WO2020103048A1 - 储能管理及控制方法、系统、计算机设备、存储介质 - Google Patents

储能管理及控制方法、系统、计算机设备、存储介质

Info

Publication number
WO2020103048A1
WO2020103048A1 PCT/CN2018/116767 CN2018116767W WO2020103048A1 WO 2020103048 A1 WO2020103048 A1 WO 2020103048A1 CN 2018116767 W CN2018116767 W CN 2018116767W WO 2020103048 A1 WO2020103048 A1 WO 2020103048A1
Authority
WO
WIPO (PCT)
Prior art keywords
energy storage
sequence
energy
electricity
storage device
Prior art date
Application number
PCT/CN2018/116767
Other languages
English (en)
French (fr)
Inventor
徐楠
苏明
王春光
陈光濠
Original Assignee
亿可能源科技（上海）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 亿可能源科技（上海）有限公司 filed Critical 亿可能源科技（上海）有限公司
Priority to CN201880002440.7A priority Critical patent/CN111466063B/zh
Priority to PCT/CN2018/116767 priority patent/WO2020103048A1/zh
Publication of WO2020103048A1 publication Critical patent/WO2020103048A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • 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
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Definitions

  • the present application relates to the technical field of industrial control, in particular to an energy storage management method, an energy storage control method, various systems, computer equipment, and storage media.
  • the grid calculates the cost of power supply in a more timely manner.
  • some places have more closely combined the cost of power supply and the price of electricity, thus forming a way to use floating electricity prices.
  • the floating electricity price means that the electricity price purchased by the electricity user changes with time.
  • how to better use energy storage devices to reduce electricity costs has become an urgent problem to be solved.
  • the purpose of the present application is to provide an energy storage management method, an energy storage control method, and various systems, computer equipment, and storage media, for solving the problem of how to use an energy storage device to reduce electricity costs in the prior art.
  • the first aspect of the present application provides an energy storage management method for managing an energy storage device that provides stored electrical energy for a power consumer.
  • the energy storage management method includes the following steps: acquiring A power supply prediction sequence available to the power consumer and a power consumption prediction sequence of the power consumer within a power consumption period; and energy storage parameters of the energy storage device acquired based on preset acquisition conditions , And the power supply prediction sequence and the power consumption prediction sequence in the power consumption period, generating the energy sequence of the energy storage device in the power consumption period, so that the energy storage device is based on the energy sequence management.
  • the power supply prediction sequence includes a power price prediction sequence
  • the step of obtaining a power price prediction sequence within a power consumption cycle includes any one of the following: Electricity price forecasting sequence within the electricity period; based on the deviation between the acquired historical electricity price forecasting sequence and the corresponding historical actual electricity price, predicting the electricity price forecasting sequence within the electricity usage period available to the electricity consumer; based on The obtained electricity price related information predicts the electricity price prediction sequence within the electricity consumption period.
  • the power supply prediction sequence includes a self-power supply amount prediction sequence of a self-powered system
  • the step of acquiring the self-power supply amount prediction sequence within a power consumption period includes: Based on the acquired power generation related information of the self-powered system, predict a self-powered amount prediction sequence in the power consumption period.
  • the step of obtaining a power consumption prediction sequence of a power consumer includes: obtaining power consumption-related information according to power consumption factors within the power consumption cycle; and according to The power consumption related information is used to predict the power consumption prediction sequence in the power consumption period.
  • the energy storage parameter based on the energy storage device acquired with a preset acquisition condition, and a power supply prediction sequence and power consumption in the power consumption period includes: under at least one constraint condition, with the total power consumption price in the power consumption period as the optimization goal, generated in The energy sequence of the energy storage device in the power consumption period; wherein the constraint condition includes a constraint condition determined based on the energy storage parameter.
  • the step of describing an energy sequence of the energy storage device includes: under at least one constraint condition, generating one or more candidate energy sequences within the power consumption period; and under at least one constraint condition
  • the low total price of electricity consumption in the cycle is the optimization goal, and the generated one or more candidate energy sequences are optimized to obtain the energy sequence of the energy storage device in the electricity consumption cycle.
  • the step of optimizing the generated one or more candidate energy sequences includes: according to the optimization goal of lowering the total electricity price within the electricity cycle And the set cut-off condition, determine a candidate energy sequence from the one or more candidate energy sequences, and use it as the energy sequence; and when the cut-off condition is not satisfied, under at least one constraint condition, based on The updating strategy updates the generated at least one candidate energy sequence, and repeats the above steps according to the updated candidate energy sequence until there is a candidate energy sequence that meets the cut-off condition.
  • the energy storage parameters include at least two of the following: detected or predicted energy stored by the energy storage device, capacity of the energy storage device, and charge of the energy storage device Discharge parameters, loss parameters of energy storage devices.
  • the acquisition condition includes at least one of the following: an event to update a power supply prediction sequence, an event to update a power consumption prediction sequence, and an update cycle; wherein, the update cycle is It is determined based on the update cycle of the power supply prediction sequence and / or the update cycle of the power consumption prediction sequence.
  • the energy storage management method further includes the step of displaying at least one of the energy sequence, the power supply prediction sequence, and the power consumption prediction sequence.
  • a second aspect of the present application provides an energy storage control method for controlling an energy storage device that provides stored electrical energy for a consumer.
  • the energy storage control method includes the following steps: acquiring the energy storage management method described above The generated energy sequence of the energy storage device within a power consumption period; based on the energy value corresponding to the operation time interval in the acquired energy sequence, it is determined that the energy storage device is used to control the energy storage device in the operation time interval Describe the control information for the operation of the energy storage device.
  • the energy storage control method further includes a step of controlling the operation of the energy storage device within a corresponding operation time interval based on the control information.
  • the energy storage control method further includes the step of acquiring and displaying at least one of the energy sequence, the power supply prediction sequence, and the power consumption prediction sequence.
  • the energy storage control method further includes the step of updating the control information based on the newly generated energy sequence.
  • control information includes at least one of the following: charge and discharge control information of the energy storage device, and a target energy storage value of the energy storage device during the operation time interval.
  • a third aspect of the present application provides an energy storage management system for managing an energy storage device that provides stored electrical energy for an electricity consumer, including: an acquisition module for acquiring energy available for the electricity consumer within a power consumption period The used power supply prediction sequence and the power consumption prediction sequence of the electricity consumer; and a generation module for the energy storage parameter of the energy storage device acquired based on the preset acquisition condition and the electricity consumption period The power supply prediction sequence and the power consumption prediction sequence of the energy storage device to generate the energy sequence of the energy storage device in the power consumption period, so that the energy storage device is managed based on the energy sequence.
  • the power supply prediction sequence includes a power price prediction sequence
  • the acquisition module includes at least one of the following: a first acquisition unit, configured to acquire the power consumption period The electricity price prediction sequence within; the second acquisition unit for predicting the electricity price within the electricity consumption period available to the electricity consumer based on the deviation between the acquired historic electricity price prediction sequence and the corresponding historical actual electricity price A prediction sequence; a third acquisition unit, configured to predict the electricity price prediction sequence within the electricity consumption period based on the acquired electricity price related information.
  • the power supply prediction sequence includes a self-power supply amount prediction sequence of a self-powered system
  • the acquisition module includes a fourth acquisition unit that is based on the acquired self-powered system The relevant information of power generation is used to predict the self-supply amount prediction sequence in the power consumption period.
  • the acquisition module includes a fifth acquisition unit configured to acquire electricity-related information according to electricity consumption factors in the electricity consumption cycle; and according to the electricity-related information Information to predict the power consumption prediction sequence within the power consumption cycle.
  • the generation module includes: a generation unit configured to optimize the total power consumption price within the power consumption cycle under at least one constraint condition, Generating an energy sequence of the energy storage device during the power consumption period; wherein the constraint condition includes a constraint condition determined based on the energy storage parameter.
  • the generating unit is configured to generate one or more candidate energy sequences within the power consumption period under at least one constraint condition; and under at least one constraint condition And optimize the generated one or more candidate energy sequences to obtain the energy of the energy storage device in the electricity consumption cycle with the total electricity price in the electricity consumption cycle as the optimization goal sequence.
  • the generating unit is configured to select from one or more Determine one candidate energy sequence from each candidate energy sequence and use it as the energy sequence; and when the cut-off condition is not satisfied, under at least one constraint condition, perform the at least one candidate energy sequence generated according to the update strategy Update, and repeat the above steps according to the updated candidate energy sequence until there is a candidate energy sequence that meets the cut-off condition.
  • the energy storage parameters include at least two of the following: detected or predicted energy stored by the energy storage device, capacity of the energy storage device, and charge of the energy storage device Discharge parameters, loss parameters of energy storage devices.
  • the acquisition condition includes at least one of the following: an event to update a power supply prediction sequence, an event to update a power consumption prediction sequence, and an update period; wherein, the update period is It is determined based on the update cycle of the power supply prediction sequence and / or the update cycle of the power consumption prediction sequence.
  • the energy storage management system further includes an output module for outputting at least one of the energy sequence, the power supply prediction sequence, and the power consumption prediction sequence for display .
  • a fourth aspect of the present application provides an energy storage control system for controlling an energy storage device that provides stored electrical energy for a consumer, including: an acquisition module for acquiring an energy storage management system as described above The generated energy sequence of the energy storage device within a power consumption period; a determination module for determining the energy storage device in the operation time interval based on the energy value corresponding to the operation time interval in the acquired energy sequence Control information for controlling the operation of the energy storage device.
  • the energy storage control system further includes a control module for controlling the operation of the energy storage device within a corresponding operation time interval based on the control information.
  • the energy storage control system further includes: a display module configured to acquire and display at least one of the energy sequence, the power supply prediction sequence, and the power consumption prediction sequence .
  • the energy storage control system further includes: an update module, configured to update the control information based on the newly generated energy sequence.
  • control information includes at least one of the following: charge and discharge control information of the energy storage device, and a target energy storage value of the energy storage device in the predicted time interval.
  • a fifth aspect of the present application provides a server, including: an interface unit for acquiring power supply related information available to a power consumer within a power consumption cycle and power consumption related information of the power consumer; a storage unit, For storing at least one program; and a processing unit for calling the at least one program to coordinate the interface unit and the storage unit to execute the energy storage management method as described above.
  • a sixth aspect of the present application provides a computer device, including: an interface unit for acquiring power supply related information available to a power consumer within a power consumption cycle and power consumption related information of the power consumer; a storage unit, For storing at least one program; and a processing unit for calling the at least one program to coordinate the interface unit and the storage unit to execute the energy storage control method as described above.
  • a seventh aspect of the present application provides a computer-readable storage medium that stores at least one program that executes the energy storage management method described above when called.
  • An eighth aspect of the present application provides a computer-readable storage medium that stores at least one program that executes the energy storage control method described above when called.
  • a ninth aspect of the present application provides an energy storage control system, including: the server as described above and the computer device as described above.
  • the energy storage management method, energy storage control method, systems, computer equipment, and storage medium of the present application have the following beneficial effects: based on the acquired power supply prediction sequence, power consumption prediction sequence, and energy storage device storage
  • the energy parameter generates an energy sequence of the energy storage device within a power consumption period, so that the energy storage device can be managed based on the energy sequence, thereby achieving the purpose of lowest total price of electricity consumption.
  • Figure 1 shows the schematic diagram of the electric energy transmission relationship between the power generation system, self-powered system, power consumption system and energy storage device.
  • FIG. 2 shows a schematic structural diagram of an embodiment of the server of the present application.
  • FIG. 3 shows a flowchart of the energy storage management method of the present application.
  • 4a to 4d respectively show schematic diagrams of the electricity price prediction sequence, the self-supply amount prediction sequence, the power consumption prediction sequence and the energy storage device energy sequence within a power consumption cycle based on the energy storage management method of the present application.
  • FIG. 5 shows a schematic diagram of the total electricity price obtained by the electricity user based on the energy storage management method of the present application and the total electricity price when there is no energy storage device.
  • FIG. 6 shows a schematic structural diagram of an embodiment of the computer device of the present application.
  • FIG. 7 shows a flowchart of the energy storage control method of the present application.
  • FIG. 8 shows a schematic structural diagram of an embodiment of an energy storage management system running on a server side of this application.
  • FIG. 9 shows a schematic structural diagram of an energy storage control system operated by a computer device according to an embodiment of the present application.
  • FIG. 10 shows a schematic diagram of a network architecture of an energy storage control system according to an embodiment of the present application.
  • A, B or C or "A, B and / or C” means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C” .
  • the exception to this definition only occurs when a combination of elements, functions, steps, or operations are inherently mutually exclusive in certain ways.
  • FIG. 1 shows a schematic diagram of the power transmission relationship between the power generation system, the self-powered system, the power consumption system, and the energy storage device.
  • the power generation system is managed by the power supplier, and the self-powered system, power consumption system and energy storage device are located on the side of the power consumer, park, building, etc.
  • the power generation system provides power to the power consumption system and energy storage device through the power grid .
  • Self-powered system is used to provide electricity to the electricity system.
  • self-powered systems such as solar power generation systems, wind power generation systems, energy conversion power generation systems, etc.
  • energy storage devices such as chemical energy storage devices.
  • the existing two-stage electricity price mechanism it is easy to design the control method of the energy storage device to store electricity when the electricity price is low and release the electricity when the electricity price is high, so as to achieve the purpose of reducing electricity charges.
  • the electricity price mechanism changes from a two-stage sectionalized electricity price to a multi-stage sectionalized electricity price and other charging methods that fluctuate with time, the control of the energy storage device becomes extremely complicated.
  • this application provides an energy storage management method for managing Energy storage device to store electrical energy.
  • the energy storage management method is mainly executed by an energy storage management system.
  • the energy storage management system may be a software system configured on the server side, which uses the hardware of the configured server side to execute a corresponding program to provide the energy consumer with the energy sequence of the energy storage device within the power cycle to be predicted, so that The electric party can manage the energy storage device based on the energy sequence.
  • the power consumption cycle is exemplified by natural days and natural months.
  • the energy sequence refers to a set of multiple energy values of the energy storage device to be managed in chronological order within the power consumption cycle.
  • the generated energy sequence of the energy storage device can be used to help the user manage the energy storage device, so as to manage the energy storage device to achieve the purpose of using the lowest cost of electricity in each power cycle.
  • the present application provides an energy storage management method.
  • the energy storage management method is mainly executed by the server.
  • the server includes but is not limited to a single server, server cluster, distributed server group, cloud server, etc.
  • the cloud server includes a public cloud (Public Cloud) server and a private cloud (Private Cloud) server, where the public or private cloud server includes Software-as-a-Service (software as a service, SaaS ), Platform-as-a-Service (Platform as a Service, PaaS) and Infrastructure-as-a-Service (Infrastructure as a Service, IaaS), etc.
  • the private cloud server is, for example, Facebook Cloud Computing Service Platform, Amazon Cloud Computing Service Platform, Baidu Cloud Computing Platform, Tencent Cloud Computing Platform, and so on.
  • the service end is in communication with the electricity price distribution system of the electricity supplier, the energy storage control system of the energy storage device, the electricity control system of the electricity consumer, the production activity management system, the self-powered system, etc.
  • the electricity price issuance system is a system where electricity suppliers (or power market managers, such as government departments) issue electricity prices.
  • the electricity price issuance system publishes the electricity price forecast sequence every 24 minutes thereafter.
  • the energy storage control system includes but is not limited to: a detection device for detecting energy stored in the energy storage device, a charge and discharge control system of the energy storage device, and the like.
  • the power consumption control system includes, but is not limited to: a metering device (such as an electricity meter) installed in an enterprise, an electrical equipment control system, and the like.
  • the production activity management system includes but is not limited to: production process execution system (MES, Manufacturing Execution System), enterprise resource planning system (ERP, Enterprise Resource) Planning, etc.
  • the self-powered system includes but is not limited to: a detection device for detecting the power generation amount of the self-powered system, a power generation control system of the self-powered system, and the like.
  • Examples of the third-party system include its own server for storing historical electricity data, a server for storing historical electricity price data, and a WEB server for acquiring enterprise electricity plans.
  • Examples of the Internet data include weather forecast data and the like, where the weather forecast data may be predicted based on historical weather weather data acquired from the Internet, or weather forecast data directly acquired from a weather website or other websites.
  • FIG. 2 shows a schematic structural diagram of an embodiment of the server of the present application.
  • the server includes an interface unit 11, a storage unit 12, and a processing unit 13.
  • the storage unit 12 includes a non-volatile memory, a storage server, and the like.
  • the non-volatile memory is exemplified by solid-state hard disk or U disk.
  • the storage server is used to store the acquired various power consumption related information and power supply related information.
  • the interface unit 11 includes a network interface, a data line interface, and the like.
  • the network interface includes but is not limited to: a network interface device based on Ethernet, a network interface device based on a mobile network (3G, 4G, 5G, etc.), a network interface device based on short-range communication (WiFi, Bluetooth, etc.), etc.
  • the data line interface includes but is not limited to: USB interface, RS232, etc.
  • the interface unit is in data connection with each system of the power supply side, each system of the power consumption side, a third-party system, the Internet, and the like.
  • the processing unit 13 connects the interface unit 11 and the storage unit 12 and includes at least one of a CPU or a chip with integrated CPU, a programmable logic device (FPGA), and a multi-core processor.
  • the processing unit 13 also includes a memory for temporarily storing data, such as a memory, a register.
  • the energy storage management method mainly depends on the processing unit 13 in the server to execute, by the processing unit reading at least one program stored in the storage unit 12, and according to the processing unit and the storage unit, the interface unit and other hardware units Hardware connection between them to exchange data.
  • the processing unit may perform the following steps at the beginning of the electricity price change to obtain the energy sequence provided by the energy storage management method to manage the energy storage device during the current electricity consumption cycle .
  • the actual electricity consumption of the electricity consumer is constantly changing, and the energy stored in the energy storage device needs to be adaptively adjusted in time so that the electricity cost of the electricity consumer in the entire electricity settlement cycle is as low as possible.
  • the processing unit will repeatedly perform the following steps to adjust the energy in the energy storage device in time.
  • the power supply prediction and the power consumption prediction sequence available to the power consumer within a power consumption period are obtained.
  • the power consumption cycle is the aforementioned power consumption cycle to be predicted, which may be a predetermined power consumption cycle, or may be a power consumption cycle set according to the available variable power price change cycle.
  • the floating electricity price change period refers to the time interval of electricity price change.
  • the period of change in floating electricity prices is the length of time that a single electricity price is maintained.
  • the period of change in floating electricity prices is the update duration of a floating electricity price sequence.
  • the power supply prediction sequence includes a plurality of sets of power supply quantities predicted by a power supplier, a self-powered system, or a third party in a time sequence during a power consumption period.
  • the third party includes a plurality of sets of power supply quantities predicted in chronological order during the power consumption cycle based on simulations obtained from power consumers regarding power supply-related parameter data, historical power supply data, and the like.
  • the power supply prediction sequence includes a power price prediction sequence.
  • the step of obtaining the power supply prediction sequence within a power consumption period in step S110 includes the step of obtaining the power price prediction sequence within a power consumption period.
  • the electricity price prediction sequence refers to a set of a plurality of electricity prices predicted in chronological order within the electricity consumption period.
  • the step of obtaining the electricity price prediction sequence within a power consumption period may include directly obtaining the electricity price prediction sequence from a third party and using it as the power supply prediction sequence in step S110.
  • the electricity price prediction sequence provided by a third party is usually a electricity price prediction sequence spanning a certain length of time. Therefore, the above electricity consumption period can also be set based on the time span of the electricity price prediction sequence provided by a third party. In the case that the electricity price prediction sequence provided by the third party spans 12 hours, the above electricity consumption period may be set to 12 hours or less, so that the electricity price prediction sequence obtained from the third party can be directly used in subsequent processing.
  • the step of acquiring the electricity price forecast sequence within a power consumption period may include: based on the acquired historical electricity price forecast sequence And the deviation between the corresponding historical actual electricity prices, predicting the electricity price prediction sequence within the electricity consumption period available to the electricity consumer, so as to improve the accuracy of the electricity price prediction sequence on which the energy sequence is generated, In turn, the accuracy of the generated energy sequence is improved.
  • the historical electricity price prediction sequence provided by a third party and the corresponding historical actual electricity price are first obtained.
  • a historical electricity price prediction sequence of a certain historical time period (such as the previous year) can be obtained from a third party or other data platform, and the historical actual electricity price corresponding to at least one historical electricity price prediction value in the historical electricity price prediction sequence can be obtained; and Calculate the electricity price error between the above historical electricity price forecast value and the corresponding historical actual electricity price to obtain a electricity price error range; using the above electricity price error range as a correction parameter, the electricity price within the electricity cycle obtained from a third party
  • the prediction sequence is modified to obtain the electricity price prediction sequence on which the energy sequence is generated.
  • multiple electricity price error ranges can also be obtained according to the length of time, and based on the multiple electricity price error ranges The electricity price prediction sequence of the corresponding duration within the electricity consumption period is revised.
  • the power supplier does not provide the electricity price prediction sequence
  • the step of obtaining the electricity price prediction sequence within a power consumption period may include: predicting the electricity price cycle based on the obtained electricity price related information Electricity price forecast sequence.
  • the electricity price-related information includes, but is not limited to, at least one of the following: historical actual electricity price series, electricity price rules in the electricity market, other factors that affect electricity price changes, and so on.
  • the historical actual electricity price sequence refers to a collection of a plurality of actual electricity prices in chronological order within a certain historical time period. For example, historical actual electricity price sequences can be obtained from third parties or other data platforms.
  • the electricity price rules in the electricity market refer to electricity price rules set by the local government or electricity supplier for the area under its jurisdiction, which include but are not limited to: fine electricity prices set based on the electricity demand of the electricity consumers. Examples of the other factors that affect electricity price changes include weather and holidays. For example, the electricity price prediction sequence within a power consumption period is predicted based on the obtained weather forecast, the published holiday vacation schedule, and the historical actual electricity price sequence, etc.
  • the electricity price forecast sequence is obtained by establishing a forecast model.
  • the historical actual electricity price series, weather forecast, holiday vacation arrangement, etc. are used as the input of the prediction model, and prediction algorithms such as random forest (Random Forest), long-short-term memory network (LSTM), iterative decision tree (GBRT), convolutional neural network (CNN), etc., to obtain the electricity price prediction sequence within the power consumption cycle as output.
  • prediction algorithms such as random forest (Random Forest), long-short-term memory network (LSTM), iterative decision tree (GBRT), convolutional neural network (CNN), etc.
  • the results of the electricity price prediction sequence can be corrected according to the error range of the prediction model.
  • the above embodiments for obtaining the electricity price prediction sequence are only examples, rather than limitations on the present application.
  • a person skilled in the art can construct a model for predicting a price forecast sequence in combination with the foregoing various embodiments. For example, based on the input of the above prediction model, the prediction algorithm used, and the error range of the historical electricity price data obtained through detection, the electricity price prediction sequence is calculated, so as to improve the accuracy of subsequent predictions.
  • the power supply prediction sequence further includes a self-power supply amount prediction sequence.
  • the self-power supply amount prediction sequence refers to a set of a plurality of self-power supply amounts predicted in chronological order within a power consumption period.
  • the self-powered system includes but is not limited to: photovoltaic power generation system, heat conversion system, triple supply system, wind energy power generation system, and the like.
  • the step of obtaining the power supply prediction sequence in a power consumption cycle in step S110 includes the step of obtaining the self-power supply amount prediction sequence in a power consumption cycle.
  • the step S110 includes predicting a self-powered amount prediction sequence within the power consumption period based on the acquired power generation related information of the self-powered system.
  • the power generation related information includes but is not limited to: historical power generation data, and factors affecting power generation based on the working principle of the self-powered system.
  • the factors that affect power generation mainly include solar irradiance.
  • the factors that affect power generation mainly include wind speed and wind direction.
  • the factors that affect power generation mainly include the heat conversion efficiency of the system, the detected temperature, and so on.
  • a self-powered quantity prediction sequence by establishing a prediction model.
  • the results of the self-power supply amount prediction sequence can be corrected according to the error range of the prediction model.
  • the above implementations of the obtained self-power supply amount prediction sequence are only examples, rather than limitations on the present application.
  • a person skilled in the art may combine various embodiments mentioned in the aforementioned electricity price prediction sequence to construct a model for predicting the self-powered amount prediction sequence. For example, based on the input of the prediction model, the prediction algorithm used, and the error range obtained by the detection, the self-powered quantity prediction sequence is calculated to improve the accuracy of subsequent predictions.
  • the power supply prediction sequence obtainable by performing the step S110 may include only the electricity price prediction sequence or the self-power supply amount prediction sequence; There are no restrictions here.
  • the step of acquiring the power consumption prediction sequence of the power consumer includes: obtaining power consumption related information according to the power consumption factors in the power consumption cycle, and predicting the power consumption related information according to the power consumption related information Power consumption forecast sequence within the power consumption cycle.
  • the power consumption prediction sequence refers to a set of a plurality of power consumption predicted in chronological order within the power consumption cycle.
  • the electricity consumption obtained by the electricity consumer is related to the electricity consumption factors of its daily production activities.
  • the power consumption factors include but are not limited to: artificial plans such as production schedules, shopping mall activity plans, and plans summarized according to weather or social activity laws (such as working days and holidays).
  • the power-related information may include historical power consumption data of the product A produced, equipment usage information determined based on the production schedule of the product A, power consumption information of the equipment, etc. .
  • the power-related information may include air-conditioning use information set based on the season, air-conditioning power use information, work day and holiday lighting lamps, computer use information, and the like. In some cases where air-conditioning usage information is not set, air-conditioning usage information may also be determined based on weather forecast conditions. For example, the use of air conditioning is controlled based on the predicted temperature.
  • a prediction model can be established to obtain a power consumption prediction sequence.
  • the power consumption prediction sequence of the power consumption side in the power consumption period is obtained as an output.
  • the results of the electricity consumption prediction sequence can be corrected according to the error range of the prediction model.
  • step S120 based on the energy storage parameters of the energy storage device acquired under the preset acquisition condition, and the power supply prediction sequence and the power consumption prediction sequence within the power cycle, an energy sequence of the energy storage device during the power cycle is generated , So that the energy storage device is managed based on the energy sequence.
  • the preset acquisition condition includes at least one of the following: an event to update the power supply prediction sequence, an event to update the power consumption prediction sequence, and an update cycle; wherein, the update cycle is based on the update cycle of the power supply prediction sequence and And / or the update cycle of the power consumption prediction sequence.
  • the events for updating the power supply prediction sequence include, but are not limited to: third-party power price prediction sequence update events, changes in factors that affect power prices, and so on.
  • changes in the factors that affect electricity prices include events that result in an increase in electricity consumption on a newly added activity day, which in turn leads to changes in electricity prices, and changes in factors that affect the power generation of the self-powered system.
  • changes in the factors that affect the power generation of the self-powered system include: events that result in a decrease in the amount of photovoltaic power generation caused by sudden weather changes, which leads to changes in the amount of self-powered power.
  • the events that update the power consumption prediction sequence also include, but are not limited to: events that change the factors that affect power consumption. For example, the increase or decrease in electricity consumption due to changes in production schedules.
  • the update period is determined based on the update period of the power supply prediction sequence.
  • the update period of the power supply prediction sequence may be a preset update period, or may be an update period set according to the change period of the floating electricity price. For example, in the case where the floating electricity price changes every 30 minutes, the update cycle is set to update every 30 minutes.
  • the update period is determined based on the update period of the power consumption prediction sequence.
  • the update cycle of the power consumption prediction sequence may be a preset update cycle, or may be set according to the adjustment of the power consumption plan. For example, when adjusting the production schedule, the update period is set according to the corresponding adjustment event.
  • the update period is determined based on the update period of the power supply prediction sequence and the update period of the power consumption prediction sequence.
  • the energy storage parameters of the energy storage device are acquired whenever the electricity price prediction sequence changes, and the energy storage parameters of the energy storage device are acquired each time the electricity consumption plan is adjusted.
  • the update cycle also includes updates that are not performed according to the operations recommended by the energy storage management method. For example, when the operator is recommended to charge the energy storage device at a certain time according to the energy storage management method, but because the operator does not operate according to the recommendation, when the operator operates again, it needs to be updated first, and then based on the update Of energy storage management recommends that the energy storage device be operated accordingly.
  • the energy storage parameters include at least two of the following: detected or predicted energy stored by the energy storage device, capacity of the energy storage device, charge and discharge parameters of the energy storage device, and loss parameters of the energy storage device.
  • the capacity of the energy storage device includes the maximum capacity and the minimum capacity of the energy storage device.
  • the charge and discharge parameters of the energy storage device include the charge speed of the energy storage device, the discharge speed of the energy storage device, and the upper and lower limits of charge and discharge power.
  • the loss parameters of the energy storage device include the energy conversion rate of the energy storage process of the energy storage device, the energy conversion rate of the energy release process of the energy storage device, and the energy loss rate of the idle process of the energy storage device.
  • the energy storage parameter may also be a parameter group determined based on temperature-related variables.
  • the power supply prediction sequence, the power consumption prediction sequence, and the energy storage parameters of the energy storage device are updated.
  • the next generation is generated based on the updated power supply prediction sequence, the power consumption prediction sequence, and the acquired energy storage parameters from the update time The energy sequence within the power cycle. Taking an update cycle of 30 minutes and a power cycle of 24 hours as an example, the server generates the next 24-hour energy sequence every 30 minutes, where the energy sequence may include predicted and ordered at 30-minute intervals The energy value stored by the energy storage device.
  • the server can perform energy storage management of the energy storage device according to the actual management needs of the power user, and then generate an energy sequence that meets the management needs.
  • the management needs include but are not limited to: minimize the total price of electricity consumption, minimize the electricity consumption of peak electricity consumption, etc.
  • the server performs energy management on the energy storage device based on the energy sequence generated by the acquisition condition.
  • step S120 includes: generating an energy sequence of the energy storage device during the electricity consumption period with the optimization goal of low total electricity consumption price within the electricity consumption period under at least one constraint condition .
  • the constraint condition includes a constraint condition determined based on the energy storage parameter. Among them, when the total electricity price in the power consumption period is the lowest, the optimization objective function is:
  • t represents the t-th time
  • EG2L represents the electricity purchased by the electricity consumer from the grid and used directly
  • EG2B represents the electricity purchased and stored by the electricity grid from the electricity grid
  • EB2L represents the energy storage device of the electricity consumer is released and used
  • P G represents the real-time price of electricity purchased from the grid
  • P B represents the price converted from the costs of charge and discharge, loss and other costs of the energy storage device.
  • E btty (t) is the amount of electricity stored in the energy storage device at time t
  • E btty (t- ⁇ t) is the amount of electricity stored in the energy storage device at (t- ⁇ t) time
  • ⁇ E is the amount of energy stored or released within the unit time ⁇ t Power.
  • the expression of ⁇ E is:
  • e charge represents the energy conversion rate during the charging process of the energy storage device
  • e discharge represents the energy conversion rate during the discharge process of the energy storage device
  • E loss represents the self-discharge amount of the energy storage device within a unit time ⁇ t.
  • At least one constraint condition is set according to the energy storage parameters of the energy storage device that can be actually acquired, which is intended to avoid abnormalities in the energy storage device when managing the energy storage device. For example, to avoid a certain energy value in the generated energy sequence exceeding the maximum capacity of the energy storage device.
  • the constraint conditions of the model include at least one of the following: Constraints set by the device, and constraints set based on the relationship between power consumption and power supply.
  • the constraint conditions set for the energy storage device include at least one of the following:
  • E btty_MIN represents the minimum capacity of the energy storage device
  • E btty_MAX represents the maximum capacity of the energy storage device
  • CR charge represents the charging speed of the energy storage device
  • CR discharge represents the discharging speed of the energy storage device.
  • the constraint conditions set based on the relationship between power consumption and power supply refer to the power consumed by the consumer at a certain moment is the power purchased from the grid, the power provided by the discharge of the energy storage device, and the self-powered system.
  • the difference between the total electricity demand of the consumer and the predicted result of the self-power supply is the sum of the electricity purchased from the grid and used directly and the electricity released and used by the energy storage device (E G2L + E B2L ) constraints. That is to say, within a certain period of time, the upper limit of the discharge amount of the energy storage device is equal to the difference between the total power demand and the self-powered amount. If the discharge amount of the energy storage device is insufficient, the electricity purchased from the power grid is used to make up.
  • the self-powered amount of the self-powered system can also be sold to the power supplier according to the actual situation, which does not affect the energy storage management scheme described in this application and will not be detailed here.
  • step S120 under at least one constraint condition, with the total power consumption in the power consumption cycle as an optimization goal, an energy of the energy storage device in the power consumption cycle is generated
  • the steps of the sequence include: under at least one constraint condition, generating one or more candidate energy sequences within the electricity consumption period; and under at least one constraint condition and at a total electricity consumption price within the electricity consumption period Low is the optimization goal, optimize the generated one or more candidate energy sequences to obtain the energy sequence of the energy storage device in the power consumption period.
  • the initialization candidate energy sequence (also called initialization candidate solution) may be generated in a random manner to generate one or more preset candidate energy sequences, that is, candidate solutions.
  • the generated candidate solution is one, and under at least one constraint condition and with the total electricity price in the power consumption cycle as the optimization goal, the candidate solution is optimized.
  • a candidate solution for the applied electrical cycle is generated.
  • the low total electricity price is the energy sequence of the optimization goal.
  • the generated candidate solutions are multiple, and under at least one constraint condition and with the total electricity price in the power consumption cycle as the optimization goal, select and / or select from multiple candidate solutions Adjust to get the energy sequence.
  • the total electricity price corresponding to each of the plurality of candidate solutions generated under the constraint conditions is calculated, and the candidate solution with the lowest total electricity price is selected as the generated energy sequence.
  • calculate the total electricity price corresponding to each of the candidate solutions generated under the constraint condition and select the candidate solution with the lowest total electricity price; use the total electricity price corresponding to the candidate solution within a ⁇ t duration
  • the trend of change is to optimize the generated candidate solution to obtain an energy sequence that is optimized under at least one constraint condition and with a low total electricity price in the electricity cycle.
  • the step of optimizing the generated one or more candidate energy sequences includes: according to the cut-off condition set based on the optimization goal of low total electricity price in the electricity cycle, from Determine one candidate energy sequence from one or more candidate energy sequences, and use it as the energy sequence; and when the cut-off condition is not satisfied, under at least one constraint condition, at least one candidate generated according to the update strategy The energy sequence is updated, and the above steps are repeated according to the updated candidate energy sequence until there is a candidate energy sequence that meets the cut-off condition.
  • the cut-off condition includes that the actual number of iterations reaches the preset number of iterations, or the change of the optimal target result of the latest iterations is less than the preset threshold.
  • the update strategy includes, but is not limited to, Lagrange Multiplier, Sequential Linear Programming (SLP), Sequential Quadratic Programming (SQP), Interior Point (Interior Point), and Outer Point Method ( Exterior), Active Set, Active Region, Trust Region Reflection, Heuristic Algorithm, Meta-heuristic Algorithm, Evolutionary Algorithm, Group Intelligence Algorithms (Swarm Intelligence), Neural Networks, Tabu Search Algorithm, Simulated Annealing Algorithm, Ant Colony Optimization Algorithm, Particle Swarm Optimization Algorithm, Differential Evolution, Greedy Random Adaptive Search, Clonal Selection Algorithm, Artificial Immune System Algorithm , And other similar traditional optimization strategies or intelligent optimization strategies.
  • the high-dimensional solution space is constrained and restricted to satisfy the constraint conditions
  • multiple candidate solutions are obtained, each of which is 48-dimensional; all of them are substituted into the above optimization objective function to obtain the optimization target value corresponding to each candidate solution (abbreviation: evaluation step); then, Sort according to the optimization target value corresponding to the candidate solution, filter and retain a certain number of excellent solutions and eliminate the remaining solutions (referred to as: screening step); the optimization target value in the order from small to large (that is, the total price of electricity Sort from low to high), filter out the candidate solutions corresponding to the top n (n ⁇ 1) optimization target value, and eliminate the remaining solutions.
  • Mutation cloning step a certain probability (variation rate) of random mutations is introduced during the cloning process to generate new candidate solutions based on the retained candidate solutions.
  • the mutation rate is limited by the constraints of the above model to ensure that the new candidate solution obtained is based on the slight changes made by the candidate solution before the mutation clone.
  • the mutation rate may be introduced to all solutions of the cloned solutions of the reserved candidate solutions, or may be introduced to only part of the solutions.
  • the candidate solution corresponding to the minimum optimization target value is selected as the energy sequence of the energy storage device.
  • the above steps can be adaptively adjusted and selected based on other algorithms mentioned above.
  • the method of determining the energy sequence of the energy storage device by using the other algorithms mentioned above and other algorithms that can be applied to the technical idea described in this application should be regarded as a specific example based on the technical idea described in this application, which is not here Details one by one.
  • the energy storage management method of the present application further includes the step of displaying at least one of the energy sequence, the power supply prediction sequence, and the power consumption prediction sequence.
  • FIG. 4a to FIG. 4d are shown as the electricity price prediction sequence, the self-supply amount prediction sequence, the power consumption prediction sequence and the energy storage device energy sequence in a power cycle based on the energy storage management method of the present application schematic diagram.
  • FIG. 4a shows the electricity price prediction sequence obtained based on the energy storage management method of the application;
  • FIG. 4a shows the electricity price prediction sequence obtained based on the energy storage management method of the application;
  • FIG. 4a shows the electricity price prediction sequence obtained based on the energy storage management method of the application;
  • FIG. 4a shows the electricity price prediction sequence obtained based on the energy storage management method of the application;
  • FIG. 4b shows the energy storage management method based on the application The obtained self-power supply prediction sequence, wherein curve 4b-1 is the self-power supply upper limit prediction sequence, curve 4b-2 is the self-power supply amount prediction sequence, and curve 4b-3 is the self-power supply lower limit prediction sequence.
  • Fig. 4c shows the electricity consumption forecast sequence obtained by the electricity consumer based on the energy storage management method of the present application, where curve 4c-1 is the electricity consumption upper limit forecast sequence, and curve 4c-2 is the electricity consumption forecast sequence and curve 4c-3 is the lower power consumption forecast sequence.
  • curve 4d shows the energy sequence of the energy storage device obtained based on the energy storage management method of the present application, where curve 1 is the total electricity price when the energy consumer does not use the energy storage device, and curve 2 is the electricity consumer based on the present application The total electricity price obtained by the energy storage management method.
  • FIG. 5 is a schematic diagram of the total electricity price obtained by the electricity user based on the energy storage management method of the present application and the total electricity price when no energy storage device is used.
  • curve 1 Represents the total electricity price obtained by the electricity user based on the energy storage management method of the present application
  • curve 2 represents the electricity price when the electricity user does not use the energy storage device, as can be seen from the figure, compared to the case of not using the energy storage device , Affected by the capacity of the energy storage system and the electricity consumption of the electricity user, the total electricity cost savings using the energy storage management method of this application is about 5% -20%.
  • the energy storage management method of the present application generates an energy sequence of the energy storage device within a power cycle based on the acquired power supply prediction sequence, power consumption prediction sequence and energy storage parameters of the energy storage device, so that The energy storage device can be managed based on the energy sequence, thereby achieving the purpose of the lowest total electricity price.
  • the present application also provides an energy storage control method for controlling an energy storage device that provides stored electrical energy for a consumer.
  • the energy storage control method is mainly executed by an energy storage control system.
  • the energy storage control system may be a software system configured on a computer device, which uses an electric party to control the energy storage device based on the obtained energy sequence of the energy storage device, so as to realize electricity consumption within the electricity consumption cycle The purpose of the lowest total price.
  • the computer device may be a device located in a power control room of an enterprise, or a server in the Internet.
  • the server includes but is not limited to a single server, server cluster, distributed server cluster, cloud server, etc.
  • the cloud server includes a public cloud (Public Cloud) server and a private cloud (Private Cloud) server, where the public or private cloud server includes Software-as-a-Service (software as a service, SaaS ), Platform-as-a-Service (Platform as a Service, PaaS) and Infrastructure-as-a-Service (Infrastructure as a Service, IaaS), etc.
  • the private cloud server is, for example, Facebook Cloud Computing Service Platform, Amazon Cloud Computing Service Platform, Baidu Cloud Computing Platform, Tencent Cloud Computing Platform, and so on.
  • the computer equipment and the electricity supplier's electricity price release system, the energy storage control system of the energy storage device, the electricity use control system of the electricity consumer, the production activity management system, the self-powered system and other communication connections, and even data connection The three-party system, and the use of crawler technology to obtain Internet data related to the electricity consumption of the consumers in the Internet.
  • the electricity price issuance system is a system where electricity suppliers (or power market managers, such as government departments) issue electricity prices.
  • the energy storage control system includes but is not limited to: a detection device for detecting energy stored in the energy storage device, a charge and discharge control system of the energy storage device, and the like.
  • the power consumption control system includes, but is not limited to, a metering device (such as an electricity meter) installed in an enterprise, an electrical equipment control system, and the like.
  • the production activity management system includes but is not limited to: production process execution system (MES, Manufacturing Execution System), enterprise resource planning system (ERP, Enterprise Resource) Planning, etc.
  • the self-powered system includes but is not limited to: a detection device for detecting the power generation amount of the self-powered system, a power generation control system of the self-powered system, and the like.
  • Examples of the third-party system include its own server for storing historical electricity data, a server for storing historical electricity price data, and a WEB server for acquiring enterprise electricity plans.
  • Examples of the Internet data include weather forecast data and the like, where the weather forecast data may be predicted based on historical weather weather data acquired from the Internet, or weather forecast data directly acquired from a weather website or other websites.
  • FIG. 6 is a schematic structural diagram of an embodiment of a computer device of the present application.
  • the computer device includes an interface unit 61, a storage unit 62, and a processing unit 63.
  • the storage unit 62 includes a non-volatile memory, a storage server, and the like.
  • the non-volatile memory is exemplified by solid-state hard disk or U disk.
  • the storage server is used to store the acquired various power consumption related information and power supply related information.
  • the interface unit 61 includes a network interface, a data line interface, and the like.
  • the network interface includes but is not limited to: a network interface device based on Ethernet, a network interface device based on a mobile network (3G, 4G, 5G, etc.), a network interface device based on short-range communication (WiFi, Bluetooth, etc.), etc.
  • the data line interface includes but is not limited to: USB interface, RS232, etc.
  • the interface unit is in data connection with each system of the power supply side, each system of the power consumption side, a third-party system, the Internet, and the like.
  • the processing unit 63 connects the interface unit 61 and the storage unit 62, and includes at least one of a CPU or a chip integrated with a CPU, a programmable logic device (FPGA), and a multi-core processor.
  • the processing unit 63 also includes a memory for temporarily storing data, such as a memory and a register.
  • FIG. 7 shows a flowchart of the energy storage control method.
  • the processing unit 63 reads at least one program, power-related information, and power-related information stored in the storage unit to execute the energy storage control method described below.
  • the power consumption related information and the power supply related information are acquired by the processing unit from the interface unit in advance and stored in the storage unit.
  • step S710 the energy sequence of the energy storage device generated by the energy storage management method within a power consumption cycle is acquired.
  • the specific implementation manner of step S710 is as described in FIGS. 2 to 3 and corresponding descriptions, and details are not described herein again.
  • step S720 based on the energy value corresponding to the operation time interval in the acquired energy sequence, it is determined that the energy storage device uses control information for controlling the operation of the energy storage device during the operation time interval.
  • the operation time interval may be customized by the power user, or may be set according to the time interval of adjacent energy values in the energy sequence of the energy storage device acquired in step S710. For example, in the case where the operation time interval is customized by the power consumer, first, the start time customized by the power consumer may be used as the update cycle in step S710 to obtain the latest energy storage device within a power consumption cycle Based on the corresponding energy value in the energy sequence, to determine the control information for controlling the operation of the energy storage device in the custom operation time interval.
  • the operation time interval may be set to correspond to the energy sequence diagram The time interval during which the device can be charged and discharged.
  • control information includes charge and discharge control information of the energy storage device and / or a target energy storage value of the energy storage device during the operation time interval.
  • the charge and discharge control information includes but is not limited to: charge and discharge speed, charge and discharge time, and charge and discharge duration.
  • the target energy storage value of the energy storage device during the operation time interval refers to the amount of electricity charged or discharged by the energy storage device within a certain period of time, and the charge and discharge speed of the energy storage device can be obtained based on the target energy storage value and the operation time interval.
  • the energy storage control method of the present application further includes the step of controlling the operation of the energy storage device within the corresponding operation time interval based on the control information. For example, based on the charge and discharge control information, the energy storage device is controlled to perform a charge and discharge operation from a certain charge and discharge time at a certain charge and discharge speed for a certain charge and discharge duration. As another example, the energy storage device is controlled based on the target energy storage value to select different charge and discharge speeds to reach the target energy storage value within a certain operation time interval.
  • the energy storage control method of the present application further includes the step of acquiring and displaying at least one of the energy sequence, the power supply prediction sequence, and the power consumption prediction sequence, so that the user can visually observe the energy sequence of the energy storage device and each prediction sequence.
  • step S710 updates the power supply prediction sequence, the power consumption prediction sequence, and the energy storage parameters based on the preset acquisition conditions, thereby obtaining a new energy sequence
  • the energy storage control method of the present application accordingly includes The step of updating the control information with the newly generated energy sequence. For example, taking a power consumption cycle of 24 hours and an update cycle of 30 minutes as an example, first, obtain the energy sequence of the energy storage device within 24 hours according to step S710, and determine that the energy storage device is used to control energy storage during the operation time interval according to step S720 Control information for device operation, and then the user operates the energy storage device based on the control information.
  • the new energy sequence of the energy storage device within 24 hours from the moment is updated, and the control information based on the new energy sequence is generated again, and then, based on the new control information, the user To operate. It can be seen that although the energy sequence of the energy storage device is displayed as an overall change in the next 24 hours (power cycle), in fact, the user only needs to pay attention to the operation information within 30 minutes (update cycle), and every 30 minutes is based on the new The energy sequence controls the energy storage device accordingly.
  • the energy storage control method of the present application controls the operation of the energy storage device based on the energy sequence of the acquired energy storage device, so as to achieve the purpose of the lowest total electricity price.
  • the energy storage management system is a software system configured on the server side. Please refer to FIG. 8, which is a schematic structural diagram of an embodiment of the energy storage management system.
  • the energy storage management system 2 includes program modules such as an acquisition module 21 and a generation module 22.
  • the obtaining module 21 is used to obtain a power supply prediction sequence that can be used by the power consumer within a power consumption cycle and a power consumption prediction sequence of the power consumer.
  • the power consumption cycle is the aforementioned power consumption cycle to be predicted, which may be a predetermined power consumption cycle, or may be a power consumption cycle set according to the available variable power price change cycle.
  • the floating electricity price change period refers to the time interval of electricity price change.
  • the period of change in floating electricity prices is the length of time that a single electricity price is maintained.
  • the period of change in floating electricity prices is the update duration of a floating electricity price sequence.
  • the power supply prediction sequence includes a plurality of sets of power supply quantities predicted by a power supplier, a self-powered system, or a third party in a time sequence during a power consumption period.
  • the third party includes a plurality of sets of power supply quantities predicted in chronological order during the power consumption cycle based on simulations obtained from power consumers regarding power supply-related parameter data, historical power supply data, and the like.
  • the power supply prediction sequence includes a power price prediction sequence.
  • the acquisition module 21 includes at least one of the following: a first acquisition unit for acquiring the electricity price prediction sequence within the electricity consumption period; and one for acquiring based on the acquired historical electricity price prediction sequence and the corresponding historical actual electricity price
  • the third acquisition unit of the sequence is used to predict the electricity price forecast in the electricity consumption period based on the acquired electricity price-related information.
  • the first acquisition unit may be used to directly acquire the electricity consumption period Series of electricity price forecasts.
  • the second acquisition unit may be used to obtain the deviation between the acquired historical electricity price prediction sequence and the corresponding historical actual electricity price , To predict the electricity price prediction sequence within the electricity consumption period available to the electricity consumer.
  • the power supplier does not provide the electricity price prediction sequence
  • the step of obtaining the electricity price prediction sequence within a power consumption period may include: predicting the electricity price cycle based on the obtained electricity price related information Electricity price forecast sequence.
  • the electricity price-related information includes, but is not limited to, at least one of the following: historical actual electricity price series, electricity price rules in the electricity market, other factors that affect electricity price changes, and so on.
  • the historical actual electricity price sequence refers to a collection of a plurality of actual electricity prices in chronological order within a certain historical time period. For example, historical actual electricity price sequences can be obtained from third parties or other data platforms.
  • the electricity price rules in the electricity market refer to electricity price rules set by the local government or electricity supplier for the area under its jurisdiction, which include but are not limited to: fine electricity prices set based on the electricity demand of the electricity consumers. Examples of the other factors that affect electricity price changes include weather and holidays. For example, the electricity price prediction sequence within a power consumption period is predicted based on the obtained weather forecast, the published holiday vacation schedule, and the historical actual electricity price sequence, etc.
  • the electricity price forecast sequence is obtained by establishing a forecast model.
  • the historical actual electricity price series, weather forecast, holiday vacation arrangement, etc. are used as the input of the prediction model, and prediction algorithms such as random forest (Random Forest), long-short-term memory network (LSTM), iterative decision tree (GBRT), convolutional neural network (CNN), etc., to obtain the electricity price prediction sequence within the power consumption cycle as output.
  • prediction algorithms such as random forest (Random Forest), long-short-term memory network (LSTM), iterative decision tree (GBRT), convolutional neural network (CNN), etc.
  • the results of the electricity price prediction sequence can be corrected according to the error range of the prediction model.
  • the above embodiments for obtaining the electricity price prediction sequence are only examples, rather than limitations on the present application.
  • a person skilled in the art can construct a model for predicting a price forecast sequence in combination with the foregoing various embodiments. For example, based on the input of the above prediction model, the prediction algorithm used, and the error range of the historical electricity price data obtained through detection, the electricity price prediction sequence is calculated to improve the accuracy of subsequent predictions.
  • the power supply prediction sequence further includes a self-power supply amount prediction sequence.
  • the self-power supply amount prediction sequence refers to a set of a plurality of self-power supply amounts predicted in chronological order within a power consumption period.
  • the self-powered system includes but is not limited to: photovoltaic power generation system, heat conversion system, triple supply system, wind energy power generation system, and the like.
  • the acquisition module 21 includes a fourth acquisition unit for predicting the self-power supply amount prediction sequence in the power consumption period based on the acquired power generation related information of the self-power supply system.
  • the power generation related information includes but is not limited to: historical power generation data, and factors affecting power generation based on the working principle of the self-powered system.
  • the factors that affect power generation mainly include solar irradiance.
  • the factors that affect power generation mainly include wind speed and wind direction.
  • the factors affecting power generation mainly include the heat conversion efficiency of the system, the detected temperature, and so on.
  • the fourth acquisition unit can obtain the self-power supply amount prediction sequence by establishing a prediction model.
  • the fourth acquisition unit may also correct the result of the self-power supply amount prediction sequence according to the error range of the prediction model.
  • the above implementations of the obtained self-power supply amount prediction sequence are only examples, rather than limitations on the present application.
  • a person skilled in the art may combine various embodiments mentioned in the aforementioned electricity price prediction sequence to construct a model for predicting the self-powered amount prediction sequence. For example, based on the input of the prediction model, the prediction algorithm used, and the error range obtained by the detection, the self-powered quantity prediction sequence is calculated to improve the accuracy of subsequent predictions.
  • the power supply prediction sequence obtainable by the acquisition module 21 may include only the electricity price prediction sequence or the self-power supply amount prediction sequence; or both the electricity price prediction sequence and the self-power supply amount prediction sequence. There are no restrictions here.
  • the obtaining module 21 is further configured to obtain power consumption related information according to the power consumption factor in the power consumption cycle; and according to the power consumption related information, predict the fifth of the power consumption prediction sequence in the power consumption cycle Get the unit.
  • the power consumption prediction sequence refers to a set of a plurality of power consumption predicted in chronological order within the power consumption cycle.
  • the electricity consumption obtained by the electricity consumer is related to the electricity consumption factors of its daily production activities.
  • the power consumption factors include but are not limited to: artificial plans such as production schedules, shopping mall activity plans, and plans summarized according to weather or social activity laws (such as working days and holidays).
  • the electricity-related information may include historical electricity consumption data of the produced product A, equipment usage information determined based on the production schedule of the product A, and electricity consumption information of the equipment .
  • the power-related information may include air-conditioning use information set based on the season, air-conditioning power use information, work day and holiday lighting lamps, computer use information, and the like. In some cases where air-conditioning usage information is not set, air-conditioning usage information may also be determined based on weather forecast conditions. For example, the use of air conditioning is controlled based on the predicted temperature.
  • the fifth acquisition unit can obtain the power consumption prediction sequence by establishing a prediction model.
  • the power consumption prediction sequence of the power consumption side in the power consumption period is obtained as an output.
  • the fifth acquisition unit may also correct the result of the power consumption prediction sequence according to the error range of the prediction model.
  • the generating module 22 is configured to generate, based on the energy storage parameters of the energy storage device acquired with preset acquisition conditions, the power supply prediction sequence and the power consumption prediction sequence within the power consumption period, within the power consumption period The energy sequence of the energy storage device, so that the energy storage device is managed based on the energy sequence.
  • the preset acquisition condition includes at least one of the following: an event to update the power supply prediction sequence, an event to update the power consumption prediction sequence, and an update cycle; wherein, the update cycle is based on the update cycle of the power supply prediction sequence and And / or the update cycle of the power consumption prediction sequence.
  • the events for updating the power supply prediction sequence include, but are not limited to: third-party power price prediction sequence update events, changes in factors that affect power prices, and so on.
  • changes in the factors that affect electricity prices include events that result in an increase in electricity consumption on a newly added activity day, which in turn leads to changes in electricity prices, and changes in factors that affect the power generation of the self-powered system.
  • changes in the factors that affect the power generation of the self-powered system include: events that result in a decrease in the amount of photovoltaic power generation caused by sudden weather changes, which leads to changes in the amount of self-powered power.
  • the events that update the power consumption prediction sequence also include, but are not limited to: events that change the factors that affect power consumption. For example, the increase or decrease in electricity consumption due to changes in production schedules.
  • the update period is determined based on the update period of the power supply prediction sequence.
  • the update period of the power supply prediction sequence may be a preset update period, or may be an update period set according to the change period of the floating electricity price. For example, in the case where the floating electricity price changes every 30 minutes, the update cycle is set to update every 30 minutes.
  • the update period is determined based on the update period of the power consumption prediction sequence.
  • the update cycle of the power consumption prediction sequence may be a preset update cycle, or may be set according to the adjustment of the power consumption plan. For example, when adjusting the production schedule, the update period is set according to the corresponding adjustment event.
  • the update period is determined based on the update period of the power supply prediction sequence and the update period of the power consumption prediction sequence.
  • the energy storage parameters of the energy storage device are acquired whenever the electricity price prediction sequence changes, and the energy storage parameters of the energy storage device are acquired each time the electricity consumption plan is adjusted.
  • the update cycle also includes updates that are not performed according to the operations recommended by the energy storage management method. For example, when the operator is recommended to charge the energy storage device at a certain time according to the energy storage management method, but because the operator does not operate according to the recommendation, when the operator operates again, it needs to be updated first, and then based on the update Of energy storage management recommends that the energy storage device be operated accordingly.
  • the energy storage parameters include at least two of the following: detected or predicted energy stored by the energy storage device, capacity of the energy storage device, charge and discharge parameters of the energy storage device, and loss parameters of the energy storage device.
  • the capacity of the energy storage device includes the maximum capacity and the minimum capacity of the energy storage device.
  • the charge and discharge parameters of the energy storage device include the charge speed of the energy storage device, the discharge speed of the energy storage device, and the upper and lower limits of charge and discharge power.
  • the loss parameters of the energy storage device include the energy conversion rate of the energy storage process of the energy storage device, the energy conversion rate of the energy release process of the energy storage device, and the energy loss rate of the idle process of the energy storage device.
  • the energy storage parameter may also be a parameter group determined based on temperature-related variables.
  • the generating module 22 includes a generating unit for generating, in at least one constraint condition, a low total electricity price within the power consumption cycle as an optimization goal, and generating the power cycle Within the energy sequence of the energy storage device; wherein the constraint condition includes a constraint condition determined based on the energy storage parameter.
  • the optimization objective function is:
  • t represents the t-th time
  • EG2L represents the electricity purchased by the electricity consumer from the grid and used directly
  • EG2B represents the electricity purchased and stored by the electricity grid from the electricity grid
  • EB2L represents the energy storage device of the electricity consumer is released and used
  • P G represents the real-time price of electricity purchased from the grid
  • P B represents the price converted from the costs of charge and discharge, loss and other costs of the energy storage device.
  • E btty (t) is the amount of electricity stored in the energy storage device at time t
  • E btty (t- ⁇ t) is the amount of electricity stored in the energy storage device at (t- ⁇ t) time
  • ⁇ E is the amount of energy stored or released within the unit time ⁇ t Power.
  • the expression of ⁇ E is:
  • e charge represents the energy conversion rate during the charging process of the energy storage device
  • e discharge represents the energy conversion rate during the discharge process of the energy storage device
  • E loss represents the self-discharge amount of the energy storage device within a unit time ⁇ t.
  • At least one constraint condition is set according to the energy storage parameters of the energy storage device that can be actually acquired, which is intended to avoid abnormalities in the energy storage device when managing the energy storage device. For example, to avoid a certain energy value in the generated energy sequence exceeding the maximum capacity of the energy storage device.
  • the constraint conditions of the model include at least one of the following: Constraints set by the device, and constraints set based on the relationship between power consumption and power supply.
  • the constraint conditions set for the energy storage device include at least one of the following:
  • E btty_MIN represents the minimum capacity of the energy storage device
  • E btty_MAX represents the maximum capacity of the energy storage device
  • CR charge represents the charging speed of the energy storage device
  • CR discharge represents the discharging speed of the energy storage device.
  • the constraint conditions set based on the relationship between power consumption and power supply refer to the power consumed by the consumer at a certain moment is the power purchased from the grid, the power provided by the discharge of the energy storage device, and the self-powered system.
  • the difference between the total electricity demand of the consumer and the predicted result of the self-power supply is the sum of the electricity purchased from the grid and used directly and the electricity released and used by the energy storage device (E G2L + E B2L ) constraints. That is to say, within a certain period of time, the upper limit of the discharge amount of the energy storage device is equal to the difference between the total power demand and the self-powered amount. If the discharge amount of the energy storage device is insufficient, the electricity purchased from the power grid is used to make up.
  • the self-powered amount of the self-powered system can also be sold to the power supplier according to the actual situation, which does not affect the energy storage management scheme described in this application and will not be detailed here.
  • the generating unit is configured to generate one or more candidate energy sequences within the power consumption period under at least one constraint condition; and under at least one constraint condition
  • the low total electricity consumption price in the electricity cycle is the optimization goal, and the generated one or more candidate energy sequences are optimized to obtain the energy sequence of the energy storage device in the electricity cycle.
  • the initialization candidate energy sequence (also called initialization candidate solution) may be generated in a random manner to generate one or more preset candidate energy sequences, that is, candidate solutions.
  • the generated candidate solution is one, and under at least one constraint condition and with the low total electricity price in the electricity consumption cycle as the optimization goal, the candidate solution is optimized.
  • a candidate solution for the applied electrical cycle is generated.
  • the low total electricity price is the energy sequence of the optimization goal.
  • the generated candidate solutions are multiple, and under at least one constraint condition and with the total electricity price in the power consumption cycle as the optimization goal, select and / or select from multiple candidate solutions Adjust to get the energy sequence.
  • the total electricity price corresponding to each of the plurality of candidate solutions generated under the constraint conditions is calculated, and the candidate solution with the lowest total electricity price is selected as the generated energy sequence.
  • calculate the total electricity price corresponding to each of the candidate solutions generated under the constraint condition and select the candidate solution with the lowest total electricity price; use the total electricity price corresponding to the candidate solution within a ⁇ t duration
  • the trend of change is to optimize the generated candidate solution to obtain an energy sequence that is optimized under at least one constraint condition and with a low total electricity price in the electricity cycle.
  • the generating unit is configured to determine one of the one or more candidate energy sequences according to a cut-off condition set based on an optimization goal with a low total electricity price in the electricity cycle
  • the candidate energy sequence and use it as the energy sequence; and when the cut-off condition is not satisfied, under at least one constraint condition, update the generated at least one candidate energy sequence according to the update strategy, and follow the updated
  • the candidate energy sequence repeats the above steps until there is a candidate energy sequence that meets the cut-off condition.
  • the cut-off condition includes that the actual number of iterations reaches the preset number of iterations, or the change of the optimal target result of the latest iterations is less than the preset threshold.
  • the update strategy includes, but is not limited to, Lagrange Multiplier, Sequential Linear Programming (SLP), Sequential Quadratic Programming (SQP), Interior Point (Interior Point), and Outer Point Method ( Exterior), Active Set, Active Region, Trust Region Reflection, Heuristic Algorithm, Meta-heuristic Algorithm, Evolutionary Algorithm, Group Intelligence Algorithms (Swarm Intelligence), Neural Networks, Tabu Search Algorithm, Simulated Annealing Algorithm, Ant Colony Optimization Algorithm, Particle Swarm Optimization Algorithm, Differential Evolution, Greedy Random Adaptive Search, Clonal Selection Algorithm, Artificial Immune System Algorithm , And other similar traditional optimization strategies or intelligent optimization strategies.
  • the energy storage management system of the present application further includes an output module for outputting at least one of the energy sequence, the power supply prediction sequence, and the power consumption prediction sequence for display.
  • the working mode of each module in the energy storage management system of the present application is the same as or similar to the corresponding steps in the above energy storage management method, and details are not described herein again.
  • the application also provides an energy storage control system.
  • the energy storage control system is a software system configured in computer equipment. Please refer to FIG. 9, which is a schematic structural diagram of an embodiment of the energy storage control system.
  • the energy storage control system 3 includes program modules such as an acquisition module 31 and a determination module 32.
  • the obtaining module 31 is used to obtain the energy sequence of the energy storage device generated by the energy storage management system within a power cycle.
  • the determining module 32 is configured to determine control information used by the energy storage device to control the operation of the energy storage device during the operation time interval based on the energy value corresponding to the operation time interval in the acquired energy sequence.
  • the operation time interval may be customized by the power user, or may be set according to the time interval of adjacent energy values in the energy sequence of the obtained energy storage device.
  • the control information includes charge and discharge control information of the energy storage device and / or a target energy storage value of the energy storage device during the operation time interval.
  • the charge and discharge control information includes but is not limited to: charge and discharge speed, charge and discharge time, and charge and discharge duration.
  • the target energy storage value of the energy storage device during the operation time interval refers to the amount of electricity charged or discharged by the energy storage device within a certain period of time, and the charge and discharge speed of the energy storage device can be obtained based on the target energy storage value and the operation time interval.
  • the energy storage control system of the present application further includes a control module for controlling the operation of the energy storage device within a corresponding operation time interval based on the control information.
  • the energy storage control system of the present application further includes a display module for acquiring and displaying at least one of the energy sequence, the power supply prediction sequence, and the power consumption prediction sequence.
  • the energy storage control system of the present application further includes an update module, The update module is used to update the control information based on the newly generated energy sequence.
  • the working mode of each module in the energy storage control system of the present application is the same as or similar to the corresponding steps in the above energy storage control method, and details are not described here.
  • the present application also provides a computer-readable storage medium that stores at least one program, and the at least one program executes any of the foregoing energy storage management methods when called.
  • the present application also provides a computer-readable storage medium that stores at least one program that executes any of the foregoing energy storage control methods when called.
  • the technical solution of the present application can be embodied in the form of a software product in essence or part that contributes to the existing technology
  • the computer software product can include one or more machine executable instructions stored thereon A machine-readable medium.
  • the instructions When these instructions are executed by one or more machines, such as a computer, a computer network, or other electronic devices, the instructions may cause the one or more machines to perform operations according to the embodiments of the present application. For example, the steps of the robot positioning method are executed.
  • Machine-readable media may include, but is not limited to, floppy disks, optical disks, CD-ROM (compact disk-read only memory), magneto-optical disks, ROM (read only memory), RAM (random access memory), EPROM (erasable) In addition to programmable read only memory), EEPROM (electrically erasable programmable read only memory), magnetic or optical cards, flash memory, or other types of media / machine readable media suitable for storing machine executable instructions.
  • the storage medium may be located in a robot or a third-party server, such as a server that provides an application store. There are no restrictions on specific application stores, such as Huawei App Store, Apple App Store, etc.
  • This application can be used in many general-purpose or special-purpose computing system environments or configurations.
  • the present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types.
  • the present application may also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected through a communication network.
  • program modules may be located in local and remote computer storage media including storage devices.
  • the application also provides an energy storage control system.
  • the energy storage control system includes the server and computer equipment provided in any of the foregoing examples. Please refer to FIG. 10, which shows a schematic diagram of the network architecture of the energy storage control system controlling the energy storage device in one embodiment.
  • the server 41 and the computer device 42 may both be located on the side of the power consumer, or both may be located on any geographic location where data communication can be performed through data transmission networks such as the Internet, mobile networks, or any one of them may be The other side is located in another geographic location where data communication is possible.
  • the computer device 42 can send control instructions to the energy storage device 43 through data communication and collect energy storage parameters of the energy storage device 43.
  • the server 41 also communicates with the metering device 44 on the power consumer side to obtain the power consumption of the power consumer detected by the metering device 44 for the server 41 to include The obtained electricity consumption related information of electricity consumption is used to predict the electricity consumption prediction sequence in the electricity consumption period.
  • the power consumer further includes a self-powered system 45.
  • the server 41 obtains power generation related information of the self-powered system 45 through data communication.
  • the self-powered system 45 uses heat conversion to generate electricity, and the corresponding server 41 obtains temperature information of the self-powered system 45 as one of its power generation-related information.
  • the server 41 predicts the self-power supply amount prediction sequence within a power cycle by acquiring power generation related information of the self-power supply system 45; Electricity consumption information such as electricity consumption and production scheduling of the electricity party, to predict the electricity consumption forecast sequence within the same electricity consumption cycle; obtain energy storage of the energy storage device 43 at the beginning of the electricity consumption cycle through the computer device 42 Parameters; and access to third-party electricity price prediction sequences.
  • the constraints determined by the server 41 based on the energy storage parameters include: 1) Capacity of the energy storage device 43: E btty_MIN ⁇ E btty ⁇ E btty_MAX , and 2) Charge and discharge speed of the energy storage device 43: 0 ⁇ E / ⁇ t ⁇ CR charge or CR discharge ⁇ E / ⁇ t ⁇ 0; take the low total price of electricity consumption as the optimization goal in this power cycle, and randomly generate multiple candidate energy storage sequences; by calculating each candidate energy storage sequence Corresponding to the total electricity price, select the n candidate energy storage sequences with the lowest total electricity price; clone the corresponding number of reserved n candidate energy storage sequences, and introduce a certain probability (variation rate) during the cloning process Random mutation, and get new candidate energy storage sequence.
  • the mutation rate is limited by the constraints of the above model to ensure that the obtained new candidate energy storage sequence is based on small changes made by the candidate solution before the mutation clone.
  • the mutation rate is introduced to all solutions of the cloned solutions of the reserved candidate energy storage sequences, or the mutation rate may be introduced to only part of the solutions.
  • the generated candidate energy sequences are screened and mutated and cloned until the actual number of iterations reaches the cut-off condition of the preset number of iterations; the candidate energy storage sequence corresponding to the lowest total electricity price is finally selected As an energy sequence of the energy storage device 43, and send the obtained energy sequence to the computer device 42.
  • the computer device 42 generates control information for controlling the energy storage device 43 to adjust from the currently stored energy value E0 to E1 according to the latest energy value E1 in the acquired energy sequence, and controls the energy storage device 43 according to the control information Perform energy storage adjustment.
  • the server 41 when any one of the electricity price forecasting sequence, the electricity consumption forecasting sequence, the self-power supply forecasting sequence, or the energy storage parameter is updated, the server 41 then generates an energy sequence based on the latest data for the computer The device 42 timely controls the energy storage device 43 to adjust the energy storage. In this way, the goal of using energy storage to reduce electricity costs under the floating electricity price mechanism is achieved.
  • the present application based on the acquired power supply prediction sequence, power consumption prediction sequence, and energy storage parameters of the energy storage device, the present application generates an energy sequence of the energy storage device within a power consumption period, so that the energy can be based on the energy
  • the sequence manages the energy storage device, thereby achieving the purpose of the lowest total electricity price.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Power Engineering (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

本申请提供一种储能管理方法、储能控制方法及各系统、计算机设备、存储介质。所述储能管理方法用于管理为用电方提供储备电能的储能装置，所述储能管理方法包括下述步骤：获取在一用电周期内可供所述用电方使用的供电预测序列以及所述用电方的用电量预测序列；以及基于以预设获取条件而获取的所述储能装置的储能参数，以及所述用电周期内的供电预测序列和用电量预测序列，生成在所述用电周期内所述储能装置的能量序列，以使得基于所述能量序列对所述储能装置进行管理。本申请基于所述能量序列对所述储能装置进行管理，进而实现用电总价最低的目的。

Description

储能管理及控制方法、系统、计算机设备、存储介质 技术领域
本申请涉及工业控制技术领域，特别是涉及一种储能管理方法、储能控制方法及各系统、计算机设备、存储介质。
背景技术
现今，随着储能装置成本降低，在一些工矿企业、企业园区开始设置储能装置，企业利用储能装置在低电价期间进行储能操作、在高电价期间进行供电操作，来降低对电网购电的成本。
与此同步发展的，电网对供电成本的计算更加及时，针对如工业用电等用电场景，一些地方将供电成本与用电价格更紧密的结合起来，由此形成了利用浮动电价的方式来向用电方收取电费。其中，浮动电价是指用电方所购买的电价随时间变化而变化。随着浮动电价加入现有电价机制，如何更好地利用储能装置来降低用电成本成为亟待解决的问题。
发明内容
鉴于此，本申请的目的在于提供一种储能管理方法、储能控制方法及各系统、计算机设备、存储介质，用于解决现有技术中如何利用储能装置降低用电成本的问题。
为实现上述目的及其他相关目的，本申请的第一方面提供一种储能管理方法，用于管理为用电方提供储备电能的储能装置，所述储能管理方法包括下述步骤：获取在一用电周期内可供所述用电方使用的供电预测序列以及所述用电方的用电量预测序列；以及基于以预设获取条件而获取的所述储能装置的储能参数，以及所述用电周期内的供电预测序列和用电量预测序列，生成在所述用电周期内所述储能装置的能量序列，以使得基于所述能量序列对所述储能装置进行管理。
在本申请的第一方面的某些实施方式中，所述供电预测序列中包含电价预测序列，所述获取在一用电周期内的电价预测序列的步骤包括以下任一种：获取所述用电周期内的电价预测序列；基于所获取的历史电价预测序列以及相应的历史实际电价之间的偏差，预测可供所述用电方使用的所述用电周期内的电价预测序列；基于所获取的电价相关信息，预测所述用电周期内的电价预测序列。
在本申请的第一方面的某些实施方式中，所述供电预测序列中包含自供电系统的自供电量预测序列，所述获取在一用电周期内的自供电量预测序列的步骤包括：基于所获取的自供 电系统的发电相关信息，预测所述用电周期内的自供电量预测序列。
在本申请的第一方面的某些实施方式中，所述获取用电方的用电量预测序列的步骤包括：按照所述用电周期内的用电因素获取用电相关信息；以及根据所述用电相关信息，预测所述用电周期内的用电量预测序列。
在本申请的第一方面的某些实施方式中，所述基于以预设获取条件而获取的所述储能装置的储能参数，以及所述用电周期内的供电预测序列和用电量预测序列，生成在所述用电周期内所述储能装置的能量序列的步骤包括：在至少一个约束条件下，以在所述用电周期内的用电总价低为优化目标，生成在所述用电周期内所述储能装置的能量序列；其中，所述约束条件包括基于所述储能参数确定的约束条件。
在本申请的第一方面的某些实施方式中，所述在至少一个约束条件下，以在所述用电周期内的用电总价低为优化目标，生成在所述用电周期内所述储能装置的一能量序列的步骤包括：在至少一个约束条件下，生成在所述用电周期内的一个或多个候选能量序列；以及在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，对所生成的一个或多个候选能量序列进行优化处理，得到在所述用电周期内所述储能装置的能量序列。
在本申请的第一方面的某些实施方式中，对所生成的一个或多个候选能量序列进行优化处理的步骤包括：根据以在所述用电周期内的用电总价低为优化目标而设置的截止条件，从所述一个或多个候选能量序列中确定一个候选能量序列，并将其作为所述能量序列；以及当不满足所述截止条件时，在至少一个约束条件下，依据更新策略将所生成的至少一个候选能量序列进行更新，并按照更新后的候选能量序列重复上述步骤直至存在一个候选能量序列符合所述截止条件。
在本申请的第一方面的某些实施方式中，所述储能参数包括以下至少两个：所检测的或所预测的储能装置存储的能量、储能装置的容量、储能装置的充放电参数、储能装置的损失参数。
在本申请的第一方面的某些实施方式中，所述获取条件包括以下至少一种：更新供电预测序列的事件，更新用电量预测序列的事件，更新周期；其中，所述更新周期是基于所述供电预测序列的更新周期和/或所述用电量预测序列的更新周期而确定的。
在本申请的第一方面的某些实施方式中，所述储能管理方法还包括将所述能量序列、供电预测序列和用电量预测序列中的至少一种予以显示的步骤。
本申请的第二方面提供一种储能控制方法，用于控制为用电方提供储备电能的储能装置，所述储能控制方法包括下述步骤：获取由如上所述的储能管理方法所生成的在一用电周期内所述储能装置的能量序列；基于所获取的能量序列中操作时间区间所对应的能量值，确定所 述储能装置在所述操作时间区间用于控制所述储能装置操作的控制信息。
在本申请的第二方面的某些实施方式中，所述储能控制方法还包括基于所述控制信息控制所述储能装置在相应操作时间区间内的操作的步骤。
在本申请的第二方面的某些实施方式中，所述储能控制方法还包括：获取并显示所述能量序列、供电预测序列和用电量预测序列中的至少一种的步骤。
在本申请的第二方面的某些实施方式中，所述储能控制方法还包括基于最新生成的能量序列对所述控制信息进行更新的步骤。
在本申请的第二方面的某些实施方式中，所述控制信息包括以下至少一种：储能装置的充放电控制信息、储能装置在操作时间区间的目标储能值。
本申请的第三方面提供一种储能管理系统，用于管理为用电方提供储备电能的储能装置，包括：获取模块，用于获取在一用电周期内可供所述用电方使用的供电预测序列以及所述用电方的用电量预测序列；以及生成模块，用于基于以预设获取条件而获取的所述储能装置的储能参数，以及所述用电周期内的供电预测序列和用电量预测序列，生成在所述用电周期内所述储能装置的能量序列，以使得基于所述能量序列对所述储能装置进行管理。
在本申请的第三方面的某些实施方式中，所述供电预测序列中包含电价预测序列，所述获取模块包括下述中至少之一：第一获取单元，用于获取所述用电周期内的电价预测序列；第二获取单元，用于基于所获取的历史电价预测序列以及相应的历史实际电价之间的偏差，预测可供所述用电方使用的所述用电周期内的电价预测序列；第三获取单元，用于基于所获取的电价相关信息，预测所述用电周期内的电价预测序列。
在本申请的第三方面的某些实施方式中，所述供电预测序列中包含自供电系统的自供电量预测序列，所述获取模块包括第四获取单元，用于基于所获取的自供电系统的发电相关信息，预测所述用电周期内的自供电量预测序列。
在本申请的第三方面的某些实施方式中，所述获取模块包括第五获取单元，用于按照所述用电周期内的用电因素获取用电相关信息；以及根据所述用电相关信息，预测所述用电周期内的用电量预测序列。
在本申请的第三方面的某些实施方式中，所述生成模块包括：生成单元，用于在至少一个约束条件下，以在所述用电周期内的用电总价低为优化目标，生成在所述用电周期内所述储能装置的能量序列；其中，所述约束条件包括基于所述储能参数确定的约束条件。
在本申请的第三方面的某些实施方式中，所述生成单元用于在至少一个约束条件下，生成在所述用电周期内的一个或多个候选能量序列；以及在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，对所生成的一个或多个候选能量序列进行优化处理，得 到在所述用电周期内所述储能装置的能量序列。
在本申请的第三方面的某些实施方式中，所述生成单元用于根据以在所述用电周期内的用电总价低为优化目标而设置的截止条件，从所述一个或多个候选能量序列中确定一个候选能量序列，并将其作为所述能量序列；以及当不满足所述截止条件时，在至少一个约束条件下，依据更新策略将所生成的至少一个候选能量序列进行更新，并按照更新后的候选能量序列重复上述步骤直至存在一个候选能量序列符合所述截止条件。
在本申请的第三方面的某些实施方式中，所述储能参数包括以下至少两个：所检测的或所预测的储能装置存储的能量、储能装置的容量、储能装置的充放电参数、储能装置的损失参数。
在本申请的第三方面的某些实施方式中，所述获取条件包括以下至少一种：更新供电预测序列的事件，更新用电量预测序列的事件，更新周期；其中，所述更新周期是基于所述供电预测序列的更新周期和/或所述用电量预测序列的更新周期而确定的。
在本申请的第三方面的某些实施方式中，所述储能管理系统还包括输出模块，用于输出所述能量序列、供电预测序列和用电量预测序列中的至少一种以予以显示。
本申请的第四方面提供一种储能控制系统，用于对为用电方提供储备电能的储能装置进行控制，包括：获取模块，用于获取由如前所述的储能管理系统所生成的在一用电周期内所述储能装置的能量序列；确定模块，用于基于所获取的能量序列中操作时间区间所对应的能量值，确定所述储能装置在所述操作时间区间用于控制所述储能装置操作的控制信息。
在本申请的第四方面的某些实施方式中，所述储能控制系统还包括控制模块，用于基于所述控制信息控制所述储能装置在相应操作时间区间内的操作。
在本申请的第四方面的某些实施方式中，所述储能控制系统还包括：显示模块，用于获取并显示所述能量序列、供电预测序列和用电量预测序列中的至少一种。
在本申请的第四方面的某些实施方式中，所述储能控制系统还包括：更新模块，用于基于最新生成的能量序列对所述控制信息进行更新。
在本申请的第四方面的某些实施方式中，所述控制信息包括以下至少一种：储能装置的充放电控制信息、储能装置在预测时间区间的目标储能值。
本申请的第五方面提供一种服务端，包括：接口单元，用于获取一用电周期内可供用电方使用的供电相关信息以及所述用电方的用电相关信息；存储单元，用于存储至少一个程序；以及处理单元，用于调用所述至少一个程序以协调所述接口单元和存储单元执行如前所述的储能管理方法。
本申请的第六方面提供一种计算机设备，包括：接口单元，用于获取一用电周期内可供 用电方使用的供电相关信息以及所述用电方的用电相关信息；存储单元，用于存储至少一个程序；以及处理单元，用于调用所述至少一个程序以协调所述接口单元和存储单元执行如前所述的储能控制方法。
本申请的第七方面提供一种计算机可读存储介质，存储至少一种程序，所述至少一种程序在被调用时执行如前所述的储能管理方法。
本申请的第八方面提供一种计算机可读存储介质，存储至少一种程序，所述至少一种程序在被调用时执行如前所述的储能控制方法。
本申请的第九方面提供一种储能控制系统，包括：如前所述的服务端和如前所述的计算机设备。
如上所述，本申请的储能管理方法、储能控制方法及各系统、计算机设备、存储介质，具有以下有益效果：基于所获取的供电预测序列、用电量预测序列以及储能装置的储能参数，生成在一用电周期内储能装置的能量序列，以使得可以基于所述能量序列对所述储能装置进行管理，进而实现用电总价最低的目的。
附图说明
图1显示为发电系统、自供电系统、用电系统和储能装置之间的电能传输关系示意图。
图2显示为本申请服务端在一实施方式中的结构示意图。
图3显示为本申请储能管理方法的流程图。
图4a至图4d分别显示为基于本申请储能管理方法的在一用电周期内的电价预测序列、自供电量预测序列、用电量预测序列以及储能装置的能量序列的示意图。
图5显示为用电方基于本申请储能管理方法获得的用电总价与无储能装置时的用电总价的曲线示意图。
图6显示为本申请的计算机设备在一实施方式中的结构示意图。
图7显示为本申请储能控制方法的流程图。
图8显示为本申请借助服务端运行的储能管理系统在一实施方式中的结构示意图。
图9显示为本申请借助计算机设备运行的储能控制系统在一实施方式中的结构示意图。
图10显示为本申请的储能控制系统在一实施方式中的网络架构示意图。
具体实施方式
以下由特定的具体实施例说明本申请的实施方式，熟悉此技术的人士可由本说明书所揭露的内容轻易地了解本申请的其他优点及功效。
再者，如同在本文中所使用的，单数形式“一”、“一个”和“该”旨在也包括复数形式，除非上下文中有相反的指示。应当进一步理解，术语“包含”、“包括”表明存在所述的特征、步骤、操作、元件、组件、项目、种类、和/或组，但不排除一个或多个其他特征、步骤、操作、元件、组件、项目、种类、和/或组的存在、出现或添加。此处使用的术语“或”和“和/或”被解释为包括性的，或意味着任一个或任何组合。因此，“A、B或C”或者“A、B和/或C”意味着“以下任一个：A；B；C；A和B；A和C；B和C；A、B和C”。仅当元件、功能、步骤或操作的组合在某些方式下内在地互相排斥时，才会出现该定义的例外。
请参阅图1，其显示为发电系统、自供电系统、用电系统和储能装置之间的电能传输关系示意图。其中，发电系统由电力供应方管理，自供电系统、用电系统和储能装置位于用电企业、园区、楼宇等用电方一侧，发电系统通过电网向用电系统和储能装置提供电力，自供电系统用于向用电系统提供电力。其中，自供电系统如太阳能发电系统、风力发电系统、换能发电系统等。此外，储能装置如化学储能装置等。对于现有分两段的电价机制下，容易设计储能装置的控制方式，使其在电价低时存储电能，以及在电价高时释放电能，以实现降低电费的目的。然而，当电价机制由两段式分段电价变成多段式分段电价等随时间浮动的计费方式时，储能装置的控制就变得极为复杂。
为了能够在电价和用电总量等信息处于变化状态下，提高对储能装置的利用率，以有效降低用电成本，本申请提供一种储能管理方法，用于管理为用电方提供储备电能的储能装置。所述储能管理方法主要由储能管理系统来执行。其中，所述储能管理系统可以是配置在服务端的软件系统，其利用所配置服务端的硬件执行相应程序以为用电方提供在待预测的用电周期内的储能装置的能量序列，使得用电方能够基于所述能量序列对储能装置进行管理。其中，所述用电周期举例为自然日、自然月等。所述能量序列是指在用电周期内依时间顺序的待管理的储能装置的多个能量值的集合。所生成的储能装置的能量序列可用来帮助用电方对储能装置进行管理，以便通过管理储能装置而实现在每个用电周期内用电成本尽量低的目的。
为此，本申请提供一种储能管理方法。所述储能管理方法主要由服务端来执行。在此，所述服务端包括但不限于单台服务器、服务器集群、分布式服务器群、云服务端等。其中，所述云服务端包括公共云(Public Cloud)服务端与私有云(Private Cloud)服务端，其中，所述公共或私有云服务端包括Software-as-a-Service(软件即服务，SaaS)、Platform-as-a-Service(平台即服务，PaaS)及Infrastructure-as-a-Service(基础设施即服务，IaaS)等。所述私有云服务端例如阿里云计算服务平台、亚马逊(Amazon)云计算服务平台、百度云计算平台、腾讯云计算平台等等。
在此，所述服务端与电力供应商的电价发布系统，与储能装置的储能控制系统，与用电方的用电控制系统、生产活动的管理系统、自供电系统等通信连接，甚至还可以数据连接第三方系统，以及利用爬虫技术获取互联网中与用电方用电相关的互联网数据等。其中，所述电价发布系统是电力供应商(或电力市场管理方，如政府部门)发布电价的系统。例如，电价发布系统每隔30分钟发布一次此后24小时的电价预测序列。所述储能控制系统包括但不限于：用于检测储能装置所存储能量的检测装置、储能装置充放电控制系统等。所述用电控制系统包括但不限于：安装在企业内的计量装置(如电度表)、电气设备控制系统等。所述生产活动的管理系统包括但不限于：生产过程执行系统(MES，Manufacturing Execution System)、企业资源计划系统(ERP，Enterprise Resource Planning)等。所述自供电系统包括但不限于：用于检测自供电系统的发电量的检测装置、自供电系统的发电控制系统等。所述第三方系统举例包括自有的用于存储历史用电数据服务器、用于存储历史电价数据服务器、用于获取企业用电计划的WEB服务器等。所述互联网数据举例包括天气预报数据等，其中，所述天气预报数据可以是基于从互联网获取的历史同期的天气数据预测而得的，或者从气象网站或其他网站直接获取的天气预报数据。
请参阅图2，其显示为本申请的服务端在一实施方式中的结构示意图，如图所示，所述服务端包括接口单元11、存储单元12、以及处理单元13。其中，存储单元12包含非易失性存储器、存储服务器等。其中，所述非易失性存储器举例为固态硬盘或U盘等。所述存储服务器用于存储所获取的各种用电相关信息和供电相关信息。接口单元11包括网络接口、数据线接口等。其中所述网络接口包括但不限于：以太网的网络接口装置、基于移动网络(3G、4G、5G等)的网络接口装置、基于近距离通信(WiFi、蓝牙等)的网络接口装置等。所述数据线接口包括但不限于：USB接口、RS232等。所述接口单元与供电方的各系统、用电方的各系统、第三方系统、互联网等数据连接。处理单元13连接接口单元11和存储单元12，其包含：CPU或集成有CPU的芯片、可编程逻辑器件(FPGA)和多核处理器中的至少一种。处理单元13还包括内存、寄存器等用于临时存储数据的存储器。
请参阅图3，其显示为所述储能管理方法的流程图。其中，所述储能管理方法主要依靠服务端中的处理单元13来执行，藉由处理单元读取存储单元12所存储的至少一个程序，并依据处理单元与存储单元、接口单元等硬件单元之间的硬件连接，从而进行数据交互。在一些实际应用中，所述处理单元可在电价变动的起始时刻执行下述各步骤，以得到在当前用电周期期间按照所述储能管理方法所提供的能量序列对储能装置进行管理。在又一些实际应用中，受用电方实际用电量的不断变化，储能装置所存储的能量需适应性及时调整，以使用用电方在整个电结算周期的用电成本尽量低。为此，所述处理单元将重复执行下述各步骤，以 便及时调整储能装置中的能量。
在步骤S110中，获取在一用电周期内可供用电方使用的供电预测以及用电方的用电量预测序列。其中，所述用电周期为前述待预测的用电周期，其可以是预先约定的用电周期，还可以是根据所能得到的浮动电价变化周期而设置的用电周期。其中，所述浮动电价变化周期是指电价变化的时间间隔。例如，浮动电价变化周期为单一电价所维持的时长。又如，浮动电价变化周期为一个浮动电价序列的更新时长。所述供电预测序列包括供电方、自供电系统、或第三方在用电周期内依时间顺序预测的多个供电量的集合。其中，所述第三方包括依据从用电方所获取的与供电相关的参数数据、历史供电数据等进行模拟得到的在用电周期内依时间顺序预测的多个供电量的集合。
在一些实施例中，在可供用电方使用的电力包括从电力供应商处购买的情况下，所述供电预测序列包含电价预测序列。相应地，步骤S110中获取在一用电周期内的供电预测序列的步骤包括获取在一用电周期内的电价预测序列的步骤。其中，所述电价预测序列是指在用电周期内依时间顺序预测的多个电价的集合。
实际应用中，存在第三方(例如，单独的电价预测系统、电力供应商或单独的电价定价系统)提供电价预测序列的情况。基于此，在一种实施方式中，获取在一用电周期内的电价预测序列的步骤可以包括直接获取来自第三方的电价预测序列并将其作为步骤S110中的供电预测序列。在此，需要说明的是，第三方提供的电价预测序列通常是跨一定时长的电价预测序列，因此，上述用电周期还可基于第三方提供的电价预测序列所跨时长来设置，例如，在第三方提供的电价预测序列所跨时长为12小时的情况下，上述用电周期可设置为12小时或小于12小时，以使得在后续处理中能够直接使用获取自第三方的电价预测序列。
实际上，第三方发布的电价预测序列与实际电价存在偏差，因而，在另一种实施方式中，获取在一用电周期内的电价预测序列的步骤可以包括：基于所获取的历史电价预测序列以及相应的历史实际电价之间的偏差，预测可供所述用电方使用的所述用电周期内的电价预测序列，以使得提高用于生成能量序列所基于的电价预测序列的准确度，进而提高所生成能量序列的准确度。
在一示例中，首先获取第三方提供的历史电价预测序列以及相应的历史实际电价。例如，可以自第三方或其他数据平台获取一定历史时间段(如上一年)的历史电价预测序列，以及获取所述历史电价预测序列中至少一个历史电价预测值所对应的的历史实际电价；然后对上述历史电价预测值和所对应的历史实际电价之间的电价误差进行统计，得到一电价误差范围；以上述电价误差范围作为修正参数，对获取自第三方的所述用电周期内的电价预测序列进行修正，以获得用于生成能量序列所基于的电价预测序列。需要说明的是，在对上述历史电价 预测序列和历史实际电价之间的电价误差进行统计时，还可以依时长获取多个电价误差范围，并基于所述多个电价误差范围对获取自第三方的所述用电周期内的相应时长的电价预测序列进行修正。
在又一些实施方式中，电力供应商不提供电价预测序列，所述获取在一用电周期内的电价预测序列的步骤可以包括：基于所获取的电价相关信息，预测所述用电周期内的电价预测序列。其中，所述电价相关信息包括但不限于以下至少一种：历史实际电价序列、用电市场的电价规则、影响电价变化的其他因素等。其中，所述历史实际电价序列是指在一定历史时间段内依时间顺序的多个实际电价的集合。例如，可以自第三方或其他数据平台获取历史实际电价序列。所述用电市场的电价规则是指地方政府或电力供应商为所管辖的区域设置的电价规则，其包括但不限于：基于用电方用电需量而设置的罚款电价等。所述影响电价变化的其他因素举例包括天气、节假日等。例如，基于所获取的天气预报、发布的节假日休假安排、以及历史实际电价序列等来预测在一用电周期内的电价预测序列。
基于上述，通过建立预测模型来获得电价预测序列。在一示例中，在综合考虑上述电价相关信息的情况下，以历史实际电价序列、天气预报、节假日休假安排等作为预测模型的输入，采用预测算法如随机森林(Random Forest)、长短期记忆网络(LSTM)、迭代决策树(GBRT)、卷积神经网络(CNN)等进行计算，获得用电周期内的电价预测序列以作为输出。此外，还可以根据预测模型的误差范围对电价预测序列的结果进行修正。
需要说明的是，上述各获取电价预测序列的实施方式仅为举例，而非对本申请的限制。本领域技术人员可结合前述多种实施方式构建预测电价预测序列的模型。例如基于上述预测模型的输入、所采用的预测算法，以及经检测获得的历史电价数据的误差范围计算电价预测序列，以便提高后续预测的准确度。
在另一些实施例中，在用电方配置有自供电系统，即可供用电方使用的电力包括自供电系统提供的电力的情况下，所述供电预测序列还包括自供电量预测序列。其中，所述自供电量预测序列是指在用电周期内依时间顺序预测的多个自供电量的集合。所述自供电系统包括但不限于：光伏发电系统、热转换系统、三联供系统、风能发电系统等。
相应地，步骤S110中获取在一用电周期内的供电预测序列的步骤包括获取在一用电周期内的自供电量预测序列的步骤。根据实际用电方所使用的自供电系统，所述步骤S110包括基于所获取的自供电系统的发电相关信息，预测所述用电周期内的自供电量预测序列。其中，所述发电相关信息包括但不限于：历史发电数据、基于自供电系统工作原理的影响发电的因素。例如，在自供电系统采用光伏发电的情况下，影响发电的因素主要包括太阳辐照度等。又如，在自供电系统采用风能发电的情况下，影响发电的因素主要包括风速、风向等。再如， 在自供电系统采用热转换发电的情况下，影响发电的因素主要包括系统的热转换效率、所检测到的温度等。
基于上述，可以通过建立预测模型来获得自供电量预测序列。以所述发电相关信息作为预测模型的输入，采用预测算法如随机森林(Random Forest)、长短期记忆网络(LSTM)、迭代决策树(GBRT)、卷积神经网络(CNN)等进行计算，获得用电周期内的自供电量预测序列以作为输出。此外，还可以根据预测模型的误差范围对自供电量预测序列的结果进行修正。
需要说明的是，上述各获取自供电量预测序列的实施方式仅为举例，而非对本申请的限制。本领域技术人员可结合前述电价预测序列中提及的多种实施方式构建预测自供电量预测序列的模型。例如基于预测模型的输入、所采用的预测算法，以及经检测获得的误差范围计算自供电量预测序列，以便提高后续预测的准确度。
还需要说明的是，上述各利用自供电系统的自供电量预测的方式仅为举例，而非对本申请的限制。本领域技术人员应理解，所述自供电量预测序列所基于的发电相关信息根据实际自供电系统的供电方式的不同而不同，在此不再一一赘述。
还需要说明的是，根据实际情况，通过执行所述步骤S110可获得的供电预测序列可仅包括电价预测序列、或自供电量预测序列；或者既包含电价预测序列也包含自供电量预测序列。在此可不做限制。
此外，在步骤S110中，获取用电方的用电量预测序列的步骤包括：按照所述用电周期内的用电因素获取用电相关信息，以及根据所述用电相关信息，预测所述用电周期内的用电量预测序列。其中，所述用电量预测序列是指在用电周期内依时间顺序预测的多个用电量的集合。用电方获取用电量与其日常生产活动的用电因素相关。其中，所述用电因素包括但不限于：人为计划例如排产计划、商场活动计划，根据天气或社会活动规律(如工作日、节假日)而总结的计划。例如，针对工厂生产产品A的用电情况，所述用电相关信息可以包括生产产品A的历史用电数据、基于产品A的排产计划确定的设备使用信息、所述设备的用电信息等。再如，针对办公楼的用电情况，所述用电相关信息可以包括基于季节设置的空调使用信息、空调用电信息、工作日和节假日照明灯、电脑等的使用信息等。在某些未设置空调使用信息的情况下，还可以基于天气预报情况确定空调使用信息。例如，依据预报的气温控制空调的使用。
基于上述，可以通过建立预测模型来获得用电量预测序列。以所述用电相关信息作为预测模型的输入，采用预测算法如随机森林(Random Forest)、长短期记忆网络(LSTM)、迭代决策树(GBRT)、卷积神经网络(CNN)等进行计算，获得用电周期内用电方的电量 预测序列以作为输出。此外，还可以根据预测模型的误差范围对用电量预测序列的结果进行修正。
需要说明的是，上述基于用电相关信息的用电量预测方式仅为举例，而非对本申请的限制。本领域技术人员应理解，影响所述用电量预测序列的其他用电相关信息也可作为预测模型的输入以经过预测算法获得用电量预测序列，在此不再一一赘述。
在步骤S120中，基于以预设获取条件而获取的储能装置的储能参数，以及用电周期内的供电预测序列和用电量预测序列，生成在用电周期内储能装置的能量序列，以使得基于所述能量序列对储能装置进行管理。
其中，所述预设获取条件包括以下至少一种：更新供电预测序列的事件，更新用电量预测序列的事件，更新周期；其中，所述更新周期是基于所述供电预测序列的更新周期和/或所述用电量预测序列的更新周期而确定的。
在此，更新供电预测序列的事件包括但不限于：第三方电价预测序列更新事件、影响电价的因素发生变化等。所述影响电价的因素发生变化举例包括新增活动日导致用电量增加进而导致电价变化的事件、影响自供电系统发电的因素发生变化等。其中所述影响自供电系统发电的因素发生变化举例包括：天气突变造成的光伏发电量减少进而导致自供电量变化的事件等。另外，更新用电量预测序列的事件还包括但不限于：影响用电量的因素发生变化的事件。例如因排产计划变化造成的用电量增加或减少的事件。
此外，在一些实施例中，所述更新周期基于供电预测序列的更新周期而确定。其中，供电预测序列的更新周期可以是预先设置的更新周期，也可以是根据浮动电价变化周期设置的更新周期。例如，在浮动电价为每30分钟变化一次的情况下，所述更新周期设置为每30分钟更新一次。在另一些实施例中，所述更新周期基于用电量预测序列的更新周期而确定。其中，用电量预测序列的更新周期可以是预先设置的更新周期，也可以是根据用电计划的调整而设置更新周期。例如，当调整排产计划时，根据所对应的调整事件而设置更新周期。在又一些实施例中，所述更新周期是基于供电预测序列的更新周期和用电量预测序列的更新周期而确定的。例如，每当电价预测序列变化时获取储能装置的储能参数，以及每当用电计划调整时，获取储能装置的储能参数。另外，所述更新周期还包括未依据储能管理方法所建议的操作进行操作而进行的更新。例如，当依据储能管理方法建议操作员在某时刻对储能装置进行充电操作，但由于操作员未依据所述建议进行操作，则当操作员再次操作时，需先更新，然后基于更新后的储能管理建议对储能装置进行相应操作。
所述储能参数包括以下至少两个：所检测的或所预测的储能装置存储的能量、储能装置的容量、储能装置的充放电参数、储能装置的损失参数。其中，储能装置的容量包括储能装 置的最大容量和最小容量。储能装置的充放电参数包括储能装置的充电速度、储能装置的放电速度、充放电功率上下限等。储能装置的损失参数包括储能装置的能量存储过程的能量转化率、储能装置的能量释放过程的能量转化率、储能装置的闲置过程的能量损失率。所述储能参数还可以是基于温度相关变量而确定的参数组。
当服务端在工作期间达到预设获取条件时，供电预测序列、用电量预测序列以及储能装置的储能参数被更新。在一些示例中，供电预测序列和用电量预测序列中的任一被更新，则从更新时刻起基于更新后的供电预测序列、用电量预测序列、和所获取的储能参数生成下一用电周期内的能量序列。以更新周期为30分钟，用电周期为24小时为例，所述服务端每隔30分钟生成下一24小时的能量序列，其中，所述能量序列可包含依30分钟时间间隔预测并排序的储能装置所存储的能量值。
在此，所述服务端可依据用电方的实际管理需求进行储能装置的储能管理，进而生成符合管理需求的能量序列。其中，所述管理需求包括但不限于：尽量减少用电总价、尽量减少用电峰值的用电量等。所述服务端基于所述获取条件而生成的能量序列对储能装置进行能量管理。
在某些实施例中，步骤S120包括：在至少一个约束条件下，以在所述用电周期内的用电总价低为优化目标，生成在所述用电周期内储能装置的能量序列。其中，所述约束条件包括基于所述储能参数确定的约束条件。其中，以用电周期内的用电总价最低为优化目标的情况下，优化目标函数为：
Figure PCTCN2018116767-appb-000001
其中，t表示第t时刻，E G2L表示用电方从电网购买并直接使用的电量；E G2B表示用电方从电网购买并存储的电量；E B2L表示用电方的储能装置释放并使用的电量；P G表示从电网购买电力的实时电价；P B表示储能装置的充放电成本、损耗等代价所折算的价格。
此外，对于储能装置，其模型数学描述可以为：
E btty(t)＝E btty(t-Δt)+ΔE
其中，E btty(t)为t时刻储能装置中存储的电量，E btty(t-Δt)为(t-Δt)时刻储能装置中存储的电量，ΔE为单位时间Δt内存储或释放的电量。此外，ΔE表达式为：
ΔE＝E G2B×e charge；E B2L＝0
或者，ΔE＝E B2L×e discharge；E G2B＝0
或者，ΔE＝E loss；E B2L＝E G2B＝0
其中，e charge表示储能装置的充电过程的能量转化率；e discharge表示储能装置的放电过程的能量转化率；E loss表示单位时间Δt内储能装置的自放电量。
在此，根据实际所能获取的储能装置的储能参数，而设置至少一个约束条件，其旨在在管理储能装置时避免储能装置出现异常。例如，避免所生成的能量序列中的某一能量值超出储能装置的最大容量等。基于上述优化目标函数以及储能装置的模型，其中，储能装置充电量E G2B和储能装置放电量E B2L受储能装置的模型控制，该模型的约束条件包括以下至少一种：针对储能装置而设置的约束条件，以及基于电能消耗和电能供应之间关系而设置的约束条件。
其中，针对储能装置而设置的约束条件包括以下至少一种：
1)储能装置的容量：E btty_MIN≤E btty≤E btty_MAX
2)储能装置的充放电速度：0≤ΔE/Δt≤CR charge或者CR discharge≤ΔE/Δt≤0；其中，E btty_MIN表示储能装置的最小容量；E btty_MAX表示储能装置的最大容量；CR charge表示储能装置的充电速度；CR discharge表示储能装置的放电速度。同时，上述储能装置相关变量均为温度相关变量。
其中，基于电能消耗和电能供应之间关系而设置的约束条件是指用电方在某一时刻的所消耗的电能为从电网购买的电能、储能装置放电提供的电能以及自供电系统所产生的自供电量所对应的电能中至少一个或多个的总和，即(E G2L+E B2L+E P2L)，其中，E P2L表示用电方的实时自供电量。在自供电量均用于用电方设备运行的情况下，用电方总需电量与自供电量预测结果之差作为从电网购买且直接使用的电量与储能装置释放并使用的电量之和(E G2L+E B2L)的约束条件。也就是说，在某一时间段内，储能装置的放电量上限等于总需电量与自供电量之差，若储能装置的放电量不足，则采用从电网购买的电量来补足。
需要说明的是，自供电系统的自供电量也可以根据实际情况将多余部分卖给电力供应商，其不影响本申请所描述的储能管理方案，在此不予详述。
在一种实施方式中，步骤S120中在至少一个约束条件下，以在所述用电周期内的用电总低为优化目标，生成在所述用电周期内所述储能装置的一能量序列的步骤包括：在至少一个约束条件下，生成在所述用电周期内的一个或多个候选能量序列；以及在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，对所生成的一个或多个候选能量序列进行优化处理，得到在所述用电周期内所述储能装置的能量序列。
在某些实施例中，基于所预测的或所检测的储能装置存储的能量，以及上述所有约束条件，生成在用电周期内的一个或多个候选能量序列。在此，对于初始化候选能量序列(也可称为初始化候选解)可以采用随机的方式，生成预设的一个或多个候选能量序列，即候选解。
其中，在一些示例中，所生成的候选解为一个，在至少一个约束条件下且以在所述用电 周期内的用电总价低为优化目标，对该候选解进行优化处理。例如，在上述约束条件下，生成对应用电周期的一个候选解。利用该候选解所对应的用电总价在一Δt时长内的变化趋势，对所生成的一个候选解进行优化处理，以得到在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标的能量序列。
在另一些示例中，所生成的候选解为多个，在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，从多个候选解中筛选和/或调整，以得到能量序列。例如，计算在约束条件下所生成的多个候选解各自所对应的用电总价，选择用电总价最低的候选解为所生成的能量序列。又如，计算在约束条件下所生成的多个候选解各自所对应的用电总价，选择用电总价最低的候选解；利用该候选解所对应的用电总价在一Δt时长内的变化趋势，对所生成的一个候选解进行优化处理，以得到在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标的能量序列。
其中，在某些实施例中，对所生成的一个或多个候选能量序列进行优化处理的步骤包括：根据以在用电周期内的用电总价低为优化目标而设置的截止条件，从一个或多个候选能量序列中确定一个候选能量序列，并将其作为所述能量序列；以及当不满足所述截止条件时，在至少一个约束条件下，依据更新策略将所生成的至少一个候选能量序列进行更新，并按照更新后的候选能量序列重复上述步骤直至存在一个候选能量序列符合所述截止条件。
其中，所述截止条件包括实际迭代次数达到预设迭代次数，或者最近的若干次迭代的最优目标结果变化小于预设阈值。所述更新策略包括但并不限于拉格朗日乘子法(Lagrange Multiplier)、序列线性规划法(SLP)、序列二次规划法(SQP)、内点法(Interior Point)、外点法(Exterior Point)、有效集法(Active Set)、信赖域反射算法(Trust Region Reflective)、启发式算法(Heuristic Algorithms)、元启发式算法(Meta-heuristic Algorithms)、进化算法(Evolutionary Algorithms)、群智能算法(Swarm Intelligence Algorithms)、神经网络算法(Neural Networks)、禁忌搜索算法、模拟退火算法、蚁群优化算法、粒子群优化算法、差分进化、贪婪随机自适应搜索、克隆选择算法、人工免疫系统算法、以及其他类似的传统优化策略或智能优化策略。
以更新周期为30分钟，用电周期为24小时为例，基于上述储能装置的模型约束条件以及一定的先验计算，对高维解空间进行约束限制，将解空间限定在满足约束条件的局部空间范围内，得到多个候选解，其中每个候选解为48维；将其全部代入上述优化目标函数中，获得每个候选解所对应的优化目标值(简称：评估步骤)；然后，依据候选解所对应的优化目标值进行排序，筛选并保留其中一定数量的优秀解并淘汰其余的解(简称：筛选步骤)；将优化目标值按照从小到大的顺序(即用电总价从低到高的顺序)排序，筛选出排名前n(n≥1) 的优化目标值所对应的候选解，并淘汰其余的解。接下来，对筛选保留下来的n个候选解进行相应数量的克隆，同时在克隆过程中引入一定概率(变异率)的随机变异，以基于保留下来的各候选解生成新的候选解(简称：变异克隆步骤)。其中，所述变异率受上述模型约束条件的限制，以确保所得到的新的候选解是基于变异克隆前的候选解所做的微小变化而得的。其中，可以对所保留的候选解的克隆解全部解都引入变异率，也可以仅对部分解引入变异率。重复进行评估、筛选、变异克隆的步骤，直至满足实际迭代次数达到预设迭代次数的截止条件为止；将最终获得的所有候选解全部代入上述优化目标函数中，获得每个候选解所对应的优化目标值，选取最小优化目标值所对应的候选解作为储能装置的能量序列。
以上述储能装置的模型约束条件和优化目标为例并利用SQP算法得到能量序列的具体示例如下：在上述储能装置的模型约束条件以及一定的先验计算的约束下，利用泰勒展开将目标函数和约束函数进行转换，并利用转换后的目标函数和约束函数进行计算以得到一个候选解和误差梯度；基于所得到的误差梯度对所述候选解进行调整，重复计算候选解和调整的执行步骤，直至满足误差梯度小于预设梯度阈值的截止条件为止；将最终获得的候选解作为储能装置的能量序列。
需要说明的是，上述任一示例所述的截止条件与所使用的算法并非严格一一对应，也可以根据实际设计需要进行设置，例如为最近的若干次迭代的最优目标结果变化小于预设阈值等，在此不再赘述。此外，上述数值仅为举例而并非对本申请的限制，本领域技术人员可以基于本申请的思想任意选取数值进行计算。
还需要说明的是，在对候选解进行评估、筛选、迭代处理期间，除了变异克隆处理方式之外，还可以基于前述提及的其他算法对上述各步骤进行适应性调整和选用，为此，利用前述提及的其他算法，以及其他可应用于本申请所述技术思想的算法来确定储能装置的能量序列的方式，应视为基于本申请所述技术思想下的具体示例，在此不一一详述。
此外，本申请的储能管理方法还包括将所述能量序列、供电预测序列和用电量预测序列中的至少一种予以显示的步骤。请参阅图4a至图4d，其分别显示为基于本申请储能管理方法的在一用电周期内的电价预测序列、自供电量预测序列、用电量预测序列以及储能装置的能量序列的示意图。如图所示，本申请中，以用电周期设置为24小时为例，图4a显示为基于本申请储能管理方法所获取的电价预测序列；图4b显示为基于本申请储能管理方法所获取的自供电量预测序列，其中，曲线4b-1为自供电量上限预测序列、曲线4b-2为自供电量预测序列及曲线4b-3为自供电量下限预测序列。图4c显示为基于本申请储能管理方法所获取的用电方的用电量预测序列，其中，曲线4c-1为用电量上限预测序列、曲线4c-2为用电量预测序列、曲线4c-3为用电量下限预测序列。图4d显示为基于本申请储能管理方法所获取的 储能装置的能量序列，其中，曲线1为用电方不使用储能装置时的用电总价，曲线2为用电方基于本申请储能管理方法获得的用电总价。
此外，请参阅图5，图5显示为用电方基于本申请储能管理方法获得的用电总价与不使用储能装置时的用电总价的曲线示意图，如图所示，曲线1表示用电方基于本申请储能管理方法获得的用电总价，曲线2表示用电方不使用储能装置时的用电总价，由图可知，相较于不使用储能装置的情况，受到储能系统容量、用电方用电量等情况影响，采用本申请储能管理方法的总电费节省约在5％-20％之间。
综上所述，本申请的储能管理方法基于所获取的供电预测序列、用电量预测序列以及储能装置的储能参数，生成在一用电周期内储能装置的能量序列，以使得可以基于所述能量序列对所述储能装置进行管理，进而实现用电总价最低的目的。
对于用电方来说，在浮动电价机制下，用户可以通过自有的储能装置，在电价低时购买一定的电力并存储，并在电价高时将存储的电力释放以供用户自身使用，以期达到一定程度降低电费的目的。然而，实际应用中，用电方在何时控制储能装置、控制储能装置充电还是放电、需要充电或放电的电量是多少，都存在着不确定性。为此，本申请还提供一种储能控制方法，用于控制为用电方提供储备电能的储能装置。所述储能控制方法主要由储能控制系统来执行。其中，所述储能控制系统可以是配置在计算机设备上的软件系统，其基于所获取的储能装置的能量序列来使用电方对储能装置进行控制，以实现在用电周期内用电总价最低的目的。
在此，所述计算机设备可以是位于企业的用电调控机房的设备，或为互联网中一服务端。所述服务端包括但不限于单台服务器、服务器集群、分布式服务器群、云服务端等。其中，所述云服务端包括公共云(Public Cloud)服务端与私有云(Private Cloud)服务端，其中，所述公共或私有云服务端包括Software-as-a-Service(软件即服务，SaaS)、Platform-as-a-Service(平台即服务，PaaS)及Infrastructure-as-a-Service(基础设施即服务，IaaS)等。所述私有云服务端例如阿里云计算服务平台、亚马逊(Amazon)云计算服务平台、百度云计算平台、腾讯云计算平台等等。
所述计算机设备与电力供应商的电价发布系统，储能装置的储能控制系统，用电方的用电控制系统、生产活动的管理系统、自供电系统等通信连接，甚至还可以数据连接第三方系统，以及利用爬虫技术获取互联网中与用电方用电相关的互联网数据等。其中，所述电价发布系统是电力供应商(或电力市场管理方，如政府部门)发布电价的系统。所述储能控制系统包括但不限于：用于检测储能装置所存储能量的检测装置、储能装置充放电控制系统等。所述用电控制系统包括但不限于：安装在企业内的计量装置(如电度表)、电气设备控制系 统等。所述生产活动的管理系统包括但不限于：生产过程执行系统(MES，Manufacturing Execution System)、企业资源计划系统(ERP，Enterprise Resource Planning)等。所述自供电系统包括但不限于：用于检测自供电系统的发电量的检测装置、自供电系统的发电控制系统等。所述第三方系统举例包括自有的用于存储历史用电数据服务器、用于存储历史电价数据服务器、用于获取企业用电计划的WEB服务器等。所述互联网数据举例包括天气预报数据等，其中，所述天气预报数据可以是基于从互联网获取的历史同期的天气数据预测而得的，或者从气象网站或其他网站直接获取的天气预报数据。
请参阅图6，其显示为本申请的计算机设备在一实施方式中的结构示意图，如图所示，所述计算机设备包括接口单元61、存储单元62和处理单元63。其中，存储单元62包含非易失性存储器、存储服务器等。其中，所述非易失性存储器举例为固态硬盘或U盘等。所述存储服务器用于存储所获取的各种用电相关信息和供电相关信息。接口单元61包括网络接口、数据线接口等。其中所述网络接口包括但不限于：以太网的网络接口装置、基于移动网络(3G、4G、5G等)的网络接口装置、基于近距离通信(WiFi、蓝牙等)的网络接口装置等。所述数据线接口包括但不限于：USB接口、RS232等。所述接口单元与供电方的各系统、用电方的各系统、第三方系统、互联网等数据连接。处理单元63连接接口单元61和存储单元62，其包含：CPU或集成有CPU的芯片、可编程逻辑器件(FPGA)和多核处理器中的至少一种。处理单元63还包括内存、寄存器等用于临时存储数据的存储器。
请参阅图7，其显示为所述储能控制方法的流程图。处理单元63读取存储单元所存储的至少一个程序、用电相关信息以及供电相关信息以执行如下所述的储能控制方法。其中，所述用电相关信息和所述供电相关信息是处理单元预先自接口单元获取并保存在存储单元中的。
在步骤S710中，获取由储能管理方法所生成的在一用电周期内储能装置的能量序列。其中，步骤S710的具体实现方式如图2至图3及其相应描述所述，在此不再赘述。
在步骤S720中，基于所获取的能量序列中操作时间区间所对应的能量值，确定储能装置在操作时间区间用于控制储能装置操作的控制信息。其中，所述操作时间区间可以是用电方自定义的，也可以是根据步骤S710所获取的储能装置的能量序列中相邻能量值的时间间隔而设置的。例如，在所述操作时间区间为用电方自定义的情况下，首先可以以用电方自定义的起始时刻作为步骤S710中的更新周期，获得最新的一用电周期内的储能装置的能量序列，然后基于所述能量序列中对应的能量值，确定在自定义操作时间区间用于控制储能装置操作的控制信息。在所述操作时间区间为基于步骤S710所获取的储能装置的能量序列而设置的情况下，例如基于如图4d所示的能量序列图，可以设置操作时间区间分别对应于能量序列图中储 能装置充电、放电阶段的时间区间。
另外，所述控制信息包括储能装置的充放电控制信息和/或储能装置在操作时间区间的目标储能值。其中，所述充放电控制信息包括但不限于：充放电速度、充放电时刻、充放电时长。储能装置在操作时间区间的目标储能值是指在一定时间段内储能装置充电或放电的电量，基于所述目标储能值以及操作时间区间可以获得储能装置的充放电速度。
鉴于此，本申请储能控制方法还包括基于所述控制信息控制储能装置在相应操作时间区间内的操作的步骤。例如，基于充放电控制信息控制储能装置自某一充放电时刻以某一充放电速度持续某一充放电时长进行充放电操作。再如，基于目标储能值控制储能装置选择不同的充放电速度以在某一操作时间区间内达到目标储能值。
另外，本申请储能控制方法还包括获取并显示所述能量序列、供电预测序列和用电量预测序列中的至少一种的步骤，以使得用户可以直观观察储能装置的能量序列以及各预测序列。
此外，由于步骤S710中基于预设获取条件对供电预测序列、用电量预测序列以及储能参数进行更新，进而获得新的能量序列的步骤，因而，本申请储能控制方法相应地还包括基于最新生成的能量序列对所述控制信息进行更新的步骤。例如，以用电周期为24小时，更新周期为30分钟为例，首先，根据步骤S710获取24小时内储能装置的能量序列，根据步骤S720确定储能装置在操作时间区间用于控制储能装置操作的控制信息，然后，用户基于所述控制信息对储能装置进行操作。当达到30分钟的更新周期时，更新从此刻起24小时内储能装置的新的能量序列，并再次生成基于该新的能量序列的控制信息，然后，用户基于新的控制信息对储能装置进行操作。由此可见，虽然储能装置的能量序列显示为未来24小时(用电周期)的整体变化，但实际上，用户仅需关注30分钟(更新周期)内的操作信息，每30分钟基于新的能量序列对储能装置进行相应控制。
综上所述，本申请的储能控制方法基于所获取储能装置的能量序列控制储能装置进行操作，以实现用电总价最低的目的。
本申请还提供一种储能管理系统。所述储能管理系统为配置在服务端的软件系统。请参阅图8，其显示为所述储能管理系统在一实施方式中的结构示意图。所述储能管理系统2包含获取模块21和生成模块22等程序模块。
其中，获取模块21用于获取在一用电周期内可供所述用电方使用的供电预测序列以及所述用电方的用电量预测序列。其中，所述用电周期为前述待预测的用电周期，其可以是预先约定的用电周期，还可以是根据所能得到的浮动电价变化周期而设置的用电周期。其中，所述浮动电价变化周期是指电价变化的时间间隔。例如，浮动电价变化周期为单一电价所维持 的时长。又如，浮动电价变化周期为一个浮动电价序列的更新时长。所述供电预测序列包括供电方、自供电系统、或第三方在用电周期内依时间顺序预测的多个供电量的集合。其中，所述第三方包括依据从用电方所获取的与供电相关的参数数据、历史供电数据等进行模拟得到的在用电周期内依时间顺序预测的多个供电量的集合。
在一些实施例中，在可供用电方使用的电力包括从电力供应商处购买的情况下，所述供电预测序列包含电价预测序列。相应地，获取模块21包括下述中至少之一：用于获取所述用电周期内的电价预测序列的第一获取单元；用于基于所获取的历史电价预测序列以及相应的历史实际电价之间的偏差，预测可供所述用电方使用的所述用电周期内的电价预测序列的第二获取单元；用于基于所获取的电价相关信息，预测所述用电周期内的电价预测序列的第三获取单元。在一些实施方式中，在第三方(例如，单独的电价预测系统、电力供应商或单独的电价定价系统)提供电价预测序列的情况下，可使用第一获取单元直接获取所述用电周期内的电价预测序列。然而，实际上，第三方发布的电价预测序列与实际电价存在偏差，因而，在这种情况下，可使用第二获取单元基于所获取的历史电价预测序列以及相应的历史实际电价之间的偏差，预测可供所述用电方使用的所述用电周期内的电价预测序列。
在又一些实施方式中，电力供应商不提供电价预测序列，所述获取在一用电周期内的电价预测序列的步骤可以包括：基于所获取的电价相关信息，预测所述用电周期内的电价预测序列。其中，所述电价相关信息包括但不限于以下至少一种：历史实际电价序列、用电市场的电价规则、影响电价变化的其他因素等。其中，所述历史实际电价序列是指在一定历史时间段内依时间顺序的多个实际电价的集合。例如，可以自第三方或其他数据平台获取历史实际电价序列。所述用电市场的电价规则是指地方政府或电力供应商为所管辖的区域设置的电价规则，其包括但不限于：基于用电方用电需量而设置的罚款电价等。所述影响电价变化的其他因素举例包括天气、节假日等。例如，基于所获取的天气预报、发布的节假日休假安排、以及历史实际电价序列等来预测在一用电周期内的电价预测序列。
基于上述，通过建立预测模型来获得电价预测序列。在一示例中，在综合考虑上述电价相关信息的情况下，以历史实际电价序列、天气预报、节假日休假安排等作为预测模型的输入，采用预测算法如随机森林(Random Forest)、长短期记忆网络(LSTM)、迭代决策树(GBRT)、卷积神经网络(CNN)等进行计算，获得用电周期内的电价预测序列以作为输出。此外，还可以根据预测模型的误差范围对电价预测序列的结果进行修正。
需要说明的是，上述各获取电价预测序列的实施方式仅为举例，而非对本申请的限制。本领域技术人员可结合前述多种实施方式构建预测电价预测序列的模型。例如基于上述预测模型的输入、所采用的预测算法，以及经检测获得的历史电价数据的误差范围计算电价预测 序列，以便提高后续预测的准确度。
在另一些实施例中，在用电方配置有自供电系统，即可供用电方使用的电力包括自供电系统提供的电力的情况下，所述供电预测序列还包括自供电量预测序列。其中，所述自供电量预测序列是指在用电周期内依时间顺序预测的多个自供电量的集合。所述自供电系统包括但不限于：光伏发电系统、热转换系统、三联供系统、风能发电系统等。相应地，获取模块21包括用于基于所获取的自供电系统的发电相关信息，预测所述用电周期内的自供电量预测序列的第四获取单元。其中，所述发电相关信息包括但不限于：历史发电数据、基于自供电系统工作原理的影响发电的因素。例如，在自供电系统采用光伏发电的情况下，影响发电的因素主要包括太阳辐照度等。又如，在自供电系统采用风能发电的情况下，影响发电的因素主要包括风速、风向等。再如，在自供电系统采用热转换发电的情况下，影响发电的因素主要包括系统的热转换效率、所检测到的温度等。
基于上述，第四获取单元可以通过建立预测模型来获得自供电量预测序列。以所述发电相关信息作为预测模型的输入，采用预测算法如随机森林(Random Forest)、长短期记忆网络(LSTM)、迭代决策树(GBRT)、卷积神经网络(CNN)等进行计算，获得用电周期内的自供电量预测序列以作为输出。此外，第四获取单元还可以根据预测模型的误差范围对自供电量预测序列的结果进行修正。
需要说明的是，上述各获取自供电量预测序列的实施方式仅为举例，而非对本申请的限制。本领域技术人员可结合前述电价预测序列中提及的多种实施方式构建预测自供电量预测序列的模型。例如基于预测模型的输入、所采用的预测算法，以及经检测获得的误差范围计算自供电量预测序列，以便提高后续预测的准确度。
还需要说明的是，上述各利用自供电系统的自供电量预测的方式仅为举例，而非对本申请的限制。本领域技术人员应理解，所述自供电量预测序列所基于的发电相关信息根据实际自供电系统的供电方式的不同而不同，在此不再一一赘述。
还需要说明的是，根据实际情况，获取模块21可获得的供电预测序列可仅包括电价预测序列、或自供电量预测序列；或者既包含电价预测序列也包含自供电量预测序列。在此可不做限制。
此外，获取模块21还用于按照所述用电周期内的用电因素获取用电相关信息；以及根据所述用电相关信息，预测所述用电周期内的用电量预测序列的第五获取单元。其中，所述用电量预测序列是指在用电周期内依时间顺序预测的多个用电量的集合。用电方获取用电量与其日常生产活动的用电因素相关。其中，所述用电因素包括但不限于：人为计划例如排产计划、商场活动计划，根据天气或社会活动规律(如工作日、节假日)而总结的计划。例如， 针对工厂生产产品A的用电情况，所述用电相关信息可以包括生产产品A的历史用电数据、基于产品A的排产计划确定的设备使用信息、所述设备的用电信息等。再如，针对办公楼的用电情况，所述用电相关信息可以包括基于季节设置的空调使用信息、空调用电信息、工作日和节假日照明灯、电脑等的使用信息等。在某些未设置空调使用信息的情况下，还可以基于天气预报情况确定空调使用信息。例如，依据预报的气温控制空调的使用。
基于上述，第五获取单元可以通过建立预测模型来获得用电量预测序列。以所述用电相关信息作为预测模型的输入，采用预测算法如随机森林(Random Forest)、长短期记忆网络(LSTM)、迭代决策树(GBRT)、卷积神经网络(CNN)等进行计算，获得用电周期内用电方的电量预测序列以作为输出。此外，第五获取单元还可以根据预测模型的误差范围对用电量预测序列的结果进行修正。
需要说明的是，上述基于用电相关信息的用电量预测方式仅为举例，而非对本申请的限制。本领域技术人员应理解，影响所述用电量预测序列的其他用电相关信息也可作为预测模型的输入以经过预测算法获得用电量预测序列，在此不再一一赘述。
生成模块22用于基于以预设获取条件而获取的所述储能装置的储能参数，以及所述用电周期内的供电预测序列和用电量预测序列，生成在所述用电周期内所述储能装置的能量序列，以使得基于所述能量序列对所述储能装置进行管理。
其中，所述预设获取条件包括以下至少一种：更新供电预测序列的事件，更新用电量预测序列的事件，更新周期；其中，所述更新周期是基于所述供电预测序列的更新周期和/或所述用电量预测序列的更新周期而确定的。
在此，更新供电预测序列的事件包括但不限于：第三方电价预测序列更新事件、影响电价的因素发生变化等。所述影响电价的因素发生变化举例包括新增活动日导致用电量增加进而导致电价变化的事件、影响自供电系统发电的因素发生变化等。其中所述影响自供电系统发电的因素发生变化举例包括：天气突变造成的光伏发电量减少进而导致自供电量变化的事件等。另外，更新用电量预测序列的事件还包括但不限于：影响用电量的因素发生变化的事件。例如因排产计划变化造成的用电量增加或减少的事件。
此外，在一些实施例中，所述更新周期基于供电预测序列的更新周期而确定。其中，供电预测序列的更新周期可以是预先设置的更新周期，也可以是根据浮动电价变化周期设置的更新周期。例如，在浮动电价为每30分钟变化一次的情况下，所述更新周期设置为每30分钟更新一次。在另一些实施例中，所述更新周期基于用电量预测序列的更新周期而确定。其中，用电量预测序列的更新周期可以是预先设置的更新周期，也可以是根据用电计划的调整而设置更新周期。例如，当调整排产计划时，根据所对应的调整事件而设置更新周期。在又 一些实施例中，所述更新周期是基于供电预测序列的更新周期和用电量预测序列的更新周期而确定的。例如，每当电价预测序列变化时获取储能装置的储能参数，以及每当用电计划调整时，获取储能装置的储能参数。另外，所述更新周期还包括未依据储能管理方法所建议的操作进行操作而进行的更新。例如，当依据储能管理方法建议操作员在某时刻对储能装置进行充电操作，但由于操作员未依据所述建议进行操作，则当操作员再次操作时，需先更新，然后基于更新后的储能管理建议对储能装置进行相应操作。
所述储能参数包括以下至少两个：所检测的或所预测的储能装置存储的能量、储能装置的容量、储能装置的充放电参数、储能装置的损失参数。其中，储能装置的容量包括储能装置的最大容量和最小容量。储能装置的充放电参数包括储能装置的充电速度、储能装置的放电速度、充放电功率上下限等。储能装置的损失参数包括储能装置的能量存储过程的能量转化率、储能装置的能量释放过程的能量转化率、储能装置的闲置过程的能量损失率。所述储能参数还可以是基于温度相关变量而确定的参数组。
在某些实施方式中，生成模块22包括生成单元，生成单元用于在至少一个约束条件下，以在所述用电周期内的用电总价低为优化目标，生成在所述用电周期内所述储能装置的能量序列；其中，所述约束条件包括基于所述储能参数确定的约束条件。其中，以用电周期内的用电总价最低为优化目标的情况下，优化目标函数为：
Figure PCTCN2018116767-appb-000002
其中，t表示第t时刻，E G2L表示用电方从电网购买并直接使用的电量；E G2B表示用电方从电网购买并存储的电量；E B2L表示用电方的储能装置释放并使用的电量；P G表示从电网购买电力的实时电价；P B表示储能装置的充放电成本、损耗等代价所折算的价格。
此外，对于储能装置，其模型数学描述可以为：
E btty(t)＝E btty(t-Δt)+ΔE
其中，E btty(t)为t时刻储能装置中存储的电量，E btty(t-Δt)为(t-Δt)时刻储能装置中存储的电量，ΔE为单位时间Δt内存储或释放的电量。此外，ΔE表达式为：
ΔE＝E G2B×e charge；E B2L＝0
或者，ΔE＝E B2L×e discharge；E G2B＝0
或者，ΔE＝E loss；E B2L＝E G2B＝0
其中，e charge表示储能装置的充电过程的能量转化率；e discharge表示储能装置的放电过程的能量转化率；E loss表示单位时间Δt内储能装置的自放电量。
在此，根据实际所能获取的储能装置的储能参数，而设置至少一个约束条件，其旨在在管理储能装置时避免储能装置出现异常。例如，避免所生成的能量序列中的某一能量值超出储能装置的最大容量等。基于上述优化目标函数以及储能装置的模型，其中，储能装置充电量E G2B和储能装置放电量E B2L受储能装置的模型控制，该模型的约束条件包括以下至少一种：针对储能装置而设置的约束条件，以及基于电能消耗和电能供应之间关系而设置的约束条件。
其中，针对储能装置而设置的约束条件包括以下至少一种：
1)储能装置的容量：E btty_MIN≤E btty≤E btty_MAX
2)储能装置的充放电速度：0≤ΔE/Δt≤CR charge或者CR discharge≤ΔE/Δt≤0；其中，E btty_MIN表示储能装置的最小容量；E btty_MAX表示储能装置的最大容量；CR charge表示储能装置的充电速度；CR discharge表示储能装置的放电速度。同时，上述储能装置相关变量均为温度相关变量。
其中，基于电能消耗和电能供应之间关系而设置的约束条件是指用电方在某一时刻的所消耗的电能为从电网购买的电能、储能装置放电提供的电能以及自供电系统所产生的自供电量所对应的电能中至少一个或多个的总和，即(E G2L+E B2L+E P2L)，其中，E P2L表示用电方的实时自供电量。在自供电量均用于用电方设备运行的情况下，用电方总需电量与自供电量预测结果之差作为从电网购买且直接使用的电量与储能装置释放并使用的电量之和(E G2L+E B2L)的约束条件。也就是说，在某一时间段内，储能装置的放电量上限等于总需电量与自供电量之差，若储能装置的放电量不足，则采用从电网购买的电量来补足。
需要说明的是，自供电系统的自供电量也可以根据实际情况将多余部分卖给电力供应商，其不影响本申请所描述的储能管理方案，在此不予详述。
在一种实施方式中，所述生成单元用于在至少一个约束条件下，生成在所述用电周期内的一个或多个候选能量序列；以及在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，对所生成的一个或多个候选能量序列进行优化处理，得到在所述用电周期内所述储能装置的能量序列。
在某些实施例中，基于所预测的或所检测的储能装置存储的能量，以及上述所有约束条件，生成在用电周期内的一个或多个候选能量序列。在此，对于初始化候选能量序列(也可称为初始化候选解)可以采用随机的方式，生成预设的一个或多个候选能量序列，即候选解。
其中，在一些示例中，所生成的候选解为一个，在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，对该候选解进行优化处理。例如，在上述约束条件下，生成对应用电周期的一个候选解。利用该候选解所对应的用电总价在一Δt时长内的变化趋势，对所生成的一个候选解进行优化处理，以得到在至少一个约束条件下且以在所述用电周期内 的用电总价低为优化目标的能量序列。
在另一些示例中，所生成的候选解为多个，在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，从多个候选解中筛选和/或调整，以得到能量序列。例如，计算在约束条件下所生成的多个候选解各自所对应的用电总价，选择用电总价最低的候选解为所生成的能量序列。又如，计算在约束条件下所生成的多个候选解各自所对应的用电总价，选择用电总价最低的候选解；利用该候选解所对应的用电总价在一Δt时长内的变化趋势，对所生成的一个候选解进行优化处理，以得到在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标的能量序列。
在某些实施例中，所述生成单元用于根据以在所述用电周期内的用电总价低为优化目标而设置的截止条件，从所述一个或多个候选能量序列中确定一个候选能量序列，并将其作为所述能量序列；以及当不满足所述截止条件时，在至少一个约束条件下，依据更新策略将所生成的至少一个候选能量序列进行更新，并按照更新后的候选能量序列重复上述步骤直至存在一个候选能量序列符合所述截止条件。
其中，所述截止条件包括实际迭代次数达到预设迭代次数，或者最近的若干次迭代的最优目标结果变化小于预设阈值。所述更新策略包括但并不限于拉格朗日乘子法(Lagrange Multiplier)、序列线性规划法(SLP)、序列二次规划法(SQP)、内点法(Interior Point)、外点法(Exterior Point)、有效集法(Active Set)、信赖域反射算法(Trust Region Reflective)、启发式算法(Heuristic Algorithms)、元启发式算法(Meta-heuristic Algorithms)、进化算法(Evolutionary Algorithms)、群智能算法(Swarm Intelligence Algorithms)、神经网络算法(Neural Networks)、禁忌搜索算法、模拟退火算法、蚁群优化算法、粒子群优化算法、差分进化、贪婪随机自适应搜索、克隆选择算法、人工免疫系统算法、以及其他类似的传统优化策略或智能优化策略。
此外，本申请的储能管理系统还包括输出模块，所述输出模块用于输出所述能量序列、供电预测序列和用电量预测序列中的至少一种以予以显示。
在此，本申请储能管理系统中各模块的工作方式与上述储能管理方法中对应步骤相同或相似，在此不再赘述。
本申请还提供一种储能控制系统。所述储能控制系统为配置在计算机设备的软件系统。请参阅图9，其显示为所述储能控制系统在一实施方式中的结构示意图。所述储能控制系统3包含获取模块31和确定模块32等程序模块。
其中，获取模块31用于获取由储能管理系统所生成的在一用电周期内所述储能装置的能量序列。确定模块32用于基于所获取的能量序列中操作时间区间所对应的能量值，确定所 述储能装置在所述操作时间区间用于控制所述储能装置操作的控制信息。其中，所述操作时间区间可以是用电方自定义的，也可以是根据所获取的储能装置的能量序列中相邻能量值的时间间隔而设置的。
所述控制信息包括储能装置的充放电控制信息和/或储能装置在操作时间区间的目标储能值。其中，所述充放电控制信息包括但不限于：充放电速度、充放电时刻、充放电时长。储能装置在操作时间区间的目标储能值是指在一定时间段内储能装置充电或放电的电量，基于所述目标储能值以及操作时间区间可以获得储能装置的充放电速度。
此外，本申请的储能控制系统还包括控制模块，所述控制模块用于基于所述控制信息控制所述储能装置在相应操作时间区间内的操作。
另外，本申请的储能控制系统还包括显示模块，所述显示模块用于获取并显示所述能量序列、供电预测序列和用电量预测序列中的至少一种。
此外，由于获取模块可以基于预设获取条件对供电预测序列、用电量预测序列以及储能参数进行更新，进而获得新的能量序列的步骤，因而，本申请储能控制系统还包括更新模块，所述更新模块用于基于最新生成的能量序列对所述控制信息进行更新。
在此，本申请储能控制系统中各模块的工作方式与上述储能控制方法中对应步骤相同或相似，在此不再赘述。
另外需要说明的是，通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到本申请的部分或全部可借助软件并结合必需的通用硬件平台来实现。基于这样的理解，本申请还提供一种计算机可读存储介质，所述存储介质存储有至少一个程序，所述至少一种程序在被调用时执行前述的任一所述的储能管理方法。此外，本申请还提供一种计算机可读存储介质，所述存储介质存储有至少一个程序，所述至少一种程序在被调用时执行前述的任一所述的储能控制方法。
基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可包括其上存储有机器可执行指令的一个或多个机器可读介质，这些指令在由诸如计算机、计算机网络或其他电子设备等一个或多个机器执行时可使得该一个或多个机器根据本申请的实施例来执行操作。例如执行机器人的定位方法中的各步骤等。机器可读介质可包括，但不限于，软盘、光盘、CD-ROM(紧致盘-只读存储器)、磁光盘、ROM(只读存储器)、RAM(随机存取存储器)、EPROM(可擦除可编程只读存储器)、EEPROM(电可擦除可编程只读存储器)、磁卡或光卡、闪存、或适于存储机器可执行指令的其他类型的介质/机器可读介质。其中，所述存储介质可位于机器人也可位于第三方服务器中，如位于提供某应用商城的服务器中。在此对具体应用商城不做限制， 如小米应用商城、华为应用商城、苹果应用商城等。
本申请可用于众多通用或专用的计算系统环境或配置中。例如：个人计算机、服务器计算机、手持设备或便携式设备、平板型设备、多处理器系统、基于微处理器的系统、置顶盒、可编程的消费电子设备、网络PC、小型计算机、大型计算机、包括以上任何系统或设备的分布式计算环境等。
本申请可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本申请，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本申请还提供一种储能控制系统。所述储能控制系统包括前述任一示例中所提供的服务端和计算机设备。请参阅图10，其显示为所述储能控制系统控制储能装置在一种实施方式中的网络架构示意图。其中，所述服务端41和计算机设备42可均位于用电方侧，或者均位于可通过互联网、移动网络等数据传输网络进行数据通信的任一地理位置，还或者其中任一位于用电方侧、另一位于可数据通信的其他地理位置。所述计算机设备42可通过数据通信方式向储能装置43发送控制指令，以及收集储能装置43的储能参数。在一些示例中，所述服务端41还与用电方侧的计量装置44数据通信，用以获取计量装置44所检测的所述用电方的用电量，以供服务端41根据包含所获取的用电量的用电相关信息，预测所述用电周期内的用电量预测序列。在又一些示例中，所述用电方还包括自供电系统45，根据自供电系统45的实际类型，所述服务端41通过数据通信方式获取自供电系统45的发电相关信息。例如，所述自供电系统45采用热转换发电，对应的所述服务端41获取自供电系统45的温度信息，以作为其发电相关信息之一。
以图10为例，所述储能控制系统的执行过程举例如下：所述服务端41通过获取自供电系统45的发电相关信息，预测一用电周期内的自供电量预测序列；通过获取用电方的用电量及排产等用电相关信息，预测同一用电周期内用电量预测序列；通过所述计算机设备42获取储能装置43在所述用电周期起始时刻的储能参数；以及获取第三方的电价预测序列。服务端41基于所述储能参数而确定的约束条件包括：1)储能装置43的容量：E btty_MIN≤E btty≤E btty_MAX，以及2)储能装置43的充放电速度：0≤ΔE/Δt≤CR charge或者CR discharge≤ΔE/Δt≤0；以在该用电周期内用电总价低为优化目标，采用随机方式生成多个候选储能序列；通过计算每个候选储能序列所对应的用电总价，选取用电总价最低的n个候选 储能序列；对所保留的n个候选储能序列进行相应数量的克隆，同时在克隆过程中引入一定概率(变异率)的随机变异，并得到新的候选储能序列。其中，所述变异率受上述模型约束条件的限制，以确保所得到的新的候选储能序列是基于变异克隆前的候选解所做的微小变化而得的。其中，对所保留的候选储能序列的克隆解全部解都引入变异率，也可以仅对部分解引入变异率。在上述约束条件的约束下，对所生成的候选能量序列进行筛选和变异克隆，直至满足实际迭代次数达到预设迭代次数的截止条件为止；最终选取用电总价最低所对应的候选储能序列作为储能装置43的能量序列，并将所得到的能量序列发送给计算机设备42。
所述计算机设备42根据所获取的能量序列中最近时刻的能量值E1，生成控制储能装置43从当前存储的能量值E0调整至E1的控制信息，并按照所述控制信息控制储能装置43进行储能调整。
在此，当电价预测序列、用电量预测序列、自供电量预测序列、或储能参数中的任一种被更新时，所述服务端41随之依据最新的数据生成能量序列，以便计算机设备42及时控制储能装置43进行储能调整。由此实现在浮动电价机制下用电方利用储能降低用电成本的目的。
需要说明的是，上述工作过程仅为举例，而非对本申请的限制，事实上，利用前述服务端所提供的任一方式生成储能装置的能量序列都可以替换该示例中的生成方式。在此不再一一详述。
综上所述，本申请基于所获取的供电预测序列、用电量预测序列以及储能装置的储能参数，生成在一用电周期内储能装置的能量序列，以使得可以基于所述能量序列对所述储能装置进行管理，进而实现用电总价最低的目的。
上述实施例仅例示性说明本申请的原理及其功效，而非用于限制本申请。任何熟悉此技术的人士皆可在不违背本申请的精神及范畴下，对上述实施例进行修饰或改变。因此，举凡所属技术领域中具有通常知识者在未脱离本申请所揭示的精神与技术思想下所完成的一切等效修饰或改变，仍应由本申请的权利要求所涵盖。

Claims (35)

  1. 一种储能管理方法，用于管理为用电方提供储备电能的储能装置，其特征在于，包括下述步骤：
    获取在一用电周期内可供所述用电方使用的供电预测序列以及所述用电方的用电量预测序列；以及
    基于以预设获取条件而获取的所述储能装置的储能参数，以及所述用电周期内的供电预测序列和用电量预测序列，生成在所述用电周期内所述储能装置的能量序列，以使得基于所述能量序列对所述储能装置进行管理。
  2. 根据权利要求1所述的储能管理方法，其特征在于，所述供电预测序列中包含电价预测序列，所述获取在一用电周期内的电价预测序列的步骤包括以下任一种：
    获取所述用电周期内的电价预测序列；
    基于所获取的历史电价预测序列以及相应的历史实际电价之间的偏差，预测可供所述用电方使用的所述用电周期内的电价预测序列；
    基于所获取的电价相关信息，预测所述用电周期内的电价预测序列。
  3. 根据权利要求1所述的储能管理方法，其特征在于，所述供电预测序列中包含自供电系统的自供电量预测序列，所述获取在一用电周期内的自供电量预测序列的步骤包括：
    基于所获取的自供电系统的发电相关信息，预测所述用电周期内的自供电量预测序列。
  4. 根据权利要求1所述的储能管理方法，其特征在于，所述获取用电方的用电量预测序列的步骤包括：
    按照所述用电周期内的用电因素获取用电相关信息；以及
    根据所述用电相关信息，预测所述用电周期内的用电量预测序列。
  5. 根据权利要求1所述的储能管理方法，其特征在于，所述基于以预设获取条件而获取的所述储能装置的储能参数，以及所述用电周期内的供电预测序列和用电量预测序列，生成在所述用电周期内所述储能装置的能量序列的步骤包括：
    在至少一个约束条件下，以在所述用电周期内的用电总价低为优化目标，生成在所述用电周期内所述储能装置的能量序列；其中，所述约束条件包括基于所述储能参数确定的约束条件。
  6. 根据权利要求5所述的储能管理方法，其特征在于，所述在至少一个约束条件下，以在所述用电周期内的用电总价低为优化目标，生成在所述用电周期内所述储能装置的一能量序列的步骤包括：
    在至少一个约束条件下，生成在所述用电周期内的一个或多个候选能量序列；以及
    在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，对所生成的一个或多个候选能量序列进行优化处理，得到在所述用电周期内所述储能装置的能量序列。
  7. 根据权利要求6所述的储能管理方法，其特征在于，对所生成的一个或多个候选能量序列进行优化处理的步骤包括：
    根据以在所述用电周期内的用电总价低为优化目标而设置的截止条件，从所述一个或多个候选能量序列中确定一个候选能量序列，并将其作为所述能量序列；以及
    当不满足所述截止条件时，在至少一个约束条件下，依据更新策略将所生成的至少一个候选能量序列进行更新，并按照更新后的候选能量序列重复上述步骤直至存在一个候选能量序列符合所述截止条件。
  8. 根据权利要求1或5所述的储能管理方法，其特征在于，所述储能参数包括以下至少两个：所检测的或所预测的储能装置存储的能量、储能装置的容量、储能装置的充放电参数、储能装置的损失参数。
  9. 根据权利要求1所述的储能管理方法，其特征在于，所述获取条件包括以下至少一种：更新供电预测序列的事件，更新用电量预测序列的事件，更新周期；其中，所述更新周期是基于所述供电预测序列的更新周期和/或所述用电量预测序列的更新周期而确定的。
  10. 根据权利要求1所述的储能管理方法，其特征在于，还包括将所述能量序列、供电预测序列和用电量预测序列中的至少一种予以显示的步骤。
  11. 一种储能控制方法，用于控制为用电方提供储备电能的储能装置，其特征在于，包括下述步骤：
    获取由如权利要求1-9中任一所述的储能管理方法所生成的在一用电周期内所述储能 装置的能量序列；
    基于所获取的能量序列中操作时间区间所对应的能量值，确定所述储能装置在所述操作时间区间用于控制所述储能装置操作的控制信息。
  12. 根据权利要求11所述的储能控制方法，其特征在于，还包括基于所述控制信息控制所述储能装置在相应操作时间区间内的操作的步骤。
  13. 根据权利要求11所述的储能控制方法，其特征在于，还包括：获取并显示所述能量序列、供电预测序列和用电量预测序列中的至少一种的步骤。
  14. 根据权利要求11-13中任一所述的储能控制方法，其特征在于，还包括基于最新生成的能量序列对所述控制信息进行更新的步骤。
  15. 根据权利要求11所述的储能控制方法，其特征在于，所述控制信息包括以下至少一种：储能装置的充放电控制信息、储能装置在操作时间区间的目标储能值。
  16. 一种储能管理系统，用于管理为用电方提供储备电能的储能装置，其特征在于，包括：
    获取模块，用于获取在一用电周期内可供所述用电方使用的供电预测序列以及所述用电方的用电量预测序列；以及
    生成模块，用于基于以预设获取条件而获取的所述储能装置的储能参数，以及所述用电周期内的供电预测序列和用电量预测序列，生成在所述用电周期内所述储能装置的能量序列，以使得基于所述能量序列对所述储能装置进行管理。
  17. 根据权利要求16所述的储能管理系统，其特征在于，所述供电预测序列中包含电价预测序列，所述获取模块包括下述中至少之一：
    第一获取单元，用于获取所述用电周期内的电价预测序列；
    第二获取单元，用于基于所获取的历史电价预测序列以及相应的历史实际电价之间的偏差，预测可供所述用电方使用的所述用电周期内的电价预测序列；
    第三获取单元，用于基于所获取的电价相关信息，预测所述用电周期内的电价预测序列。
  18. 根据权利要求16所述的储能管理系统，其特征在于，所述供电预测序列中包含自供电系统的自供电量预测序列，所述获取模块包括第四获取单元，用于基于所获取的自供电系统的发电相关信息，预测所述用电周期内的自供电量预测序列。
  19. 根据权利要求16所述的储能管理系统，其特征在于，所述获取模块包括第五获取单元，用于按照所述用电周期内的用电因素获取用电相关信息；以及根据所述用电相关信息，预测所述用电周期内的用电量预测序列。
  20. 根据权利要求16所述的储能管理系统，其特征在于，所述生成模块包括：
    生成单元，用于在至少一个约束条件下，以在所述用电周期内的用电总价低为优化目标，生成在所述用电周期内所述储能装置的能量序列；其中，所述约束条件包括基于所述储能参数确定的约束条件。
  21. 根据权利要求20所述的储能管理系统，其特征在于，所述生成单元用于在至少一个约束条件下，生成在所述用电周期内的一个或多个候选能量序列；以及在至少一个约束条件下且以在所述用电周期内的用电总价低为优化目标，对所生成的一个或多个候选能量序列进行优化处理，得到在所述用电周期内所述储能装置的能量序列。
  22. 根据权利要求21所述的储能管理系统，其特征在于，所述生成单元用于根据以在所述用电周期内的用电总价低为优化目标而设置的截止条件，从所述一个或多个候选能量序列中确定一个候选能量序列，并将其作为所述能量序列；以及当不满足所述截止条件时，在至少一个约束条件下，依据更新策略将所生成的至少一个候选能量序列进行更新，并按照更新后的候选能量序列重复上述步骤直至存在一个候选能量序列符合所述截止条件。
  23. 根据权利要求16或20所述的储能管理系统，其特征在于，所述储能参数包括以下至少两个：所检测的或所预测的储能装置存储的能量、储能装置的容量、储能装置的充放电参数、储能装置的损失参数。
  24. 根据权利要求16所述的储能管理系统，其特征在于，所述获取条件包括以下至少一种：更新供电预测序列的事件，更新用电量预测序列的事件，更新周期；其中，所述更新周期是基于所述供电预测序列的更新周期和/或所述用电量预测序列的更新周期而确定的。
  25. 根据权利要求16所述的储能管理系统，其特征在于，还包括输出模块，用于输出所述能量序列、供电预测序列和用电量预测序列中的至少一种以予以显示。
  26. 一种储能控制系统，用于对为用电方提供储备电能的储能装置进行控制，其特征在于，包括：
    获取模块，用于获取由如权利要求16-24中任一所述的储能管理系统所生成的在一用电周期内所述储能装置的能量序列；
    确定模块，用于基于所获取的能量序列中操作时间区间所对应的能量值，确定所述储能装置在所述操作时间区间用于控制所述储能装置操作的控制信息。
  27. 根据权利要求26所述的储能控制系统，其特征在于，还包括控制模块，用于基于所述控制信息控制所述储能装置在相应操作时间区间内的操作。
  28. 根据权利要求26所述的储能控制系统，其特征在于，还包括：显示模块，用于获取并显示所述能量序列、供电预测序列和用电量预测序列中的至少一种。
  29. 根据权利要求26-28所述的储能控制系统，其特征在于，还包括：更新模块，用于基于最新生成的能量序列对所述控制信息进行更新。
  30. 根据权利要求26所述的储能控制系统，其特征在于，所述控制信息包括以下至少一种：储能装置的充放电控制信息、储能装置在预测时间区间的目标储能值。
  31. 一种服务端，其特征在于，包括：
    接口单元，用于获取一用电周期内可供用电方使用的供电相关信息以及所述用电方的用电相关信息；
    存储单元，用于存储至少一个程序；以及
    处理单元，用于调用所述至少一个程序以协调所述接口单元和存储单元执行如权利要求1-10中任一所述的储能管理方法。
  32. 一种计算机设备，其特征在于，包括：
    接口单元，用于获取一用电周期内可供用电方使用的供电相关信息以及所述用电方的用 电相关信息；
    存储单元，用于存储至少一个程序；以及
    处理单元，用于调用所述至少一个程序以协调所述接口单元和存储单元执行如权利要求11-15中任一所述的储能控制方法。
  33. 一种计算机可读存储介质，其特征在于，存储至少一种程序，所述至少一种程序在被调用时执行如权利要求1-10中任一所述的储能管理方法。
  34. 一种计算机可读存储介质，其特征在于，存储至少一种程序，所述至少一种程序在被调用时执行如权利要求11-15中任一所述的储能控制方法。
  35. 一种储能控制系统，其特征在于，包括：如权利要求31所述的服务端和如权利要求32所述的计算机设备。
PCT/CN2018/116767 2018-11-21 2018-11-21 储能管理及控制方法、系统、计算机设备、存储介质 WO2020103048A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201880002440.7A CN111466063B (zh) 2018-11-21 2018-11-21 储能管理及控制方法、系统、计算机设备、存储介质
PCT/CN2018/116767 WO2020103048A1 (zh) 2018-11-21 2018-11-21 储能管理及控制方法、系统、计算机设备、存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/116767 WO2020103048A1 (zh) 2018-11-21 2018-11-21 储能管理及控制方法、系统、计算机设备、存储介质

Publications (1)

Publication Number Publication Date
WO2020103048A1 true WO2020103048A1 (zh) 2020-05-28

Family

ID=70773767

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/116767 WO2020103048A1 (zh) 2018-11-21 2018-11-21 储能管理及控制方法、系统、计算机设备、存储介质

Country Status (2)

Country Link
CN (1) CN111466063B (zh)
WO (1) WO2020103048A1 (zh)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112906961A (zh) * 2021-02-08 2021-06-04 阳光电源（上海）有限公司 储能控制方法、装置、非易失性存储介质及电子装置
CN113191564A (zh) * 2021-05-18 2021-07-30 阳光电源股份有限公司 一种光伏功率预测方法、装置及服务器
CN114243846A (zh) * 2021-12-22 2022-03-25 歌尔光学科技有限公司 供电控制方法、系统、可穿戴设备及计算机可读存储介质
CN114938008A (zh) * 2022-06-15 2022-08-23 国网河北省电力有限公司经济技术研究院 储能容量和储热容量配置方法、装置及终端设备
CN116613893A (zh) * 2023-07-20 2023-08-18 南方电网调峰调频发电有限公司信息通信分公司 发电企业的区域电能智慧管理方法及装置
CN116961061A (zh) * 2023-07-26 2023-10-27 广东永光新能源设计咨询有限公司 一种储能设备的控制方法、装置及电子设备
CN117060456A (zh) * 2023-08-21 2023-11-14 深圳中保动力新能源科技有限公司 一种基于人工智能的储能系统控制方法及装置
CN117353306A (zh) * 2023-12-06 2024-01-05 浙江浙石油综合能源销售有限公司 一种光储充放电调度方法、系统、电子设备、存储介质
CN117394370A (zh) * 2023-12-12 2024-01-12 北京本果信息技术有限公司 一种供电网智能动态节电调度系统及方法
CN117595332A (zh) * 2024-01-19 2024-02-23 成都智邦科技有限公司 一种基于储能系统的配电网均衡供电方法
CN117996802A (zh) * 2024-03-15 2024-05-07 广州智光储能科技有限公司 一种电力系统的储能配置方法、装置、系统及存储介质
CN118074124A (zh) * 2024-04-12 2024-05-24 广州疆海科技有限公司 一种电能管理方法及装置
CN118249383A (zh) * 2024-05-28 2024-06-25 新乡市镇华电力科技有限公司 一种储能电站功率分配方法及系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112418496B (zh) * 2020-11-10 2022-04-22 国网四川省电力公司经济技术研究院 一种基于深度学习的配电台区储能配置方法
CN113346602B (zh) * 2021-05-19 2022-09-06 青岛海尔空调器有限总公司 显示元件控制方法、装置、设备、介质及程序产品
CN116865227B (zh) * 2023-06-30 2024-08-23 国家电投集团科学技术研究院有限公司 一种直流微网可再生能源制氢方法、装置及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102447256A (zh) * 2010-10-12 2012-05-09 三星电子株式会社 电力管理系统和控制电力管理系统的方法
CN104321943A (zh) * 2012-03-30 2015-01-28 索尼公司 能量存储
CN106707778A (zh) * 2016-12-06 2017-05-24 长沙理工大学 一种基于模型预测控制的家庭综合能源智能优化管理系统
CN106953362A (zh) * 2017-05-03 2017-07-14 北京天诚同创电气有限公司 并网型微电网的能量管理方法及系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9568901B2 (en) * 2012-08-27 2017-02-14 Nec Corporation Multi-objective energy management methods for micro-grids
CN104716693B (zh) * 2013-12-13 2017-06-06 华为技术有限公司 一种分布式储能电池的能量管理方法及控制器、系统
CN108321826A (zh) * 2018-04-10 2018-07-24 阳光电源股份有限公司 储能系统容量配置方法、装置以及系统
CN108288116B (zh) * 2018-04-19 2022-04-05 图灵人工智能研究院（南京）有限公司 储电预测方法、系统及计算机设备、存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102447256A (zh) * 2010-10-12 2012-05-09 三星电子株式会社 电力管理系统和控制电力管理系统的方法
CN104321943A (zh) * 2012-03-30 2015-01-28 索尼公司 能量存储
CN106707778A (zh) * 2016-12-06 2017-05-24 长沙理工大学 一种基于模型预测控制的家庭综合能源智能优化管理系统
CN106953362A (zh) * 2017-05-03 2017-07-14 北京天诚同创电气有限公司 并网型微电网的能量管理方法及系统

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112906961A (zh) * 2021-02-08 2021-06-04 阳光电源（上海）有限公司 储能控制方法、装置、非易失性存储介质及电子装置
CN113191564A (zh) * 2021-05-18 2021-07-30 阳光电源股份有限公司 一种光伏功率预测方法、装置及服务器
CN114243846A (zh) * 2021-12-22 2022-03-25 歌尔光学科技有限公司 供电控制方法、系统、可穿戴设备及计算机可读存储介质
CN114938008A (zh) * 2022-06-15 2022-08-23 国网河北省电力有限公司经济技术研究院 储能容量和储热容量配置方法、装置及终端设备
CN116613893B (zh) * 2023-07-20 2024-01-16 南方电网调峰调频发电有限公司信息通信分公司 发电企业的区域电能智慧管理方法及装置
CN116613893A (zh) * 2023-07-20 2023-08-18 南方电网调峰调频发电有限公司信息通信分公司 发电企业的区域电能智慧管理方法及装置
CN116961061B (zh) * 2023-07-26 2024-03-19 广东永光新能源设计咨询有限公司 一种储能设备的控制方法、装置及电子设备
CN116961061A (zh) * 2023-07-26 2023-10-27 广东永光新能源设计咨询有限公司 一种储能设备的控制方法、装置及电子设备
CN117060456A (zh) * 2023-08-21 2023-11-14 深圳中保动力新能源科技有限公司 一种基于人工智能的储能系统控制方法及装置
CN117060456B (zh) * 2023-08-21 2024-04-30 深圳中保动力新能源科技有限公司 一种基于人工智能的储能系统控制方法及装置
CN117353306A (zh) * 2023-12-06 2024-01-05 浙江浙石油综合能源销售有限公司 一种光储充放电调度方法、系统、电子设备、存储介质
CN117353306B (zh) * 2023-12-06 2024-03-22 浙江浙石油综合能源销售有限公司 一种光储充放电调度方法、系统、电子设备、存储介质
CN117394370A (zh) * 2023-12-12 2024-01-12 北京本果信息技术有限公司 一种供电网智能动态节电调度系统及方法
CN117394370B (zh) * 2023-12-12 2024-02-20 北京本果信息技术有限公司 一种供电网智能动态节电调度系统及方法
CN117595332A (zh) * 2024-01-19 2024-02-23 成都智邦科技有限公司 一种基于储能系统的配电网均衡供电方法
CN117595332B (zh) * 2024-01-19 2024-04-02 成都智邦科技有限公司 一种基于储能系统的配电网均衡供电方法
CN117996802A (zh) * 2024-03-15 2024-05-07 广州智光储能科技有限公司 一种电力系统的储能配置方法、装置、系统及存储介质
CN118074124A (zh) * 2024-04-12 2024-05-24 广州疆海科技有限公司 一种电能管理方法及装置
CN118249383A (zh) * 2024-05-28 2024-06-25 新乡市镇华电力科技有限公司 一种储能电站功率分配方法及系统

Also Published As

Publication number Publication date
CN111466063B (zh) 2023-09-12
CN111466063A (zh) 2020-07-28

Similar Documents

Publication Publication Date Title
WO2020103048A1 (zh) 储能管理及控制方法、系统、计算机设备、存储介质
JP6765567B2 (ja) 発電システム及びエネルギー生成システム
JP7320503B2 (ja) エネルギ貯蔵システムを最適に制御するためのシステム及び方法
JP6178045B2 (ja) エネルギー管理システム、エネルギー管理方法、プログラムおよびサーバ装置
JP5596220B2 (ja) エネルギー消費管理のためのシステム、方法及びコンピュータプログラム
Alam et al. Computational methods for residential energy cost optimization in smart grids: A survey
CN108416503A (zh) 具有资产规模调整的建筑物能量成本优化系统
US11663541B2 (en) Building energy system with load-following-block resource allocation
US20130066482A1 (en) Apparatus and method for executing energy demand response process in an electrical power network
WO2013102932A2 (en) System and method facilitating forecasting, optimization and visualization of energy data for an industry
WO2020103046A1 (zh) 储能管理及控制方法、系统、计算机设备、存储介质
KR102173207B1 (ko) 분산 전원의 스케쥴링 및 실시간 제어를 통한 빌딩 에너지 관리 장치
JP5712216B2 (ja) エネルギー供給システムまたはエネルギー消費システムの最適化された制御
Ghasemkhani et al. Reinforcement learning based pricing for demand response
JP2017050919A (ja) 需要電力予測装置、需要電力予測方法及びコンピュータプログラム
US12119646B2 (en) Systems and methods for renewable powerplant serving multiple loads
CN115906408A (zh) 基于建筑负荷预测的能源调度系统及方法
CN114707737A (zh) 一种基于边缘计算的预测用电量的系统和方法
WO2024105199A1 (en) System and method to control electric vehicle fleet charging or microgrid operation considering a heuristic approach to extend battery life
CN110535143B (zh) 面向智能住宅动态需求响应的能源管理方法和装置
JP6285265B2 (ja) 電力管理システム、電力管理方法、及び電力管理プログラム
KR20190121621A (ko) 에너지 관리 시스템
EP4372942A1 (en) System and method for peak load power management for charging of an electric vehicle fleet and/or operation of a microgrid
EP4372641A1 (en) System and method to control electric vehicle fleet charging or microgrid operation considering a heuristic approach to extend battery life
EP4371807A1 (en) Optimized control of power depots using multi-tenant charging system-of-systems

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18940850

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18940850

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 18940850

Country of ref document: EP

Kind code of ref document: A1