and can be specifically executed by hardware or software in the terminal.
The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet having a touch sensitive surface (e.g., a touch screen display and/or a touch pad). It should also be appreciated that in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer having a touch-sensitive surface (e.g., a touch screen display and/or a touch pad).
In the following various embodiments, a terminal including a display and a touch sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.
The execution body of the demand control device method provided by the embodiment of the present application may be an electronic device or a functional module or a functional entity capable of implementing the demand control device method in the electronic device, where the electronic device includes, but is not limited to, a mobile phone, a tablet computer, a camera, a wearable device, and the like, and the demand control device method provided by the embodiment of the present application is described below by taking the electronic device as an execution body.
The method for controlling the demand according to the embodiment of the present application is applied to the charge storage system 310.
The charge storage system 310 includes a user side 312 and an energy storage system 311, the charge storage system 310 is connected to the power grid 320, the user side 312 can use the electric energy provided by the power grid 320, and the energy storage system 311 can also store the electric energy for the user side 312 to use.
The energy storage system 311 may include energy storage batteries, energy storage converters, energy storage controllers, and the like.
As shown in fig. 1, the demand control device method includes: steps 110 to 140.
Step 110, obtaining a historical electricity load of the user side 312.
The historical electricity load is historical load data of electricity used by the user side 312.
In this embodiment, the historical electricity load of the user side 312 may be obtained by collecting the electricity load data of the electricity meter set by the user side 312.
It will be appreciated that, according to the historical electricity load of the user side 312, the time-varying rule of the electricity load of the user side 312 can be analyzed, so as to determine whether the electricity load of the user side 312 will rise or fall in the future.
Step 120, based on the historical electricity load, determining the load change trend of the user side 312 in the next electricity period.
In this embodiment, the electricity consumption process of the user side 312 is divided into a plurality of electricity consumption periods according to a preset time granularity, and the load change trend of the next electricity consumption period is analyzed according to the historical electricity consumption load.
Taking a time granularity of 5 minutes as an example.
The duration of each power utilization period is 5 minutes, and the load change trend of the user side 312 in the next period of 5 minutes is determined according to the historical power utilization load of the user side 312.
In actual execution, the time granularity can be 1 minute, 3 minutes, 5 minutes and other times of time, so that the calculation of the required value is facilitated; the time granularity is set within 15 minutes so as to control the demand, save the electricity charge, and the time granularity larger than 15 minutes cannot achieve the effect of controlling the demand.
In this embodiment, the load change trend of the next power utilization period indicates whether the power utilization load of the user side 312 will rise or fall in the next power utilization period, and the load change trend has two categories, namely rising and falling.
In actual implementation, the load change trend may be represented by a numerical value, for example, an increase corresponds to 0 and a decrease corresponds to 1.
The load change trend may also be represented using a slope, for example, the possible power load for the next power use period is 120kW, the current load is 100kW, and the load change trend is 20; if the next power utilization period is likely 80kW, the load variation trend is equal to minus 20.
It should be noted that, the load change trend of the next power utilization period represents the change trend of the power utilization load of the user side 312, and is not the accurate power utilization value of the user side 312 in the next period, so that the prediction accuracy of the load change trend is higher, and the calculation complexity is lower.
It will be appreciated that, according to the historical electricity load of the user side 312, the load change trend of the user side 312 in the next electricity usage period is determined, and the historical electricity load of the user side 312 may be the electricity load data in the past historical electricity usage period.
In some embodiments, step 110 of obtaining the historical electricity load of the user side 312 may include:
a historical load sequence of the user side 312 during a historical electricity usage period is obtained.
In this embodiment, the historical load sequence is a sequence formed by power load data of a plurality of past power consumption periods, and the power consumption process of the user side 312 can be divided into a plurality of power consumption periods according to a preset time granularity, so as to obtain the power load data of the past power consumption periods (i.e. the historical power consumption periods) and obtain the historical load sequence.
Taking a time granularity of 5 minutes as an example.
And acquiring a historical load sequence with the time granularity of 5 minutes in the past 1 hour, wherein the historical load sequence comprises power utilization load data corresponding to 12 power utilization time periods.
And judging the load change trend of the user side 312 in the next 5-minute period according to the change rule of the power load data in the historical load sequence.
Step 130, determining an energy storage charge-discharge power value corresponding to the next electricity utilization period based on the target demand value of the user side 312, the current electricity utilization load and the load variation trend.
The target demand value may be a contract demand of the user side 312, or may be a current actual maximum demand of the user side 312 in the current month, where whether the target demand value is the contract demand or the maximum demand is determined according to an electric charge settlement manner of the user side 312.
The current power load of the user side 312 may be power load data of the user side 312 at the current time, or may be power load data of the user side 312 in the current power period.
In this step, according to the target demand value, the current power consumption load and the load change trend of the user side 312, the current system state of the load storage and the future load trend are combined, and the energy storage charge-discharge power value reasonable in the next power consumption period is calculated.
Step 140, controlling the charge and discharge power of the energy storage system 311 based on the energy storage charge and discharge power value.
In this embodiment, according to the stored energy charging and discharging power value corresponding to the next electricity utilization period, the charging and discharging power of the energy storage system 311 in the next electricity utilization period is regulated and controlled, so that the demand of the charge storage system 310 can be effectively reduced, and the purpose of saving electricity charge is achieved.
In actual implementation, the energy storage charge-discharge power value may be issued to an energy storage converter of the energy storage system 311, and the charge-discharge power of the energy storage system 311 is controlled by the energy storage converter.
It can be understood that the energy storage charging and discharging power value has two situations, namely an energy storage charging power value and an energy storage discharging power value, when the energy storage charging and discharging power value is the energy storage charging power value, the energy storage system 311 is controlled to charge according to the energy storage charging power value, and when the energy storage charging and discharging power value is the energy storage discharging power value, the energy storage system 311 is controlled to discharge according to the energy storage discharging power value.
In the related art, according to the real-time user load, the energy storage real-time power is regulated and controlled, and the method is only suitable for a system with higher capability of processing real-time data, and for a strategy with larger regulation and control time granularity, the load average value in the time granularity cannot be ensured not to exceed the target demand value.
According to the embodiment of the application, the historical electricity load of the user side 312 is used for predicting the load change trend of the next electricity utilization period of the user side 312, so that the power regulation and control of the next electricity utilization period of the energy storage system 311 are realized, the data processing capability requirement is lower, and the load value in the electricity utilization period for carrying out the power regulation and control is ensured not to exceed the preset demand value by adjusting the time granularity of the electricity utilization period.
In the related technology, by predicting a load value of a time granularity in the future and then giving out energy storage real-time power according to the predicted load value and a certain rule, the accuracy requirement on a prediction algorithm is higher, when the load fluctuation of a user side is larger, the accurate load value is difficult to predict, and the strategy possibly gives out an opposite energy storage control instruction.
According to the embodiment of the application, the load change trend of the future electricity utilization period is predicted, an accurate power value is not required to be predicted, the prediction accuracy is higher, the calculation complexity is lower, the current load state and the future load trend are integrated, a reasonable energy storage charge-discharge power value can be calculated for energy storage regulation and control, the required amount can be effectively reduced, and the electricity charge is saved.
According to the demand control method provided by the embodiment of the application, the load change trend of the next electricity utilization period is determined through the historical electricity utilization load, the current load state and the future load trend of the charge storage system 310 are synthesized, the reasonable energy storage charge-discharge power value is calculated, the charge-discharge behavior of the energy storage system 311 is controlled, the demand of the charge storage system 310 can be effectively reduced, and the purpose of saving electricity charge is achieved.
In some embodiments, step 120, determining the load change trend of the user side 312 in the next power utilization period based on the historical power utilization load may include:
inputting the historical electricity load into a target prediction model to obtain a load change trend of the next electricity period output by the target prediction model;
the target prediction model is obtained through training of a supervised learning algorithm or a prediction algorithm based on historical load data samples of the load storage system 310.
In this embodiment, the historical load data samples of the load storage system 310 may be actual electricity load data of the electricity usage side over a period of time.
And according to the historical load sequence of the user side 312 in the historical electricity utilization period, predicting through a target prediction model to obtain the load change trend of the user side 312 in the next electricity utilization period.
Taking a time granularity of 5 minutes as an example.
A historical load sequence of 5 minutes time granularity in the past 1 hour is obtained, and the load change trend of the user side 312 in the next 5 minutes period is predicted by the target prediction model.
The historical load data sample of the training target prediction model may be real electricity load data of the electricity utilization side in a period of 1 month or more.
It can be appreciated that the greater the data volume of the historical load data samples, the greater the prediction accuracy of the trained target prediction model.
In this embodiment, the target prediction model may be trained by a supervised learning algorithm or predictive algorithm.
The input of the target prediction model is a load sequence of a past period, the output is a change trend of a load of a future period, training is carried out through a supervision learning algorithm, a deterministic label is given to the change trend of the future load, the correlation characteristic of load data and time can be learned through the training of the prediction algorithm, and the future can be predicted by utilizing the historical data.
In some embodiments, the target prediction model may be a long-short term memory neural network, which may be trained by a random gradient descent method.
Among them, long Short-Term Memory neural network (LSTM) is a time-circulating neural network capable of learning Long-Term dependence.
In this embodiment, the electricity consumption of the industry or enterprise with the charge storage system 310 is mostly regular, and the electricity consumption of the charge storage system 310 is learned through the long-short-term memory neural network, and the random gradient descent method is collected for training, so that the load change trend of the user side 312 in the next electricity consumption period can be accurately predicted.
In some embodiments, step 130, determining the energy storage charge-discharge power value corresponding to the next power utilization period based on the target demand value of the user side 312, the current power utilization load and the load variation trend may include:
inputting the target demand value, the current power load and the load change trend into a target decision model to obtain an energy storage charge-discharge power value corresponding to the next power utilization period output by the target decision model;
the target decision model is obtained by training a deep reinforcement learning algorithm based on a historical load data sample, a load change trend sample and a demand value sample of the load storage system 310.
In this embodiment, the input of the target decision model trained by the deep reinforcement learning algorithm is a target demand value, a current power load and a load change trend corresponding to the next power period, and the output is an energy storage charge and discharge power value corresponding to the next power period.
It can be understood how to determine the decision problem of the next power utilization period for regulating the energy storage charging/discharging power value of the energy storage system 311 belongs to the future period.
Reinforcement learning (Reinforcement Learning, RL) is one type of machine learning, and unlike supervised learning and unsupervised learning, rewards are obtained by continuous interaction of agents with the environment (i.e., taking action), thereby constantly optimizing its own action strategy in hopes of maximizing its long term benefit (sum of rewards), which is suitable for solving decision-making problems.
In this embodiment, through the deep reinforcement learning algorithm (Deep Reinforcement Learning, DRL), the target decision model is trained by combining the historical load data sample, the load change trend sample, the demand value sample and other samples of the charge storage system 310, and the trained target decision model can output a reasonable energy storage charge-discharge power value, so as to reduce the demand of the charge storage system 310 and save the electricity charge.
In some embodiments, the target decision model is a multi-layer perceptron neural network that is trained by actor commentary algorithms.
In some embodiments, during training of the deep reinforcement learning algorithm, the input state of the target decision model includes a user side load, an energy storage charge amount, a demand value and a load trend, and the input action of the target decision model includes energy storage charge and discharge power.
The user side load and the stored energy charge are data of a historical load data sample of the charge storage system 310, the user side load is a power consumption load of the user side 312 of the charge storage system 310, and the stored energy charge is a charge of the energy storage system 311 of the charge storage system 310.
The demand value is data of a demand value sample of the charge storage system 310, and the load trend is data of a load change trend sample.
In actual implementation, the load change trend sample may be a sample formed by output data of the target prediction model, that is, the target prediction model is trained by the historical load data sample of the load storage system 310, and then the load change trend sample and the demand value sample of the target prediction model are combined to train the target decision model.
A specific embodiment is described below.
In this embodiment, the load variation trend of the next electricity utilization period is predicted by the target prediction model, and the energy storage charge-discharge power value of the next electricity utilization period is output by the target decision model in combination with the current load state and the future load trend, so as to control the charge-discharge behavior of the energy storage system 311, so as to reduce the demand of the charge storage system 310 and save the electricity charge.
1. Model training stage.
The target prediction model is represented by a symbol f, the time granularity of the target prediction model for prediction is 5 minutes, the current time granularity is represented by a symbol t, and the load on the user side at the moment t is represented by l t And (3) representing.
The input of the target prediction model is represented by the symbol x, x t ＝[l t-11 ,…,l t ]Is a 12-dimensional vector representing the last 12 5 minutes of user side load, i.e., the past 1 hour of historical load sequence.
In actual implementation, x t Or can be a 6-dimensional vector, i.e. a historical load sequence of the past 0.5 hours, x t The dimension of (c) may be adjusted according to the actual situation.
The output of the target prediction model is represented by a symbol f (x), and f (x) represents the load change trend of 5 minutes in the future predicted by the target prediction model.
In this embodiment, the load change trend adopts a one hot encoding method, which is a 2-dimensional vector, and f (x) is [1,0] when the load change trend is rising, and f (x) is [0,1] when the load change trend is falling.
In some embodiments, the load trend may also be represented by the load variance Δl=l t+1 -l t The expression form of the load change trend can be adjusted according to actual conditions.
The target prediction model is trained by the following steps:
step 1, acquiring electricity load data of the charge storage system 310 for the past n days, and processing the electricity load data into historical load data samples.
The electrical load data is processed at a time granularity of 5 minutes, with historical load data samples being a set of (x, y) sets.
Where x is the 12 5-minute user side load, and y is the 13 th 5-minute load change trend value.
In this embodiment, when l 13 >l 12 At the time y= [1,0]When l 13 ≤l 12 At the time y= [0,1]。
And 2, randomly selecting samples (x, y) from the historical load data samples, and inputting the x into a prediction model f to obtain a prediction result f (x).
And 3, calculating cross entropy loss based on f (x) and y, and updating parameters of the target prediction model by using a random gradient descent method.
And 4, repeatedly executing the steps 2 to 4 until the target prediction model converges or the iteration reaches the specified number of rounds.
Step 5: and saving the trained target prediction model.
The target decision model is trained by the following steps:
step 1, initializing a simulation environment, and randomly selecting 0 time of one day from load data of the past n days of the load storage system 310 as an initial state.
In the energy storage scenario, 1 day is generally used as one round of reinforcement learning, the power consumption behavior of the user side 312 is also 1 cycle for 1 day, the initial state of the round is selected as 0, and the end state of the round is selected as 24.
In actual execution, 1 week may also be selected as one round of reinforcement learning.
Step 2: the simulation environment feeds back the state s of the current moment t to the intelligent agent (namely the target decision model) t 。
Wherein the state s t Is vector (l) t ,soc t ,dt,f(x t ),t)，l t Representing the load on the user side, soc at time t t Represents the energy storage charge quantity at the time t, d t Represents the demand value at time t, f (x t ) And the load trend of the t+1 time predicted by the target prediction model is shown.
Step 3: the intelligent agent is based on the state s t Output action a t 。
Wherein action a t ∈[-P ess ,P ess ]Action a t Is energy storage charging and discharging power.
In this embodiment, when a t The sign is positive to indicate the charging behavior, when a t The sign is negative to indicate discharge behavior, the value to indicate power value, P ess Representing the power rating of the battery of the energy storage system 311.
Step 4: the simulation environment is based on state s t And action a t Transition to the next state s t+1 And feed back the prize value r t+1 。
In this embodiment, the prize valuer t+1 Representing a demand control reward, and when the grid-connected point power of the next power utilization period is higher than the corresponding demand value, the reward value r t+1 Is negative, when the grid-connected point power of the next power utilization period is lower than the corresponding demand value, the value r is rewarded t+1 Positive values.
In actual implementation, the grid-connected point power of the next power utilization period may be the sum of the power utilization load of the next power utilization period and the energy storage charge-discharge power value of the next power utilization period.
Step 5, step(s) t ,a t ,r t+1 ,s t+1 ) Saving in a cache.
And 6, repeatedly executing the steps 1 to 5 until the round is finished or the designated times are reached.
In this step, the round means 1 day.
Step 7: randomly selecting n(s) t ,a t ,r t+1 ,s t+1 ) And updating parameters of the agent target decision model by using an actor commentator algorithm.
Step 8: and repeatedly executing the steps 1 to 7 until convergence or reaching the designated number of rounds.
Step 9: and saving the trained target decision model.
2. Model reasoning stage.
Step 1, acquiring a historical load sequence [ l ] with granularity of 5 minutes in the past hour t-11 ,…,l t ]。
And step 2, predicting through a trained target prediction model to obtain the load change trend of the next 5 minutes.
Step 3, the target demand value and the current power load of the user side 312 are obtained.
And 4, obtaining the energy storage charge and discharge power value of the next 5 minutes through a trained target decision model according to the target demand value of the user side 312, the current power load and the load change trend of the next 5 minutes.
And 5, transmitting the energy storage charge-discharge power value to the energy storage converter, and controlling the charge-discharge state and power of the energy storage system 311.
In the embodiment, the current load state and the future load trend of the charge storage system 310 are comprehensively considered, and the reasonable energy storage charge-discharge power value is calculated through the target prediction model and the target decision model, so that the method is suitable for the charge storage system 310 with larger control time granularity, and the influence of the load value prediction precision difference on the energy storage control effect can be solved.
According to the method for controlling the demand, provided by the embodiment of the application, the execution main body can be the demand control device. In the embodiment of the present application, a method for executing the demand control device by the demand control device is taken as an example, and the demand control device provided in the embodiment of the present application is described.
The embodiment of the application also provides a demand control device.
The demand control device is applied to a charge storage system 310, the charge storage system 310 comprises a user side 312 and an energy storage system 311, and the charge storage system 310 is connected with a power grid 320.
As shown in fig. 2, the demand control device includes:
an obtaining module 210, configured to obtain a historical electricity load of the user side 312;
a first processing module 220, configured to determine a load change trend of the user side 312 in a next power utilization period based on the historical power utilization load;
The second processing module 230 is configured to determine an energy storage charge-discharge power value corresponding to the next power utilization period based on the target demand value of the user side 312, the current power utilization load and the load variation trend;
the control module 240 is configured to control the charge and discharge power of the energy storage system 311 based on the energy storage charge and discharge power value.
According to the demand control device provided by the embodiment of the application, the load change trend of the next electricity utilization period is determined through the historical electricity utilization load, the current load state and the future load trend of the charge storage system 310 are synthesized, the reasonable energy storage charge-discharge power value is calculated, and the charge-discharge behavior of the energy storage system 311 is controlled, so that the demand of the charge storage system 310 can be effectively reduced, and the purpose of saving electricity charge is realized.
In some embodiments, the first processing module 220 is configured to input a historical electricity load into the target prediction model, and obtain a load variation trend of a next electricity period output by the target prediction model;
the target prediction model is obtained through training of a supervised learning algorithm or a prediction algorithm based on historical load data samples of the load storage system 310.
In some embodiments, the target predictive model is a long-short term memory neural network that is trained by a random gradient descent method.
In some embodiments, the second processing module 230 is configured to input the target demand value, the current power load and the load variation trend to the target decision model, and obtain the stored energy charge-discharge power value corresponding to the next power utilization period output by the target decision model;
the target decision model is obtained by training a deep reinforcement learning algorithm based on a historical load data sample, a load change trend sample and a demand value sample of the load storage system 310.
In some embodiments, during training of the deep reinforcement learning algorithm, the input state of the target decision model includes a user side load, an energy storage charge amount, a demand value and a load trend, and the input action of the target decision model includes energy storage charge and discharge power.
In some embodiments, the target decision model is a multi-layer perceptron neural network that is trained by actor commentary algorithms.
In some embodiments, the obtaining module 210 is configured to obtain a historical load sequence of the user side 312 during a historical electricity usage period.
The demand control device in the embodiment of the application can be an electronic device or a component in the electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. By way of example, the electronic device may be a mobile phone, tablet computer, notebook computer, palm computer, vehicle-mounted electronic device, mobile internet appliance (Mobile Internet Device, MID), augmented reality (augmented reality, AR)/Virtual Reality (VR) device, robot, wearable device, ultra-mobile personal computer, UMPC, netbook or personal digital assistant (personal digital assistant, PDA), etc., but may also be a server, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (TV), teller machine or self-service machine, etc., and the embodiments of the present application are not limited in particular.
The demand control device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, and the embodiment of the present application is not limited specifically.
The demand control device provided in the embodiment of the present application can implement each process implemented by the method embodiment of fig. 1, and in order to avoid repetition, a detailed description is omitted here.
The embodiment of the application also provides a charge storage system 310.
As shown in fig. 3, the charge storage system 310 is connected to a power grid 320, and the charge storage system 310 includes:
the user side 312 and the energy storage system 311, wherein the user side 312 is connected with the energy storage system 311;
the controller is connected with the user side 312 and the energy storage system 311, and is used for executing the demand control method.
According to the charge storage system 310 provided by the embodiment of the application, the load change trend of the next electricity utilization period is determined through the historical electricity utilization load, the current load state and the future load trend of the charge storage system 310 are synthesized, the reasonable energy storage charge-discharge power value is calculated, and the charge-discharge behavior of the energy storage system 311 is controlled, so that the demand of the charge storage system 310 can be effectively reduced, and the purpose of saving electricity charge is achieved.
In some embodiments, the charge storage system 310 may also include a power generation side.
In this embodiment, the power generation side is connected to the user side 312, and the power generation power of the power generation side can be taken into account in the user side load.
For example, the power generation side may be a photovoltaic power generation device and the user side load is the actual load of the user side 312 that reduces the optical power of the photovoltaic power generation device.
In some embodiments, as shown in fig. 4, an electronic device 400 is further provided in the embodiments of the present application, which includes a processor 401, a memory 402, and a computer program stored in the memory 402 and capable of running on the processor 401, where the program, when executed by the processor 401, implements the processes of the foregoing embodiments of the method of the demand control device, and the same technical effects are achieved, and for avoiding repetition, a detailed description is omitted herein.
The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device.
The embodiment of the application also provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the processes of the method embodiment of the demand control device, and can achieve the same technical effects, and in order to avoid repetition, the description is omitted here.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes computer readable storage medium such as computer readable memory ROM, random access memory RAM, magnetic or optical disk, etc.
The embodiment of the application also provides a computer program product, which comprises a computer program, wherein the computer program realizes the method of the demand control device when being executed by a processor.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes computer readable storage medium such as computer readable memory ROM, random access memory RAM, magnetic or optical disk, etc.
The embodiment of the application further provides a chip, the chip comprises a processor and a communication interface, the communication interface is coupled with the processor, the processor is used for running programs or instructions, the processes of the method embodiment of the demand control device can be realized, the same technical effects can be achieved, and the repetition is avoided, and the description is omitted here.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the application, the scope of which is defined by the claims and their equivalents.
Claims (13)
1. A demand control method, wherein the method is applied to a charge storage system, the charge storage system comprising a user side and an energy storage system, the charge storage system being connected to a power grid, the method comprising:
acquiring the historical electricity load of the user side;
based on the historical electricity load, determining a load change trend of the user side in the next electricity utilization period;
determining an energy storage charge-discharge power value corresponding to the next electricity utilization period based on the target demand value of the user side, the current electricity utilization load and the load change trend;
and controlling the charge and discharge power of the energy storage system based on the energy storage charge and discharge power value.
2. The demand control method according to claim 1, wherein the determining a load change trend of the user side in a next electricity usage period based on the historical electricity usage load includes:
inputting the historical electricity load to a target prediction model, and obtaining the load change trend of the next electricity period output by the target prediction model;
the target prediction model is obtained through training of a supervised learning algorithm or a prediction algorithm based on historical load data samples of the load storage system.
3. The demand control method according to claim 2, wherein the target prediction model is a long-short-term memory neural network, and the long-short-term memory neural network is trained by a random gradient descent method.
4. The demand control method according to any one of claims 1 to 3, wherein the determining the stored energy charge-discharge power value corresponding to the next electricity utilization period based on the target demand value of the user side, the current electricity utilization load, and the load change trend includes:
inputting the target demand value, the current power consumption load and the load change trend into a target decision model to obtain the energy storage charge-discharge power value corresponding to the next power consumption period output by the target decision model;
the target decision model is obtained through training of a deep reinforcement learning algorithm based on a historical load data sample, a load change trend sample and a demand value sample of the load storage system.
5. The demand control method according to claim 4, wherein in the training process of the deep reinforcement learning algorithm, the input state of the target decision model includes a user side load, an energy storage charge amount, a demand value and a load trend, and the input action of the target decision model includes energy storage charge and discharge power.
6. The demand control method of claim 4, wherein the target decision model is a multi-layer perceptron neural network trained by an actor commentator algorithm.
7. A demand control method according to any one of claims 1 to 3, wherein the obtaining the historical electricity load of the user side includes:
and acquiring a historical load sequence of the user side in a historical electricity utilization period.
8. A demand control device, wherein the device is applied to a charge storage system, the charge storage system comprising a user side and an energy storage system, the charge storage system being connected to a power grid, the device comprising:
the acquisition module is used for acquiring the historical electricity load of the user side;
the first processing module is used for determining the load change trend of the user side in the next power utilization period based on the historical power utilization load;
the second processing module is used for determining an energy storage charge-discharge power value corresponding to the next power utilization period based on the target demand value of the user side, the current power utilization load and the load change trend;
and the control module is used for controlling the charge and discharge power of the energy storage system based on the energy storage charge and discharge power value.
9. A charge storage system, wherein the charge storage system is connected to a power grid, the charge storage system comprising:
the system comprises a user side and an energy storage system, wherein the user side is connected with the energy storage system;
a controller connected to the user side and the energy storage system, the controller being configured to perform the demand control method of any one of claims 1-7.
10. The charge storage system of claim 9, further comprising:
and the power generation side is connected with the user side.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the demand control method according to any one of claims 1-7 when executing the program.
12. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the demand control method according to any one of claims 1-7.
13. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the demand control method as claimed in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310651145.7A CN116826796A (en) | 2023-06-02 | 2023-06-02 | Demand control method, device and charge storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310651145.7A CN116826796A (en) | 2023-06-02 | 2023-06-02 | Demand control method, device and charge storage system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116826796A true CN116826796A (en) | 2023-09-29 |
Family
ID=88115935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310651145.7A Pending CN116826796A (en) | 2023-06-02 | 2023-06-02 | Demand control method, device and charge storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116826796A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117728472A (en) * | 2023-12-29 | 2024-03-19 | 日新鸿晟智慧能源(上海)有限公司 | User side energy storage working day fine calculation method and fine calculation model |
-
2023
- 2023-06-02 CN CN202310651145.7A patent/CN116826796A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117728472A (en) * | 2023-12-29 | 2024-03-19 | 日新鸿晟智慧能源(上海)有限公司 | User side energy storage working day fine calculation method and fine calculation model |
| CN117728472B (en) * | 2023-12-29 | 2024-05-28 | 日新鸿晟智慧能源(上海)有限公司 | User side energy storage working day fine calculation method and fine calculation model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wan et al. | Model-free real-time EV charging scheduling based on deep reinforcement learning | |
| Lu et al. | Multi-agent deep reinforcement learning based demand response for discrete manufacturing systems energy management | |
| CN112529727A (en) | Micro-grid energy storage scheduling method, device and equipment based on deep reinforcement learning | |
| Raglend et al. | Solution to profit based unit commitment problem using particle swarm optimization | |
| Fuselli et al. | Action dependent heuristic dynamic programming for home energy resource scheduling | |
| Jasmin et al. | Reinforcement learning approaches to economic dispatch problem | |
| Zhou et al. | Reinforcement learning-based scheduling strategy for energy storage in microgrid | |
| Huang et al. | A control strategy based on deep reinforcement learning under the combined wind-solar storage system | |
| Lu et al. | A hybrid deep learning-based online energy management scheme for industrial microgrid | |
| CN112491094B (en) | Hybrid-driven micro-grid energy management method, system and device | |
| CN108429256A (en) | Operation of Electric Systems optimization method and terminal device | |
| CN116826796A (en) | Demand control method, device and charge storage system | |
| Tan et al. | Bi-level optimization of charging scheduling of a battery swap station based on deep reinforcement learning | |
| Kong et al. | Real-time pricing method for VPP demand response based on PER-DDPG algorithm | |
| Odonkor et al. | Automated design of energy efficient control strategies for building clusters using reinforcement learning | |
| Soman et al. | Peak forecasting for battery-based energy optimizations in campus microgrids | |
| Lv et al. | Hierarchical learning optimisation method for the coordination dispatch of the inter‐regional power grid considering the quality of service index | |
| CN117726143A (en) | Environment-friendly micro-grid optimal scheduling method and system based on deep reinforcement learning | |
| CN116545025A (en) | Optimal scheduling method, device, equipment and storage medium for power distribution network | |
| Liu et al. | Deep reinforcement learning for stochastic dynamic microgrid energy management | |
| Sun et al. | DSM pricing method based on A3C and LSTM under cloud-edge environment | |
| Liu et al. | Pricing and charging scheduling for cooperative electric vehicle charging stations via deep reinforcement learning | |
| Dou et al. | Double‐deck optimal schedule of micro‐grid based on demand‐side response | |
| Hu et al. | Fractional-order long-term price guidance mechanism based on bidirectional prediction with attention mechanism for electric vehicle charging | |
| CN116845930A (en) | Energy storage control method and device of micro-grid system and micro-grid system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |