Comprehensive scheduling method and device for power system

Abstract

The invention discloses a power system comprehensive scheduling method and equipment, and the method comprises the steps: collecting the meteorological data of a target power system, the first historical power generation data of each renewable energy unit, and the second historical power generation data of each non-renewable energy unit, and determining the power generation prediction strategy of each renewable energy unit, and obtaining corresponding power generation prediction data, carrying out comparative analysis on each power generation prediction data and the first threshold data to obtain a first evaluation result of each renewable energy unit, and carrying out comparative analysis on each second historical power generation data and the second threshold data to obtain a second evaluation result of each non-renewable energy unit. And further obtaining a comprehensive evaluation result of the target power system, and controlling a functional component corresponding to the target power system to execute a corresponding scheduling strategy. According to the comprehensive dispatching method and device for the power system, the reliability of evaluation of the power system is improved, and effective dispatching of the power system is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method and device for comprehensive dispatching of power systems. Background Art

[0002] Comprehensive evaluation of power system refers to the process of comprehensively evaluating the operating status of power system through analysis, measurement and calculation of various elements of power system. Through comprehensive analysis of various performance indicators of power system, it can ensure that the power system can meet the power demand of users under normal operation and restore power supply as soon as possible under abnormal conditions, so as to achieve effective dispatch of power system.

[0003] However, the existing technology uses the same calculation method for all power system evaluation indicators, without considering the interference of environmental factors on the power system evaluation, resulting in low reliability of the comprehensive evaluation of the power system and inability to achieve effective scheduling of the power system.

[0004] It can be seen that how to improve the reliability of comprehensive evaluation of power systems, so as to achieve effective dispatch of power systems, has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] The present invention provides a method and device for comprehensive dispatching of an electric power system to solve the technical problem that the prior art does not take into account the interference of environmental factors on the evaluation of the electric power system, resulting in low reliability of the comprehensive evaluation of the electric power system and inability to achieve effective dispatching of the electric power system.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a comprehensive dispatching method for a power system.

[0007] Collecting meteorological data of the target power system, first historical power generation data of each renewable energy unit, and second historical power generation data of each non-renewable energy unit; Performing correlation analysis on the first historical power generation data and the meteorological data of each renewable energy unit, and determining a power generation prediction strategy corresponding to each renewable energy unit based on results of all the correlation analyses; According to the power generation prediction strategy and the first historical power generation data, power generation prediction is performed on each of the renewable energy units to obtain power generation prediction data of each of the renewable energy units; A dual-reference progressive algorithm is used to sequentially compare and analyze each of the power generation prediction data and the first threshold data preset for the current renewable energy unit, so as to obtain a first evaluation result for each of the renewable energy units; a dual-reference progressive algorithm is used to sequentially compare and analyze each of the second historical power generation data and the second threshold data preset for the current non-renewable energy unit, so as to obtain a second evaluation result for each of the non-renewable energy units; Quantifying the first evaluation result and the second evaluation result respectively to obtain a comprehensive evaluation result of the target power system, wherein the comprehensive evaluation result at least includes a voltage evaluation result, a power margin result, a load result, and a response speed result; The functional components corresponding to the target power system are controlled to respectively execute the dispatching strategies corresponding to the voltage evaluation result, the power margin result, the load result and the response speed result.

[0008] As one of the preferred solutions, the power generation prediction strategy includes a neural network association prediction strategy and a historical data analysis prediction strategy; The performing correlation analysis on the first historical power generation data and the meteorological data of each renewable energy unit, and determining the power generation prediction strategy corresponding to each renewable energy unit based on the results of all the correlation analyses, comprises: Calculating the Pearson correlation coefficient between each of the first historical power generation data and each of the meteorological data, processing all of the Pearson correlation coefficients, and obtaining a comprehensive reference value of the correlation coefficient and a meteorological-related power generation factor of each of the renewable energy units; The renewable energy generating units corresponding to all the meteorologically correlated power generation factors greater than the comprehensive reference value of the correlation coefficient are regarded as meteorologically strongly correlated power generation units, and the power generation prediction strategies of all the meteorologically strongly correlated power generation units are set to be neural network correlation prediction strategies; The renewable energy generating units corresponding to all the meteorologically correlated power generation factors that are less than or equal to the comprehensive reference value of the correlation coefficient are regarded as meteorologically weakly correlated power generation units, and the power generation prediction strategies of all the meteorologically weakly correlated power generation units are set as historical data analysis prediction strategies.

[0009] As one of the preferred solutions, the processing of all the Pearson correlation coefficients to obtain a comprehensive reference value of the correlation coefficient and a meteorological-related power generation factor of each renewable energy unit includes: taking an average value of the Pearson correlation coefficients of all the first historical power generation data and all the meteorological data as a comprehensive reference value of the correlation coefficient; The average value of the Pearson correlation coefficient between the first historical power generation data of each renewable energy unit and all the meteorological data is used as the meteorological-related power generation factor of each renewable energy unit.

[0010] As one preferred solution, the power generation prediction of each of the renewable energy units is performed according to the power generation prediction strategy and the first historical power generation data to obtain the power generation prediction data of each of the renewable energy units, including: If the power generation prediction strategy of the current renewable energy unit is the neural network association prediction strategy, all the Pearson correlation coefficients of the current renewable energy unit that are greater than the comprehensive reference value of the correlation coefficient are used as the key Pearson correlation coefficients of the current renewable energy unit; Using the meteorological data corresponding to all the key Pearson correlation coefficients as the key meteorological impact data of the current renewable energy unit; A BP neural network model is used to perform forecast analysis on the first historical power generation data of the current renewable energy unit and all the key meteorological impact data to obtain power generation forecast data of the current renewable energy unit.

[0011] As one preferred solution, performing power generation prediction on each of the renewable energy units according to the power generation prediction strategy and the first historical power generation data to obtain power generation prediction data of each of the renewable energy units further includes: If the power generation forecasting strategy of the current renewable energy unit is the historical data analysis forecasting strategy, determining the order of the non-seasonal moving average term of the seasonal autoregressive integrated moving average model based on the random volatility characteristics of the first historical power generation data of the current renewable energy unit; The first historical power generation data of the current renewable energy unit is input into the seasonal autoregressive integrated moving average model, and the power generation prediction data of the current renewable energy unit is output.

[0012] As one of the preferred solutions, the step of determining the order of the non-seasonal moving average term of the seasonal autoregressive integrated moving average model based on the random volatility characteristics of the first historical power generation data of the current renewable energy unit includes: Using the ratio of the standard deviation of the first historical power generation data of the current renewable energy unit to the corresponding Hurst index as the random fluctuation interference index of the current renewable energy unit; The product of the normalized processing result of the random fluctuation interference index and the preset number of average items is used as the order of the non-seasonal moving average item of the seasonal autoregressive integrated moving average model.

[0013] As one preferred solution, before using the BP neural network model to predict and analyze the first historical power generation data of the current renewable energy unit and all the key meteorological impact data, the method further includes: The first historical power generation data and all the key meteorological impact data are normalized.

[0014] As one preferred solution, before controlling the functional components corresponding to the target power system to respectively execute the dispatching strategies corresponding to the voltage evaluation result, the power margin result, the load result and the response speed result, the method further includes: The scheduling strategy is simulated and verified using a simulation model, and the scheduling strategy is adjusted and optimized based on the results of the simulation verification.

[0015] As one of the preferred solutions, the result of the simulation verification includes verification success and verification failure; The adopting a simulation model to simulate and verify the scheduling strategy includes: respectively setting parameters corresponding to the voltage evaluation result, the power margin result, the load result and the response speed result in the simulation model, and executing the scheduling strategy; The various operation data collected during the execution process are analyzed. If the analysis result meets the preset requirements, the result of the simulation verification is determined to be a successful verification; if the analysis result does not meet the preset requirements, the result of the simulation verification is determined to be a failed verification.

[0016] Another embodiment of the present invention provides an electric power system comprehensive dispatching device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements an electric power system comprehensive dispatching method as described above.

[0017] Compared with the prior art, the embodiments of the present invention have the following advantages: (1) Collect meteorological data of the target power system, first historical power generation data of each renewable energy unit, and second historical power generation data of each non-renewable energy unit; considering that the power generation of renewable energy units may fluctuate due to interference from environmental factors, resulting in low reference value of historical data of renewable energy units, correlation analysis is performed on the first historical power generation data and meteorological data of each renewable energy unit, and the power generation forecasting strategy corresponding to each renewable energy unit is determined based on the results of all correlation analyses. Different power generation forecasting strategies are set for different renewable energy units according to the degree of correlation between historical power generation data and environmental factors. Power generation forecasting is performed on each renewable energy unit according to the power generation forecasting strategy and the first historical power generation data, and power generation forecasting data of each renewable energy unit is obtained, thereby improving the reliability of power generation data forecasting of renewable energy units; (2) A dual-benchmark progressive algorithm is used to compare and analyze each power generation forecast data with the first threshold data preset for the current renewable energy unit in turn, and a first evaluation result of each renewable energy unit is obtained; a dual-benchmark progressive algorithm is used to compare and analyze each second historical power generation data with the second threshold data preset for the current non-renewable energy unit in turn, and a second evaluation result of each non-renewable energy unit is obtained. By comparing the power generation forecast data of the renewable energy unit with the target data instead of directly evaluating the power system based on the historical power generation data, the reliability of the power system evaluation is improved. In combination with the dual-benchmark progressive algorithm, the target value is set according to the statistical distribution characteristics of the power generation forecast data to avoid the interference of the changes in the input power generation forecast data and the uncertainty of the model on the evaluation results, and the reliability of the power system evaluation is further improved. (3) Quantifying the first evaluation result and the second evaluation result respectively to obtain a comprehensive evaluation result of the target power system, wherein the comprehensive evaluation result at least includes a voltage evaluation result, a power surplus result, a load result, and a response speed result; controlling the corresponding functional components of the target power system to respectively execute the dispatching strategies corresponding to the voltage evaluation result, the power surplus result, the load result, and the response speed result; and using a simulation model to simulate and verify the dispatching strategy before executing the corresponding dispatching strategy, which is helpful to discover potential problems and risks, adjust and optimize the dispatching strategy, and improve the stability and efficiency of the power system; (4) Considering that the power generation of renewable energy units may fluctuate due to interference from environmental factors, the historical data of renewable energy units have low reference significance. By setting different evaluation strategies for renewable energy units and non-renewable energy units, and setting different prediction strategies for different historical power generation data of renewable energy units, the final comprehensive evaluation results are obtained, and the corresponding dispatching strategies are executed, which comprehensively improves the reliability of the power system evaluation and realizes the effective dispatch of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a comprehensive dispatching method for a power system in one embodiment of the present invention; Figure 2 It is a schematic diagram of obtaining comprehensive evaluation results in one embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0021] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0022] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0023] An embodiment of the present invention provides a method for comprehensive dispatching of a power system. For details, see Figure 1~Figure 2 , Figure 1 FIG. 1 is a flow chart of a method for comprehensive dispatching of a power system in one embodiment of the present invention. Figure 2 It is a schematic diagram showing the acquisition of comprehensive evaluation results in one embodiment of the present invention.

[0024] A flowchart of a comprehensive dispatching method for a power system in one embodiment of the present invention includes the following steps S1 to S4, which are specifically as follows: Step S1: collecting meteorological data of the target power system, first historical power generation data of each renewable energy unit, and second historical power generation data of each non-renewable energy unit.

[0025] It should be noted that historical power generation data can reflect the actual operating conditions of the power system, including the changing trend of power generation, power generation efficiency, and the stability of power generation equipment. By analyzing these data, we can fully understand the historical performance of the power system and provide basic data support for comprehensive evaluation. The power generation of renewable energy will be affected by meteorological factors. Therefore, before conducting a comprehensive evaluation of the power system, it is necessary to collect the historical power generation data and meteorological data of the power system.

[0026] Specifically, meteorological data of the target power system, first historical power generation data of each renewable energy unit, and second historical power generation data of each non-renewable energy unit are collected at regular intervals, and data cleaning and outlier processing are performed on all data.

[0027] It should be noted that the collection time interval is a preset value. In this embodiment, the collection time interval is 30 minutes. As for the value of the collection time interval, as other implementation methods, the implementer can choose it at will, and this application does not impose any special restrictions on this.

[0028] Step S2: Perform correlation analysis on the first historical power generation data and meteorological data of each renewable energy unit, and determine the power generation prediction strategy corresponding to each renewable energy unit based on the results of all correlation analyses; perform power generation prediction on each renewable energy unit according to the power generation prediction strategy and the first historical power generation data to obtain power generation prediction data for each renewable energy unit.

[0029] It should be noted that considering that the power generation of renewable energy units will be disturbed by environmental factors and fluctuate, the historical data of renewable energy units has a low reference value. If the power system is evaluated directly based on historical power generation data, the reliability of the evaluation results is low. Therefore, according to the different degrees of interference of environmental factors on the power generation of renewable energy units, different power generation prediction strategies need to be adopted for the prediction of power generation data of renewable energy units.

[0030] It should be further explained that the power generation prediction strategy includes a neural network association prediction strategy and a historical data analysis prediction strategy.

[0031] Specifically, the Pearson correlation coefficient between each first historical power generation data and each meteorological data is calculated, and the average value of the Pearson correlation coefficients between all the first historical power generation data and all meteorological data is used as the comprehensive reference value of the correlation coefficient; the average value of the Pearson correlation coefficients between the first historical power generation data and all meteorological data of each renewable energy unit is used as the meteorological-related power generation factor of each renewable energy unit.

[0032] Furthermore, all renewable energy units corresponding to meteorologically correlated power generation factors greater than the comprehensive reference value of the correlation coefficient are regarded as meteorologically strongly correlated power generation units, and the power generation prediction strategies of all meteorologically strongly correlated power generation units are set to the neural network correlation prediction strategy; all renewable energy units corresponding to meteorologically correlated power generation factors less than or equal to the comprehensive reference value of the correlation coefficient are regarded as meteorologically weakly correlated power generation units, and the power generation prediction strategies of all meteorologically weakly correlated power generation units are set to the historical data analysis prediction strategy.

[0033] Furthermore, according to the power generation prediction strategy and the first historical power generation data, power generation prediction is performed on each renewable energy unit to obtain power generation prediction data of each renewable energy unit.

[0034] Specifically, if the power generation prediction strategy of the current renewable energy unit is a neural network association prediction strategy, all Pearson correlation coefficients of the current renewable energy unit that are greater than the comprehensive reference value of the correlation coefficient are used as the key Pearson correlation coefficients of the current renewable energy unit; the meteorological data corresponding to all the key Pearson correlation coefficients are used as the key meteorological impact data of the current renewable energy unit; the BP neural network model is used to predict and analyze the first historical power generation data and all key meteorological impact data of the current renewable energy unit to obtain the power generation prediction data of the current renewable energy unit.

[0035] If the power generation forecasting strategy of the current renewable energy unit is a historical data analysis forecasting strategy, the order of the non-seasonal moving average term of the seasonal autoregressive integral moving average model is determined based on the random volatility characteristics of the first historical power generation data of the current renewable energy unit; the first historical power generation data of the current renewable energy unit is input into the seasonal autoregressive integral moving average model, and the power generation forecasting data of the current renewable energy unit is output.

[0036] It should be noted that the seasonal autoregressive integrated moving average model captures the seasonal characteristics of the time series by adding seasonal differences, seasonal autoregressive and seasonal moving average terms. In the seasonal autoregressive integrated moving average model, the non-seasonal moving average term can capture the random fluctuations or noise in the time series. The BP neural network model is a multi-layer feedforward neural network, and its main features are signal forward transmission and error back propagation. By collecting the historical power generation data of the power system and using the BP neural network for training and learning, the power generation data of the power system can be predicted. The BP neural network model and the seasonal autoregressive integrated moving average model are both well-known technologies and will not be described in detail in this embodiment.

[0037] As an embodiment of the present application, before using the BP neural network model to predict and analyze the first historical power generation data and all key meteorological impact data of the current renewable energy unit, the first historical power generation data and all key meteorological impact data are normalized.

[0038] In this step, the specific method for determining the order of the non-seasonal moving average term of the seasonal autoregressive integrated moving average model based on the random volatility characteristics of the first historical power generation data of the current renewable energy unit is: taking the ratio of the standard deviation of the first historical power generation data of the current renewable energy unit and the corresponding Hurst index as the random fluctuation interference index of the current renewable energy unit; taking the product of the normalized processing result of the random fluctuation interference index and the preset number of average terms as the order of the non-seasonal moving average term of the seasonal autoregressive integrated moving average model.

[0039] It should be noted that the standard deviation is a statistic used to measure the degree of dispersion or variation of a set of data, and the Hurst index is an important indicator used to measure whether a time series has long-term memory. The calculation of the standard deviation and the Hurst index are both well-known technologies, and this embodiment will not be described in detail here. When the standard deviation of the first historical power generation data is larger and the corresponding Hurst index is smaller, it means that the degree of variation of the first historical power generation data is higher and the autocorrelation is worse, and the random fluctuation characteristics of the power generation data of the current renewable energy unit are more obvious. When the seasonal autoregressive integrated moving average model is used to predict the power generation of the renewable energy unit, the larger the order of the non-seasonal moving average term should be set to capture the random fluctuation characteristics of the first historical power generation data of the renewable energy unit.

[0040] Step S3: Using a dual-benchmark progressive algorithm, each power generation prediction data is compared with the first threshold data preset for the current renewable energy unit in turn for analysis, and a first evaluation result of each renewable energy unit is obtained; using a dual-benchmark progressive algorithm, each second historical power generation data is compared with the second threshold data preset for the current non-renewable energy unit in turn for analysis, and a second evaluation result of each non-renewable energy unit is obtained.

[0041] It should be noted that the dual-benchmark progressive algorithm sets two benchmark values ​​for each indicator. The first threshold data includes the first renewable energy power generation benchmark value and the second renewable energy power generation benchmark value, and the second threshold data includes the first non-renewable energy power generation benchmark value and the second non-renewable energy power generation benchmark value. The target value is set according to the statistical distribution characteristics of the power generation forecast data, which avoids the changes in the input power generation forecast data and the uncertainty of the model from interfering with the evaluation results. The dual-benchmark progressive algorithm is a well-known technology and will not be described in detail in this embodiment.

[0042] Specifically, the first renewable energy power generation benchmark value, the second renewable energy power generation benchmark value and the power generation forecast data are input into the dual benchmark progressive algorithm to calculate the first evaluation result of the corresponding renewable energy unit. The first non-renewable energy power generation benchmark value, the second non-renewable energy power generation benchmark value and the second historical power generation data are input into the dual benchmark progressive algorithm to calculate the second evaluation result of the corresponding non-renewable energy unit.

[0043] Step S4: quantify the first evaluation result and the second evaluation result respectively to obtain a comprehensive evaluation result of the target power system, and control the corresponding functional components of the target power system to execute the corresponding dispatching strategy.

[0044] Specifically, the first evaluation result and the second evaluation result are quantified respectively to obtain a comprehensive evaluation result of the target power system.

[0045] As an embodiment of the present application, all first evaluation results and all second evaluation results are weightedly summed layer by layer to serve as a comprehensive evaluation result of the target power system.

[0046] It should be noted that the comprehensive evaluation result includes at least voltage evaluation result, power margin result, load result and response speed result.

[0047] Furthermore, the functional components corresponding to the target power system are controlled to respectively execute dispatch strategies corresponding to the voltage evaluation results, the power margin results, the load results and the response speed results.

[0048] In one embodiment, the scheduling strategy is as follows: It should be noted that the target range of voltage fluctuation is ±2% of the standard value. Low voltage (-5%) means that the system voltage is 5% lower than the standard value, and the voltage needs to be increased. Insufficient margin (90%) means that the power margin is 90%, which is lower than the target value of 95%, and the power generation needs to be increased. Excessive load (110%) means that the system load is 110% of the rated load, and the load needs to be reduced or the power supply capacity needs to be increased. Slow response (15 seconds) means that the system response time is 15 seconds, which is 10 seconds higher than the target value, and the scheduling strategy needs to be optimized to improve the response speed.

[0049] After implementing the above dispatch strategy, the operating status of the target power system has been significantly improved. The specific results are as follows: As an embodiment of the present application, before the functional components corresponding to the control target power system respectively execute the dispatching strategies corresponding to the voltage evaluation results, power margin results, load results and response speed results, a simulation model is used to simulate and verify the dispatching strategies, and the dispatching strategies are adjusted and optimized based on the results of the simulation verification.

[0050] In this embodiment, a simulation model is used to simulate and verify the scheduling strategy, including: In the simulation model, parameters corresponding to the voltage evaluation results, power margin results, load results and response speed results are set respectively, and the scheduling strategy is executed; various operating data collected during the execution process are analyzed, and if the analysis result meets the preset requirements, the result of the simulation verification is determined to be a successful verification; if the analysis result does not meet the preset requirements, the result of the simulation verification is determined to be a failed verification.

[0051] In one embodiment, the above scheduling strategy is simulated and verified using Simulink, and the results are as follows: In this embodiment, the target value is a preset requirement, and if all simulation results meet the target value, the result of the simulation verification is a successful verification. If one simulation result does not meet the target value, the result of the simulation verification is a failed verification.

[0052] In one embodiment of the present invention, a power system integrated dispatching device is provided, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, an power system integrated dispatching method as described above is implemented.

[0053] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A comprehensive dispatching method for a power system, characterized in that: The method comprises: Collecting meteorological data of the target power system, first historical power generation data of each renewable energy unit, and second historical power generation data of each non-renewable energy unit; Performing correlation analysis on the first historical power generation data and the meteorological data of each renewable energy unit, and determining a power generation prediction strategy corresponding to each renewable energy unit based on results of all the correlation analyses; According to the power generation prediction strategy and the first historical power generation data, power generation prediction is performed on each of the renewable energy units to obtain power generation prediction data of each of the renewable energy units; A dual-reference progressive algorithm is used to sequentially compare and analyze each of the power generation prediction data and the first threshold data preset for the current renewable energy unit, so as to obtain a first evaluation result for each of the renewable energy units; a dual-reference progressive algorithm is used to sequentially compare and analyze each of the second historical power generation data and the second threshold data preset for the current non-renewable energy unit, so as to obtain a second evaluation result for each of the non-renewable energy units; Quantifying the first evaluation result and the second evaluation result respectively to obtain a comprehensive evaluation result of the target power system, wherein the comprehensive evaluation result at least includes a voltage evaluation result, a power margin result, a load result, and a response speed result; The functional components corresponding to the target power system are controlled to respectively execute the dispatching strategies corresponding to the voltage evaluation result, the power margin result, the load result and the response speed result.

2. A method for comprehensive dispatching of a power system according to claim 1, characterized in that: The power generation prediction strategy includes a neural network association prediction strategy and a historical data analysis prediction strategy; The performing correlation analysis on the first historical power generation data and the meteorological data of each renewable energy unit, and determining the power generation prediction strategy corresponding to each renewable energy unit based on the results of all the correlation analyses, comprises: Calculating the Pearson correlation coefficient between each of the first historical power generation data and each of the meteorological data, processing all of the Pearson correlation coefficients, and obtaining a comprehensive reference value of the correlation coefficient and a meteorological-related power generation factor of each of the renewable energy units; The renewable energy generating units corresponding to all the meteorologically correlated power generation factors greater than the comprehensive reference value of the correlation coefficient are regarded as meteorologically strongly correlated power generation units, and the power generation prediction strategies of all the meteorologically strongly correlated power generation units are set to be neural network correlation prediction strategies; The renewable energy generating units corresponding to all the meteorologically correlated power generation factors that are less than or equal to the comprehensive reference value of the correlation coefficient are regarded as meteorologically weakly correlated power generation units, and the power generation prediction strategies of all the meteorologically weakly correlated power generation units are set as historical data analysis prediction strategies.

3. A method for comprehensive dispatching of a power system according to claim 2, characterized in that: The processing of all the Pearson correlation coefficients to obtain a comprehensive reference value of the correlation coefficient and a meteorological-related power generation factor of each renewable energy unit includes: taking an average value of the Pearson correlation coefficients of all the first historical power generation data and all the meteorological data as a comprehensive reference value of the correlation coefficient; The average value of the Pearson correlation coefficient between the first historical power generation data of each renewable energy unit and all the meteorological data is used as the meteorological-related power generation factor of each renewable energy unit.

4. A method for comprehensive dispatching of a power system according to claim 2, characterized in that: The step of performing power generation prediction on each of the renewable energy units according to the power generation prediction strategy and the first historical power generation data to obtain power generation prediction data of each of the renewable energy units includes: If the power generation prediction strategy of the current renewable energy unit is the neural network association prediction strategy, all the Pearson correlation coefficients of the current renewable energy unit that are greater than the comprehensive reference value of the correlation coefficient are used as the key Pearson correlation coefficients of the current renewable energy unit; Using the meteorological data corresponding to all the key Pearson correlation coefficients as the key meteorological impact data of the current renewable energy unit; A BP neural network model is used to perform forecast analysis on the first historical power generation data of the current renewable energy unit and all the key meteorological impact data to obtain power generation forecast data of the current renewable energy unit.

5. A method for comprehensive dispatching of a power system according to claim 2, characterized in that: The step of performing power generation prediction on each of the renewable energy units according to the power generation prediction strategy and the first historical power generation data to obtain power generation prediction data of each of the renewable energy units further includes: If the power generation forecasting strategy of the current renewable energy unit is the historical data analysis forecasting strategy, determining the order of the non-seasonal moving average term of the seasonal autoregressive integrated moving average model based on the random volatility characteristics of the first historical power generation data of the current renewable energy unit; The first historical power generation data of the current renewable energy unit is input into the seasonal autoregressive integrated moving average model, and the power generation prediction data of the current renewable energy unit is output.

6. A method for comprehensive dispatching of a power system according to claim 5, characterized in that: The step of determining the order of the non-seasonal moving average term of the seasonal autoregressive integrated moving average model based on the random volatility characteristics of the first historical power generation data of the current renewable energy unit includes: Using the ratio of the standard deviation of the first historical power generation data of the current renewable energy unit to the corresponding Hurst index as the random fluctuation interference index of the current renewable energy unit; The product of the normalized processing result of the random fluctuation interference index and the preset number of average items is used as the order of the non-seasonal moving average item of the seasonal autoregressive integrated moving average model.

7. A method for comprehensive dispatching of a power system according to claim 4, characterized in that: Before using the BP neural network model to perform forecast analysis on the first historical power generation data of the current renewable energy unit and all the key meteorological impact data, the method further includes: The first historical power generation data and all the key meteorological impact data are normalized.

8. A method for comprehensive dispatching of a power system according to claim 1, characterized in that: Before controlling the functional components corresponding to the target power system to respectively execute the dispatching strategies corresponding to the voltage evaluation result, the power margin result, the load result, and the response speed result, the method further includes: The scheduling strategy is simulated and verified using a simulation model, and the scheduling strategy is adjusted and optimized based on the results of the simulation verification.

9. A method for comprehensive dispatching of a power system according to claim 8, characterized in that: The result of the simulation verification includes verification success and verification failure; The adopting a simulation model to simulate and verify the scheduling strategy includes: respectively setting parameters corresponding to the voltage evaluation result, the power margin result, the load result and the response speed result in the simulation model, and executing the scheduling strategy; The various operation data collected during the execution process are analyzed. If the analysis result meets the preset requirements, the result of the simulation verification is determined to be a successful verification; if the analysis result does not meet the preset requirements, the result of the simulation verification is determined to be a failed verification.

10. A comprehensive dispatching device for a power system, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, an electric power system comprehensive dispatching method as described in any one of claims 1 to 9 is implemented.

Images