Fire storage combined frequency modulation control method and device based on double closed-loop optimization

Abstract

The invention belongs to the field of electric power, and discloses a fire-storage combined frequency modulation control method and device based on double closed-loop optimization, and the method comprises the steps: carrying out the prediction of a load instruction of a fire-storage combined system in a future time period through a load prediction model in response to a collected AGC instruction signal, a load prediction model is constructed based on variational mode decomposition and bidirectional long-short-term memory network fusion; inputting the predicted load instruction and the actual load instruction into a third-order frequency modulation demand calculation model, and calculating the frequency modulation power demand of the thermal power storage combined system; according to a chaos quantum particle swarm optimization algorithm, with comprehensive minimization of the adjustment cost, the frequency modulation deviation and the energy storage life loss of the thermal power and energy storage combined system as a target, optimal output distribution between the thermal power generating unit and the energy storage system is carried out on the frequency modulation power demand; and evaluating the health degree of the energy storage system in the thermal power storage combined system based on the capacity attenuation mechanism, and adjusting the weight or constraint condition of the optimization target in the chaotic quantum particle swarm optimization algorithm according to the health degree.

Description

Technical Field

[0001] This invention belongs to the field of power, and particularly relates to a method and device for combined thermal and energy storage frequency regulation control based on dual closed-loop optimization. Background Technology

[0002] Thermal power units, as the traditional mainstay of frequency regulation, suffer from slow response speed and limited ramp-up capability, making it difficult to meet rapidly changing frequency regulation demands. Energy storage systems offer millisecond-level response speed and flexible adjustment capabilities, but standalone configurations are costly and have limited lifespans. Combined thermal and energy storage frequency regulation has become an effective means to improve system frequency regulation performance.

[0003] In related technologies, combined thermal power and energy storage frequency regulation control often employs open-loop or single closed-loop control strategies, which cannot simultaneously address both energy storage lifespan degradation and the accuracy of unit load prediction during frequency regulation. Traditional frequency regulation methods mainly suffer from insufficient prediction accuracy, a singular optimization objective, a lack of closed-loop lifespan protection, and a contradiction between response speed and accuracy. Specifically, AGC command signals exhibit strong nonlinearity and randomness, making it difficult for a single prediction model to accurately capture their changing patterns, resulting in significant deviations between pre-allocation strategies and actual demands. Most methods only aim to minimize frequency regulation deviation or optimize economics, without comprehensively considering energy storage lifespan degradation, leading to rapid capacity decay and reduced economic efficiency over long-term operation. Existing methods often employ fixed weights or constraints, failing to dynamically adjust control strategies based on the actual health status of the energy storage, making it difficult to achieve a balance between lifespan and economic efficiency. Thermal power units have slow response but good economics, while energy storage has fast response but high costs; existing allocation strategies struggle to achieve an optimal balance between rapid response and long-term economic efficiency. Summary of the Invention

[0004] In view of this, the present invention discloses a method and device for combined frequency regulation control of fire and energy storage based on dual closed-loop optimization, which can solve the shortcomings of related technologies.

[0005] To achieve the above objectives, the present invention discloses the following technical solution:

[0006] According to a first aspect of the present invention, a combined thermal power and energy storage frequency regulation control method based on dual closed-loop optimization is proposed, comprising: In response to the acquired AGC command signal, the load command of the fire-storage combined system for future periods is predicted by the load prediction model, which is constructed based on the fusion of variational mode decomposition and bidirectional long short-term memory network. The predicted load command and the actual load command are input into a pre-constructed third-order frequency regulation demand calculation model that includes proportional, integral and derivative terms to calculate the frequency regulation power demand of the combined fire and energy storage system. Based on the improved chaotic quantum particle swarm optimization algorithm, with the goal of minimizing the overall adjustment cost, frequency regulation deviation and energy storage life loss of the thermal power-storage combined system, the output of the frequency regulation power demand is optimally allocated between the thermal power unit and the energy storage system. The health of the energy storage system in the combined fire and energy storage system is assessed based on the capacity decay mechanism, and the optimization target weights or constraints in the chaotic quantum particle swarm optimization algorithm are adjusted according to the health status to form a lifetime protection closed-loop control.

[0007] According to a second aspect of the present invention, a combined thermal power and energy storage frequency regulation control device based on dual closed-loop optimization is proposed, the device comprising: Prediction Unit: In response to the acquired AGC command signal, it predicts the load command of the fire-storage combined system for future periods through a load prediction model. The load prediction model is constructed based on the fusion of variational mode decomposition and bidirectional long short-term memory network. Calculation unit: Inputs the predicted load command and actual load command obtained from the forecast into a pre-constructed third-order frequency regulation demand calculation model containing proportional, integral and differential terms, and calculates the frequency regulation power demand of the combined fire and energy storage system; Allocation Unit: Based on the improved chaotic quantum particle swarm optimization algorithm, with the goal of minimizing the overall adjustment cost, frequency regulation deviation and energy storage life loss of the thermal power-storage combined system, the unit performs optimal power allocation between the thermal power unit and the energy storage system for the frequency regulation power demand. Adjustment Unit: Based on the capacity decay mechanism, assesses the health of the energy storage system in the combined fire and energy storage system, and adjusts the optimization target weights or constraints in the chaotic quantum particle swarm optimization algorithm according to the health status to form a lifetime protection closed-loop control.

[0008] According to a third aspect of the present invention, an electronic device is provided, comprising: processor; Memory used to store processor-executable instructions; The processor implements the steps of the method as described in the first aspect by running the executable instructions.

[0009] According to a fourth aspect of the invention, a computer-readable storage medium is provided having computer instructions stored thereon that, when executed by a processor, implement the steps of the method as described in the first aspect.

[0010] As can be seen from the above technical solutions, the thermal power and energy storage joint frequency regulation control method disclosed in this invention is based on dual closed-loop optimization: On the one hand, by constructing a load forecasting model based on the fusion of variational mode decomposition and bidirectional long short-term memory network, the problem of insufficient prediction accuracy of single models for nonlinear and non-stationary AGC command signals is overcome. By decomposing the signal into multiple intrinsic mode components and reconstructing them after high-precision prediction, the accuracy and reliability of short-term load forecasting are improved. On the other hand, by constructing a third-order frequency regulation demand model that integrates actual and predicted load commands, and applying an improved chaotic quantum particle swarm optimization algorithm, dynamic optimal allocation of thermal power and energy storage output is achieved under a rolling time-domain optimization framework aimed at minimizing system adjustment cost, frequency regulation deviation, and energy storage lifetime loss. This ensures rapid and accurate frequency adjustment while reducing operating costs and delaying the capacity decay of energy storage devices. In addition, this invention introduces a dynamic assessment model of energy storage health based on the capacity decay mechanism, forming a unique lifetime protection closed-loop control mechanism. When the assessed health indicates battery degradation, the target weights and operating constraints can be adjusted and optimized, thereby guiding the control strategy towards a lifetime protection priority mode, solving the problem of severe lifetime loss of energy storage systems due to frequent charging and discharging in traditional methods. Attached Figure Description

[0011] Figure 1 This is an exemplary embodiment of an architecture diagram of a combined thermal power and energy storage frequency regulation control system based on dual closed-loop optimization. Figure 2 This is a flowchart of an exemplary embodiment of a combined frequency modulation control method for thermal power and energy storage based on dual closed-loop optimization; Figure 3 This is a schematic diagram illustrating a VMD-BiLSTM model for predicting future load commands, provided in an exemplary embodiment. Figure 4 This is a schematic structural diagram of a device provided in an exemplary embodiment; Figure 5 This is a block diagram of an exemplary embodiment of a combined fire and energy storage frequency regulation control device based on dual closed-loop optimization. Detailed Implementation

[0012] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of the present invention as detailed in the appended claims.

[0013] It should be noted that in other embodiments, the corresponding methods are not necessarily performed in the order shown and described in this invention. The method comprises steps. In some other embodiments, the method may include more or fewer steps than those described in this invention. Furthermore, a single step described in this invention may be broken down into multiple steps in other embodiments; and multiple steps described in this invention may be combined into a single step in other embodiments.

[0014] Thermal power units, as the traditional mainstay of frequency regulation, suffer from slow response speed and limited ramp-up capability, making it difficult to meet rapidly changing frequency regulation demands. Energy storage systems offer millisecond-level response speed and flexible adjustment capabilities, but standalone configurations are costly and have limited lifespans. Combined thermal and energy storage frequency regulation has become an effective means to improve system frequency regulation performance.

[0015] In related technologies, combined thermal power and energy storage frequency regulation control often employs open-loop or single closed-loop control strategies, which cannot simultaneously address both energy storage lifespan degradation and the accuracy of unit load prediction during frequency regulation. Traditional frequency regulation methods mainly suffer from insufficient prediction accuracy, a singular optimization objective, a lack of closed-loop lifespan protection, and a contradiction between response speed and accuracy. Specifically, AGC command signals exhibit strong nonlinearity and randomness, making it difficult for a single prediction model to accurately capture their changing patterns, resulting in significant deviations between pre-allocation strategies and actual demands. Most methods only aim to minimize frequency regulation deviation or optimize economics, without comprehensively considering energy storage lifespan degradation, leading to rapid capacity decay and reduced economic efficiency over long-term operation. Existing methods often employ fixed weights or constraints, failing to dynamically adjust control strategies based on the actual health status of the energy storage, making it difficult to achieve a balance between lifespan and economic efficiency. Thermal power units have slow response but good economics, while energy storage has fast response but high costs; existing allocation strategies struggle to achieve an optimal balance between rapid response and long-term economic efficiency.

[0016] To address the shortcomings in related technologies, this invention proposes a method and device for combined thermal and energy storage frequency regulation control based on dual closed-loop optimization.

[0017] Figure 1 This is an exemplary embodiment of an architecture diagram of a combined thermal power and energy storage frequency regulation control system based on dual closed-loop optimization, as shown below. Figure 1 As shown, the system includes an outer-loop prediction framework and an inner-loop control framework. The outer-loop prediction framework includes a data acquisition unit, a signal preprocessing unit, and a prediction unit.

[0018] The data acquisition unit is used to monitor AGC commands in real time. Frequency modulation power requirements ,load Climbing speed setting The data signals involved in the calculation are processed by the following units: the signal preprocessing unit performs moving average filtering and outlier removal on the collected data; and the prediction unit uses a hybrid prediction model that combines variational mode decomposition and bidirectional long short-term memory network to predict the future load command of the unit.

[0019] The inner-loop control framework comprises an optimization decision-making unit, an instruction execution unit, and a health management unit. The optimization decision-making unit constructs a third-order dynamic demand calculation model incorporating proportional, integral, and derivative terms. The instruction execution unit applies an improved chaotic quantum particle swarm optimization algorithm to achieve optimal allocation of thermal power and energy storage output, converting the optimization results into control instructions for thermal power units and instructions for the energy storage converter (PCS). The health management unit calculates the health status of the energy storage system in real time. Based on this, the objective function weights and constraints in the decision-making unit are dynamically adjusted and optimized to achieve closed-loop protection.

[0020] Figure 2 This is a flowchart illustrating an exemplary embodiment of a combined thermal power and energy storage frequency regulation control method based on dual closed-loop optimization. (See attached diagram.) Figure 2 As shown, the method may include the following steps: Step 201: In response to the collected AGC command signal, the load command of the fire-storage combined system for future periods is predicted by the load prediction model, which is constructed based on the fusion of variational mode decomposition and bidirectional long short-term memory network.

[0021] Specifically, the load forecasting model is used to predict the load command of the combined fire and storage system for future periods. This includes: decomposing the model input data into the load forecasting model into multiple intrinsic mode function components using a variational mode decomposition algorithm; independently predicting each intrinsic mode function component using the bidirectional long short-term memory network; and reconstructing and superimposing the prediction results of each component to obtain the predicted load command.

[0022] like Figure 3 As shown, the variational mode decomposition (VMD) algorithm decomposes the model input data into K intrinsic mode function (IMF) components to effectively separate different frequency components in the load command. Then, a bidirectional long short-term memory network (BiLSTM) is used to independently predict each IMF component, fully exploring its temporal forward and backward dependencies. Finally, the prediction results of each component are reconstructed and superimposed to obtain a high-precision ultra-short-term load command prediction value for a future period of time.

[0023] Furthermore, the objective function constraints of the VMD are as follows: ; in, The amplitude of the modal component. The center frequency of the modal component, This is the original signal.

[0024] The number of modes K can be set as a multiple of 2, the penalty factor α can be set as a multiple of 500, and the ADMM algorithm is used to solve iteratively.

[0025] The BiLSTM network adopts a two-layer structure, and the final output is an ultra-short-term load command curve with a step size of 1 minute and a prediction duration of 1 hour.

[0026] Step 202: Input the predicted load command and the actual load command obtained from the forecast into a pre-constructed third-order frequency regulation demand calculation model that includes proportional, integral and differential terms, and calculate the frequency regulation power demand of the combined fire and energy storage system.

[0027] The expression for the third-order frequency modulation demand calculation model is as follows: ; Among them, P req (t) represents the frequency modulation power requirement, P AGCact (t) represents the actual load command, P AGCpred (t+t) p (This refers to a load forecasting command.) , , For frequency modulation dynamic coefficients, Let be the frequency modulation deviation at time t. This is the gain coefficient for AGC instructions. To predict the weighting factor of load commands, The inertial time constant of the AGC command. For the predicted duration.

[0028] Step 203: Based on the improved chaotic quantum particle swarm optimization algorithm, with the goal of minimizing the overall adjustment cost, frequency regulation deviation and energy storage life loss of the thermal power-storage combined system, the output of the frequency regulation power demand is optimally allocated between the thermal power unit and the energy storage system.

[0029] The objective function of the chaotic quantum particle swarm optimization algorithm is expressed as follows: ; in, , , To optimize the target coefficient, its initial value is determined by training with historical data and adjusted based on the health feedback.

[0030] Furthermore, the optimal allocation of power output between thermal power units and energy storage systems for the frequency regulation power demand includes: incorporating information from the load forecasting model to generate a joint thermal power-storage frequency regulation rolling time-domain optimization strategy, the expression of which is: ; Among them, the output of thermal power units With the output of the energy storage system Satisfy constraints , To predict duration, This represents the maximum ramp rate of the thermal power unit. , These represent the maximum and minimum values ​​for energy storage charging and discharging, respectively. To maximize the output of energy storage.

[0031] Step 204: Evaluate the health of the energy storage system in the combined fire and energy storage system based on the capacity decay mechanism, and adjust the optimization target weights or constraints in the chaotic quantum particle swarm optimization algorithm according to the health status to form a lifetime protection closed-loop control.

[0032] Specifically, assessing the health of the energy storage system in the combined thermal and energy storage system based on the capacity decay mechanism includes: constructing an energy storage health assessment model based on the capacity decay mechanism, and calculating the health based on the assessment model. The expression for the dynamic assessment model of energy storage health is as follows: ; in, This refers to the number of charge-discharge cycles. For capacity loss, This refers to the battery's nominal capacity.

[0033] when When the health level drops to the preset protection value, it can be dynamically adjusted. , , , , Correlation coefficients are used to guide the optimization algorithm to prioritize the protection of energy storage batteries.

[0034] In this embodiment, on the one hand, a load forecasting model based on the fusion of variational mode decomposition and bidirectional long short-term memory network overcomes the problem of insufficient prediction accuracy of single models for nonlinear and non-stationary AGC command signals. By decomposing the signal into multiple intrinsic mode components and reconstructing them after high-precision prediction, the accuracy and reliability of short-term load forecasting are improved. On the other hand, by constructing a third-order frequency regulation demand model that integrates actual and predicted load commands and applying an improved chaotic quantum particle swarm optimization algorithm, dynamic optimal allocation of thermal power and energy storage output is achieved under a rolling time-domain optimization framework aimed at minimizing system adjustment cost, frequency regulation deviation, and energy storage lifetime loss. This ensures rapid and accurate frequency adjustment while reducing operating costs and delaying the capacity decay of energy storage devices. In addition, this invention introduces a dynamic assessment model of energy storage health based on the capacity decay mechanism, forming a unique lifetime protection closed-loop control mechanism. When the assessed health indicates battery degradation, the target weights and operating constraints can be adjusted and optimized, thereby guiding the control strategy towards a lifetime protection priority mode, solving the problem of severe lifetime loss of energy storage systems due to frequent charging and discharging in traditional methods.

[0035] In one embodiment, the method further includes: using the collected AGC input signal as a valid identifier, and employing a moving average filter and box plot method to remove outliers, so as to generate model input data for inputting the load prediction model.

[0036] The AGC (Automatic Guided Collection) input signal is used as a valid identifier. When the AGC input signal is "1", it indicates that the AGC command is valid; when it is "0", it indicates that the AGC command is invalid and the data for that period needs to be removed. Valid AGC command signals undergo data cleaning, using a moving average filter to smooth data fluctuations, and then outliers are identified and removed using a box plot method to form the model input data for the prediction model.

[0037] In this embodiment, the AGC (Automatic Guided Collection) input signal is used as a valid identifier. Outlier removal is achieved through a combination of moving average filtering and box plotting, ensuring the quality of the data input to the prediction model. Identifying and removing invalid data from AGC exits or abnormal operating conditions prevents the prediction model from learning incorrect patterns. Moving average filtering smooths signal fluctuations and reduces random noise interference. Box plotting identifies outliers based on statistical characteristics, improving the robustness of data cleaning.

[0038] Figure 4 This is a schematic structural diagram of a device provided in an exemplary embodiment. Please refer to... Figure 4At the hardware level, the device includes a processor 402, an internal bus 404, a network interface 406, memory 408, and non-volatile memory 410, and may also include other hardware required for its functions. One or more embodiments of the present invention can be implemented in software, for example, the processor 402 reads the corresponding computer program from the non-volatile memory 410 into memory 408 and then runs it. Of course, in addition to software implementation, one or more embodiments of the present invention do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0039] Please refer to Figure 5 A dual-closed-loop optimized combined thermal and energy storage frequency modulation control device can be applied to, for example... Figure 5 The device shown, in order to implement the technical solution of the present invention, includes: The prediction unit 501 is used to predict the load command of the fire-storage combined system for future periods in response to the collected AGC command signal, and the load prediction model is constructed based on the fusion of variational mode decomposition and bidirectional long short-term memory network. The calculation unit 502 is used to input the predicted load command and the actual load command obtained from the forecast into a pre-constructed third-order frequency regulation demand calculation model containing proportional, integral and differential terms, and to calculate the frequency regulation power demand of the combined fire and storage system. The allocation unit 503 is used to perform optimal power allocation between the thermal power unit and the energy storage system based on the improved chaotic quantum particle swarm optimization algorithm, with the goal of minimizing the overall adjustment cost, frequency regulation deviation and energy storage life loss of the thermal power-storage combined system. The adjustment unit 504 is used to evaluate the health of the energy storage system in the combined fire and energy storage system based on the capacity decay mechanism, and adjust the optimization target weights or constraints in the chaotic quantum particle swarm optimization algorithm according to the health, so as to form a lifetime protection closed-loop control.

[0040] Optionally, the device further includes: The elimination unit 505 is used to use the collected AGC input signal as a valid identifier, and to use the moving average filtering and box plot method to eliminate outliers in order to generate model input data for input into the load prediction model.

[0041] Optionally, the prediction unit 501 is specifically used for: The model input data of the load prediction model is decomposed into multiple intrinsic mode function components according to the variational mode decomposition algorithm; Each intrinsic mode function component is independently predicted using the bidirectional long short-term memory network, and the prediction results of each component are reconstructed and superimposed to obtain the predicted load command.

[0042] Optionally, the expression for the third-order frequency modulation demand calculation model is: ; Among them, P req (t) represents the frequency modulation power requirement, P AGCact (t) represents the actual load command, P AGCpred (t+t) p (This refers to a load forecasting command.) , , For frequency modulation dynamic coefficients, Let be the frequency modulation deviation at time t. This is the gain coefficient for AGC instructions. To predict the weighting factor of load commands, The inertial time constant of the AGC command. For the predicted duration.

[0043] Optionally, the objective function of the chaotic quantum particle swarm optimization algorithm is expressed as follows: ; in, , , To optimize the target coefficient, its initial value is determined by training with historical data and adjusted based on the health feedback.

[0044] Furthermore, the allocation unit 503 is specifically used for: By incorporating the information from the load forecasting model, a rolling time-domain optimization strategy for combined thermal power and energy storage frequency regulation is generated, the expression of which is: ; Among them, the output of thermal power units With the output of the energy storage system Satisfy constraints , To predict duration, This represents the maximum ramp rate of the thermal power unit. , These represent the maximum and minimum values ​​for energy storage charging and discharging, respectively. To maximize the output of energy storage.

[0045] Optionally, the adjustment unit 504 is specifically used for: A dynamic assessment model for energy storage health based on capacity decay mechanism is constructed, and the health level is calculated based on the assessment model. The expression for the dynamic assessment model of energy storage health is as follows: ; in, This refers to the number of charge-discharge cycles. For capacity loss, This refers to the battery's nominal capacity.

[0046] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which can take the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email sending and receiving device, game console, tablet computer, wearable device, or any combination of these devices.

[0047] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0048] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0049] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0050] For any computer-readable medium (or computer-readable storage medium) as described above or otherwise, computer instructions may be stored thereon, which, when executed by a processor, implement one or more of the above embodiments, thereby realizing the technical solution of the present invention.

[0051] The present invention also proposes a computer program that, when executed by a processor, implements one or more of the embodiments described above, thereby realizing the technical solution of the present invention. This computer program may be specifically recorded on the above-described or other computer-readable media, and the present invention does not impose any limitations on this.

[0052] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0053] The foregoing has described specific embodiments of the invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0054] The terminology used in one or more embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in one or more embodiments of the invention and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0055] It should be understood that although the terms first, second, third, etc., may be used to describe various information in one or more embodiments of the present invention, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of one or more embodiments of the present invention, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0056] The above description is merely a preferred embodiment of one or more embodiments of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of the present invention should be included within the protection scope of one or more embodiments of the present invention.

Claims

1. A combined frequency regulation control method for thermal power and energy storage based on dual closed-loop optimization, characterized in that, include: In response to the acquired AGC command signal, the load command of the fire-storage combined system for future periods is predicted by the load prediction model, which is constructed based on the fusion of variational mode decomposition and bidirectional long short-term memory network. The predicted load command and the actual load command are input into a pre-constructed third-order frequency regulation demand calculation model that includes proportional, integral and derivative terms to calculate the frequency regulation power demand of the combined fire and energy storage system. Based on the improved chaotic quantum particle swarm optimization algorithm, with the goal of minimizing the overall adjustment cost, frequency regulation deviation and energy storage life loss of the thermal power-storage combined system, the output of the frequency regulation power demand is optimally allocated between the thermal power unit and the energy storage system. The health of the energy storage system in the combined fire and energy storage system is assessed based on the capacity decay mechanism, and the optimization target weights or constraints in the chaotic quantum particle swarm optimization algorithm are adjusted according to the health status to form a lifetime protection closed-loop control.

2. The method according to claim 1, characterized in that, The method further includes: The collected AGC input signals are used as valid identifiers, and outliers are removed using moving average filtering and box plot method to generate model input data for the load prediction model.

3. The method according to claim 1, characterized in that, The method of predicting the load command of the combined fire and energy storage system for future periods using a load forecasting model includes: The model input data of the load prediction model is decomposed into multiple intrinsic mode function components according to the variational mode decomposition algorithm; Each intrinsic mode function component is independently predicted using the bidirectional long short-term memory network, and the prediction results of each component are reconstructed and superimposed to obtain the predicted load command.

4. The method according to claim 1, characterized in that, The expression for the third-order frequency modulation demand calculation model is as follows: ； Among them, P req (t) represents the frequency modulation power requirement, P AGCact (t) represents the actual load command, P AGCpred (t+t) p (This refers to a load forecasting command.) , , For frequency modulation dynamic coefficients, Let be the frequency modulation deviation at time t. This is the gain coefficient for AGC instructions. To predict the weighting factor of load commands, The inertial time constant of the AGC command. For the predicted duration.

5. The method according to claim 1, characterized in that, The objective function of the chaotic quantum particle swarm optimization algorithm is expressed as follows: ； in, , , To optimize the target coefficient, its initial value is determined by training with historical data and adjusted based on the health feedback.

6. The method according to claim 5, characterized in that, The optimal allocation of power output between thermal power units and energy storage systems for the frequency regulation power demand includes: By incorporating the information from the load forecasting model, a rolling time-domain optimization strategy for combined thermal power and energy storage frequency regulation is generated, the expression of which is: ； Among them, the output of thermal power units With the output of the energy storage system Satisfy constraints , To predict duration, This represents the maximum ramp rate of the thermal power unit. , These represent the maximum and minimum values ​​for energy storage charging and discharging, respectively. To maximize the output of energy storage.

7. The method according to claim 1, characterized in that, The assessment of the health of the energy storage system in the combined thermal and energy storage system based on the capacity decay mechanism includes: A dynamic assessment model for energy storage health based on capacity decay mechanism is constructed, and the health level is calculated based on the assessment model. The expression for the dynamic assessment model of energy storage health is as follows: ； in, This refers to the number of charge-discharge cycles. For capacity loss, This refers to the battery's nominal capacity.

8. A combined thermal power and energy storage frequency regulation control device based on dual closed-loop optimization, characterized in that, The device includes: Prediction Unit: In response to the acquired AGC command signal, it predicts the load command of the fire-storage combined system for future periods through a load prediction model. The load prediction model is constructed based on the fusion of variational mode decomposition and bidirectional long short-term memory network. Calculation unit: Inputs the predicted load command and actual load command obtained from the forecast into a pre-constructed third-order frequency regulation demand calculation model containing proportional, integral and differential terms, and calculates the frequency regulation power demand of the combined fire and energy storage system; Allocation Unit: Based on the improved chaotic quantum particle swarm optimization algorithm, with the goal of minimizing the overall adjustment cost, frequency regulation deviation and energy storage life loss of the thermal power-storage combined system, the unit performs optimal power allocation between the thermal power unit and the energy storage system for the frequency regulation power demand. Adjustment Unit: Based on the capacity decay mechanism, assesses the health of the energy storage system in the combined fire and energy storage system, and adjusts the optimization target weights or constraints in the chaotic quantum particle swarm optimization algorithm according to the health status to form a lifetime protection closed-loop control.

9. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor implements the steps of the method as described in any one of claims 1-7 by running the executable instructions.

10. A computer-readable storage medium storing computer instructions thereon, characterized in that, When executed by the processor, this instruction implements the steps of the method as described in any one of claims 1-7.

Images