Energy storage system charging and discharging control method and device

Abstract

The application discloses a kind of energy storage system charge-discharge control method and device, the method includes: the characteristic data of influence spot price of next day released by electric power market is acquired;Based on the characteristic data, the peak period and the valley period of spot price of next day are predicted;According to the predicted peak period and the valley period, the operating state of the wind farm matched with energy storage system and the operating constraint of energy storage system, generate and execute the charge-discharge control instruction of the energy storage system, so that the energy storage system is charged in predicted valley period, and discharged in predicted peak period.Using the present scheme can improve the utilization efficiency of energy storage system.

Description

Technical Field

[0001] This application relates to the field of power system automation control technology, and in particular to a charging and discharging control method and device for an energy storage system. Background Technology

[0002] Currently, when wind farms equipped with energy storage participate in the electricity spot market, they often adopt simple fixed-period charging and discharging strategies. These strategies fail to fully consider the real-time operating status of the wind farm, grid dispatch instructions, and grid demand. This may result in the inability to absorb and store curtailed wind power, leading to a waste of renewable energy. Alternatively, the inability to accurately match the actual needs of the grid may prevent the energy storage system from fully playing its supporting role in maintaining grid power balance. Ultimately, the overall utilization efficiency of the energy storage system fails to achieve optimal results.

[0003] Therefore, finding a charging and discharging control method for energy storage systems to improve their utilization efficiency has become an urgent technical problem to be solved. Summary of the Invention

[0004] This application provides a charging and discharging control method and apparatus for an energy storage system, which can improve the utilization efficiency of the energy storage system.

[0005] This application provides a charging and discharging control method for an energy storage system, including: Obtain characteristic data released by the electricity market that affect the spot electricity price the following day; Based on the aforementioned feature data, predict the peak and off-peak periods for the next day's spot electricity price; Based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system, charging and discharging control commands for the energy storage system are generated and executed, so that the energy storage system charges during the predicted valley period and discharges during the predicted peak period.

[0006] The beneficial effects of this application are as follows: It acquires characteristic data from the electricity market that influences the next day's spot electricity price, and based on this data, predicts the peak and valley periods for the next day's spot electricity price, thereby accurately matching the actual needs of the power grid and avoiding losses caused by fixed-time charging and discharging. Then, based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system, it generates and executes charging and discharging control commands for the energy storage system, enabling the energy storage system to charge during the predicted valley periods and discharge during the predicted peak periods. By generating charging and discharging commands through real-time sensing of the wind farm's operating status, the utilization rate of renewable resources is improved; simultaneously, subject to the operating constraints of the energy storage system, it ensures that the grid dispatch requirements are met and safe operation is guaranteed, further improving the utilization efficiency of the energy storage system.

[0007] In one embodiment, acquiring the characteristic data released by the electricity market that affects the spot electricity price the following day includes: Obtain market-released data on grid power forecasts, power generation plans, and weather forecasts for the following day.

[0008] In one embodiment, predicting the peak and off-peak hours of the spot electricity price for the next day based on the feature data includes: Input the feature data into the peak-valley time prediction model; Obtain the peak and valley period division results of the next day's spot electricity price output by the peak and valley period prediction model.

[0009] In one embodiment, generating and executing charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system includes: When it is determined that the wind farm is in a power curtailment operation state, a charging command is generated for the energy storage system; Determine whether the state of charge of the energy storage system is lower than the upper limit of the state of charge; If it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge, the output of the wind turbines in the wind farm is adjusted to generate more electricity, and the charging command is issued to the energy storage system to control it to perform the charging action. If it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge, then the energy storage system is controlled to stop charging.

[0010] In one embodiment, generating a charging command for the energy storage system includes: The maximum allowable charging power of the energy storage system is compared with the current power curtailment value of the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

[0011] In one embodiment, generating and executing charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system includes: When it is determined that the wind farm is in a non-power-curtailment operation state and the current time is in the predicted valley period, a charging command is generated for the energy storage system. Determine whether the state of charge of the energy storage system is lower than the upper limit of the state of charge; If it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge, the following action is performed: the charging command is issued to the energy storage system to control it to perform the charging action; If it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge, then the energy storage system is controlled to stop charging.

[0012] In one embodiment, generating a charging command for the energy storage system includes: The maximum allowable charging power of the energy storage system is compared with the real-time power generation of the wind turbines in the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

[0013] In one embodiment, generating and executing charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system includes: When it is determined that the wind farm is in a non-power-curtailment operation state and the current time is within the predicted peak period, a discharge command is generated for the energy storage system. Determine whether the state of charge of the energy storage system is higher than the state of charge limit; If it is determined that the state of charge of the energy storage system is higher than the state of charge limit, the following action is performed: the discharge command is issued to the energy storage system to control it to perform a discharge action; If it is determined that the state of charge of the energy storage system has reached the lower limit of the state of charge, then the energy storage system is controlled to stop discharging.

[0014] In one embodiment, generating a discharge command for the energy storage system includes: Calculate the difference between the currently received automatic power generation control command and the real-time power generation of the wind turbines in the wind farm; The maximum permissible discharge power of the energy storage system is compared with the difference, and the smaller of the two is taken as the discharge power value of the discharge command.

[0015] In one embodiment, the operating constraints of the energy storage system include: The sum of the power generation of the wind turbines in the wind farm and the charging and discharging power of the energy storage system shall not exceed the limit value of the currently received automatic power generation control command.

[0016] In one embodiment, the operational constraints of the energy storage system further include: When the state of charge of the energy storage system is lower than a preset state of charge threshold, the step of generating and executing the charge and discharge control command for the energy storage system is prohibited from issuing a discharge command to the energy storage system, so as to restrict its discharge action.

[0017] In one embodiment, the peak-valley prediction model is a model obtained by machine learning training based on the mapping relationship between feature data in historical market data and the peak and valley periods of historical spot electricity prices.

[0018] In one embodiment, the method further includes: After the charging and discharging control command is executed, the additional revenue achieved by the wind-storage coordinated control method is calculated based on the actual charging and discharging power records of the energy storage system, the peak-valley price difference of the spot electricity price, and the on-grid power of the wind farm.

[0019] In one embodiment, the method is applied to a photovoltaic power station with a supporting energy storage system, wherein the operating status of the wind farm with the supporting energy storage system is replaced by the operating status of the photovoltaic power station with the supporting energy storage system.

[0020] In one embodiment, the method is used to control an energy storage system comprising at least one energy storage unit. The step of generating and executing charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm supporting the energy storage system, and the operating constraints of the energy storage system further includes: The total charging and discharging power requirement of the energy storage system is determined according to the charging and discharging control command. Based on the real-time state of charge, rated power, and preset economic indicators of each energy storage unit, the total charging and discharging power demand is allocated to at least a portion of the multiple energy storage units for execution.

[0021] This application also provides a charging and discharging control device for an energy storage system, comprising: The acquisition module is used to acquire characteristic data released by the electricity market that affect the spot electricity price the following day; The prediction module is used to predict the peak and off-peak periods of the spot electricity price for the next day based on the feature data. The generation module is used to generate and execute charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm supporting the energy storage system, and the operating constraints of the energy storage system, so that the energy storage system performs charging during the predicted valley period and discharging during the predicted peak period.

[0022] In one embodiment, the acquisition module is further configured to: Obtain market-released data on grid power forecasts, power generation plans, and weather forecasts for the following day.

[0023] In one embodiment, the prediction module includes: The input submodule is used to input the feature data into the peak-valley time period prediction model; The acquisition submodule is used to acquire the peak and valley time division results of the next day's spot electricity price output by the peak and valley time prediction model.

[0024] In one embodiment, the generation module includes: The first generation submodule is used to generate a charging command for the energy storage system when it is determined that the wind farm is in a power curtailment operation state. The first judgment submodule is used to determine whether the state of charge of the energy storage system is lower than the upper limit of the state of charge. The adjustment submodule is used to adjust the output of the wind turbines in the wind farm to generate more electricity if it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge, and to issue the charging command to the energy storage system to control it to perform the charging action.

[0025] In one embodiment, the first generation submodule is further configured to: The maximum allowable charging power of the energy storage system is compared with the current power curtailment value of the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

[0026] In one embodiment, the generation module includes: The second generation submodule is used to generate a charging command for the energy storage system when it is determined that the wind farm is in a non-power-curtailment operation state and the current time is in the predicted valley period. The second judgment submodule is used to determine whether the state of charge of the energy storage system is lower than the upper limit of the state of charge. The execution submodule is used to perform the following actions if it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge: issue the charging command to the energy storage system and control it to perform the charging action; The second stop submodule is used to control the energy storage system to stop charging if it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge.

[0027] In one embodiment, the second generation submodule is further configured to: The maximum allowable charging power of the energy storage system is compared with the real-time power generation of the wind turbines in the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

[0028] In one embodiment, the generation module includes: The third generation submodule is used to generate a discharge command for the energy storage system when it is determined that the wind farm is in a non-power-curtailment operation state and the current time is in the predicted peak period. The third judgment submodule is used to determine whether the state of charge of the energy storage system is higher than the state of charge limit. The execution submodule is also configured to, if it is determined that the state of charge of the energy storage system is higher than the state of charge limit, perform the following action: issue the discharge command to the energy storage system and control it to perform the discharge action; The third stop submodule is used to control the energy storage system to stop discharging if it is determined that the state of charge of the energy storage system has reached the lower limit of the state of charge.

[0029] In one embodiment, the third generation submodule is further configured to: Calculate the difference between the currently received automatic power generation control command and the real-time power generation of the wind turbines in the wind farm; The maximum permissible discharge power of the energy storage system is compared with the difference, and the smaller of the two is taken as the discharge power value of the discharge command.

[0030] In one embodiment, the operating constraints of the energy storage system include: The sum of the power generation of the wind turbines in the wind farm and the charging and discharging power of the energy storage system shall not exceed the limit value of the currently received automatic power generation control command.

[0031] In one embodiment, the operational constraints of the energy storage system further include: When the state of charge of the energy storage system is lower than a preset state of charge threshold, the step of generating and executing the charge and discharge control command for the energy storage system is prohibited from issuing a discharge command to the energy storage system, so as to restrict its discharge action.

[0032] In one embodiment, the peak-valley prediction model is a model obtained by machine learning training based on the mapping relationship between feature data in historical market data and the peak and valley periods of historical spot electricity prices.

[0033] In one embodiment, the apparatus further includes: The calculation module is used to calculate the additional revenue achieved by the wind-storage coordinated control method after the charging and discharging control command is executed, based on the actual charging and discharging power records of the energy storage system, the peak-valley price difference of the spot electricity price, and the on-grid power of the wind farm.

[0034] In one embodiment, the method is applied to a photovoltaic power station with a supporting energy storage system, wherein the operating status of the wind farm with the supporting energy storage system is replaced by the operating status of the photovoltaic power station with the supporting energy storage system.

[0035] In one embodiment, the method is used to control an energy storage system comprising at least one energy storage unit, and the generation module further includes: A determination submodule is used to determine the total charging and discharging power requirement of the energy storage system according to the charging and discharging control command; The allocation submodule is used to allocate the total charging and discharging power demand to at least a portion of the plurality of energy storage units based on the real-time state of charge, rated power, and preset economic indicators of each energy storage unit.

[0036] This application also provides a charging and discharging control system for an energy storage system, including: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to implement the energy storage system charging and discharging control method described in any of the above embodiments.

[0037] This application also provides a computer-readable storage medium, which, when the instructions in the storage medium are executed by a processor corresponding to the energy storage system charge-discharge control system, enables the energy storage system charge-discharge control system to implement the energy storage system charge-discharge control method described in any of the above embodiments.

[0038] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0039] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0040] The accompanying drawings are provided to further illustrate the present application and form part of the specification. They are used together with the embodiments of the present application to explain the application and do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a charging and discharging control method for an energy storage system according to an embodiment of this application; Figure 2 This is a flowchart illustrating the charging and discharging control of an energy storage system according to one embodiment of this application; Figure 3 This is a schematic diagram of the structure of a charging and discharging control device for an energy storage system according to an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of a charging and discharging control system for an energy storage system according to one embodiment of this application. Detailed Implementation

[0041] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application.

[0042] Figure 1 This is a flowchart of a charging and discharging control method for an energy storage system according to an embodiment of this application, as follows: Figure 1As shown, the method can be implemented as follows: S101-S103: In step S101, characteristic data that affects the spot electricity price on the following day, as released by the electricity market, are obtained; In step S102, based on the feature data, the peak and off-peak periods of the spot electricity price for the next day are predicted; In step S103, based on the predicted peak and valley periods, the operating status of the wind farm supporting the energy storage system, and the operating constraints of the energy storage system, charging and discharging control commands for the energy storage system are generated and executed, so that the energy storage system charges during the predicted valley period and discharges during the predicted peak period.

[0043] This application acquires characteristic data released by the electricity market that influences the spot electricity price the following day. For example, it acquires grid power forecast data, generation plan data, and weather forecast data released by the market for the following day. For grid power forecast data, the system's predicted load curve and the total predicted output curve of new energy power generation (wind power, photovoltaic) within the region can be obtained through the data interface of the regional or national grid electricity trading market / dispatch center, with a time granularity of 15 minutes or 1 hour. Generation plan data can be obtained from the market data platform through daily generation plan data of major power plants (such as thermal power, hydropower, and nuclear power). Weather forecast data can be obtained through the API interface of the national meteorological department or commercial meteorological services, specifically including meteorological data of the wind farm's location, such as wind speed, wind direction, temperature, and air pressure, which directly affect the wind power output, and meteorological data of major load centers within the region, such as temperature, humidity, precipitation probability, and wind speed, which indirectly affect the overall grid load level.

[0044] Based on the aforementioned feature data, the peak and valley periods of the next day's spot electricity price are predicted. Specifically, the feature data is input into a peak-valley period prediction model, which can be a model trained using machine learning based on the mapping relationship between feature data in historical market data and historical peak and valley periods of spot electricity prices. The peak and valley period division results of the next day's spot electricity price, output by the peak-valley period prediction model, are obtained.

[0045] For example, the first step is to establish a complete dataset containing historical electricity prices. This data should maintain the same time granularity and timestamps as the aforementioned meteorological, planning, and forecast data. A typical sample dataset includes timestamps, electricity prices, meteorological forecast data (wind speed, temperature, etc.), system load forecasts, renewable energy processing forecasts, and power plant generation plans. It can also include whether it's a weekday or a holiday. Then, mature time-series forecasting methods, such as neural networks and time-series regression models, can be used for training. The model takes power forecasts, generation plans, and meteorological forecasts as input and electricity prices as output to obtain time-of-use electricity price forecast curves. Based on a pre-defined peak-valley judgment logic, peak and valley periods are determined. For example, the top 30% of the electricity price forecast curves are considered peak periods, the bottom 30% are valley periods, and the remainder are normal periods. Thresholds can be set according to different market characteristics.

[0046] Furthermore, based on the characteristic data affecting spot electricity prices collected on D-1 day, such as power forecasts, power generation plans, and weather forecasts, at the beginning of D day, the peak and valley periods of the spot electricity price on that day can be predicted by combining the stored historical data with the peak and valley prediction model, providing a basis for energy storage charging and discharging decisions.

[0047] Based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system, charging and discharging control commands for the energy storage system are generated and executed, so that the energy storage system charges during the predicted valley period and discharges during the predicted peak period. Figure 2 This is a flowchart illustrating the charging and discharging control of an energy storage system according to one embodiment of this application, as follows: Figure 2 As shown, the following steps need to be performed: 1. Determine if the wind farm is currently experiencing power curtailment: (1) When the wind farm experiences power curtailment, the energy storage system only charges and does not discharge.

[0048] At this point, an energy storage charging command is generated. The charging power value of the command is the minimum of the maximum allowable charging power of the energy storage and the current curtailed power of the wind farm, to avoid overcharging. During charging, the state of charge (SOC) of the energy storage is monitored in real time. To prevent the SOC from rising too high, it is determined whether the SOC has reached its upper limit. When the SOC reaches the upper limit, charging stops to prevent overcharging and protect battery safety. If the upper limit has not been reached, the energy storage executes the charging command to adjust the output of the wind turbines in the wind farm, increasing the power generation of the turbines to use the excess electricity generated by the turbines for energy storage charging, thus achieving effective recovery of curtailed wind power.

[0049] (2) When the wind farm does not experience power curtailment, obtain the current peak and valley electricity prices.

[0050] ① When the current electricity price is at its peak, an energy storage discharge command is generated. The command takes the minimum value between the maximum discharge power of the energy storage and the required power generation of the energy storage. The required power generation of the energy storage is equal to the difference between the AGC (Automatic Generation Control) command and the real-time power generation of the wind turbines in the wind farm. During the discharge process, the state of charge (SOC) of the energy storage is monitored in real time. To prevent the SOC from dropping too low, it is determined whether the SOC has reached a lower limit. When the SOC reaches the lower limit, the energy storage stops discharging; if it has not reached the lower limit, the energy storage executes the discharge command.

[0051] During peak electricity price periods, the power market experiences tight supply and high prices. At this time, energy storage systems prioritize discharging commands to alleviate grid pressure, improve power system stability, and increase electricity revenue. The minimum value is calculated as the maximum energy storage discharge power minus the real-time generating power of the wind turbines in the wind farm, calculated from the AGC command. This is because the AGC command represents the grid's power generation requirement for the wind farm, and the difference between the AGC command and the real-time generating power of the wind turbines represents the additional power generation the wind farm needs. The energy storage discharge power cannot exceed this value; otherwise, the wind farm's power generation will exceed the grid's requirements, affecting the grid's stable operation. Discharge stops when the energy storage's State of Charge (SOC) reaches a lower limit (e.g., 10%) to prevent over-discharge, protect the energy storage device, and ensure a certain reserve of energy to cope with potential emergencies.

[0052] ② When the current electricity price is in a low-price period, an energy storage charging command is generated. The command takes the minimum value between the maximum allowable charging power of the energy storage and the real-time power generation of the wind turbines in the wind farm. During the discharge process, the state of charge (SOC) of the energy storage is monitored in real time. To prevent the SOC from rising too high, it is determined whether the SOC has reached its upper limit. When the SOC reaches the upper limit, the energy storage stops charging; if it has not reached the upper limit, the energy storage executes the charging command.

[0053] Low electricity prices during off-peak hours mean ample electricity supply and lower prices, at which time energy storage systems will prioritize charging commands. Because of ample electricity supply, there is often a risk of wind curtailment. By converting curtailed wind power into chemical energy for storage, the efficiency of wind power utilization is improved, and charging during off-peak hours reduces the electricity cost of energy storage.

[0054] To avoid the energy storage charging power exceeding the actual power generation capacity of the wind turbine, and to prevent unreasonable situations where the wind turbine's power generation is insufficient but the energy storage is required to charge at high power, ensuring the feasibility and economy of the charging process, the minimum value between the maximum allowable charging power of the energy storage and the real-time power generation of the wind turbine in the wind farm is taken. When the energy storage's State of Charge (SOC) has not reached its upper limit, charging is prioritized; when the energy storage's SOC reaches its upper limit and charging can no longer continue, charging is stopped to avoid overcharging, protect the energy storage device, and extend its service life. In one embodiment, when the energy storage's SOC reaches its upper limit, whether to discharge externally will be considered based on grid demand or other dispatch instructions from the wind farm.

[0055] It is understood that during the operation of the energy storage system, the sum of the power generation of the wind turbines in the wind farm and the charging and discharging power of the energy storage system must not exceed the limit value of the currently received automatic power generation control command. When the energy storage system is discharging, the wind turbine power generation (positive output) + energy storage discharge power (also positive output) ≤ AGC command limit value; when the energy storage system is charging, the wind turbine power generation (positive output) - energy storage charging power (because charging absorbs power from the grid, equivalent to negative output) ≤ AGC command limit value. Simultaneously, when the state of charge of the energy storage system is lower than a preset state of charge threshold (e.g., 10%), the step of generating and executing the charging and discharging control command for the energy storage system is prohibited from issuing a discharge command to the energy storage system, thereby restricting its discharge action.

[0056] Scenario 1: Power curtailment at a wind farm Assuming the maximum allowable charging power of energy storage is 10MW, and the current power curtailed at the wind farm is 8MW, with the real-time generating power of the wind turbines below their maximum capacity due to curtailment, the system first determines that it is currently under curtailment and generates a charging command with a value of min(10MW, 8MW) = 8MW. Then, it checks the energy storage's State of Charge (SOC). If it has not reached the upper limit (e.g., 95%), the 8MW charging command is issued, thus effectively recovering and utilizing the curtailed wind power. Simultaneously, since the energy storage charging process increases the power consumption of the wind farm, the overall grid-connected power of the wind farm still meets the grid dispatch requirements.

[0057] Scenario 2: No power curtailment, and during the predicted off-peak electricity price period. Assuming the maximum allowable charging power of energy storage is 10MW, the current actual generating power of the wind turbine is 15MW, and the AGC command is 20MW, the system determines that there is no electricity and it is in a valley period. Therefore, it generates a charging command with a value of min(10MW, 15MW) = 10MW. The operation is executed after checking that the energy storage SOC has not reached the upper limit. At this time, the total output power of the power station is the wind turbine power of 15MW minus the energy storage charging power of 10MW, which is 5MW, lower than the AGC command, thus meeting the requirements. This operation stores electricity during low-price periods.

[0058] Scenario 3: No power curtailment, and during the predicted peak electricity price period. Assuming the maximum discharge power of the energy storage is 10MW, the current actual power generated by the wind turbine is 12MW, and the AGC command is 18MW, the system determines that there is no power supply and it is in the peak period, so it generates a discharge command. First, the available power space is calculated: AGC command (18MW) - real-time power generation of the wind turbine in the wind farm (12MW) = 6MW. The discharge command value is min(10MW, 6MW) = 6MW. After checking that the energy storage SOC is greater than the lower limit (e.g., 10%), it is executed. At this time, the total output power of the station is the wind turbine power of 12MW plus the energy storage discharge power of 6MW, which is 18MW, exactly reaching the upper limit of the AGC command, realizing more discharge during periods of high grid demand and peak electricity prices.

[0059] The method provided in this application can be used to control an energy storage system containing at least one energy storage unit. In this method, when controlling the charging and discharging of the energy storage system, the total charging and discharging power requirement of the energy storage system is first determined. Then, based on the real-time state of charge, rated power, and preset economic indicators of each energy storage unit, the total charging and discharging power requirement is allocated to at least a portion of the multiple energy storage units for execution. For example, energy storage units that meet the discharge conditions are selected, and energy storage units that meet the total charging and discharging power requirement are determined based on a pre-determined charging and discharging cost coefficient for each energy storage unit (e.g., the smaller the coefficient, the lower the cost, and the higher the corresponding economic benefit).

[0060] It is understood that the method provided in this application can also be applied to photovoltaic power plants with supporting energy storage systems. In this case, the operating status of the wind farm with supporting energy storage system in the above method can be replaced with the operating status of the photovoltaic power plant with supporting energy storage system.

[0061] The beneficial effects of this application are as follows: It acquires characteristic data from the electricity market that influences the next day's spot electricity price, and based on this data, predicts the peak and valley periods for the next day's spot electricity price, thereby accurately matching the actual needs of the power grid and avoiding losses caused by fixed-time charging and discharging. Then, based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system, it generates and executes charging and discharging control commands for the energy storage system, enabling the energy storage system to charge during the predicted valley periods and discharge during the predicted peak periods. By generating charging and discharging commands through real-time sensing of the wind farm's operating status, the utilization rate of renewable resources is improved; simultaneously, subject to the operating constraints of the energy storage system, it ensures that the grid dispatch requirements are met and safe operation is guaranteed, further improving the utilization efficiency of the energy storage system.

[0062] In one embodiment, step S101 above can be implemented as step A1 as follows: In step A1, obtain grid power forecast data, power generation plan data, and weather forecast data for the next day released by the market.

[0063] In one embodiment, step S102 above can be implemented as steps A2-A3 as follows: In step A2, the feature data is input into the peak-valley time period prediction model; In step A3, the peak and valley periods of the next day's spot electricity price are divided as output by the peak-valley period prediction model.

[0064] In one embodiment, step S103 above can be implemented as steps B1-B4 as follows: In step B1, when it is determined that the wind farm is in a power curtailment operation state, a charging command is generated for the energy storage system. In step B2, it is determined whether the state of charge of the energy storage system is lower than the upper limit of the state of charge. In step B3, if it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge, the output of the wind turbine in the wind farm is adjusted to generate more electricity, and the charging command is issued to the energy storage system to control it to perform the charging action. In step B4, if it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge, then the energy storage system is controlled to stop charging.

[0065] In one embodiment, step B1 above can also be implemented as the following steps: The maximum allowable charging power of the energy storage system is compared with the current power curtailment value of the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

[0066] In one embodiment, step S103 above can be implemented as steps C1-C4 as follows: In step C1, when it is determined that the wind farm is in a non-power-curtailment operation state and the current time is in the predicted valley period, a charging command for the energy storage system is generated. In step C2, it is determined whether the state of charge of the energy storage system is lower than the upper limit of the state of charge. In step C3, if it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge, the following action is performed: the charging command is issued to the energy storage system to control it to perform the charging action; In step C4, if it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge, then the energy storage system is controlled to stop charging.

[0067] In one embodiment, step C1 above can also be implemented as the following steps: The maximum allowable charging power of the energy storage system is compared with the real-time power generation of the wind turbines in the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

[0068] In one embodiment, step S103 above can be implemented as steps D1-D4 as follows: In step D1, when it is determined that the wind farm is in a non-power-curtailment operation state and the current time is in the predicted peak period, a discharge command is generated for the energy storage system. In step D2, it is determined whether the state of charge of the energy storage system is higher than the state of charge limit; In step D3, if it is determined that the state of charge of the energy storage system is higher than the state of charge limit, the following action is performed: the discharge command is issued to the energy storage system to control it to perform the discharge action; In step D4, if it is determined that the state of charge of the energy storage system has reached the lower limit of the state of charge, then the energy storage system is controlled to stop discharging.

[0069] In one embodiment, step D1 above can also be implemented as steps D11-D12: In step D11, the difference between the currently received automatic power generation control command and the real-time power generation of the wind turbines in the wind farm is calculated; In step D12, the maximum allowable discharge power of the energy storage system is compared with the difference, and the smaller of the two is taken as the discharge power value of the discharge command.

[0070] In one embodiment, the operating constraints of the energy storage system include: The sum of the power generation of the wind turbines in the wind farm and the charging and discharging power of the energy storage system shall not exceed the limit value of the currently received automatic power generation control command.

[0071] In one embodiment, the operational constraints of the energy storage system further include: When the state of charge of the energy storage system is lower than a preset state of charge threshold, the step of generating and executing the charge and discharge control command for the energy storage system is prohibited from issuing a discharge command to the energy storage system, so as to restrict its discharge action.

[0072] In one embodiment, the peak-valley prediction model is a model obtained by machine learning training based on the mapping relationship between feature data in historical market data and the peak and valley periods of historical spot electricity prices.

[0073] In one embodiment, the method may also be implemented as follows: After the charging and discharging control command is executed, the additional revenue achieved by the wind-storage coordinated control method is calculated based on the actual charging and discharging power records of the energy storage system, the peak-valley price difference of the spot electricity price, and the on-grid power of the wind farm.

[0074] In one embodiment, the method is applied to a photovoltaic power station with a supporting energy storage system, wherein the operating status of the wind farm with the supporting energy storage system is replaced by the operating status of the photovoltaic power station with the supporting energy storage system.

[0075] In one embodiment, the method is used to control an energy storage system containing at least one energy storage unit, and step S103 above can be implemented as steps E1-E2 as follows: In step E1, the total charging and discharging power requirement of the energy storage system is determined according to the charging and discharging control command; In step E2, the total charging and discharging power demand is allocated to at least a portion of the multiple energy storage units based on the real-time state of charge, rated power, and preset economic indicators of each energy storage unit.

[0076] Figure 3 This is a schematic diagram of the structure of a charging and discharging control device for an energy storage system according to one embodiment of this application, as shown below. Figure 3 As shown, the device includes: Module 301 is used to acquire characteristic data released by the electricity market that affect the spot electricity price the following day; Prediction module 302 is used to predict the peak and off-peak periods of the spot electricity price for the next day based on the feature data; The generation module 303 is used to generate and execute charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm supporting the energy storage system, and the operating constraints of the energy storage system, so that the energy storage system performs charging during the predicted valley period and discharging during the predicted peak period.

[0077] In one embodiment, the acquisition module is further configured to: Obtain market-released data on grid power forecasts, power generation plans, and weather forecasts for the following day.

[0078] In one embodiment, the prediction module includes: The input submodule is used to input the feature data into the peak-valley time period prediction model; The acquisition submodule is used to acquire the peak and valley time division results of the next day's spot electricity price output by the peak and valley time prediction model.

[0079] In one embodiment, the generation module includes: The first generation submodule is used to generate a charging command for the energy storage system when it is determined that the wind farm is in a power curtailment operation state. The first judgment submodule is used to determine whether the state of charge of the energy storage system is lower than the upper limit of the state of charge. The adjustment submodule is used to adjust the output of the wind turbines in the wind farm to generate more electricity if it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge, and to issue the charging command to the energy storage system to control it to perform the charging action. The first stop submodule is used to control the energy storage system to stop charging if it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge.

[0080] In one embodiment, the first generation submodule is further configured to: The maximum allowable charging power of the energy storage system is compared with the current power curtailment value of the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

[0081] In one embodiment, the generation module includes: The second generation submodule is used to generate a charging command for the energy storage system when it is determined that the wind farm is in a non-power-curtailment operation state and the current time is in the predicted valley period. The second judgment submodule is used to determine whether the state of charge of the energy storage system is lower than the upper limit of the state of charge. The execution submodule is used to perform the following actions if it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge: issue the charging command to the energy storage system and control it to perform the charging action; The second stop submodule is used to control the energy storage system to stop charging if it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge.

[0082] In one embodiment, the second generation submodule is further configured to: The maximum allowable charging power of the energy storage system is compared with the real-time power generation of the wind turbines in the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

[0083] In one embodiment, the generation module includes: The third generation submodule is used to generate a discharge command for the energy storage system when it is determined that the wind farm is in a non-power-curtailment operation state and the current time is in the predicted peak period. The third judgment submodule is used to determine whether the state of charge of the energy storage system is higher than the state of charge limit. The execution submodule is also configured to, if it is determined that the state of charge of the energy storage system is higher than the state of charge limit, perform the following action: issue the discharge command to the energy storage system and control it to perform the discharge action; The third stop submodule is used to control the energy storage system to stop discharging if it is determined that the state of charge of the energy storage system has reached the lower limit of the state of charge.

[0084] In one embodiment, the third generation submodule is further configured to: Calculate the difference between the currently received automatic power generation control command and the real-time power generation of the wind turbines in the wind farm; The maximum permissible discharge power of the energy storage system is compared with the difference, and the smaller of the two is taken as the discharge power value of the discharge command.

[0085] In one embodiment, the operating constraints of the energy storage system include: The sum of the power generation of the wind turbines in the wind farm and the charging and discharging power of the energy storage system shall not exceed the limit value of the currently received automatic power generation control command.

[0086] In one embodiment, the operational constraints of the energy storage system further include: When the state of charge of the energy storage system is lower than a preset state of charge threshold, the step of generating and executing the charge and discharge control command for the energy storage system is prohibited from issuing a discharge command to the energy storage system, so as to restrict its discharge action.

[0087] In one embodiment, the peak-valley prediction model is a model obtained by machine learning training based on the mapping relationship between feature data in historical market data and the peak and valley periods of historical spot electricity prices.

[0088] In one embodiment, the apparatus further includes: The calculation module is used to calculate the additional revenue achieved by the wind-storage coordinated control method after the charging and discharging control command is executed, based on the actual charging and discharging power records of the energy storage system, the peak-valley price difference of the spot electricity price, and the on-grid power of the wind farm.

[0089] In one embodiment, the method is applied to a photovoltaic power station with a supporting energy storage system, wherein the operating status of the wind farm with the supporting energy storage system is replaced by the operating status of the photovoltaic power station with the supporting energy storage system.

[0090] In one embodiment, the method is used to control an energy storage system comprising at least one energy storage unit, and the generation module further includes: A determination submodule is used to determine the total charging and discharging power requirement of the energy storage system according to the charging and discharging control command; The allocation submodule is used to allocate the total charging and discharging power demand to at least a portion of the plurality of energy storage units based on the real-time state of charge, rated power, and preset economic indicators of each energy storage unit.

[0091] Figure 4 This is a schematic diagram of the hardware structure of a charging and discharging control system for an energy storage system according to one embodiment of this application, as shown below. Figure 4 As shown, the energy storage system's charge and discharge control system includes: At least one processor 420; and, Memory 404 communicatively connected to the at least one processor 420; wherein, The memory 404 stores instructions that can be executed by the at least one processor 420 to implement the energy storage system charging and discharging control method described in any of the above embodiments.

[0092] Reference Figure 4 The energy storage system charge and discharge control system 400 may include one or more of the following components: processing component 402, memory 404, power supply component 406, input / output (I / O) interface 408, sensor component 410, and communication component 412.

[0093] Processing component 402 typically controls the overall operation of the energy storage system charging and discharging control system 400. Processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the above-described method. Furthermore, processing component 402 may include one or more modules to facilitate interaction between processing component 402 and other components. The processor 420 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0094] Memory 404 is configured to store various types of data to support the operation of the energy storage system charge / discharge control system 400. Examples of this data include instructions for any application or method operating on the energy storage system charge / discharge control system 400. Memory 404 can be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. Memory 404 can also be an external storage device of the terminal device, such as a plug-in hard disk equipped on the terminal device. Memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Memory 404 is used to store programs and data required by this application. Memory 404 can also be used to temporarily store data that has been output or will be output.

[0095] Power supply component 406 provides power to various components of the energy storage system charge / discharge control system 400. Power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the energy storage system charge / discharge control system 400.

[0096] I / O interface 408 provides an interface between processing component 402 and peripheral interface modules, such as keyboards, click wheels, buttons, etc.

[0097] Sensor assembly 410 includes one or more sensors for providing status assessments of various aspects of the energy storage system charge / discharge control system 400. Additionally, sensor assembly 410 can detect the on / off state of the energy storage system charge / discharge control system 400, the relative positioning of components, and the operating status of the energy storage system charge / discharge control system 400 or one of its components. In some embodiments, sensor assembly 410 may include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor, etc.

[0098] Communication component 412 is configured to enable the energy storage system charge / discharge control system 400 to provide wired or wireless communication capabilities with other devices and cloud platforms. The energy storage system charge / discharge control system 400 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 412 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 412 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0099] In an exemplary embodiment, the energy storage system charge and discharge control system 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the energy storage system charge and discharge control method described in any of the above embodiments.

[0100] This application also provides a computer-readable storage medium, which, when the instructions in the storage medium are executed by a processor corresponding to the energy storage system charge-discharge control system, enables the energy storage system charge-discharge control system to implement the energy storage system charge-discharge control method described in any of the above embodiments.

[0101] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0102] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0103] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0105] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A charging and discharging control method for an energy storage system, characterized in that, include: Obtain characteristic data released by the electricity market that affect the spot electricity price the following day; Based on the aforementioned feature data, predict the peak and off-peak periods for the next day's spot electricity price; Based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system, charging and discharging control commands for the energy storage system are generated and executed, so that the energy storage system charges during the predicted valley period and discharges during the predicted peak period.

2. The method as described in claim 1, characterized in that, The prediction of peak and off-peak periods for the next day's spot electricity price based on the aforementioned feature data includes: Input the feature data into the peak-valley time prediction model; Obtain the peak and valley period division results of the next day's spot electricity price output by the peak and valley period prediction model.

3. The method as described in claim 1, characterized in that, The step of generating and executing charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system includes: When it is determined that the wind farm is in a power curtailment operation state, a charging command is generated for the energy storage system; Determine whether the state of charge of the energy storage system is lower than the upper limit of the state of charge; If it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge, the output of the wind turbines in the wind farm is adjusted to generate more electricity, and the charging command is issued to the energy storage system to control it to perform the charging action. If it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge, then the energy storage system is controlled to stop charging.

4. The method as described in claim 3, characterized in that, The generation of charging instructions for the energy storage system includes: The maximum allowable charging power of the energy storage system is compared with the current power curtailment value of the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

5. The method as described in claim 1, characterized in that, The step of generating and executing charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system includes: When it is determined that the wind farm is in a non-power-curtailment operation state and the current time is in the predicted valley period, a charging command is generated for the energy storage system. Determine whether the state of charge of the energy storage system is lower than the upper limit of the state of charge; If it is determined that the state of charge of the energy storage system is lower than the upper limit of the state of charge, the following action is performed: the charging command is issued to the energy storage system to control it to perform the charging action; If it is determined that the state of charge of the energy storage system has reached the upper limit of the state of charge, then the energy storage system is controlled to stop charging.

6. The method as described in claim 5, characterized in that, The generation of charging instructions for the energy storage system includes: The maximum allowable charging power of the energy storage system is compared with the real-time power generation of the wind turbines in the wind farm, and the smaller of the two is taken as the charging power value of the charging command.

7. The method as described in claim 1, characterized in that, The step of generating and executing charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm with the supporting energy storage system, and the operating constraints of the energy storage system includes: When it is determined that the wind farm is in a non-power-curtailment operation state and the current time is within the predicted peak period, a discharge command is generated for the energy storage system. Determine whether the state of charge of the energy storage system is higher than the state of charge limit; If it is determined that the state of charge of the energy storage system is higher than the state of charge limit, the following action is performed: the discharge command is issued to the energy storage system to control it to perform a discharge action; If it is determined that the state of charge of the energy storage system has reached the lower limit of the state of charge, then the energy storage system is controlled to stop discharging.

8. The method as described in claim 7, characterized in that, Generating a discharge command for the energy storage system includes: Calculate the difference between the currently received automatic power generation control command and the real-time power generation of the wind turbines in the wind farm; The maximum permissible discharge power of the energy storage system is compared with the difference, and the smaller of the two is taken as the discharge power value of the discharge command.

9. The method as described in claim 1, characterized in that, The method is used to control an energy storage system containing at least one energy storage unit. The step of generating and executing charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm supporting the energy storage system, and the operating constraints of the energy storage system further includes: The total charging and discharging power requirement of the energy storage system is determined according to the charging and discharging control command. Based on the real-time state of charge, rated power, and preset economic indicators of each energy storage unit, the total charging and discharging power demand is allocated to at least a portion of the multiple energy storage units for execution.

10. A charging and discharging control device for an energy storage system, characterized in that, include: The acquisition module is used to acquire characteristic data released by the electricity market that affect the spot electricity price the following day; The prediction module is used to predict the peak and off-peak periods of the spot electricity price for the next day based on the feature data. The generation module is used to generate and execute charging and discharging control commands for the energy storage system based on the predicted peak and valley periods, the operating status of the wind farm supporting the energy storage system, and the operating constraints of the energy storage system, so that the energy storage system performs charging during the predicted valley period and discharging during the predicted peak period.

Images