Power grid source load adjustable resource comprehensive evaluation method, system, equipment and medium

Abstract

The invention discloses a comprehensive evaluation method, system and device for power grid source load adjustable resources and a medium, and the method comprises the steps: classifying the source load adjustable resources of a target regional power grid, and obtaining the historical power data of each type of adjustable resources; clustering the power data by adopting a density peak value clustering algorithm based on natural nearest neighbor to generate a typical operation scene set and a probability thereof; constructing a source load adjustable resource complementarity evaluation index system comprising a supply and demand complementarity evaluation index, a fluctuation complementarity evaluation index and an energy complementarity evaluation index so as to quantify each complementarity evaluation index under the typical operation scene set; the weight of each complementarity evaluation index is determined by improving the CRITIC entropy weight combination weighting method, the complementarity comprehensive score among various adjustable resources of the power grid is calculated based on the complementarity evaluation indexes after weighting and the probability, and the overall source load matching degree analysis is refined to the source load adjustable resources, so that the evaluation accuracy of the power grid source load adjustable resources is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a comprehensive evaluation method, system, equipment and medium for power grid source-load adjustable resources. Background Art

[0002] With the construction of new power systems, the proportion of renewable energy power generation represented by wind power and photovoltaic power generation has increased rapidly, resulting in increased volatility and uncertainty on the power generation side of the power system. This has put forward higher requirements on the flexible adjustment capabilities of the power system, and has also made the evaluation of adjustable resources in the power grid increasingly important.

[0003] In the existing technology, the evaluation of adjustable resources in the power grid mostly focuses on the matching assessment of the overall renewable energy output and the overall load of the regional power grid, that is, clustering and source-load matching assessment are performed for a single source side or load side scenario through a clustering algorithm, without considering refining the overall source-load matching analysis to the source-load adjustable resources, resulting in inaccurate evaluation results.

[0004] It can be seen that how to improve the accuracy of existing solutions in evaluating the adjustable resources of regional power grid sources and loads has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0005] The present invention provides a comprehensive evaluation method, system, device and medium for power grid source-load adjustable resources, which solve the problem of how to improve the evaluation accuracy of existing solutions for regional power grid source-load adjustable resources.

[0006] In order to solve the above technical problems, the first aspect of the present invention provides a comprehensive evaluation method for adjustable resources of power grid sources and loads, comprising: Classify the source-load adjustable resources in the target area power grid according to the power supply and consumption characteristics, and obtain the historical power curves of various adjustable resources to build a power supply and consumption database of source-load adjustable resources; Clustering the historical operation scenarios in the source-load adjustable resource power supply and consumption database by a density peak clustering algorithm based on natural nearest neighbors to generate a set of typical operation scenarios and their probabilities; Constructing a source-load adjustable resource complementarity evaluation index system of the target regional power grid to quantify various complementarity evaluation indicators under the typical operation scenario set; the source-load adjustable resource complementarity evaluation index system includes supply-demand complementarity evaluation index, fluctuation complementarity evaluation index and energy complementarity evaluation index; The weights of the complementarity evaluation indicators are determined by improving the CRITIC entropy weight combination weighting method, and the comprehensive scores of complementarity between various adjustable resources in the target area power grid are quantified based on the weighted complementarity evaluation indicators and the probabilities.

[0007] As one of the preferred schemes, the classification results of the source-load adjustable resources include source-side adjustable resources and load-side adjustable resources; the source-side adjustable resources include distributed photovoltaic and distributed wind power; the load-side adjustable resources include transferable loads, curtailable loads and shiftable loads among residential loads, commercial loads and industrial loads.

[0008] As one of the preferred solutions, the historical operation scenarios in the source-load adjustable resource power supply and consumption database are clustered by a density peak clustering algorithm based on natural nearest neighbors to generate a typical operation scenario set and its probability, including: Obtaining historical power curves of various adjustable resources in the power supply and consumption database of the source-load adjustable resources, and normalizing and combining the historical power curves of the adjustable resources on the same day to generate several historical operation scenarios; Clustering each of the historical operation scenarios using a density peak clustering algorithm based on natural nearest neighbors, and taking the cluster center as a typical operation scenario to construct a typical operation scenario set; The probability of each typical operation scenario is quantified according to the number of historical operation scenarios contained in each typical operation scenario in the typical operation scenario set.

[0009] As one of the preferred solutions, the historical operation scenarios are clustered using a density peak clustering algorithm based on natural nearest neighbors, and the cluster centers are used as typical operation scenarios to construct a typical operation scenario set, including: Quantifying the Euclidean distances between the historical operation scenarios to obtain a distance matrix, and quantifying the natural nearest neighbor sets of the historical operation scenarios based on the Euclidean distance matrix; quantifying the local density and relative distance of each of the historical operation scenarios through each of the natural nearest neighbor sets and the distance matrix, and selecting a number of cluster centers according to the product of each of the local densities and each of the relative distances; A number of typical operation scenarios are determined according to each of the cluster centers, so as to construct the typical operation scenario set according to each of the typical operation scenarios.

[0010] As one of the preferred solutions, the supply-demand complementarity evaluation index is expressed by the following formula: In the formula, It is an evaluation indicator of supply and demand complementarity; is the power of the adjustable resource on the a-th source side at time t; is the power of the b-th load-side adjustable resource at time t; N is an integer; The volatility complementarity evaluation index is expressed by the following formula: In the formula, It is the evaluation index of volatility complementarity; is the power change rate of the adjustable resource on the a-th source side at time t; is the power change rate of the b-th load-side adjustable resource at time t; is the time interval; The energy complementarity evaluation index is expressed by the following formula: In the formula, It is an evaluation index of energy complementarity.

[0011] As one of the preferred solutions, before determining the weights of the complementarity evaluation indicators by improving the CRITIC entropy weight combination weighting method, the following steps are included: Standardizing the complementary evaluation indicators to obtain standardized indicators, and quantifying the correlation between the complementary evaluation indicators to obtain indicator correlation; The information amount of each of the complementary evaluation indicators is quantified based on the correlation of each of the indicators to obtain the indicator information amount, and the entropy value of each of the complementary evaluation indicators is determined according to each of the standardized indicators and the indicator information amount.

[0012] As one of the preferred solutions, the weights of the complementarity evaluation indicators are determined by improving the CRITIC entropy weight combination weighting method, and the comprehensive scores of complementarity between various adjustable resources in the target regional power grid are quantified based on the weighted complementarity evaluation indicators and the probabilities, including: Based on the entropy values ​​and the information content of each indicator, the weight of each complementarity evaluation indicator is determined by improving the CRITIC entropy weight combination weighting method; wherein the weight is calculated by the following formula: In the formula, is the weight of the jth complementarity evaluation index; , are the entropy value and information content of the jth complementarity evaluation index respectively; K is 3; The complementarity evaluation indicators are weighted according to the weights, and the complementarity between various adjustable resources in the target area power grid is determined by the weighted complementarity evaluation indicators and the probabilities to output the score as the comprehensive evaluation result of the source-load adjustable resources; wherein the comprehensive complementarity score is calculated by the following formula: In the formula, is the comprehensive score of complementarity between the adjustable resources on the source side of type a and the adjustable resources on the load side of type b; is the probability of the i-th typical operation scenario; is the value of the jth complementarity evaluation index under the i-th typical operation scenario.

[0013] A second aspect of the present invention provides a comprehensive evaluation system for power grid source-load adjustable resources, comprising: A database construction module is used to classify the source-load adjustable resources in the target area power grid according to the power supply and consumption characteristics, and obtain the historical power curves of various adjustable resources to build a power supply and consumption database of source-load adjustable resources; A scenario clustering module, used to cluster the historical operation scenarios in the source-load adjustable resource supply and consumption power database by using a density peak clustering algorithm based on a natural nearest neighbor, and generate a set of typical operation scenarios and their probabilities; An indicator construction module is used to construct a source-load adjustable resource complementarity evaluation index system of the target area power grid to quantify various complementarity evaluation indicators under the typical operation scenario set; the source-load adjustable resource complementarity evaluation index system includes supply-demand complementarity evaluation index, fluctuation complementarity evaluation index and energy complementarity evaluation index; The resource evaluation module is used to determine the weights of each of the complementary evaluation indicators by improving the CRITIC entropy weight combination weighting method, and quantify the comprehensive complementarity score between various adjustable resources in the target area power grid based on the weighted complementary evaluation indicators and the probabilities.

[0014] A third aspect of the present invention provides an electronic device, comprising 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, the method for comprehensively evaluating adjustable resources of power grid sources and loads as described above is implemented.

[0015] A fourth aspect of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the comprehensive evaluation method for power grid source-load adjustable resources as described above is implemented.

[0016] Compared with the prior art, the embodiments of the present invention have the following advantages: (1) The original operation scene set is clustered using the density peak clustering algorithm based on the natural nearest neighbor. On the basis of retaining the advantages of efficient and fast clustering of the original density peak clustering algorithm, the local density definition is improved based on the natural nearest neighbor, without the need to manually specify the truncation distance, thus achieving fast and accurate recognition of the data; (2) A complementarity evaluation index system based on supply-demand matching, fluctuation matching, and energy matching was established to quantify the degree of complementarity of adjustable-source-load resources. At the same time, the complementarity evaluation based on typical operating scenarios can represent the complementarity of adjustable-source-load resources in the operating scenarios of the entire cycle, thereby improving the accuracy and efficiency of the complementarity evaluation and reducing the complexity and amount of calculation. (3) The improved CRITIC entropy weight combination weighting method is used to determine the weights. This method has a simple calculation process and is not affected by subjective factors. It can objectively and accurately calculate the weights of the evaluation indicators. In addition, the present invention refines the overall source-load matching analysis to the source-load adjustable resources, which can evaluate the complementarity between the source-load adjustable resources of the regional power grid and provide guidance for the optimal scheduling of adjustable resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the implementation mode will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of a comprehensive evaluation method of power grid source-load adjustable resources provided by a certain embodiment of the present invention; Figure 2 It is a structural diagram of a comprehensive evaluation system for power grid source-load adjustable resources provided by a certain embodiment of the present invention; Figure 3 It is a structural diagram of an electronic device provided by a certain embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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 components. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are for illustrative purposes only, and do not indicate or imply that the system or component 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] In one embodiment, if Figure 1 As shown, the first aspect of the present invention provides a comprehensive evaluation method for power grid source-load adjustable resources, comprising: S1. Classify the source-load adjustable resources in the target area power grid according to the power supply and consumption characteristics, and obtain the historical power curves of various adjustable resources to build a power supply and consumption database of source-load adjustable resources; Specifically, the present invention classifies the source-load adjustable resources in the target area power grid according to the power supply and consumption characteristics, taking the adjustable resources for power supply as the source-side adjustable resources and the adjustable resources for power consumption as the load-side adjustable resources. Then, in one embodiment, the classification results of the source-load adjustable resources include source-side adjustable resources and load-side adjustable resources; the source-side adjustable resources include distributed photovoltaics and distributed wind power; the load-side adjustable resources include transferable loads, reducible loads, and shiftable loads among residential loads, commercial loads, and industrial loads; and for the source-load power supply and consumption adjustable resources with both source-side power supply characteristics and load-side power consumption characteristics (such as new loads like electric vehicles and energy storage devices like batteries), the present invention can use the daily power interaction volume of this resource as the judgment basis to add it to the source side or the load side. For example, if the discharge amount of a battery on a certain day is A1 and the charge amount is A2, then when A1 < A2, it means that the battery discharges more than it charges on that day, so the battery can be determined as a source-side adjustable resource on that day. Similarly, when A1 > A2, the battery can be determined as a load-side adjustable resource on that day. Based on the above principle, the source-load power supply and consumption adjustable resources can be allocated to the source-side adjustable resources or the load-side adjustable resources at the corresponding time. Then, on an annual basis, historical daily power curves of various types of adjustable resources in the same period are obtained from channels such as the power grid dispatching system, power generation enterprises, and power consumption enterprises, and the threshold detection method and the maximum likelihood method are respectively used to detect and correct the abnormal data in these historical daily power curves to unify the data granularity, and a reasonable database structure is designed, including table structure, field definition, index, etc. The obtained historical power curve data is sorted, plotted, and then imported into the database to form a source-load adjustable resource power supply and consumption power database. The present invention refines the previous overall matching degree analysis of the source and load to the source-side and load-side adjustable resources, can evaluate the complementarity between various source-load adjustable resources in the regional power grid, and provides guidance for the optimal dispatching of adjustable resources.

[0024] S2. Cluster the historical operation scenarios in the source-load adjustable resource power supply and consumption power database by using the density peak clustering algorithm based on natural nearest neighbors to generate a set of typical operation scenarios and their probabilities; In one embodiment, step S2 includes: Obtain the historical power curves of various types of adjustable resources in the source-load adjustable resource power supply and consumption power database, and perform normalization and combination processing on the historical power curves of the adjustable resources on the same day to generate a number of historical operation scenarios; Cluster each of the historical operation scenarios by using the density peak clustering algorithm based on natural nearest neighbors, and use the clustering centers as the typical operation scenarios to construct a set of typical operation scenarios; Quantify the probabilities of the typical operation scenarios according to the number of historical operation scenarios contained in each typical operation scenario in the set of typical operation scenarios.

[0025] Specifically, due to the strong volatility and uncertainty of source-load adjustable resources, the source-side output curve and load curve in the same year lack regularity. It is impossible to accurately evaluate the complementarity of source-load resources based on historical data in a single scenario, and clustering the historical power curves of source-load adjustable resources separately will ignore the power timing correlation of source-load adjustable resources. Based on this, the present invention combines the power curves of the source side and the load side to form a structured set of original operation scenarios, and clusters them to reduce a large amount of historical data to several typical operation scenarios, including: Obtain n historical daily power curves of the a-th source-side adjustable resource from the power supply and consumption database of the source-load adjustable resource, and record the i-th day curve as , where N is an integer, ranging from 1, 2, ..., 24; then, the n historical daily power curves of the b-th load-side adjustable resource and the same day as the source-side adjustable resource a are obtained from the source-load adjustable resource supply and consumption power database, and the i-th day curve is recorded as ; And the daily power curve data of the two adjustable resources are normalized to unify the data magnitude and ensure data comparability; the normalization method is shown in the following formula: In the formula, and They are the data before and after normalization, i.e., the historical daily power curve data of various adjustable resources; For data The mean of For data The standard deviation of .

[0026] Then, the normalized power curve data of the source-side and load-side adjustable resources on the ith day are combined to obtain several historical operation scenarios, which are expressed by the following formula: In the formula, Run the scenario for the ith history.

[0027] Finally, the density peak clustering algorithm based on natural nearest neighbor is used to cluster these historical operation scenarios, and the cluster center is used as the typical operation scenario to form a typical operation scenario set. The probability p of each typical operation scenario is calculated according to the number of historical operation scenarios contained in each type of typical operation scenario in the typical operation scenario set. i , which is calculated by the following formula: , where v i is the number of historical operation scenarios included in each typical operation scenario; n is the total number of historical operation scenarios.

[0028] The present invention realizes the effective integration of a large amount of historical data by extracting the historical power curves of various adjustable resources from the power supply and consumption database of source-load adjustable resources; normalizing the historical power curves of adjustable resources on the same day, eliminating the differences in power magnitudes of different resources, making the data more comparable; the historical operation scenarios generated after the combined processing provide a rich and standardized data set for subsequent clustering analysis; the generated historical operation scenarios can comprehensively reflect the operating status of source-load adjustable resources at different times and under different conditions, which helps to more accurately grasp the operating laws and potential risks of resources; the typical operation scenario set can summarize and reflect the main operating status and changing trends of source-load adjustable resources, providing an important reference basis for the planning, scheduling and optimization of the power system, and helping to improve the operating efficiency and safety of the system.

[0029] In another embodiment, clustering of typical scenarios can also be achieved by combining a time series alignment method, a clustering algorithm, and a probability model, including: The similarity between the power curves of various adjustable resources is calculated by using the Dynamic Time Warping (DTW) method, that is, the DTW distance is used as the similarity metric to calculate the similarity between the normalized power curve data of the source-side and load-side adjustable resources on the i-th day; then K-Shape clustering is used to cluster based on shape similarity, and the cluster center is iteratively optimized to align with the data to adapt to the differences in power curve morphology: 1. Initialize the centroid and align all curves with the centroid using the similarity calculated by DTW; 2. Calculate shape similarity based on normalized cross-correlation, that is, use the cross-correlation distance to calculate the distance between each power curve and the cluster center, and use this distance to assign each curve to the cluster to which the nearest cluster center belongs; 3. Update the centroid to the average shape of the curves in the current cluster, that is, for each cluster, recalculate The cluster center can be updated by the average or median of all curves in the cluster under a certain distance metric; repeat 2 and 3 until convergence, and output the clustering results; then, based on the K-Shape clustering results, use the Gaussian mixture model GMM (a probability model used to represent data distribution, which can assign probabilities of belonging to different clusters to each data point) to perform probability correction on the clustering results. Through GMM, the probability distribution of each power curve belonging to different typical operating scenarios can be obtained; finally, based on the K-Shape clustering results and the probability distribution of GMM, typical operating scenarios are extracted to construct a typical operating scenario set, and each typical operating scenario corresponds to a probability value, which indicates the frequency or possibility of the scenario appearing in historical data.

[0030] The present invention combines DTW and K-Shape algorithms, which can fully consider the characteristics of time series data such as timing, trend and local changes, thereby improving the accuracy of clustering; DTW captures the nonlinear alignment relationship between time series, so that the clustering results can better reflect the morphological characteristics of the power curve; GMM is used for probability correction, and the probability of belonging to different clusters can be assigned to each power curve, thereby enhancing the reliability of the clustering results; the generated typical operation scenario set and its probability can provide strong support for power system scheduling, optimization and management, and help decision makers better understand and predict the operation behavior of adjustable resources; this method combines the advantages of multiple algorithms, has strong adaptability and flexibility, and can be applied to historical power curve data of adjustable resources of different types and scales.

[0031] In one embodiment, clustering each of the historical operation scenarios using a density peak clustering algorithm based on a natural nearest neighbor, and taking the cluster center as a typical operation scenario to construct a typical operation scenario set includes: Quantifying the Euclidean distances between the historical operation scenarios to obtain a distance matrix, and quantifying the natural nearest neighbor sets of the historical operation scenarios based on the Euclidean distance matrix; quantifying the local density and relative distance of each of the historical operation scenarios through each of the natural nearest neighbor sets and the distance matrix, and selecting a number of cluster centers according to the product of each of the local densities and each of the relative distances; A number of typical operation scenarios are determined according to each of the cluster centers, so as to construct the typical operation scenario set according to each of the typical operation scenarios.

[0032] In this embodiment, the Euclidean distance between the i-th and j-th historical operation scenarios is first calculated. , forming a distance matrix; then calculating the natural nearest neighbor set of each historical operation scenario : Assume that the number of nearest neighbors of each scene is KN, and the KN value increases from 1 and increases by 1 each time. For each running scene, sort the Euclidean distance between the scene and other scenes, select KN nearest neighbors in order from small to large according to the Euclidean distance, and form the nearest neighbor set of the scene. Calculate the number of times each scene appears in the nearest neighbor set of other scenes. When all scenes appear at least once, the KN value will no longer change. Based on this KN value, the natural nearest neighbor set corresponding to each scene can be obtained; then, based on the natural nearest neighbor set and distance matrix of each historical running scene, its local density and relative distance are quantified as follows: In the formula, is the local density of the i-th historical running scenario; is the relative distance of the i-th historical running scenario; Finally, the product of the local density and relative distance in the i-th historical operation scenario is used as the cluster center, that is, the i-th typical operation scenario, and the typical operation scenario set is constructed based on this. ,in Indicates The cluster center, i.e. Typical operation scenarios, M represents the number of cluster centers, that is, the number of typical operation scenarios.

[0033] The present invention adopts a density peak clustering algorithm based on natural nearest neighbors to cluster the historical operation scenario sets. While retaining the advantages of efficient and fast clustering of the original density peak clustering algorithm, the algorithm improves the local density definition based on natural nearest neighbors, does not require artificially specified truncation distances, and is suitable for rapid and accurate identification of various data sets; and the complementarity evaluation based on typical operation scenarios can represent the complementarity of the source-load adjustable resources in the operation scenarios of the entire cycle, thereby improving the accuracy and efficiency of the complementarity evaluation and reducing the complexity and amount of calculation.

[0034] S3. Constructing a source-load adjustable resource complementarity evaluation index system of the target regional power grid to quantify various complementarity evaluation indexes under the typical operation scenario set; the source-load adjustable resource complementarity evaluation index system includes supply-demand complementarity evaluation index, fluctuation complementarity evaluation index and energy complementarity evaluation index; Specifically, the present invention aims at the time series characteristics of the power curves on the source and load sides, and constructs a source-load adjustable resource complementarity evaluation index system based on the supply-demand matching degree, the fluctuation matching degree and the energy matching degree. Through this index system, the complementarity degree of the source-load adjustable resources can be quantified; wherein, the supply-demand complementarity evaluation index adopts the Euclidean distance to calculate the distance between the source-load power time series, which can measure the overall complementarity degree of power supply and demand in a certain period, that is, it is used to measure the similarity of the daily power curves of the source-load adjustable resources, which is expressed by the following formula: In the formula, It is an evaluation indicator of supply and demand complementarity; is the power of the adjustable resource on the a-th source side at time t; is the power of the b-type load-side adjustable resource at time t; the value range of the supply-demand complementarity evaluation index is , the closer it is to 1, the greater the similarity between the daily power curves of source-load adjustable resources, and the stronger the complementarity between supply and demand.

[0035] In addition to the complementary relationship between power supply and demand, the source-load adjustable resources may also have consistency in fluctuation trends. Therefore, the present invention defines a fluctuation complementarity evaluation index based on the source-load fluctuation change rate to analyze the source-load complementarity from the perspective of fluctuation matching, that is, to measure the similarity of the fluctuation trends of the daily power curves of the source-load adjustable resources. The fluctuation complementarity evaluation index is expressed by the following formula: In the formula, It is the evaluation index of volatility complementarity; is the power change rate of the adjustable resource on the a-th source side at time t; is the power change rate of the b-th load-side adjustable resource at time t; is the time interval; the value range of the volatility complementarity evaluation index is , the closer it is to 1, the greater the fluctuation similarity between the daily power curves of source-load adjustable resources and the stronger the fluctuation complementarity.

[0036] In order to more comprehensively reflect the power supply and demand relationship between the source and the load and evaluate the output and consumption of the adjustable resources on the source side throughout the day, the present invention sets an energy complementarity evaluation index to analyze the source-load complementarity from the perspective of energy matching, that is, to measure the output and consumption degree of the adjustable resources on the source side. The energy complementarity evaluation index is expressed by the following formula: In the formula, is the energy complementarity evaluation index; the value range of the energy complementarity evaluation index is , the closer it is to 1, the higher the output absorption rate of adjustable resources on the source side is, and the stronger the energy complementarity between source and load is. When it is equal to 1, it indicates that the adjustable resource output on the source side has been fully absorbed.

[0037] Then, based on the constructed source-load adjustable resource complementarity evaluation index system, various complementarity evaluation indicators under the typical operation scenario set are quantified. The present invention constructs a complementarity evaluation index system for source-load adjustable resources from three perspectives: supply-demand complementarity, fluctuation complementarity, and energy complementarity. By quantifying the difference and complementarity between supply and demand, it helps to optimize the power supply layout and load management, and ensure the stable operation and efficient utilization of the power grid; by quantifying fluctuation complementarity, it can guide the configuration and scheduling of the energy storage system to smooth the fluctuation of new energy power generation and improve the stability and reliability of the power grid; by quantifying energy complementarity, it helps to optimize the energy structure, improve energy utilization efficiency, and reduce dependence on traditional energy; and it can comprehensively, intuitively, and quantitatively reflect the complementary relationship of source-load adjustable resources, which can provide assistance for the planning and construction of future distributed new energy power generation or demand response, thereby ensuring the safe and stable operation of the power system.

[0038] S4. Determine the weight of each of the complementarity evaluation indicators by improving the CRITIC entropy weight combination weighting method, and quantify the comprehensive score of complementarity between various adjustable resources in the target area power grid based on the weighted complementarity evaluation indicators and the probabilities; In one embodiment, before determining the weights of the complementarity evaluation indicators by improving the CRITIC entropy weight combination weighting method, the following steps are included: Standardizing the complementary evaluation indicators to obtain standardized indicators, and quantifying the correlation between the complementary evaluation indicators to obtain indicator correlation; The information amount of each of the complementary evaluation indicators is quantified based on the correlation of each of the indicators to obtain the indicator information amount, and the entropy value of each of the complementary evaluation indicators is determined according to each of the standardized indicators and the indicator information amount.

[0039] Specifically, the present invention first performs a standardization process on each calculated complementarity evaluation index, which is performed by the following formula: In the formula, , The values ​​of the jth complementarity evaluation index in the i-th typical operation scenario before and after standardization respectively; where k = 1, 2, 3, then , , are the values ​​of the supply-demand complementarity evaluation index, fluctuation complementarity evaluation index and energy complementarity evaluation index under the i-th typical operation scenario.

[0040] Then quantify the correlation between the complementary evaluation indicators , which is carried out by the following formula: In the formula, is the average value of the pth complementarity index; is the average value of the qth complementarity index; is the value of the pth complementarity index in the ith typical operation scenario; is the value of the qth complementarity index in the ith typical operation scenario; where p and q can both be 1, 2, or 3. 1. The closer it is to 1, the greater the correlation between indicators.

[0041] Then, the information amount of each complementary evaluation index is quantified based on the calculated correlation of each index, which is performed by the following formula: In the formula, is the indicator information of the jth complementarity evaluation indicator; is the standard deviation of the jth complementarity evaluation index; is the correlation between the kth and jth complementary evaluation indicators; K is 3.

[0042] Finally, the entropy value of each complementarity evaluation index is determined according to each standardized index and the information content of each index, which is carried out by the following formula: In the formula, is the entropy value of the jth complementarity evaluation index; m ij It is the proportion of the jth complementarity evaluation index in the i-th typical operation scenario, which can also be called the normalized result.

[0043] The present invention standardizes the complementary indicators so that the indicators are comparable, laying a foundation for the subsequent quantitative correlation and entropy calculation. By quantifying the correlation between the complementary evaluation indicators, the internal connection and mutual influence between the indicators can be revealed, which is helpful for in-depth understanding of the overall structure of the evaluation system for subsequent optimization of weight distribution, ensuring that the weight distribution is more reasonable and scientific, thereby improving the accuracy and reliability of the evaluation results. By calculating the entropy value of each complementary evaluation indicator, the discrete degree and uncertainty of the information contained in the indicator can be reflected, which can serve as an important basis for decision analysis, helping decision makers to identify key indicators and potential risks, thereby formulating more effective decision-making plans.

[0044] In one embodiment, step S4 includes: Based on the entropy values ​​and the information content of each indicator, the weight of each complementarity evaluation indicator is determined by improving the CRITIC entropy weight combination weighting method; wherein the weight is calculated by the following formula: In the formula, is the weight of the jth complementarity evaluation index; The complementarity evaluation indicators are weighted according to the weights, and the comprehensive complementarity scores between various adjustable resources in the target area power grid are determined by the weighted complementarity evaluation indicators and the probabilities to output as the comprehensive evaluation result of the source-load adjustable resources; wherein the comprehensive complementarity score is calculated by the following formula: In the formula, It is the comprehensive score of the complementarity between the a-type source-side adjustable resources and the b-type load-side adjustable resources. The higher the value, the higher the complementarity between the two types of source-load resources a and b.

[0045] In the comprehensive evaluation process, the weight of each evaluation index is closely related to the credibility of the evaluation results. In order to ensure the accuracy and objectivity of the weight, it is necessary to fully consider the differences and correlations between the evaluation indicators. Therefore, the improved CRITIC entropy weight combination weighting method is adopted in this paper to determine the weight. The calculation process of this method is simple and is not affected by subjective factors. It can objectively and accurately calculate the weight of the evaluation index.

[0046] In another embodiment, the present invention may also use the entropy weight method to determine the weight of each complementarity evaluation index; or an innovative hybrid algorithm framework combining subjective and objective methods may be used, that is, the variation coefficient method, the hierarchical analysis method and the fuzzy comprehensive evaluation are combined, and the weight distribution is optimized through the game theory combination weighting, so as to obtain the weight of each complementarity evaluation index, which includes the following steps: firstly, the data of each complementarity evaluation index is normalized to eliminate the dimension effect, the mean and standard deviation of each complementarity evaluation index are calculated to obtain the corresponding variation coefficient, and the variation coefficient is normalized to obtain the objective weight W obj ; Then, the fuzzy judgment matrix is ​​constructed: experts use triangular fuzzy numbers (such as "slightly important" corresponds to (2,3,4)) instead of the traditional 1-9 scale to reduce the ambiguity of subjective judgment. At the same time, the rationality of the matrix is ​​verified by the fuzzy consistency index (FCR). If it fails, the fuzzy number boundary is adjusted, and the fuzzy analytic hierarchy process (FAHP) is used to solve the subjective weight W sub ; Finally, the subjective and objective weight vector is defined based on the subjective and objective weights (i.e. W1=W obj 、W2=W sub ), and use this to construct the combined weight (W=αW1+βW2, α and β are the combination coefficients). Through game theory optimization, the deviation between the combined weight and each single weight is minimized to obtain the deviation optimization model (min‖W-W1‖ 2 +‖W-W2‖ 2 ), after solving the model, the optimal coefficients α and β are obtained, and the final weights are obtained after normalization. The present invention realizes multi-angle weight fusion by taking into account the objectivity of data, expert experience and fuzzy information processing, improves the scientific nature of weight allocation, and effectively improves the accuracy of the evaluation of the adjustable resources of the power grid source and load.

[0047] In the embodiment of the present application, based on the problem of how to improve the accuracy of the existing scheme for evaluating the source-load adjustable resources of the regional power grid, a comprehensive evaluation method for the source-load adjustable resources of the power grid is designed. The source-load adjustable resources are classified according to the power supply and consumption characteristics to construct a database, and the density peak clustering algorithm based on the natural nearest neighbor is used to cluster the original operation scenario set in the database to obtain a typical operation scenario. On the basis of retaining the advantages of efficient and fast clustering of the original density peak clustering algorithm, the local density definition is improved based on the natural nearest neighbor, without the need to manually specify the truncation distance, thereby achieving rapid and accurate identification of data; a complementary evaluation index system based on supply and demand matching, fluctuation matching and energy matching is established The degree of complementarity between the source-load adjustable resources under each typical operating scenario is quantified to represent the complementarity of the source-load adjustable resources in the operating scenarios throughout the entire cycle, thereby improving the accuracy and efficiency of the complementarity assessment and reducing the complexity and amount of calculation; finally, the improved CRITIC entropy weight combination weighting method is used to determine the weights to weight the calculated complementarity evaluation indicators, and a comprehensive score is obtained as the output of the comprehensive evaluation results of the source-load adjustable resources in the target regional power grid; the overall source-load matching degree analysis is refined to the source-load adjustable resources, which can evaluate the complementarity between the source-load adjustable resources of the regional power grid, provide guidance for the optimal scheduling of adjustable resources, and effectively improve the accuracy of the assessment of the source-load adjustable resources of the power grid.

[0048] It should be noted that although the steps in the above flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders.

[0049] In another embodiment, if Figure 2 As shown, the second aspect of the present invention provides a comprehensive evaluation system for power grid source-load adjustable resources, comprising: The database construction module 10 is used to classify the source-load adjustable resources in the target area power grid according to the power supply and consumption characteristics, and obtain the historical power curves of various adjustable resources to build a power supply and consumption database of the source-load adjustable resources; A scenario clustering module 20, configured to cluster the historical operation scenarios in the source-load adjustable resource supply and consumption power database by using a density peak clustering algorithm based on a natural nearest neighbor, and generate a set of typical operation scenarios and their probabilities; An indicator construction module 30 is used to construct a source-load adjustable resource complementarity evaluation index system of the target regional power grid to quantify various complementarity evaluation indicators under the typical operation scenario set; the source-load adjustable resource complementarity evaluation index system includes a supply-demand complementarity evaluation index, a fluctuation complementarity evaluation index and an energy complementarity evaluation index; The resource evaluation module 40 is used to determine the weights of each of the complementary evaluation indicators by improving the CRITIC entropy weight combination weighting method, and quantify the comprehensive complementarity score between various adjustable resources in the target area power grid based on the weighted complementary evaluation indicators and the probabilities.

[0050] It should be noted that each module in the above-mentioned comprehensive evaluation system for power grid source-load adjustable resources can be fully or partially implemented by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. For the specific definition of a comprehensive evaluation system for power grid source-load adjustable resources, please refer to the definition of a comprehensive evaluation method for power grid source-load adjustable resources above. The two have the same functions and effects, which will not be repeated here.

[0051] A third aspect of the present invention provides an electronic device, the electronic device comprising: processor, memory, and bus; The bus is used to connect the processor and the memory; The memory is used to store operation instructions; The processor is used to call the operation instruction, and the executable instruction enables the processor to perform operations corresponding to the comprehensive evaluation method of power grid source and load adjustable resources as shown in the first aspect of the present application.

[0052] In an alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The electronic device 5000 shown includes: a processor 5001 and a memory 5003. The processor 5001 and the memory 5003 are connected, such as through a bus 5002. Optionally, the electronic device 5000 may also include a transceiver 5004. It should be noted that in actual applications, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation on the embodiments of the present application.

[0053] Processor 5001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 5001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0054] The bus 5002 may include a path to transmit information between the above components. The bus 5002 may be a PCI bus or an EISA bus, etc. The bus 5002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0055] The memory 5003 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an EEPROM, a CD-ROM or other optical disk storage, an optical disk storage (including a compressed optical disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0056] The memory 5003 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 5001. The processor 5001 is used to execute the application code stored in the memory 5003 to implement the content shown in any of the above method embodiments.

[0057] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0058] The fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, a comprehensive evaluation method for power grid source-load adjustable resources shown in the first aspect of the present application is implemented.

[0059] Another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0060] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0061] In summary, the present invention relates to the field of data processing technology, and discloses a comprehensive evaluation method, system, device and medium for source-load adjustable resources of a power grid. The method classifies the source-load adjustable resources of the power grid in the target area and obtains the historical power data of various adjustable resources; clusters these power data using a density peak clustering algorithm based on natural nearest neighbors to generate a typical operation scenario set and its probability; constructs a source-load adjustable resource complementarity evaluation index system including supply-demand complementarity evaluation index, fluctuation complementarity evaluation index and energy complementarity evaluation index to quantify various complementarity evaluation indexes under a typical operation scenario set; determines the weights of various complementarity evaluation indexes by improving the CRITIC entropy weight combination weighting method, calculates the comprehensive complementarity scores between various adjustable resources of the power grid based on the weighted complementarity evaluation index and probability, and refines the overall source-load matching analysis to the source-load adjustable resources to improve the evaluation accuracy of the source-load adjustable resources of the power grid.

[0062] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0063] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A comprehensive evaluation method for adjustable power grid source and load resources, characterized in that: include: Classify the source-load adjustable resources in the target area power grid according to the power supply and consumption characteristics, and obtain the historical power curves of various adjustable resources to build a power supply and consumption database of source-load adjustable resources; Clustering the historical operation scenarios in the source-load adjustable resource power supply and consumption database by a density peak clustering algorithm based on natural nearest neighbors to generate a set of typical operation scenarios and their probabilities; Constructing a source-load adjustable resource complementarity evaluation index system of the target regional power grid to quantify various complementarity evaluation indicators under the typical operation scenario set; the source-load adjustable resource complementarity evaluation index system includes supply-demand complementarity evaluation index, fluctuation complementarity evaluation index and energy complementarity evaluation index; The weights of the complementarity evaluation indicators are determined by improving the CRITIC entropy weight combination weighting method, and the comprehensive scores of complementarity between various adjustable resources in the target area power grid are quantified based on the weighted complementarity evaluation indicators and the probabilities.

2. A comprehensive evaluation method for power grid source-load adjustable resources according to claim 1, characterized in that: The classification results of the source-load adjustable resources include source-side adjustable resources and load-side adjustable resources; the source-side adjustable resources include distributed photovoltaic and distributed wind power; the load-side adjustable resources include transferable loads, curtailable loads and shiftable loads among residential loads, commercial loads and industrial loads.

3. A comprehensive evaluation method for power grid source-load adjustable resources according to claim 1, characterized in that: The historical operation scenarios in the source-load adjustable resource power supply and consumption database are clustered by a density peak clustering algorithm based on natural nearest neighbors to generate a typical operation scenario set and its probability, including: Obtaining historical power curves of various adjustable resources in the power supply and consumption database of the source-load adjustable resources, and normalizing and combining the historical power curves of the adjustable resources on the same day to generate several historical operation scenarios; Clustering each of the historical operation scenarios using a density peak clustering algorithm based on natural nearest neighbors, and taking the cluster center as a typical operation scenario to construct a typical operation scenario set; The probability of each typical operation scenario is quantified according to the number of historical operation scenarios contained in each typical operation scenario in the typical operation scenario set.

4. A comprehensive evaluation method for power grid source-load adjustable resources according to claim 3, characterized in that: The method of clustering the historical operation scenarios by using a density peak clustering algorithm based on natural nearest neighbors, and taking the cluster center as a typical operation scenario to construct a typical operation scenario set includes: Quantifying the Euclidean distances between the historical operation scenarios to obtain a distance matrix, and quantifying the natural nearest neighbor sets of the historical operation scenarios based on the Euclidean distance matrix; quantifying the local density and relative distance of each of the historical operation scenarios through each of the natural nearest neighbor sets and the distance matrix, and selecting a number of cluster centers according to the product of each of the local densities and each of the relative distances; A number of typical operation scenarios are determined according to each of the cluster centers, so as to construct the typical operation scenario set according to each of the typical operation scenarios.

5. A comprehensive evaluation method for power grid source-load adjustable resources according to claim 1, characterized in that: The supply-demand complementarity evaluation index is expressed by the following formula: In the formula, It is an evaluation indicator of supply and demand complementarity; is the power of the adjustable resource on the a-th source side at time t; is the power of the b-th load-side adjustable resource at time t; N is an integer; The volatility complementarity evaluation index is expressed by the following formula: In the formula, It is the evaluation index of volatility complementarity; is the power change rate of the adjustable resource on the a-th source side at time t; is the power change rate of the b-th load-side adjustable resource at time t; is the time interval; The energy complementarity evaluation index is expressed by the following formula: In the formula, It is an evaluation index of energy complementarity.

6. A comprehensive evaluation method for power grid source-load adjustable resources according to claim 1, characterized in that: Before determining the weights of the complementary evaluation indicators by improving the CRITIC entropy weight combination weighting method, the method includes: Standardizing the complementary evaluation indicators to obtain standardized indicators, and quantifying the correlation between the complementary evaluation indicators to obtain indicator correlation; The information amount of each of the complementary evaluation indicators is quantified based on the correlation of each of the indicators to obtain the indicator information amount, and the entropy value of each of the complementary evaluation indicators is determined according to each of the standardized indicators and the indicator information amount.

7. A comprehensive evaluation method for power grid source-load adjustable resources according to claim 6, characterized in that: The weights of the complementarity evaluation indicators are determined by improving the CRITIC entropy weight combination weighting method, and the comprehensive scores of complementarity between various adjustable resources in the target regional power grid are quantified based on the weighted complementarity evaluation indicators and the probabilities, including: Based on the entropy values ​​and the information content of each indicator, the weight of each complementarity evaluation indicator is determined by improving the CRITIC entropy weight combination weighting method; wherein the weight is calculated by the following formula: In the formula, is the weight of the jth complementarity evaluation index; , are the entropy value and information content of the jth complementarity evaluation index respectively; K is 3; The complementarity evaluation indicators are weighted according to the weights, and the comprehensive complementarity scores between various adjustable resources in the target area power grid are determined by the weighted complementarity evaluation indicators and the probabilities to output as the comprehensive evaluation result of the source-load adjustable resources; wherein the comprehensive complementarity score is calculated by the following formula: In the formula, is the comprehensive score of complementarity between the adjustable resources on the source side of type a and the adjustable resources on the load side of type b; is the probability of the i-th typical operation scenario; is the value of the jth complementarity evaluation index under the i-th typical operation scenario.

8. A comprehensive evaluation system for adjustable power grid source and load resources, characterized in that: include: A database construction module is used to classify the source-load adjustable resources in the target area power grid according to the power supply and consumption characteristics, and obtain the historical power curves of various adjustable resources to build a power supply and consumption database of source-load adjustable resources; A scenario clustering module, used to cluster the historical operation scenarios in the source-load adjustable resource supply and consumption power database by using a density peak clustering algorithm based on a natural nearest neighbor, and generate a set of typical operation scenarios and their probabilities; An indicator construction module is used to construct a source-load adjustable resource complementarity evaluation index system of the target area power grid to quantify various complementarity evaluation indicators under the typical operation scenario set; the source-load adjustable resource complementarity evaluation index system includes supply-demand complementarity evaluation index, fluctuation complementarity evaluation index and energy complementarity evaluation index; The resource evaluation module is used to determine the weights of each of the complementary evaluation indicators by improving the CRITIC entropy weight combination weighting method, and quantify the comprehensive complementarity score between various adjustable resources in the target area power grid based on the weighted complementary evaluation indicators and the probabilities.

9. An electronic device, characterized in that: It includes 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 the comprehensive evaluation method for power grid source-load adjustable resources as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the comprehensive evaluation method for power grid source-load adjustable resources as described in any one of claims 1 to 7 is implemented.

Images