Adaptive optimization platform for peak regulation and frequency modulation of power grid

Abstract

The invention discloses a power grid peak regulation and frequency modulation adaptive optimization platform, and belongs to the field of power grid peak regulation and frequency modulation, and the platform comprises a peak period gap prediction module which is used for determining a plurality of peak period gap time zones and a plurality of peak period power generation gaps; the peak regulation and frequency modulation decision module is used for generating a plurality of peak regulation and frequency modulation strategies; the peak and frequency regulation loss evaluation module is used for obtaining a plurality of peak and frequency regulation loss coefficients; the peak regulation and frequency modulation loss judgment module is used for generating a plurality of peak regulation and frequency modulation loss judgment results; the peak and frequency modulation optimization module is used for generating a peak and frequency modulation optimization strategy set; and the peak and frequency regulation execution module is used for performing peak and frequency regulation on the power grid. The technical problem that in the prior art, power grid peak period power generation gaps are difficult to effectively cope with power grid peak period peak period power generation gaps, and consequently power grid operation is unstable is solved, and the technical effects of effectively coping with the power grid peak period gaps and guaranteeing stable power grid operation through self-adaptive optimization of power grid peak period frequency modulation are achieved.

Description

Technical Field

[0001] The present invention relates to the field of power grid peak shaving and frequency modulation, and particularly to an adaptive optimization platform for power grid peak shaving and frequency modulation. Background Art

[0002] The safe and stable operation of the power grid is the core requirement of the power system. Among them, power grid peak shaving and frequency modulation play a crucial role. However, in the prior art, it is often difficult for power grid peak shaving and frequency modulation to effectively cope with the power generation gap during the peak period of the power grid, resulting in many troubles in the operation of the power grid. When the power grid load increases sharply and the power generation is insufficient to meet the demand, a power generation gap occurs during the peak period. If the peak shaving and frequency modulation are not timely and in place, the power grid frequency and voltage may fluctuate greatly, and in severe cases, even large-scale power outages may occur, causing huge losses. Traditional power grid peak shaving and frequency modulation mainly rely on the experience of power grid dispatchers and are carried out according to pre-set strategies. This method is difficult to quickly respond to the real-time changes during the peak period of the power grid, and the accuracy and efficiency of peak shaving and frequency modulation are relatively low. Moreover, different power generation gap situations during the peak period often require different peak shaving and frequency modulation strategies, and the existing fixed strategies are difficult to respond flexibly. Therefore, there is a technical problem in the prior art that power grid peak shaving and frequency modulation are difficult to effectively cope with the power generation gap during the peak period of the power grid, resulting in unstable operation of the power grid. Summary of the Invention

[0003] The present application provides an adaptive optimization platform for power grid peak shaving and frequency modulation, aiming to solve the technical problem in the prior art that power grid peak shaving and frequency modulation are difficult to effectively cope with the power generation gap during the peak period of the power grid, resulting in unstable operation of the power grid.

[0004] The adaptive optimization platform for power grid peak shaving and frequency modulation disclosed in the present application includes: a peak period gap prediction module for predicting the peak period gap of the first power generation side of the power grid according to the future time zone window, and determining a plurality of peak period gap time zones and a plurality of peak period power generation gaps, wherein the first power generation side is in grid-connected operation, and the second power generation side of the power grid is in island operation; a peak shaving and frequency modulation decision-making module for making peak shaving and frequency modulation decisions on the power grid based on a plurality of peak period gap time zones and a plurality of peak period power generation gaps according to the second power generation side, and generating a plurality of peak shaving and frequency modulation strategies; a peak shaving and frequency modulation loss evaluation module for predicting and evaluating the losses of a plurality of peak shaving and frequency modulation strategies to obtain a plurality of peak shaving and frequency modulation loss coefficients; a peak shaving and frequency modulation loss judgment module for judging whether a plurality of peak shaving and frequency modulation loss coefficients are less than the peak shaving and frequency modulation loss threshold, and generating a plurality of peak shaving and frequency modulation loss judgment results; a peak shaving and frequency modulation optimization module for optimizing and adjusting a plurality of peak shaving and frequency modulation strategies based on a plurality of peak shaving and frequency modulation loss judgment results to generate a peak shaving and frequency modulation optimization strategy set; a peak shaving and frequency modulation execution module for performing peak shaving and frequency modulation on the power grid based on a plurality of peak period gap time zones according to the second power generation side and the peak shaving and frequency modulation optimization strategy set.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages: By using a peak period gap prediction module, according to the future time zone window, the peak period gap of the first power generation side of the power grid in the grid-connected operation state is predicted to determine multiple peak period gap time zones and corresponding peak period power generation gaps, providing a basis for subsequent peak shaving and frequency modulation decision-making; through the peak shaving and frequency modulation decision-making module, based on the predicted multiple peak period gap time zones and peak period power generation gaps, and considering the operating conditions of the second power generation side of the power grid in the island operation state at the same time, peak shaving and frequency modulation decision-making is carried out to generate multiple alternative peak shaving and frequency modulation strategies. By formulating targeted peak shaving and frequency modulation strategies according to different peak period gap situations, the flexibility of the power grid's peak shaving and frequency modulation is improved; the peak shaving and frequency modulation loss evaluation module is used to predict and evaluate the losses of multiple alternative peak shaving and frequency modulation strategies to obtain the peak shaving and frequency modulation loss coefficients corresponding to each strategy, quantitatively evaluating the economy and rationality of each peak shaving and frequency modulation strategy, and providing a reference for the optimal selection of strategies; the peak shaving and frequency modulation loss judgment module is used to compare the peak shaving and frequency modulation loss coefficients of each strategy with a preset loss threshold to determine whether the requirements are met, output the corresponding peak shaving and frequency modulation loss judgment results, and screen out the strategies with lower losses. Through the peak shaving and frequency modulation optimization module, based on the peak shaving and frequency modulation loss judgment results, multiple alternative peak shaving and frequency modulation strategies are optimized and combined to generate a set of peak shaving and frequency modulation optimization strategies with the best comprehensive performance. On the premise of taking into account the safe and stable operation of the power grid, the peak shaving and frequency modulation strategy combination with the largest overall economic benefit is selected; when the predicted peak period gap is about to arrive, the peak shaving and frequency modulation execution module, based on the optimized peak shaving and frequency modulation optimization strategy set, controls the second power generation side to perform real-time peak shaving and frequency modulation on the power grid, dynamically matching the demand changes of the power grid, and effectively alleviating the peak period power generation gap of the power grid. The technical solution solves the technical problem that the power grid's peak shaving and frequency modulation in the prior art is difficult to effectively cope with the peak period power generation gap of the power grid, resulting in unstable operation of the power grid, and achieves the technical effect of effectively coping with the peak period gap of the power grid and ensuring the stable operation of the power grid through the adaptive optimization of the power grid's peak shaving and frequency modulation.

[0006] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specific embodiments of this application are specifically given. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 FIG. 1 is a schematic structural diagram of an adaptive optimization platform for power grid peak shaving and frequency modulation provided by an embodiment of this application; Figure 2 FIG. 2 is a schematic flow diagram of generating multiple peak shaving and frequency modulation strategies in the adaptive optimization platform for power grid peak shaving and frequency modulation provided by an embodiment of this application.

[0008] Explanation of the accompanying drawings: peak period gap prediction module 11, peak-shaving and frequency regulation decision module 12, peak-shaving and frequency regulation loss evaluation module 13, peak-shaving and frequency regulation loss judgment module 14, peak-shaving and frequency regulation optimization module 15, peak-shaving and frequency regulation execution module 16. DETAILED DESCRIPTION

[0009] The overall idea of the technical solution provided by this application is as follows: The embodiment of the present application provides an adaptive optimization platform for peak-shaving and frequency regulation of power grids. First, the peak-period gap prediction module is used to predict the peak-period power generation gap that may occur in the future time zone window of the power grid, and to identify and quantify the risk of power supply and demand imbalance faced by the first power generation side of the power grid in advance. Then, the peak-shaving and frequency regulation decision module automatically generates multiple alternative peak-shaving and frequency regulation strategies based on the prediction results and the actual operating status of the second power generation side of the power grid, and evaluates each strategy through the peak-shaving and frequency regulation loss evaluation module, and uses the peak-shaving and frequency regulation loss judgment module to screen out strategies that meet the loss threshold requirements. Next, the peak-shaving and frequency regulation optimization module searches and determines the peak-shaving and frequency regulation optimization strategy set with the best comprehensive performance on the premise of meeting the constraints of safe and stable operation of the power grid. Afterwards, when the predicted peak-period gap is about to arrive, the peak-shaving and frequency regulation execution module controls the second power generation side of the power grid to perform real-time peak-shaving and frequency regulation on the power grid based on the peak-shaving and frequency regulation optimization strategy set, dynamically matching the demand changes of the power grid, thereby effectively alleviating the peak-period power generation gap problem on the first power generation side of the power grid.

[0010] After introducing the basic principles of the present application, the non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the drawings in the specification.

[0011] like Figure 1 As shown, the embodiment of the present application provides a power grid peak load and frequency regulation adaptive optimization platform, which includes: The peak gap prediction module 11 is used to predict the peak gap of the first power generation side of the power grid according to the future time zone window, and determine multiple peak gap time zones and multiple peak power generation gaps, wherein the first power generation side is in a grid-connected operation state and the second power generation side of the power grid is in an island operation state.

[0012] Specifically, the peak gap prediction module 11 is used to predict and analyze the peak gap of the first power generation side in the grid that is in a grid-connected operation state according to a time zone window in the future.

[0013] First, the peak period gap prediction module 11 obtains time zone window information within a certain future time range as the future time zone window. The future time zone window is preset according to the operating characteristics of the power grid and the load change law, or can be dynamically adjusted according to real-time data. Then, based on this future time zone window, the peak period gap prediction module 11 analyzes and compares the power generation capacity and load demand of the first power generation side in the grid-connected operation state. By calculating the difference between the power generation power and the load power of the first power generation side, the time intervals during which the power grid may have a power supply gap within the future time zone window are obtained, which are multiple peak period gap time zones. At the same time, the difference between the power generation power and the load power of the first power generation side in each peak period gap time zone is determined, which is multiple peak period power generation gaps. Among them, there are two power generation sides with different operating states, including the first power generation side and the second power generation side; the first power generation side is grid-connected to the power grid, and its power generation power can be directly transmitted to the power grid; while the second power generation side is in an island operation state, and its power generation power cannot be directly transmitted to the power grid, but can provide certain auxiliary support during the peak shaving and frequency modulation of the power grid.

[0014] Through the peak period gap prediction module 11, it is possible to predict the supply-demand imbalance situation of the power grid in the future for a period of time, laying a foundation for optimizing dispatching and scientific peak shaving and frequency modulation, and improving the operating efficiency and power supply reliability of the power grid.

[0015] The peak shaving and frequency modulation decision-making module 12 is used to make peak shaving and frequency modulation decisions for the power grid based on the multiple peak period gap time zones and the multiple peak period power generation gaps, and generate multiple peak shaving and frequency modulation strategies.

[0016] Specifically, first, the peak shaving and frequency modulation decision-making module 12 receives the multiple peak period gap time zones and multiple peak period power generation gaps output by the peak period gap prediction module 11. These data reflect the power supply gap situations that the power grid may face in different time intervals in the future. Subsequently, the peak shaving and frequency modulation decision-making module 12 comprehensively considers the actual operating state and peak shaving and frequency modulation capabilities of the second power generation side. Although the second power generation side is in an island operation state, its power generation resources can provide certain support for the peak shaving and frequency modulation of the power grid. The peak shaving and frequency modulation decision-making module 12 judges to what extent it can participate in the peak shaving and frequency modulation process of the power grid by analyzing parameters such as the power generation capacity, response speed, and adjustment accuracy of the second power generation side. On the basis of mastering the peak period gap information and the state of the second power generation side, the peak shaving and frequency modulation decision-making module 12 begins to formulate corresponding peak shaving and frequency modulation strategies for each peak period gap time zone, in combination with the magnitude of the peak period power generation gap. The content of the peak shaving and frequency modulation strategy includes the output adjustment plan, adjustment time series, and adjustment power distribution of the second power generation side. Each peak period gap time zone corresponds to alternative peak shaving and frequency modulation strategies, and the peak shaving and frequency modulation decision-making module 12 generates multiple peak shaving and frequency modulation strategies for subsequent evaluation and optimization.

[0017] Through the strategy generation of the peak shaving and frequency modulation decision-making module 12, multiple peak shaving and frequency modulation strategies are obtained, laying a foundation for subsequent strategy optimization and execution, enabling the power grid to quickly make corresponding peak shaving and frequency modulation responses when facing peak period gaps, and ensuring the safe and stable operation of the power system.

[0018] The peak shaving and frequency modulation loss evaluation module 13 is used to predict and evaluate the losses of the multiple peak shaving and frequency modulation strategies, and obtain multiple peak shaving and frequency modulation loss coefficients.

[0019] Specifically, after receiving the multiple peak shaving and frequency modulation strategies generated by the peak shaving and frequency modulation decision-making module 12, the peak shaving and frequency modulation loss evaluation module 13 conducts loss prediction and evaluation on each peak shaving and frequency modulation strategy. For example, the peak shaving and frequency modulation loss evaluation module 13 considers from four aspects: power quality loss, power generation resource loss, equipment wear loss, and economic benefit loss. For power quality loss, the peak shaving and frequency modulation loss evaluation module 13 analyzes the changes in power quality indicators such as voltage and frequency of the power grid after the implementation of the peak shaving and frequency modulation strategy, predicts possible power supply quality and stability problems, and gives corresponding loss evaluation results. For power generation resource loss, the peak shaving and frequency modulation loss evaluation module 13 analyzes the impact of the adjustment of power generation output on the utilization efficiency of power generation resources when the second power generation side executes the peak shaving and frequency modulation strategy, and estimates the corresponding energy loss data. For equipment wear loss, the peak shaving and frequency modulation loss evaluation module 13 evaluates the accelerating effect of frequent output adjustment operations on the wear and aging of the power generation equipment on the second power generation side during the implementation of the peak shaving and frequency modulation strategy, and predicts the impact on the service life of the equipment and related maintenance and replacement costs. For economic benefit loss, the peak shaving and frequency modulation loss evaluation module 13 analyzes the changes in the operating costs and revenues of the power grid and the second power generation side after the implementation of the peak shaving and frequency modulation strategy, and evaluates the economic impact of the strategy. After completing the loss evaluation in the above four aspects, the peak shaving and frequency modulation loss evaluation module 13 obtains four corresponding loss index data for each peak shaving and frequency modulation strategy. Next, the peak shaving and frequency modulation loss evaluation module 13 performs weighted processing on these four loss indicators. Specifically, according to the influence degree of each loss indicator on the peak shaving and frequency modulation effect of the power grid, different weight coefficients are given, and then each loss indicator is multiplied by its weight coefficient and summed to obtain a comprehensive peak shaving and frequency modulation loss coefficient, which is used to reflect the overall loss level of the peak shaving and frequency modulation strategy.

[0020] Through the above process, the peak shaving and frequency modulation loss evaluation module 13 associates each peak shaving and frequency modulation strategy with a peak shaving and frequency modulation loss coefficient, obtains multiple peak shaving and frequency modulation loss coefficients, and forms a mapping relationship between the peak shaving and frequency modulation strategy and its peak shaving and frequency modulation loss coefficient, laying a foundation for subsequent peak shaving and frequency modulation strategy screening and optimization.

[0021] The peak shaving and frequency modulation loss judgment module 14 is used to judge whether the multiple peak shaving and frequency modulation loss coefficients are less than the peak shaving and frequency modulation loss threshold, and generate multiple peak shaving and frequency modulation loss judgment results.

[0022] Specifically, the peak shaving and frequency modulation loss judgment module 14 compares the multiple peak shaving and frequency modulation loss coefficients calculated by the peak shaving and frequency modulation loss evaluation module 13 with the preset peak shaving and frequency modulation loss threshold, and generates corresponding peak shaving and frequency modulation loss judgment results according to the comparison results.

[0023] First, the peak shaving and frequency modulation loss judgment module 14 receives the multiple peak shaving and frequency modulation loss coefficients transmitted by the peak shaving and frequency modulation loss evaluation module 13. These peak shaving and frequency modulation loss coefficients correspond one by one to the respective peak shaving and frequency modulation strategies generated by the peak shaving and frequency modulation decision module 12, reflecting the estimated loss levels of each strategy. Then, the peak shaving and frequency modulation loss judgment module 14 reads the preset peak shaving and frequency modulation loss threshold from the storage unit. This threshold represents the upper limit of the acceptable loss of the peak shaving and frequency modulation strategy, and is set according to the actual operation requirements of the power grid and empirical data. Next, the peak shaving and frequency modulation loss judgment module 14 compares the magnitude of each peak shaving and frequency modulation loss coefficient with the peak shaving and frequency modulation loss threshold. For a certain peak shaving and frequency modulation loss coefficient, if its value is less than the peak shaving and frequency modulation loss threshold, it indicates that the estimated loss level of the peak shaving and frequency modulation strategy corresponding to this peak shaving and frequency modulation loss coefficient is within the acceptable range. At this time, the peak shaving and frequency modulation loss judgment module 14 generates a judgment result of "peak shaving and frequency modulation loss acceptable". On the contrary, if the value of a certain peak shaving and frequency modulation loss coefficient is greater than or equal to the peak shaving and frequency modulation loss threshold, it means that the estimated loss level of the peak shaving and frequency modulation strategy corresponding to this peak shaving and frequency modulation loss coefficient exceeds the acceptable range. At this time, the peak shaving and frequency modulation loss judgment module 14 generates a judgment result of "peak shaving and frequency modulation loss unacceptable".

[0024] Through the peak shaving and frequency modulation loss judgment module 14, threshold comparison is performed on each peak shaving and frequency modulation loss coefficient to obtain the peak shaving and frequency modulation loss judgment results corresponding to each peak shaving and frequency modulation strategy, providing a decision basis for the subsequent optimization adjustment of the peak shaving and frequency modulation strategies.

[0025] The peak shaving and frequency modulation optimization module 15 is used to perform optimization adjustment on the multiple peak shaving and frequency modulation strategies based on the multiple peak shaving and frequency modulation loss judgment results, and generate a peak shaving and frequency modulation optimization strategy set.

[0026] Specifically, first, the peak shaving and frequency modulation optimization module 15 receives the peak shaving and frequency modulation loss judgment results corresponding to each peak shaving and frequency modulation strategy transmitted by the peak shaving and frequency modulation loss judgment module 14. For the strategies with the peak shaving and frequency modulation loss judgment result of "peak shaving and frequency modulation loss acceptable", they are directly incorporated into the peak shaving and frequency modulation optimization strategy set; for the strategies with the peak shaving and frequency modulation loss judgment result of "peak shaving and frequency modulation loss unacceptable", they enter the optimization adjustment link. In the optimization adjustment link, the peak shaving and frequency modulation optimization module 15 analyzes the main reasons for the excessively high loss of the peak shaving and frequency modulation strategy, and focuses on the influencing factors in aspects such as power quality, utilization of power generation resources, equipment wear, and economic benefits. The adjustable parameters in the strategy are selectively selected, such as the output adjustment amplitude, rate, and time of the second power generation side, and are locally optimized to reduce the overall loss of the strategy. The adjusted strategy will be evaluated again by the peak shaving and frequency modulation loss evaluation module 13 and the peak shaving and frequency modulation loss judgment module 14. If the peak shaving and frequency modulation loss judgment result of the strategy becomes "peak shaving and frequency modulation loss acceptable", it is incorporated into the peak shaving and frequency modulation optimization strategy set; if it is still "peak shaving and frequency modulation loss unacceptable", iterative optimization continues until an acceptable strategy is obtained or the iteration count upper limit is reached.

[0027] Through the optimization adjustment process, the peak shaving and frequency modulation optimization module 15 continuously improves the original strategy. While ensuring the safe and stable operation of the power grid, it minimizes various cost losses in the implementation of the strategy, achieving an optimal balance between peak shaving and frequency modulation effects and economy. After that, the peak shaving and frequency modulation optimization module 15 summarizes all the acceptable peak shaving and frequency modulation strategies after optimization to form a peak shaving and frequency modulation optimization strategy set, providing a high-quality optimal solution for the implementation of power grid peak shaving and frequency modulation, helping to improve the flexibility and overall efficiency of power grid peak shaving and frequency modulation, and making the power grid dispatching operation more intelligent and optimal.

[0028] The peak shaving and frequency modulation execution module 16 is used to perform peak shaving and frequency modulation on the power grid based on the multiple peak period gap time zones, according to the second power generation side and the peak shaving and frequency modulation optimization strategy set.

[0029] Specifically, first, the peak shaving and frequency modulation execution module 16 receives multiple peak period gap time zones identified by the peak period gap prediction module 11. These time zones are the time periods when the power grid is predicted to have a power supply gap. At the same time, the peak shaving and frequency modulation execution module 16 receives the peak shaving and frequency modulation optimization strategy set generated by the peak shaving and frequency modulation optimization module 15. This strategy set contains a series of optimized and feasible peak shaving and frequency modulation strategies. Then, the peak shaving and frequency modulation execution module 16, according to the actual operating state of the power grid, monitors in real time whether the current moment is within a certain peak period gap time zone. Once it is detected that the current moment enters the peak period gap time zone, the peak shaving and frequency modulation execution module 16 selects the corresponding peak shaving and frequency modulation strategy from the peak shaving and frequency modulation optimization strategy set, and issues the peak shaving and frequency modulation task instructions specified in this strategy to the second power generation side. After receiving the peak shaving and frequency modulation task instructions, the second power generation side adjusts its own power generation output in a timely manner according to the instruction requirements, increases the power supply support to the power grid, and makes up for the power supply shortage within the peak period gap time zone. After the peak shaving and frequency modulation task within the previous peak period gap time zone is completed, the peak shaving and frequency modulation execution module 16 continues to monitor the subsequent peak period gap time zones, and selects the corresponding peak shaving and frequency modulation strategies for execution according to the specific conditions of each time zone until the peak shaving and frequency modulation tasks within all peak period gap time zones are completed.

[0030] Through the peak shaving and frequency modulation execution module 16, according to the real-time operating state of the power grid and the peak shaving and frequency modulation requirements, the corresponding optimal peak shaving and frequency modulation strategy is selected, and through the coordinated cooperation with the second power generation side, the peak shaving and frequency modulation task of the power grid is efficiently completed, ensuring the safe and stable operation of the power grid.

[0031] Furthermore, the embodiment of the present application further includes: According to the future time zone window, the load power of the power consumption side of the power grid is predicted, and a predicted load power curve is established; according to the future time zone window, the power generation power of the first power generation side is predicted, and a predicted power generation power curve is established; based on the predicted load power curve, the peak period gap characteristics of the predicted power generation power curve are identified, and the multiple peak period gap time zones and the multiple peak period power generation gaps are generated.

[0032] In a feasible implementation, first, the peak period gap prediction module 11 obtains the time zone window information of the power grid for a period of time in the future as the future time zone window. The future time zone window is a preset future time interval with a fixed length, such as the next 24 hours, the next 7 days, etc. The selection of the time zone window needs to comprehensively consider factors such as the load characteristics of the power grid and the regulation capabilities of peak shaving and frequency modulation resources to achieve the optimal prediction effect. After determining the future time zone window, the peak period gap prediction module 11 respectively performs power predictions on the power consumption side and the first power generation side of the power grid. For the power consumption side, historical load data of the power consumption side is collected, such as power consumption at different times, load curves, etc., and then a load prediction algorithm is used to predict the load power within the future time zone window. For example, time series analysis method, artificial neural network method, etc. By mining and analyzing historical data, the rules and trends of load changes are identified and extrapolated to the future time zone window to obtain the predicted load power curve. For the first power generation side, the peak period gap prediction module 11 collects the historical operation data of the generator sets, such as power generation power, output regulation records, etc., and comprehensively considers static parameters such as the type, capacity, and efficiency of the units, as well as dynamic influencing factors such as weather conditions and electricity price policies, and uses a prediction algorithm to obtain the predicted power generation power curve of the first power generation side within the future time zone window.

[0033] After obtaining the predicted load power curve and the predicted power generation power curve, the peak period gap prediction module 11 overlaps and compares the two curves. By calculating the power difference between the two curves at each time point, it is judged which moments have the risk of power supply gap, that is, the predicted load power is greater than the predicted power generation power. The multiple moments with continuous power supply gap risks are divided into a peak period gap time zone, and the power gap values at each moment in this time zone are accumulated as the peak period power generation gap of this time zone.

[0034] Through the analysis of the entire future time zone window, the peak period gap prediction module 11 identifies multiple peak period gap time zones and corresponding peak period power generation gaps, forming a complete power supply gap prediction result of the power grid, so that the power grid peak shaving and frequency modulation can take targeted control measures in advance, thus ensuring the safe and stable operation of the power grid to the greatest extent.

[0035] Furthermore, as Figure 2 shown, the embodiments of the present application further include: Collect the power generation resource parameters of the second power generation side to obtain a peaking and frequency regulation resource set; according to the multiple peak period gap time zones and the multiple peak period power generation gaps, extract the a-th peak period gap time zone and the a-th peak period power generation gap, where a is a positive integer; perform fusion learning based on P peaking and frequency regulation decision learning models to build a peaking and frequency regulation decision maker, and embed the peaking and frequency regulation decision maker into the peaking and frequency regulation decision module, where P is a positive integer greater than 1; input the peaking and frequency regulation resource set, the a-th peak period gap time zone, and the a-th peak period power generation gap into the peaking and frequency regulation decision maker to obtain the a-th peaking and frequency regulation strategy, and add the a-th peaking and frequency regulation strategy to the multiple peaking and frequency regulation strategies.

[0036] In a preferred embodiment, first, the peaking and frequency regulation decision module 12 collects the power generation resource parameters of the second power generation side, including static and dynamic index data such as the type, capacity, regulation ability, response speed, upper and lower output limits of the generator sets owned by the second power generation side. These parameter data comprehensively describe the power generation characteristics and peaking and frequency regulation capabilities of the second power generation side, forming a complete peaking and frequency regulation resource set. The peaking and frequency regulation resource set is an important basis for formulating peaking and frequency regulation strategies, and determines to what extent the second power generation side can provide support for the peaking and frequency regulation of the power grid. Secondly, the peaking and frequency regulation decision module 12 receives the data of multiple peak period gap time zones and multiple peak period power generation gaps transmitted by the peak period gap prediction module 11. For each peak period gap time zone, the peaking and frequency regulation decision module 12 extracts the corresponding time zone and gap data therefrom to form an independent decision-making task. Among them, the variable a is used to number the multiple peak period gaps. The time zone corresponding to the a-th peak period gap is the a-th peak period gap time zone, and the corresponding power generation gap is the a-th peak period power generation gap.

[0037] Next, the peak shaving and frequency regulation decision-making module 12 uses P peak shaving and frequency regulation decision-making learning models to train and learn the historical peak shaving and frequency regulation data. Among them, the peak shaving and frequency regulation decision-making learning models adopt common machine learning algorithms such as neural networks and decision trees. By mining and analyzing the historical data, the internal laws and experiences for formulating peak shaving and frequency regulation strategies are summarized. Then, fusion learning is carried out using P peak shaving and frequency regulation decision-making learning models to integrate the advantages of different models and improve the accuracy and generalization ability of strategy decision-making. The peak shaving and frequency regulation decision-making models are fused and learned to obtain a peak shaving and frequency regulation decision-making device. The peak shaving and frequency regulation decision-making device can generate corresponding peak shaving and frequency regulation strategies according to the input peak shaving and frequency regulation resource status and peak period gap conditions. After the peak shaving and frequency regulation decision-making device is built, it will be embedded in the peak shaving and frequency regulation decision-making module 12 to become its core functional component. After that, for each peak period gap, the peak shaving and frequency regulation decision-making module 12 inputs the corresponding peak shaving and frequency regulation resource set, the a-th peak period gap time zone, and the a-th peak period power generation gap into the peak shaving and frequency regulation decision-making device. After the analysis and calculation of the peak shaving and frequency regulation decision-making device, the peak shaving and frequency regulation strategy for the a-th peak period gap can be obtained, denoted as the a-th peak shaving and frequency regulation strategy. This strategy will include several specific control measures and implementation plans, such as the output adjustment curve of the second power generation side and the standby capacity utilization plan. For each peak shaving and frequency regulation strategy obtained for a peak period gap, the peak shaving and frequency regulation decision-making module 12 adds it to a strategy set to form multiple peak shaving and frequency regulation strategies.

[0038] Through the peak shaving and frequency regulation decision-making module 12, the peak shaving and frequency regulation resources of the second power generation side are fully utilized. For the predicted peak period gap, a feasible peak shaving and frequency regulation strategy is given. While ensuring the safe and stable operation of the power grid, the peak shaving and frequency regulation benefits of the second power generation side are maximized, so that the power grid's supply-demand balance can be maintained in a timely and effective manner.

[0039] Furthermore, the embodiments of the present application further include: Based on the power grid, peak shaving and frequency regulation decision-making record collection is carried out to obtain peak shaving and frequency regulation resource set records, peak period gap time zone records, peak period power generation gap records, and peak shaving and frequency regulation strategy records; using the peak shaving and frequency regulation resource set records, the peak period gap time zone records, and the peak period power generation gap records as input information, and the peak shaving and frequency regulation strategy records as output information, supervised training is respectively carried out on the P peak shaving and frequency regulation decision-making learning models to obtain P frequency regulation decision loss coefficients; it is judged whether the P frequency regulation decision loss coefficients are less than the peak shaving and frequency regulation decision loss threshold; if the P frequency regulation decision loss coefficients are less than the peak shaving and frequency regulation decision loss threshold, P peak shaving and frequency regulation decision-making units are generated; according to the P peak shaving and frequency regulation decision-making units, fusion training is carried out to generate the peak shaving and frequency regulation decision-making device.

[0040] In a preferred embodiment, when building the peak shaving and frequency regulation decision maker, the peak shaving and frequency regulation decision module 12 adopts a fusion learning method based on P peak shaving and frequency regulation decision learning models to improve the performance and generalization ability of the decision maker.

[0041] First, analyze and sort out the historical peak shaving and frequency regulation decision records of the power grid to obtain the data records related to peak shaving and frequency regulation decisions, including the peak shaving and frequency regulation resource set records, peak period gap time zone records, peak period power generation gap records, and peak shaving and frequency regulation strategy records. Among them, the peak shaving and frequency regulation resource set records reflect the available peak shaving and frequency regulation resource status of the second power generation side at different times; the peak period gap time zone records and peak period power generation gap records reflect various power supply gap situations that have occurred in the power grid in history; the peak shaving and frequency regulation strategy records record the actual control strategies adopted by the power grid for these power supply gaps and their implementation effects. These historical data provide valuable samples for the training of the peak shaving and frequency regulation decision learning model. After obtaining the historical peak shaving and frequency regulation decision data, use P peak shaving and frequency regulation decision learning models to learn and train this data. Each peak shaving and frequency regulation decision learning model takes the peak shaving and frequency regulation resource set records, peak period gap time zone records, and peak period power generation gap records as inputs, and the peak shaving and frequency regulation strategy records as the expected outputs, and summarizes the experience rules of historical peak shaving and frequency regulation decisions through supervised learning. Among them, the peak shaving and frequency regulation decision learning model can adopt common machine learning algorithms such as neural networks and decision trees, and by adjusting the internal parameters of the model, continuously fit and optimize the mapping relationship between the decision input and the decision output.

[0042] During the training process, each peak shaving and frequency regulation decision learning model will calculate the frequency regulation decision loss coefficient, which measures the deviation between the decision-making strategy output by the model and the actual decision-making strategy in the historical records. The smaller the frequency regulation decision loss coefficient, the closer the decision-making rule learned by the model is to the actual situation, and the better the decision-making effect. By evaluating the frequency regulation decision loss coefficients of all learning models, the model with the optimal decision-making performance is selected. Specifically, a peak shaving and frequency regulation decision loss threshold is set to judge the frequency regulation decision loss coefficients of all peak shaving and frequency regulation decision learning models. If the frequency regulation decision loss coefficient of a certain model is less than the threshold, it is considered that the model has learned a relatively accurate and effective decision-making rule, and it is determined as a qualified peak shaving and frequency regulation decision unit. If the frequency regulation decision loss coefficient of a certain model is greater than or equal to the threshold, training continues until its frequency regulation decision loss coefficient is less than the threshold. After the training is completed, P peak shaving and frequency regulation decision units are obtained, and then the P peak shaving and frequency regulation decision units are fused and trained to generate a peak shaving and frequency regulation decision maker with stronger comprehensive performance. Among them, weighted average, voting and other strategies can be used for the fusion training to combine the output results of the P peak shaving and frequency regulation decision units to obtain the final decision result. Since the fusion training makes full use of the collective output of the P peak shaving and frequency regulation decision units, it can effectively reduce the limitations and uncertainties of a single model, making the generated peak shaving and frequency regulation decision maker have higher decision-making accuracy and stability.

[0043] By performing fusion learning based on P peak shaving and frequency regulation decision learning models, a peak shaving and frequency regulation decision maker with excellent performance is obtained, which brings together the advantages of various machine learning algorithms, can automatically extract peak shaving and frequency regulation decision-making knowledge from a large amount of historical operation data, and make quick and accurate judgments and strategy generation for new decision-making tasks.

[0044] Furthermore, the embodiment of the present application further includes: The peak shaving and frequency regulation loss evaluation module includes a digital twin unit, a peak shaving and frequency regulation loss evaluation unit, and a peak shaving and frequency regulation loss initial weight condition; based on the digital twin unit, the power grid is simulated for peak shaving and frequency regulation according to the a-th peak shaving and frequency regulation strategy to obtain the a-th peak shaving and frequency regulation simulation data set; the a-th peak shaving and frequency regulation simulation data set is input into the peak shaving and frequency regulation loss evaluation unit to obtain the a-th peak shaving and frequency regulation loss evaluation result; based on the a-th peak shaving and frequency regulation loss evaluation result, a proportion calculation is performed to obtain the a-th peak shaving and frequency regulation loss improvement weight condition; based on the a-th peak shaving and frequency regulation loss improvement weight condition, the weight configuration of the peak shaving and frequency regulation loss initial weight condition is optimized to generate the a-th peak shaving and frequency regulation loss weight condition; according to the a-th peak shaving and frequency regulation loss weight condition, a weighted calculation is performed on the a-th peak shaving and frequency regulation loss evaluation result to generate the a-th peak shaving and frequency regulation loss coefficient, and the a-th peak shaving and frequency regulation loss coefficient is added to the multiple peak shaving and frequency regulation loss coefficients.

[0045] In a preferred embodiment, the peaking and frequency modulation loss evaluation module 13 includes a digital twin unit, a peaking and frequency modulation loss evaluation unit, and an initial weight condition for peaking and frequency modulation loss. Among them, the digital twin unit is a virtual simulation system built based on the power grid physical model and historical operation data, which can dynamically simulate the real-time operation state of the power grid. The peaking and frequency modulation loss evaluation unit is built-in with a series of quantitative indicators and calculation models for evaluating the losses of peaking and frequency modulation strategies. The initial weight condition for peaking and frequency modulation loss is a set of preset weight parameters used to balance the importance of different loss indicators in the evaluation.

[0046] During the evaluation process, the peaking and frequency modulation loss evaluation module 13 first uses the digital twin unit to simulate and analyze the operation state of the power grid according to the a-th peaking and frequency modulation strategy. By virtually executing this strategy, the digital twin unit can generate a simulated data set of the a-th peaking and frequency modulation that highly matches the actual operation, which contains the expected changes in various operation indicators of the power grid after executing this strategy. Then, the peaking and frequency modulation loss evaluation module 13 inputs the simulated data set of the a-th peaking and frequency modulation into the peaking and frequency modulation loss evaluation unit. The peaking and frequency modulation loss evaluation unit evaluates the execution effect of this strategy from multiple perspectives according to the built-in quantitative indicators and calculation models of the peaking and frequency modulation strategy loss, and obtains a comprehensive evaluation result of the a-th peaking and frequency modulation loss, which contains multiple loss indicator values, such as power quality loss, power generation cost loss, equipment loss, etc. Each indicator reflects the impact degree of the strategy execution on a certain aspect of the power grid performance.

[0047] In order to reasonably determine the weights of various loss indicators in the overall evaluation, the peaking and frequency modulation loss evaluation module 13 first calculates the proportion of each loss indicator value in the total loss according to the evaluation result of the a-th peaking and frequency modulation loss, and obtains the a-th peaking and frequency modulation loss promotion weight condition reflecting the importance of each indicator. Then, the peaking and frequency modulation loss evaluation module 13 will adaptively adjust the preset initial weight condition for peaking and frequency modulation loss by using the a-th peaking and frequency modulation loss promotion weight condition to obtain a more reasonable a-th peaking and frequency modulation loss weight condition. This condition comprehensively considers the emphasis of each indicator under different power grid states and can objectively reflect the actual loss level of the peaking and frequency modulation strategy. After that, the peaking and frequency modulation loss evaluation module 13 applies the a-th peaking and frequency modulation loss weight condition to the evaluation result of the a-th peaking and frequency modulation loss, and calculates the comprehensive a-th peaking and frequency modulation loss coefficient by the method of weighted summation, which quantitatively describes the overall loss level of the a-th peaking and frequency modulation strategy. For each obtained peaking and frequency modulation loss coefficient of a strategy, the peaking and frequency modulation loss evaluation module 13 adds it to a loss coefficient set to form multiple peaking and frequency modulation loss coefficients.

[0048] Through the loss assessment process optimized by adaptive weights, the peaking and frequency modulation loss evaluation module 13 can make full use of the power grid digital twin technology to efficiently and accurately predict the actual effects of each peaking and frequency modulation strategy in a virtual environment, and dynamically adjust the weights of the loss assessment indicators according to the real-time state of the power grid, making the assessment results more objective and fair, and providing a reliable decision-making reference for subsequent strategy optimization.

[0049] Furthermore, the embodiments of the present application further include: Perform data cleaning on the a-th peaking and frequency modulation simulation data set to establish the a-th peaking and frequency modulation prediction matrix; activate the power quality loss assessment model, the power generation resource loss assessment model, and the power generation efficiency loss assessment model in the peaking and frequency modulation loss assessment unit; input the a-th peaking and frequency modulation prediction matrix into the power quality loss assessment model to obtain the a-th power quality loss assessment coefficient; input the a-th peaking and frequency modulation prediction matrix into the power generation resource loss assessment model to obtain the a-th power generation resource loss assessment coefficient; input the a-th peaking and frequency modulation prediction matrix into the power generation efficiency loss assessment model to generate the a-th power generation efficiency loss assessment coefficient; output the a-th power quality loss assessment coefficient, the a-th power generation resource loss assessment coefficient, and the a-th power generation efficiency loss assessment coefficient as the a-th peaking and frequency modulation loss assessment result.

[0050] In a preferred implementation manner, when the peaking and frequency modulation loss evaluation module 13 inputs the a-th peaking and frequency modulation simulation data set into the peaking and frequency modulation loss assessment unit to obtain the a-th peaking and frequency modulation loss assessment result. First, the peaking and frequency modulation loss assessment unit performs data cleaning on the a-th peaking and frequency modulation simulation data set. Data cleaning refers to the process of checking, correcting, and filtering the original data, aiming to improve the data quality and eliminate noise, outliers, and redundant information in the data. Through data cleaning, the a-th peaking and frequency modulation prediction matrix with standardized format and accurate content is obtained, which contains the expected values of various operation indicators of the power grid after implementing the a-th peaking and frequency modulation strategy and is the basis for subsequent loss assessment. After obtaining the a-th peaking and frequency modulation strategy, the peaking and frequency modulation loss assessment unit activates three built-in loss assessment models, namely the power quality loss assessment model, the power generation resource loss assessment model, and the power generation efficiency loss assessment model. These three models respectively conduct quantitative evaluations on the implementation effects of the a-th peaking and frequency modulation strategy from three aspects: power quality, power generation resource utilization, and power generation efficiency.

[0051] Subsequently, the peak shaving and frequency modulation loss assessment unit inputs the a-th peak shaving and frequency modulation prediction matrix into the power quality loss assessment model to evaluate the impact of the a-th peak shaving and frequency modulation strategy on power quality indicators such as grid voltage and frequency. By analyzing the changes in relevant indicators in the prediction matrix, a quantified a-th power quality loss assessment coefficient is obtained. The smaller the a-th power quality loss assessment coefficient, the smaller the negative impact on power quality after the strategy is implemented, and the more stable the grid operation. At the same time, the peak shaving and frequency modulation loss assessment unit inputs the a-th peak shaving and frequency modulation prediction matrix into the power generation resource loss assessment model to evaluate the utilization efficiency and waste degree of the grid power generation resources by the a-th peak shaving and frequency modulation strategy. By comparing the changes in indicators such as the output of generating units and reserve capacity before and after the implementation of the a-th peak shaving and frequency modulation strategy, the a-th power generation resource loss assessment coefficient is calculated to measure the decrease or waste of power generation resources caused by the implementation of the strategy. In addition, the peak shaving and frequency modulation loss assessment unit inputs the a-th peak shaving and frequency modulation prediction matrix into the power generation efficiency loss assessment model to evaluate the impact of the a-th peak shaving and frequency modulation strategy on power generation equipment and its auxiliary systems. By analyzing the changes in indicators such as the energy consumption level and equipment loss of power generation equipment after the implementation of the strategy, the a-th power generation efficiency loss assessment coefficient is generated to reflect the possible decrease in power generation efficiency caused by the implementation of the strategy.

[0052] After that, the peak shaving and frequency modulation loss assessment unit aggregates the a-th power quality loss assessment coefficient, the a-th power generation resource loss assessment coefficient, and the a-th power generation efficiency loss assessment coefficient obtained from the three assessment models, and outputs the a-th peak shaving and frequency modulation loss assessment result with multiple indicators integrated, comprehensively reflecting the expected loss situation of the a-th peak shaving and frequency modulation strategy in multiple aspects such as power quality, power generation resource utilization, and power generation efficiency, providing an important reference for subsequent strategy optimization.

[0053] Furthermore, the embodiment of the present application further includes: According to the multiple peak shaving and frequency modulation loss judgment results, the a-th peak shaving and frequency modulation loss judgment result corresponding to the a-th peak shaving and frequency modulation strategy is extracted; if the a-th peak shaving and frequency modulation loss judgment result is that the a-th peak shaving and frequency modulation loss coefficient is less than the peak shaving and frequency modulation loss threshold, the a-th peak shaving and frequency modulation strategy is output as the a-th peak shaving and frequency modulation optimization strategy; if the a-th peak shaving and frequency modulation loss judgment result is that the a-th peak shaving and frequency modulation loss coefficient is greater than or equal to the peak shaving and frequency modulation loss threshold, the a-th peak shaving and frequency modulation strategy is optimized according to the peak shaving and frequency modulation loss threshold to generate the a-th peak shaving and frequency modulation optimization strategy; the a-th peak shaving and frequency modulation optimization strategy is added to the peak shaving and frequency modulation optimization strategy set.

[0054] In a feasible implementation manner, the peak shaving and frequency modulation optimization module 15 adopts a strategy screening method of adaptive threshold optimization to improve the efficiency and accuracy of peak shaving and frequency modulation strategy optimization.

[0055] First, the peak-shaving and frequency modulation optimization module 15 extracts the a-th peak-shaving and frequency modulation loss judgment result corresponding to the a-th peak-shaving and frequency modulation strategy based on the multiple peak-shaving and frequency modulation loss judgment results given by the peak-shaving and frequency modulation loss judgment module 14. This judgment result shows whether the expected loss level of the a-th peak-shaving and frequency modulation strategy exceeds the acceptable range. If the a-th peak-shaving and frequency modulation loss judgment result shows that the a-th peak-shaving and frequency modulation loss coefficient of the a-th peak-shaving and frequency modulation strategy is less than the preset peak-shaving and frequency modulation loss threshold, it means that the loss level of the strategy is low and can be directly used as the preferred strategy. At this time, the peak-shaving and frequency modulation optimization module 15 outputs the a-th peak-shaving and frequency modulation strategy intact as the a-th peak-shaving and frequency modulation optimization strategy without further optimization and adjustment.

[0056] If the a-th peak-shaving and frequency modulation loss judgment result shows that the a-th peak-shaving and frequency modulation loss coefficient of the a-th peak-shaving and frequency modulation strategy is greater than or equal to the peak-shaving and frequency modulation loss threshold, it indicates that the loss level of the strategy is high and there is room for optimization. In this case, the peak-shaving and frequency modulation optimization module 15 optimizes the a-th peak-shaving and frequency modulation strategy according to the peak-shaving and frequency modulation loss threshold. The purpose of optimization adjustment is to reduce its loss level as much as possible under the premise of ensuring the feasibility of the strategy so that it meets the requirements of the peak-shaving and frequency modulation loss threshold. Among them, the peak-shaving and frequency modulation optimization module 15 can adopt heuristic search, evolutionary optimization and other algorithms, and continuously optimize the loss performance of the strategy by appropriately adjusting the key parameters in the strategy (such as peak-shaving and frequency modulation power, duration, etc.), until the a-th peak-shaving and frequency modulation optimization strategy that meets the threshold requirements is generated. Regardless of whether the a-th peak-shaving and frequency modulation strategy is directly output or optimized, the peak-shaving and frequency modulation optimization module 15 will eventually add the obtained a-th peak-shaving and frequency modulation optimization strategy to the peak-shaving and frequency modulation optimization strategy set, bringing together all high-quality peak-shaving and frequency modulation strategies.

[0057] Through the strategy screening process of adaptive threshold optimization, the peak-shaving and frequency regulation optimization module 15 makes full use of the peak-shaving and frequency regulation loss judgment results, quickly screens and optimizes the initial peak-shaving and frequency regulation strategies, obtains high-quality, low-loss optimal strategies, and improves the flexibility and adaptability of power grid peak-shaving and frequency regulation optimization.

[0058] Furthermore, the embodiment of the present application also includes: Taking the time zone of the a-th peak period gap and the power generation gap of the a-th peak period as the peak shaving and frequency modulation targets, randomly adjust the a-th peak shaving and frequency modulation strategy according to the peak shaving and frequency modulation resource set, and establish an optimization adjustment space for the a-th strategy; according to the optimization adjustment space of the a-th strategy, randomly extract the first peak shaving and frequency modulation plan; according to the peak shaving and frequency modulation loss evaluation module, conduct loss prediction and evaluation on the first peak shaving and frequency modulation plan to obtain the peak shaving and frequency modulation loss coefficient of the first plan; determine whether the peak shaving and frequency modulation loss coefficient of the first plan is less than the peak shaving and frequency modulation loss threshold; if the peak shaving and frequency modulation loss coefficient of the first plan is less than the peak shaving and frequency modulation loss threshold, add the first peak shaving and frequency modulation plan to the a-th peak shaving and frequency modulation optimization strategy; if the peak shaving and frequency modulation loss coefficient of the first plan is greater than or equal to the peak shaving and frequency modulation loss threshold, eliminate the first peak shaving and frequency modulation plan, and continue to conduct optimization analysis on the optimization adjustment space of the a-th strategy according to the peak shaving and frequency modulation loss evaluation module and the peak shaving and frequency modulation loss threshold until the a-th peak shaving and frequency modulation optimization strategy is obtained.

[0059] In a preferred implementation manner, when the judgment result of the a-th peak shaving and frequency modulation loss of the a-th peak shaving and frequency modulation strategy shows that the a-th peak shaving and frequency modulation loss coefficient is greater than or equal to the peak shaving and frequency modulation loss threshold, the peak shaving and frequency modulation optimization module 15 will conduct further optimization adjustment on the a-th peak shaving and frequency modulation strategy to generate an a-th peak shaving and frequency modulation optimization strategy that meets the threshold requirements.

[0060] First, the peak shaving and frequency modulation optimization module 15 clarifies the target of the optimization adjustment, that is, the adjusted strategy can fully meet the peak shaving and frequency modulation requirements in the time zone of the a-th peak period gap and make up for the power generation gap of the a-th peak period. Taking this as the optimization direction, the peak shaving and frequency modulation optimization module 15 randomly adjusts the key parameters of the a-th peak shaving and frequency modulation strategy according to the currently available peak shaving and frequency modulation resource set of the power grid, and forms an optimization adjustment space for the a-th strategy that contains various parameter combination possibilities on the basis of the original strategy framework. After determining the optimization adjustment space, the peak shaving and frequency modulation optimization module 15 randomly extracts a new parameter combination from this space to generate a candidate peak shaving and frequency modulation plan, denoted as the first peak shaving and frequency modulation plan. This plan retains the basic structure of the a-th peak shaving and frequency modulation strategy, but makes certain adjustments to the key parameters to seek a reduction in the loss level. To evaluate the actual loss level of the first peak shaving and frequency modulation plan, the peak shaving and frequency modulation optimization module 15 submits it to the peak shaving and frequency modulation loss evaluation module 13 for loss prediction and evaluation. The peak shaving and frequency modulation loss evaluation module 13 follows the established evaluation process, and through digital twin simulation and multi-model evaluation, obtains the loss coefficient of the first peak shaving and frequency modulation plan, that is, the peak shaving and frequency modulation loss coefficient of the first plan, and feeds it back to the peak shaving and frequency modulation optimization module 15.

[0061] Subsequently, the peak shaving and frequency modulation optimization module 15 compares the peak shaving and frequency modulation loss coefficient of the first scheme with the peak shaving and frequency modulation loss threshold. If the peak shaving and frequency modulation loss coefficient of the first scheme is less than the peak shaving and frequency modulation loss threshold, it indicates that the loss level of the first peak shaving and frequency modulation scheme has been effectively controlled and can be used as an ideal optimization result. At this time, the peak shaving and frequency modulation optimization module 15 directly adds the first peak shaving and frequency modulation scheme to the a-th peak shaving and frequency modulation optimization strategy as the final optimized scheme of the a-th peak shaving and frequency modulation strategy. However, if the peak shaving and frequency modulation loss coefficient of the first scheme is still greater than or equal to the peak shaving and frequency modulation loss threshold, it indicates that the loss level of this scheme is not yet ideal and further optimization is required. In this case, the peak shaving and frequency modulation optimization module 15 temporarily eliminates the first peak shaving and frequency modulation scheme and resamples and analyzes the optimization adjustment space of the a-th strategy according to the gap between the peak shaving and frequency modulation loss coefficient of the first scheme and the peak shaving and frequency modulation loss threshold. Through the evaluation ability of the peak shaving and frequency modulation loss evaluation module 13, the peak shaving and frequency modulation optimization module 15 continuously extracts new candidate schemes from the optimization adjustment space of the a-th strategy, evaluates their loss levels, and compares them with the threshold until an optimal scheme that meets the loss threshold requirements is found and determined as the a-th peak shaving and frequency modulation optimization strategy Based on the optimization adjustment process, the peak shaving and frequency modulation optimization module 15 fully explores the optimization potential of the a-th peak shaving and frequency modulation strategy, and finds the optimal parameter combination scheme by performing intelligent search and comparison within the given adjustment space, so as to maximize the reduction of the loss level of the strategy.

[0062] In summary, the power grid peak shaving and frequency modulation adaptive optimization platform provided by the embodiments of the present application has the following technical effects: The peak period gap prediction module is used to predict the peak period gap of the first power generation side of the power grid according to the future time zone window, and determine multiple peak period gap time zones and multiple peak period power generation gaps. Among them, the first power generation side is in grid-connected operation, and the second power generation side of the power grid is in island operation, identifying and quantifying the power supply and demand imbalance risk faced by the first power generation side of the power grid, and providing a key basis for subsequent peak shaving and frequency modulation decision-making. The peak shaving and frequency modulation decision-making module is used to make peak shaving and frequency modulation decisions on the power grid based on multiple peak period gap time zones and multiple peak period power generation gaps, generate multiple peak shaving and frequency modulation strategies, and propose corresponding peak shaving and frequency modulation countermeasures for different peak period gap situations, improving the flexibility and adaptability of the power grid to cope with peak period gaps. The peak shaving and frequency modulation loss evaluation module is used to predict and evaluate the losses of multiple peak shaving and frequency modulation strategies, obtain multiple peak shaving and frequency modulation loss coefficients, and provide an important reference for subsequent strategy screening and optimization. The peak shaving and frequency modulation loss judgment module is used to judge whether multiple peak shaving and frequency modulation loss coefficients are less than the peak shaving and frequency modulation loss threshold, generate multiple peak shaving and frequency modulation loss judgment results, judge whether each strategy meets the requirements, and screen out feasible peak shaving and frequency modulation strategies. The peak shaving and frequency modulation optimization module is used to optimize and adjust multiple peak shaving and frequency modulation strategies based on multiple peak shaving and frequency modulation loss judgment results, generate a peak shaving and frequency modulation optimization strategy set, and while realizing the safe and stable operation of the power grid, can minimize the overall loss of peak shaving and frequency modulation. The peak shaving and frequency modulation execution module is used to perform peak shaving and frequency modulation on the power grid based on multiple peak period gap time zones, according to the second power generation side and the peak shaving and frequency modulation optimization strategy set, ensuring that when the peak period gap comes, the power grid can dynamically match the change of load demand, maintain the frequency and voltage stability of the power grid, and ensure the safe operation of the power grid.

[0063] Any step of the platform described above can be stored as computer instructions or programs in an unrestricted computer memory and can be called and recognized by an unrestricted computer processor to implement any platform in the embodiments of the present application, without further limitation here.

[0064] Furthermore, the first or second described above may not only represent an order relationship, but may also represent a certain specific concept, and / or refer to the fact that multiple elements can be selected individually or in total. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and deformations.

Claims

1. An adaptive optimization platform for power grid peak shaving and frequency modulation, characterized in that The platform includes: A peak period gap prediction module, which is used to predict the peak period gap of the first power generation side of the power grid according to the future time zone window, and determine multiple peak period gap time zones and multiple peak period power generation gaps. Wherein, the first power generation side is in grid-connected operation, and the second power generation side of the power grid is in island operation; A peak shaving and frequency modulation decision-making module, which is used to make peak shaving and frequency modulation decisions on the power grid based on the multiple peak period gap time zones and the multiple peak period power generation gaps, and generate multiple peak shaving and frequency modulation strategies according to the second power generation side; A peak shaving and frequency modulation loss evaluation module, which is used to predict and evaluate the losses of the multiple peak shaving and frequency modulation strategies to obtain multiple peak shaving and frequency modulation loss coefficients; A peak shaving and frequency modulation loss judgment module, which is used to judge whether the multiple peak shaving and frequency modulation loss coefficients are less than the peak shaving and frequency modulation loss threshold, and generate multiple peak shaving and frequency modulation loss judgment results; A peak shaving and frequency modulation optimization module, which is used to optimize and adjust the multiple peak shaving and frequency modulation strategies based on the multiple peak shaving and frequency modulation loss judgment results to generate a peak shaving and frequency modulation optimization strategy set; A peak shaving and frequency modulation execution module, which is used to perform peak shaving and frequency modulation on the power grid based on the multiple peak period gap time zones, according to the second power generation side and the peak shaving and frequency modulation optimization strategy set.

2. The power grid peak shaving and frequency modulation adaptive optimization platform according to claim 1, characterized in that The peak period gap prediction module is used to predict the peak period gap of the first power generation side of the power grid according to the future time zone window, and determine multiple peak period gap time zones and multiple peak period power generation gaps, including: According to the future time zone window, predict the load power of the power consumption side of the power grid and establish a predicted load power curve; According to the future time zone window, predict the power generation power of the first power generation side and establish a predicted power generation power curve; Based on the predicted load power curve, identify the peak period gap characteristics of the predicted power generation power curve, and generate the multiple peak period gap time zones and the multiple peak period power generation gaps.

3. The power grid peak shaving and frequency modulation adaptive optimization platform according to claim 1, characterized in that The peak shaving and frequency modulation decision-making module is used to make peak shaving and frequency modulation decisions on the power grid based on the multiple peak period gap time zones and the multiple peak period power generation gaps, and generate multiple peak shaving and frequency modulation strategies according to the second power generation side, including: Collect the power generation resource parameters of the second power generation side to obtain a peak shaving and frequency modulation resource set; According to the multiple peak period gap time zones and the multiple peak period power generation gaps, extract the a-th peak period gap time zone and the a-th peak period power generation gap, where a is a positive integer; Perform fusion learning based on P peak shaving and frequency modulation decision-making learning models to build a peak shaving and frequency modulation decision-making device, and embed the peak shaving and frequency modulation decision-making device into the peak shaving and frequency modulation decision-making module, where P is a positive integer greater than 1; Input the peak shaving and frequency modulation resource set, the a-th peak period gap time zone and the a-th peak period power generation gap into the peak shaving and frequency modulation decision-making device to obtain the a-th peak shaving and frequency modulation strategy, and add the a-th peak shaving and frequency modulation strategy to the multiple peak shaving and frequency modulation strategies.

4. The power grid peak shaving and frequency modulation adaptive optimization platform according to claim 3, wherein Performing fusion learning based on P peak shaving and frequency modulation decision-making learning models to build a peak shaving and frequency modulation decision-making device, including: Collect the peak shaving and frequency modulation decision records based on the power grid to obtain the peak shaving and frequency modulation resource set records, peak period gap time zone records, peak period power generation gap records, and peak shaving and frequency modulation strategy records; Using the peak shaving and frequency modulation resource set records, the peak period gap time zone records, and the peak period power generation gap records as input information, and the peak shaving and frequency modulation strategy records as output information, perform supervised training on the P peak shaving and frequency modulation decision learning models respectively to obtain P frequency modulation decision loss coefficients; Judge whether the P frequency modulation decision loss coefficients are less than the peak shaving and frequency modulation decision loss threshold; If the P frequency modulation decision loss coefficients are less than the peak shaving and frequency modulation decision loss threshold, generate P peak shaving and frequency modulation decision units; Perform fusion training according to the P peak shaving and frequency modulation decision units to generate the peak shaving and frequency modulation decision maker.

5. The power grid peak shaving and frequency modulation adaptive optimization platform according to claim 1, wherein The peak shaving and frequency modulation loss evaluation module is used to perform loss prediction evaluation on the multiple peak shaving and frequency modulation strategies to obtain multiple peak shaving and frequency modulation loss coefficients, including: The peak shaving and frequency modulation loss evaluation module includes a digital twin unit, a peak shaving and frequency modulation loss evaluation unit, and a peak shaving and frequency modulation loss initial weight condition; Based on the digital twin unit, perform simulated peak shaving and frequency modulation on the power grid according to the a-th peak shaving and frequency modulation strategy to obtain the a-th peak shaving and frequency modulation simulation data set; Input the a-th peak shaving and frequency modulation simulation data set into the peak shaving and frequency modulation loss evaluation unit to obtain the a-th peak shaving and frequency modulation loss evaluation result; Perform proportion calculation based on the a-th peak shaving and frequency modulation loss evaluation result to obtain the a-th peak shaving and frequency modulation loss improvement weight condition; Based on the a-th peak shaving and frequency modulation loss improvement weight condition, optimize the weight configuration of the peak shaving and frequency modulation loss initial weight condition to generate the a-th peak shaving and frequency modulation loss weight condition; Perform weighted calculation on the a-th peak shaving and frequency modulation loss evaluation result according to the a-th peak shaving and frequency modulation loss weight condition to generate the a-th peak shaving and frequency modulation loss coefficient, and add the a-th peak shaving and frequency modulation loss coefficient to the multiple peak shaving and frequency modulation loss coefficients.

6. The power grid peak shaving and frequency modulation adaptive optimization platform according to claim 5, characterized in that, Input the a-th peak shaving and frequency modulation simulation data set into the peak shaving and frequency modulation loss evaluation unit to obtain the a-th peak shaving and frequency modulation loss evaluation result, including: Perform data cleaning according to the a-th peak shaving and frequency modulation simulation data set to establish the a-th peak shaving and frequency modulation prediction matrix; Activate the power quality loss evaluation model, power generation resource loss evaluation model, and power generation efficiency loss evaluation model in the peak shaving and frequency modulation loss evaluation unit; Input the a-th peak shaving and frequency modulation prediction matrix into the power quality loss evaluation model to obtain the a-th power quality loss evaluation coefficient; Input the a-th peak shaving and frequency modulation prediction matrix into the power generation resource loss evaluation model to obtain the a-th power generation resource loss evaluation coefficient; Input the a-th peak shaving and frequency modulation prediction matrix into the power generation efficiency loss evaluation model to generate the a-th power generation efficiency loss evaluation coefficient; Output the a-th power quality loss evaluation coefficient, the a-th power generation resource loss evaluation coefficient, and the a-th power generation efficiency loss evaluation coefficient as the a-th peak shaving and frequency modulation loss evaluation result.

7. The power grid peak shaving and frequency modulation adaptive optimization platform according to claim 1, characterized in that, The peak shaving and frequency modulation optimization module is used to optimize and adjust the multiple peak shaving and frequency modulation strategies based on the multiple peak shaving and frequency modulation loss judgment results, and generate a peak shaving and frequency modulation optimization strategy set, including: According to the multiple peak shaving and frequency modulation loss judgment results, extract the a-th peak shaving and frequency modulation loss judgment result corresponding to the a-th peak shaving and frequency modulation strategy; If the a-th peak shaving and frequency modulation loss judgment result is that the a-th peak shaving and frequency modulation loss coefficient is less than the peak shaving and frequency modulation loss threshold, output the a-th peak shaving and frequency modulation strategy as the a-th peak shaving and frequency modulation optimization strategy; If the a-th peak shaving and frequency modulation loss judgment result is that the a-th peak shaving and frequency modulation loss coefficient is greater than or equal to the peak shaving and frequency modulation loss threshold, optimize and adjust the a-th peak shaving and frequency modulation strategy according to the peak shaving and frequency modulation loss threshold to generate the a-th peak shaving and frequency modulation optimization strategy; Add the a-th peak shaving and frequency modulation optimization strategy to the peak shaving and frequency modulation optimization strategy set.

8. The power grid peak shaving and frequency modulation adaptive optimization platform according to claim 7, wherein If the a-th peak shaving and frequency modulation loss judgment result is that the a-th peak shaving and frequency modulation loss coefficient is greater than or equal to the peak shaving and frequency modulation loss threshold, optimize and adjust the a-th peak shaving and frequency modulation strategy according to the peak shaving and frequency modulation loss threshold to generate the a-th peak shaving and frequency modulation optimization strategy, including: Taking the a-th peak period gap time zone and the a-th peak period power generation gap as the peak shaving and frequency modulation targets, randomly adjust the a-th peak shaving and frequency modulation strategy according to the peak shaving and frequency modulation resource set to establish an a-th strategy optimization and adjustment space; Randomly extract the first peak shaving and frequency modulation plan according to the a-th strategy optimization and adjustment space; Obtain the first plan peak shaving and frequency modulation loss coefficient according to the loss prediction and evaluation of the first peak shaving and frequency modulation plan by the peak shaving and frequency modulation loss evaluation module; Judge whether the first plan peak shaving and frequency modulation loss coefficient is less than the peak shaving and frequency modulation loss threshold; If the first plan peak shaving and frequency modulation loss coefficient is less than the peak shaving and frequency modulation loss threshold, add the first peak shaving and frequency modulation plan to the a-th peak shaving and frequency modulation optimization strategy; If the first plan peak shaving and frequency modulation loss coefficient is greater than or equal to the peak shaving and frequency modulation loss threshold, eliminate the first peak shaving and frequency modulation plan, and continue to perform optimization analysis on the a-th strategy optimization and adjustment space according to the peak shaving and frequency modulation loss evaluation module and the peak shaving and frequency modulation loss threshold until the a-th peak shaving and frequency modulation optimization strategy is obtained.

Images