Energy storage strategy optimization method and device based on simulation confidence assessment
The energy storage strategy optimization method based on simulation confidence assessment, combined with multi-constraint verification and confidence assessment, solves the problems of strong subjectivity and execution bias in existing energy storage strategy optimization, and achieves more accurate revenue prediction and reliable strategy execution.
Patent Information
- Application Number
- CN202611433479.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-16
- Publication Date
- 2026-11-03
AI Technical Summary
In the optimization process of existing energy storage strategies, feature selection relies on human experience, which leads to strong subjectivity, easy omission of key influencing factors, or difficulty in removing redundant features. This results in low model prediction accuracy and poor computational efficiency. Furthermore, multi-objective optimization schemes lack practical implementation considerations, leading to discrepancies between theoretical benefits and actual implementation.
By using a simulation-based confidence assessment method, we can obtain future alternative energy storage charging and discharging strategies, conduct simulations under multiple constraints, calculate simulation and real returns, and select the optimal strategy for the future by combining return achievement rate and confidence assessment.
It improves the accuracy of profit forecasting, enhances the robustness of the strategy, achieves closed-loop optimization, ensures the reliability and economy of the strategy, and avoids economic losses caused by model mismatch.
Smart Images
Figure CN123034480A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power system energy storage control technology, and in particular to a method and apparatus for optimizing energy storage strategies based on simulation confidence assessment. Background Technology
[0002] As a key device for mitigating new energy fluctuations, peak shaving, and improving grid flexibility, the rationality of energy storage systems' scheduling strategies directly impacts grid operating efficiency and the economic viability of energy storage systems. Existing technologies for optimizing energy storage strategies generally suffer from several drawbacks. Feature selection relies heavily on human experience, leading to strong subjectivity, the easy omission of key influencing factors, and difficulty in removing redundant features. This results in low prediction accuracy and poor computational efficiency in subsequent models. Furthermore, existing optimization schemes often focus on a single objective, employing fixed weights for multi-objective trade-offs without considering factors such as power plant procurement prices, energy storage battery characteristics, and transformer capacity constraints. They fail to simulate the actual execution process of the strategy to predict theoretical returns, ultimately causing discrepancies between idealized strategies and actual implementation, making return predictions less accurate than reality. Summary of the Invention
[0003] In view of this, embodiments of this application provide a method for optimizing energy storage strategies based on simulation confidence assessment. One or more embodiments of this application also relate to an apparatus for optimizing energy storage strategies based on simulation confidence assessment, a computing device, a computer-readable storage medium, and a computer program, to address the technical deficiencies existing in the prior art.
[0004] According to a first aspect of the embodiments of this application, a method for selecting an energy storage strategy based on simulation confidence assessment is provided, comprising: Obtain future alternatives A storage charging and discharging strategy is proposed, and the energy is tested under multiple constraint verification conditions. The simulation results of each energy storage charging and discharging strategy are obtained by performing simulation correction power for each energy storage charging and discharging strategy. Based on the simulation correction power corresponding to each energy storage charging and discharging strategy, calculate the simulation benefit corresponding to each energy storage charging and discharging strategy, and obtain the optimal energy storage charging and discharging strategy for the future based on the simulation benefit corresponding to each energy storage charging and discharging strategy. Obtain the actual benefit of the optimal energy storage charging and discharging strategy in the previous cycle, and calculate the simulation confidence of the optimal energy storage charging and discharging strategy using the actual benefit and the simulated benefit. Based on the simulation confidence level of the optimal energy storage charging and discharging strategy, the comprehensive confidence score of the optimal energy storage charging and discharging strategy is calculated, and the optimal energy storage charging and discharging strategy is distributed to the energy storage power station based on the comprehensive confidence score.
[0005] Preferably, the multiple constraint verification conditions include energy storage body power constraint verification, transformer overload protection constraint verification, and battery capacity and SCO boundary constraint verification.
[0006] Preferably, the power constraint verification of the energy storage body includes:
[0007] Among them, the For the first energy storage power station The first intermediate power after power limiting at any given time; For the first energy storage power station The planned charge / discharge power at any given time; This represents the maximum charging and discharging power.
[0008] Preferably, the transformer overload protection constraint verification includes:
[0009] Among them, the For the first energy storage power station The second intermediate power after the transformer capacity verification at any time; the For the first energy storage power station The actual / predicted power load at the station at any given time; The maximum allowable load power of the transformer; This is a function that takes the minimum value.
[0010] Preferably, the battery capacity and SCO boundary constraint verification includes: Calculate the upper and lower capacity thresholds of the energy storage power station based on its maximum capacity and the preset upper and lower SOC thresholds. According to the energy storage power station The battery capacity at time t and the second intermediate power are used to calculate the first power of the energy storage power station. Battery capacity at +1 moment; If the energy storage power station is the first If the battery capacity at time +1 is not within the upper and lower capacity thresholds of the energy storage power station, then for the energy storage power station at time +1... The power is corrected by applying the second intermediate power at time +1 to obtain the power of the energy storage power station. The second intermediate power corrected at time +1, and the energy storage power station's first... The second intermediate power, corrected at time +1, is used as the first... Simulated corrected power at time +1.
[0011] Preferably, obtaining the optimal energy storage charging and discharging strategy based on the simulation benefits corresponding to each energy storage charging and discharging strategy includes: Calculate the average simulation benefit based on the simulation benefits corresponding to the historical best energy storage charging and discharging strategies with a pre-set number of parameters. Based on the average simulation gain, a maximization function is used to select from the future candidates. From the n strategy numbers of the energy storage charging and discharging strategy, select the optimal strategy number that has the highest expected future return and controllable risk, and take the energy storage charging and discharging strategy corresponding to the optimal strategy number as the optimal energy storage charging and discharging strategy in the future.
[0012] Preferably, the step of calculating the simulation confidence level of the optimal energy storage charging and discharging strategy using the real and simulated benefits includes: Based on the actual and simulated benefits of the optimal energy storage charging and discharging strategy, calculate the benefit achievement rate of the optimal energy storage charging and discharging strategy. Based on the return achievement rate and return volatility of the optimal energy storage charging and discharging strategy, the simulation confidence level of the optimal energy storage charging and discharging strategy is calculated.
[0013] According to a second aspect of the embodiments of this application, an energy storage strategy optimization device based on simulation confidence assessment is provided, comprising: The simulation-corrected power acquisition module is configured to acquire future alternatives. A storage charging and discharging strategy is proposed, and the energy is tested under multiple constraint verification conditions. The simulation results of each energy storage charging and discharging strategy are obtained by performing simulation correction power for each energy storage charging and discharging strategy. The energy storage strategy optimization module is configured to calculate the simulation benefit corresponding to each energy storage charging and discharging strategy based on the simulation correction power corresponding to each energy storage charging and discharging strategy, and obtain the optimal energy storage charging and discharging strategy in the future based on the simulation benefit corresponding to each energy storage charging and discharging strategy. The simulation confidence calculation module is configured to obtain the actual benefit of the optimal energy storage charging and discharging strategy in the previous cycle, and use the actual benefit and simulation benefit of the optimal energy storage charging and discharging strategy to calculate the simulation confidence of the optimal energy storage charging and discharging strategy. The energy storage strategy distribution module is configured to calculate the comprehensive confidence score of the optimal energy storage charging and discharging strategy based on the simulation confidence score, and distribute the optimal energy storage charging and discharging strategy to the energy storage power station based on the comprehensive confidence score.
[0014] According to a third aspect of the embodiments of this application, a computing device is provided, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement any of the steps of the energy storage strategy optimization method based on simulation confidence assessment.
[0015] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of any one of the energy storage strategy optimization methods based on simulation confidence assessment.
[0016] According to a fifth aspect of the present application, a computer program is provided, wherein when the computer program is executed in a computer, the computer is instructed to perform the steps of the above-described method for selecting an energy storage strategy based on simulation confidence assessment.
[0017] The energy storage strategy optimization scheme based on simulation confidence evaluation provided in this application has the following beneficial effects: (1) Improve the accuracy of revenue prediction: By introducing simulation verification of physical constraints such as transformer capacity coefficient and charge / discharge depth, the actual execution deviation caused by idealized strategies is avoided, making the revenue prediction closer to the real situation. (2) Enhance the robustness of the strategy: The original "revenue achievement rate" and "confidence" evaluation indicators can automatically identify those false high-quality strategies that are "theoretically high in revenue but difficult to implement in practice", preventing economic losses caused by model mismatch. (3) Achieve closed-loop optimization: The system can continuously correct the confidence of the simulation model based on actual operating data, so that the optimized strategy not only focuses on the theoretical highest revenue, but also on the reliability of strategy implementation, realizing the long-term stable operation of industrial and commercial energy storage power stations. (4) This application comprehensively evaluates the revenue achievement rate and the confidence risk of exceeding and falling short of expected revenue through a two-way penalty mechanism (i.e., revenue achievement rate and confidence). Attached Figure Description
[0018] Figure 1 This is a flowchart of an energy storage strategy optimization method based on simulation confidence assessment provided in one embodiment of this application; Figure 2 This is a schematic diagram of an energy storage strategy optimization device based on simulation confidence assessment provided in one embodiment of this application; Figure 3 This is a structural block diagram of a computing device provided in one embodiment of this application. Detailed Implementation
[0019] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the following description, suffixes such as "module," "part," or "unit" used to denote elements are used only for the purpose of illustrative purposes and have no inherent meaning. Therefore, "module," "part," or "unit" may be used interchangeably.
[0020] This application provides a method for optimizing energy storage strategies based on simulation confidence assessment. This application also relates to an apparatus for optimizing energy storage strategies based on simulation confidence assessment, a computing device, a computer-readable storage medium, and a computer program, which will be described in detail in the following embodiments.
[0021] Figure 1 A flowchart of an energy storage strategy optimization method based on simulation confidence assessment according to an embodiment of this application is shown, which specifically includes the following steps.
[0022] Step S101: Obtain future alternatives A storage charging and discharging strategy is proposed, and the energy is tested under multiple constraint verification conditions. The simulation results of each energy storage charging and discharging strategy are obtained by performing simulation correction power for each energy storage charging and discharging strategy. Step S102: Calculate the simulation benefit of each energy storage charging and discharging strategy based on the simulation correction power corresponding to each energy storage charging and discharging strategy, and obtain the optimal energy storage charging and discharging strategy for the future based on the simulation benefit of each energy storage charging and discharging strategy. Step S103: Obtain the actual benefit of the optimal energy storage charging and discharging strategy in the previous cycle, and calculate the simulation confidence of the optimal energy storage charging and discharging strategy using the actual benefit and simulation benefit of the optimal energy storage charging and discharging strategy. Step S104: Calculate the comprehensive confidence score of the optimal energy storage charging and discharging strategy based on the simulation confidence score, and distribute the optimal energy storage charging and discharging strategy to the energy storage power station based on the comprehensive confidence score.
[0023] In one specific embodiment of this application, the plurality of constraint verification conditions include energy storage body power constraint verification, transformer overload protection constraint verification, and battery capacity and SCO boundary constraint verification.
[0024] The power constraint verification of the energy storage body includes:
[0025] Among them, the For the first energy storage power station The first intermediate power after power limiting at any given time; For the first energy storage power station The planned charge / discharge power at any given time; This represents the maximum charging and discharging power.
[0026] The transformer overload protection constraint verification includes:
[0027] Among them, the For the first energy storage power station The second intermediate power after the transformer capacity verification at any time; the For the first energy storage power station The actual / predicted power load at the station at any given time; The maximum allowable load power of the transformer; This is a function that takes the minimum value.
[0028] The battery capacity and SCO boundary constraint verification includes: Calculate the upper and lower capacity thresholds of the energy storage power station based on its maximum capacity and the preset upper and lower SOC thresholds. According to the energy storage power station The battery capacity at time t and the second intermediate power are used to calculate the first power of the energy storage power station. Battery capacity at +1 moment; If the energy storage power station is the first If the battery capacity at time +1 is not within the upper and lower capacity thresholds of the energy storage power station, then for the energy storage power station at time +1... The power is corrected by applying the second intermediate power at time +1 to obtain the power of the energy storage power station. The second intermediate power corrected at time +1, and the energy storage power station's first... The second intermediate power, corrected at time +1, is used as the first... Simulated corrected power at time +1.
[0029] In one specific embodiment of this application, obtaining the optimal energy storage charging and discharging strategy based on the simulation benefits corresponding to each energy storage charging and discharging strategy includes: Calculate the average simulation benefit based on the simulation benefits corresponding to the historical best energy storage charging and discharging strategies with a pre-set number of parameters. Based on the average simulation gain, a maximization function is used to select from the future candidates. From the n strategy numbers of the energy storage charging and discharging strategy, select the optimal strategy number that has the highest expected future return and controllable risk, and take the energy storage charging and discharging strategy corresponding to the optimal strategy number as the optimal energy storage charging and discharging strategy in the future.
[0030] In one specific embodiment of this application, calculating the simulation confidence level of the optimal energy storage charging and discharging strategy using the real and simulated benefits includes: Based on the actual and simulated benefits of the optimal energy storage charging and discharging strategy, calculate the benefit achievement rate of the optimal energy storage charging and discharging strategy. Based on the return achievement rate and return volatility of the optimal energy storage charging and discharging strategy, the simulation confidence level of the optimal energy storage charging and discharging strategy is calculated.
[0031] In one specific embodiment of this application, the step of distributing the optimal energy storage charging and discharging strategy to the energy storage power station based on the comprehensive confidence score includes: obtaining the comprehensive confidence scores corresponding to a preset number of historical optimal energy storage charging and discharging strategies, and calculating the average comprehensive confidence score of the comprehensive confidence scores corresponding to the preset number of historical optimal energy storage charging and discharging strategies; if the comprehensive score of the optimal energy storage charging and discharging strategy is not less than the average comprehensive confidence score, then the optimal energy storage charging and discharging strategy is distributed to the energy storage power station; if the comprehensive score of the optimal energy storage charging and discharging strategy is less than the average comprehensive confidence score, then the optimal energy storage charging and discharging strategy is discarded.
[0032] In summary, this application constructs a high-fidelity simulation environment: before strategy issuance, it simulates the actual execution process of the strategy and predicts theoretical returns by considering the power purchase price of the power station agent, the characteristics of the energy storage battery, and the transformer capacity constraints. A confidence assessment mechanism is introduced: by comparing simulated returns with actual returns, the strategy's return achievement rate and confidence level are calculated to identify model biases. Dynamic strategy optimization is achieved: based on the confidence assessment results, the strategy with the highest expected future returns and controllable risks is selected from multiple candidate strategies for issuance and execution, realizing the intelligent operation of the energy storage power station.
[0033] The overall execution steps of this application include: policy candidate set and parameter initialization; obtaining future alternatives. A set of energy storage charging and discharging strategies are implemented, and the necessary parameters for simulation are loaded simultaneously; the strategies are simulated in parallel: for... Each candidate strategy is simulated and analyzed, and the simulation results for each strategy are calculated and output. Benefit evaluation and optimal decision-making: Based on the simulation results, the expected benefit of each strategy is calculated, and the strategy that maximizes the benefit is selected as the future execution strategy of the system. Historical backtesting and confidence assessment: [The text abruptly ends here, likely due to an incomplete sentence or missing information.] The optimal strategy for each day is calculated, along with its execution deviation and confidence index (generated daily). (Group evaluation value). By combining historical operational data, the deviation and confidence level of the strategy to be implemented are estimated to ensure the reliability of the decision.
[0034] 1. Basic Data Modeling and Parameter Acquisition Electricity pricing model: Obtain the local electricity purchase price policy for the power plant location and construct a time-of-use electricity price set. It includes electricity prices for four periods: peak, off-peak, and valley, and the corresponding time period divisions.
[0035] Strategy Model: Input energy storage power station Power of energy storage charging and discharging strategy at any time .
[0036] Energy storage power station model: Defines the physical constraints of the energy storage system, including rated capacity. Maximum charge and discharge power Charge and discharge efficiency and the permissible SOC charge / discharge range ( , ).
[0037] Transformer Model: Obtaining the Rated Capacity of Power Station Transformers and safety capacity factor Calculate the maximum allowable load power of the transformer. .
[0038] 2. Simulation Strategy Execution Algorithm Define variables and parameters: Time granularity: Each time point represents 15 minutes (i.e.) Hour).
[0039] Input strategy: 1 Time-based planned charge / discharge strategy power ( For discharge, (For charging).
[0040] Actual / Forecasted Load: 1 Actual / predicted power load at the power station at any given time The basis for determining the actual / predicted load is historical time / future time. For the sake of algorithm scalability, if the target time is historical time, then the actual load is obtained; otherwise, the predicted load is obtained.
[0041] Energy storage status: 1st Battery state of charge at any given time ; Maximum capacity; This represents the maximum charging and discharging power.
[0042] Transformer constraints: Rated capacity of the transformers at the power station and safety capacity factor Calculate the maximum allowable load power of the transformer. .
[0043] Efficiency parameters: efficiency parameters Include and ;in For discharge efficiency; For charging efficiency.
[0044] The specific execution process is as follows: S2.1 Power Constraint Verification of Energy Storage Unit First, determine the strategic power of the energy storage power station. Does it exceed the maximum allowable charge / discharge power of the energy storage converter (PCS) and battery? .
[0045] right arrive Perform the traversal:
[0046] in, This is the first intermediate power after power limiting.
[0047] S2.2 Transformer overload protection constraint verification This step ensures that the energy storage charging process, when combined with the load, will not cause transformer overload; and that the energy storage discharge process matches the power demand of industrial and commercial users.
[0048] Discharge scenario ( Energy storage discharge needs to match the electricity demand of industrial and commercial users; the maximum discharge value cannot exceed the demand value. ,Right now ; Charging scenarios ( Energy storage charging will consume transformer capacity. If the absolute value of "actual / predicted load - energy storage charging power" (i.e., the total power drawn from the grid) exceeds... The limit necessitates a reduction in charging power. Otherwise, simply use electricity according to the plan.
[0049] This is the second intermediate power after the transformer capacity has been verified.
[0050]
[0051] S2.3 Battery Capacity and SOC Boundary Constraint Verification This step is based on the previous moment. Calculate whether the current strategy will lead to overcharging or over-discharging.
[0052] Set the upper and lower limits of SOC as follows and ,For example and The capacity range of energy storage power stations is... ,Right now = ， = ; Calculate the theoretical battery capacity of the energy storage power station at the next time step: *
[0053] Among them, when hour, ; hour, . This represents the battery capacity of the energy storage power station at time t.
[0054] Power correction: like This indicates overcharging; the corrected power is: = - / ;like This indicates over-discharge; the corrected power is: = - /
[0055] The power rating for battery capacity and SOC boundary constraint verification correction is named as follows: .
[0056] S2.4 Output: After the above steps, the corrected all-day execution strategy sequence is output. This sequence represents the "simulation strategy execution status" that satisfies all physical and safety constraints, and is used for profit calculations in subsequent steps.
[0057] 3. Strategy Evaluation and Optimization Algorithm This algorithm is used to evaluate the reliability of a strategy and select the optimal solution. The specific steps are as follows: Step S3.1: Simulation revenue calculation: in accordance with Calculate the corresponding simulation benefits The calculation formula is as follows:
[0058] Step S3.2: Strategy Optimization Algorithm Calculate the simulation returns for each strategy, and select the strategy with the highest simulation returns over the three historical dates. Indicates the first The strategy in the first The total simulated revenue for each historical date. K is the number of historical dates selected.
[0059] Calculate average simulation revenue :
[0060] Optimal strategy selection (argmax function): Based on the calculated average return, the strategy index with the best overall performance is selected using a maximization function. :
[0061] Right now:
[0062] index as The strategy was determined as the future execution strategy, and its power plan included 96 time points. ={ }, where N is the number of strategies.
[0063] Step S3.3: Bias Analysis and Confidence Calculation: Obtain the actual return of the S3.2 strategy in the previous cycle during actual operation. .
[0064] Calculate the profit achievement rate: ,in .Note: This indicates that the simulation is extremely accurate; The greater the deviation from 1, the greater the deviation in strategy returns. It's the strategy number that was selected on a particular day.
[0065] Calculate the confidence score: Construct the confidence score function (), This function is related to the rate of return achievement. Positively correlated with, and negatively correlated with, return volatility. For example, if If the value is close to 1 and has small historical fluctuations, the confidence level is high; if A large deviation from 1 (indicating a large discrepancy between the simulation model and reality, or significant interference with strategy execution) indicates a low confidence level.
[0066] The strategy in the Confidence level of historical dates It consists of two parts: the achievement rate fidelity term and the volatility stability term. Its formula expression is:
[0067] Formula explanation: Achievement rate guarantee items:
[0068] Using absolute value Measurement bias. Regardless of whether the achievement rate is too high ( () or too low () (The confidence level will decrease as long as it deviates from 1).
[0069] when At that time, this item takes the maximum value of 1. It should be noted that regarding... Explanation: If A value significantly less than 1 (e.g., 0.6) indicates that actual implementation is hindered (e.g., transformer power outages, battery failures) or the simulation model is overly optimistic, making the strategy unreliable. If A confidence level significantly greater than 1 (e.g., 1.4) indicates that the simulation model is severely distorted (e.g., it underestimates electricity prices or overestimates load). Although the returns are high, it represents a "false prosperity" with extremely high future implementation risks, so the confidence level must be reduced.
[0070] This is the first adjustment factor (e.g., 2.0), used to control the penalty for deviation.
[0071] Fluctuation stability term:
[0072] Using volatility Measure risk. The greater the volatility, the faster the exponential decay, and the lower the confidence level. To quantify the grid-friendliness of the strategy, statistical characteristics of load fluctuations at the grid connection point are introduced.
[0073]
[0074] Where t represents the total number of time steps in the scheduling cycle, with a value range of 1-96; k represents the date code; This represents the actual / predicted power load at the power station on day k at time i. This represents the average load at 96:00 on day k. When the strategy returns are extremely stable ( When ), the term approaches 1.
[0075] This is the second adjustment factor (e.g., 5.0), used to control sensitivity to fluctuations.
[0076] Weighting coefficients: If model accuracy is of greater importance, it can be set... If you prioritize stable returns, you can set it in the opposite direction.
[0077] This invention introduces volatility penalties to select strategies that are "most stable and easiest to implement, even if the returns may not be the absolute highest".
[0078] Dimensional balance treatment: To facilitate horizontal comparison between different strategies, it is possible to... Normalization is performed to obtain the strategy at the th . Final confidence level of historical dates :
[0079] Industrial and commercial loads fluctuate greatly. If a strategy’s returns have been fluctuating wildly over the past three days, it indicates that the strategy is extremely sensitive to the accuracy of load forecasting and has poor robustness.
[0080] Step S5: Strategy Evaluation and Distribution 1. Strategy Distribution and Confidence Assessment Formula The optimal strategy selected on a certain day Before distributing the strategy, calculate its overall confidence score. The calculation formula is:
[0081] in, The representative strategy in the first Confidence score on the evaluation dimension of each historical date.
[0082] 2. Anomaly warning and manual review mechanism Set the average strategy score over the past 30 days as the baseline threshold. When a new strategy is issued Not lower than the historical average level (i.e. When this happens, the system issues the selected optimal strategy. When a new strategy is issued Below that historical average (i.e.) When this happens, the system will trigger an anomaly warning, requiring manual intervention to determine whether any strategies have exhibited anomalies within the past 3 days.
[0083] 3. Explanation of Exemptions for Special Circumstances During the manual review process, it is necessary to check whether the low score is due to temporary adjustments to the strategy caused by the following special circumstances: Production scheduling requirements at the site: Due to production planning, energy storage equipment is required to be taken out of grid-connected operation during specific time periods; Other objective limitations: Force majeure events such as power grid dispatch instructions, equipment maintenance, or extreme weather may force the strategy to be downgraded or temporarily changed.
[0084] If it is confirmed that the situation falls under the above special circumstances, the low score strategy can be considered a reasonable adjustment, and the decision can be made with a note of the reason; otherwise, it is necessary to further investigate whether there are any abnormalities in the strategy model or data source.
[0085] These commands are then translated into specific control instructions and sent to the energy management system (EMS) of the energy storage power station for execution via a communication protocol.
[0086] It should also be noted that, before distributing the optimal energy storage charging and discharging strategy to the energy storage power station, this application also includes an evaluation step of the optimal energy storage charging and discharging strategy, which specifically includes: The dynamic temperature simulation model of the energy storage battery at the current moment, including battery temperature, heat generation power, and heat dissipation power, is used to simulate the battery temperature at multiple moments within the target cycle, generating corresponding battery temperature simulation results. Based on the battery temperature simulation results, the high-temperature aging marginal cost and cycle aging marginal cost of the energy storage battery at the multiple times are calculated. Obtain the energy storage charging and discharging strategy to be evaluated corresponding to the energy storage battery, and determine the interaction power between the energy storage battery and the power grid at the multiple times based on the energy storage charging and discharging strategy to be evaluated; The simulated revenue of the energy storage battery during the target period is calculated based on the interaction power, the high-temperature aging marginal cost, and the cycle aging marginal cost. The confidence level is calculated based on the simulated benefits and the actual benefits of the energy storage battery during the target period, and the calculation result is determined as the evaluation result corresponding to the energy storage charging and discharging strategy to be evaluated.
[0087] Optionally, the step of simulating the battery temperature at multiple moments within the target cycle using a dynamic temperature simulation model to generate corresponding battery temperature simulation results includes: The battery temperature, heat generation power, and heat dissipation power at the current moment are processed by the temperature dynamic simulation model to generate the battery temperature simulation result at the i-th moment within the target period, where i starts from 1 and is an integer from 1 to n-1, and n is the total number of multiple moments within the target interval. The battery temperature simulation results, heat generation power, and heat dissipation power at the i-th time point are processed by the temperature dynamic simulation model to generate the battery temperature simulation results at the (i+1)-th time point within the target period. If i is incremented by 1, and if i is determined to be less than or equal to n-1, the process returns to the step of processing the battery temperature simulation results, heat generation power, and heat dissipation power at the i-th time moment through the temperature dynamic simulation model to generate the battery temperature simulation results at the (i+1)-th time moment within the target period.
[0088] Optionally, the operation steps for evaluating the optimal energy storage charging and discharging strategy further include: Calculate the capacity decay rate of the energy storage battery at the various times based on the battery temperature simulation results; The high-temperature aging marginal cost of the energy storage battery at the multiple times is calculated based on the capacity decay rate of the energy storage battery at each of the multiple times.
[0089] Optionally, the expression for the high-temperature aging marginal cost calculation process is as follows:
[0090] in, Let t be the marginal cost of high-temperature aging. The initial investment cost of energy storage batteries, This refers to the rated total capacity of the energy storage battery. Cost per unit capacity of battery Let t be the capacity decay rate at time t.
[0091] Optionally, the expression for the capacity decay rate calculation process is as follows:
[0092] in, The calendar aging frequency factor is determined by the characteristics of the battery materials and is calibrated through high-temperature storage experiments. The activation energy of the calendar aging reaction reflects the sensitivity of temperature to the aging rate. Let be the ideal gas constant. The simulation results show the battery temperature of the energy storage battery at time t. Let t be the state of charge (SOC) of the energy storage battery at time t, and z be the exponent of the SOC's impact on calendar aging, typically taking a value between 1 and 2. between.
[0093] Optionally, the operation steps for evaluating the optimal energy storage charging and discharging strategy further include: Based on the battery temperature simulation results and the depth of discharge of the energy storage battery at each time, the number of cycles corresponding to the energy storage battery at each of the multiple time points is determined. The marginal cost of cycle aging of the energy storage battery at the multiple time points is calculated based on the number of cycles corresponding to the energy storage battery at each of the multiple time points.
[0094] Optionally, the expression for the calculation process of the cyclic aging marginal cost is as follows:
[0095] in, The initial investment cost of energy storage batteries, The number of cycles for the energy storage battery at time t, based on the depth of discharge at time t. Simulation results of battery temperature Sure, Let be the absolute value of the power exchanged between the energy storage battery and the power grid at time t. The interval between any two adjacent moments within the target period is the duration of time.
[0096] Optionally, the temperature dynamic simulation model is constructed based on the battery temperature, heat generation power, heat dissipation power, battery heat capacity, and the interval between any two adjacent moments within the target period of the energy storage battery at any given time. The specific expression is as follows:
[0097] in, The simulation results show the battery temperature of the energy storage battery at time t. for The heat generation power inside the energy storage battery at all times. for The heat dissipation capacity of the energy storage battery to the environment at all times. For the heat capacity of the energy storage battery, The interval between any two adjacent moments within the target period is the duration of time.
[0098] Optionally, the expression for the heat dissipation power calculation process is as follows:
[0099] in, The convective heat transfer coefficient is... For heat dissipation area, The ambient temperature;
[0100] in, is the Nusselt number, a dimensionless number representing the intensity of convective heat transfer. The thermal conductivity of the cooling fluid. This refers to the battery length.
[0101] This application addresses the industry pain point of "artificially high" simulation returns by evaluating the optimal energy storage charging and discharging strategy and introducing the marginal cost of high-temperature aging and the marginal cost of cycle aging. By evaluating each energy storage strategy before it is implemented, aggressive strategies that may cause overheating of the energy storage battery can be identified in advance, which is beneficial to improving the safety of the energy storage system.
[0102] This application also provides an embodiment of an energy storage strategy optimization device based on simulation confidence assessment. Figure 2 A schematic diagram of a simulation-based confidence assessment-based energy storage strategy optimization device is shown as an embodiment of this application. Figure 2 As shown, the device includes: a simulation correction power acquisition module, configured to acquire future alternatives. A storage charging and discharging strategy is proposed, and the energy is tested under multiple constraint verification conditions. The system performs simulations of several energy storage charging and discharging strategies to obtain the simulation correction power corresponding to each strategy. An energy storage strategy optimization module is configured to calculate the simulation revenue of each strategy based on the simulation correction power, and to obtain the optimal energy storage charging and discharging strategy for the future based on the simulation revenue. A simulation confidence calculation module is configured to obtain the actual revenue of the optimal energy storage charging and discharging strategy in the previous period, and to calculate the simulation confidence of the optimal strategy using both the actual and simulation revenue. An energy storage strategy distribution module is configured to calculate the comprehensive confidence score of the optimal energy storage charging and discharging strategy based on the simulation confidence score, and to distribute the optimal energy storage charging and discharging strategy to the energy storage power station based on the comprehensive confidence score.
[0103] The above is an illustrative scheme of an energy storage strategy optimization device based on simulation confidence assessment according to this embodiment. It should be noted that the technical solution of this energy storage strategy optimization device based on simulation confidence assessment belongs to the same concept as the technical solution of the energy storage strategy optimization method based on simulation confidence assessment described above. Details not described in detail in the technical solution of the energy storage strategy optimization device based on simulation confidence assessment can be found in the description of the technical solution of the energy storage strategy optimization method based on simulation confidence assessment described above.
[0104] Figure 3 A structural block diagram of a computing device 300 according to an embodiment of this application is shown. The components of the computing device 300 include, but are not limited to, a memory 310 and a processor 320. The processor 320 is connected to the memory 310 via a bus 330, and a database 350 is used to store data.
[0105] The computing device 300 also includes an access device 340, which enables the computing device 300 to communicate via one or more networks 360. Examples of these networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 340 may include one or more of any type of wired or wireless network interface (e.g., a Network Interface Card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) interface, a Wi-MAX interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.
[0106] In one embodiment of this application, the aforementioned components of the computing device 300 and Figure 3 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 3 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this application. Those skilled in the art can add or replace other components as needed.
[0107] The computing device 300 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs. The computing device 300 can also be a mobile or stationary server.
[0108] The processor 320 is used to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-mentioned energy storage strategy optimization method based on simulation confidence assessment.
[0109] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-described energy storage strategy optimization method based on simulation confidence assessment.
[0110] This application also provides a computer program, wherein when the computer program is executed in a computer, the computer is instructed to perform the steps of the above-described energy storage strategy optimization method based on simulation confidence assessment.
[0111] The above are illustrative schemes of a computing device, a computer-readable storage medium, and a computer program according to this embodiment. It should be noted that each technical solution belongs to the same concept as the above-described energy storage strategy optimization method based on simulation confidence assessment. Details not described in detail for each technical solution can be found in the above-described description of the energy storage strategy optimization method based on simulation confidence assessment.
[0112] The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, but this does not limit the scope of the invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and spirit of the present invention should be within the scope of the present invention.
Claims
1. A method for optimizing energy storage strategies based on simulation confidence assessment, characterized in that, include: Obtain future alternatives A storage charging and discharging strategy is proposed, and the strategy is tested under multiple constraint verification conditions, including storage body power constraint verification, transformer overload protection constraint verification, and battery capacity and SCO boundary constraint verification. The simulation derivation of each energy storage charging and discharging strategy is carried out to obtain the simulation correction power corresponding to each energy storage charging and discharging strategy; Based on the simulation correction power corresponding to each energy storage charging and discharging strategy, calculate the simulation benefit corresponding to each energy storage charging and discharging strategy, and obtain the optimal energy storage charging and discharging strategy for the future based on the simulation benefit corresponding to each energy storage charging and discharging strategy. Obtain the actual benefit of the optimal energy storage charging and discharging strategy in the previous cycle, and calculate the simulation confidence of the optimal energy storage charging and discharging strategy using the actual benefit and the simulated benefit. Based on the simulation confidence level of the optimal energy storage charging and discharging strategy, the comprehensive confidence score of the optimal energy storage charging and discharging strategy is calculated, and the optimal energy storage charging and discharging strategy is distributed to the energy storage power station based on the comprehensive confidence score.
2. The method according to claim 1, characterized in that, The power constraint verification of the energy storage body includes: Among them, the For the first energy storage power station The first intermediate power after power limiting at any given time; For the first energy storage power station The planned charge / discharge power at any given time; This represents the maximum charging and discharging power.
3. The method according to claim 2, characterized in that, The transformer overload protection constraint verification includes: Among them, the For the first energy storage power station The second intermediate power after the transformer capacity verification at any time; the For the first energy storage power station The actual / predicted power load at the station at any given time; The maximum allowable load power of the transformer; This is a function that takes the minimum value.
4. The method according to claim 3, characterized in that, The battery capacity and SCO boundary constraint verification includes: Calculate the upper and lower capacity thresholds of the energy storage power station based on its maximum capacity and the preset upper and lower SOC thresholds. According to the energy storage power station The battery capacity at time t and the second intermediate power are used to calculate the first power of the energy storage power station. Battery capacity at +1 moment; If the energy storage power station is the first If the battery capacity at time +1 is not within the upper and lower capacity thresholds of the energy storage power station, then for the energy storage power station at time +1... The power is corrected by applying the second intermediate power at time +1 to obtain the power of the energy storage power station. The second intermediate power corrected at time +1, and the energy storage power station's first... The second intermediate power, corrected at time +1, is used as the first... Simulated corrected power at time +1.
5. The method according to claim 4, characterized in that, The process of obtaining the optimal energy storage charging and discharging strategy based on the simulation benefits corresponding to each energy storage charging and discharging strategy includes: Calculate the average simulation benefit based on the simulation benefits corresponding to the historical best energy storage charging and discharging strategies with a pre-set number of parameters. Based on the average simulation gain, a maximization function is used to select from the future candidates. From the n strategy numbers of the energy storage charging and discharging strategy, select the optimal strategy number that has the highest expected future return and controllable risk, and take the energy storage charging and discharging strategy corresponding to the optimal strategy number as the optimal energy storage charging and discharging strategy in the future.
6. The method according to claim 5, characterized in that, The calculation of the simulation confidence level of the optimal energy storage charging and discharging strategy using the real and simulated benefits includes: Based on the actual and simulated benefits of the optimal energy storage charging and discharging strategy, calculate the benefit achievement rate of the optimal energy storage charging and discharging strategy. Based on the return achievement rate and return volatility of the optimal energy storage charging and discharging strategy, the simulation confidence level of the optimal energy storage charging and discharging strategy is calculated.
7. An energy storage strategy optimization device based on simulation confidence assessment, characterized in that, include: The simulation-corrected power acquisition module is configured to acquire future alternatives. A storage charging and discharging strategy is proposed, and the strategy is tested under multiple constraint verification conditions, including storage body power constraint verification, transformer overload protection constraint verification, and battery capacity and SCO boundary constraint verification. The simulation derivation of each energy storage charging and discharging strategy is carried out to obtain the simulation correction power corresponding to each energy storage charging and discharging strategy; The energy storage strategy optimization module is configured to calculate the simulation benefit corresponding to each energy storage charging and discharging strategy based on the simulation correction power corresponding to each energy storage charging and discharging strategy, and obtain the optimal energy storage charging and discharging strategy in the future based on the simulation benefit corresponding to each energy storage charging and discharging strategy. The simulation confidence calculation module is configured to obtain the actual benefit of the optimal energy storage charging and discharging strategy in the previous cycle, and use the actual benefit and simulation benefit of the optimal energy storage charging and discharging strategy to calculate the simulation confidence of the optimal energy storage charging and discharging strategy. The energy storage strategy distribution module is configured to calculate the comprehensive confidence score of the optimal energy storage charging and discharging strategy based on the simulation confidence score, and distribute the optimal energy storage charging and discharging strategy to the energy storage power station based on the comprehensive confidence score.
8. A computing device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the energy storage strategy optimization method based on simulation confidence assessment as described in any one of claims 1 to 6.
9. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the energy storage strategy optimization method based on simulation confidence assessment as described in any one of claims 1 to 6.