Flexible controllable resource control performance quantitative evaluation method

Abstract

The invention relates to the technical field of power grid dispatching, and discloses a flexible controllable resource control performance quantitative evaluation method, which comprises the following steps: processing historical data of flexible controllable resources of a power grid to obtain a historical effective data set of the flexible controllable resources; dividing a new energy cluster, an output complementary cluster and a flexible load cluster; establishing a space-time response control performance index system and a special index system for different cluster characteristics; and for the space-time response control performance index system and the special index system, performing weighted calculation by using an entropy weight method to obtain comprehensive quantitative control performance indexes of the new energy cluster, the output complementary cluster and the flexible load cluster. According to the method, the control performance of the flexible controllable resources can be accurately and effectively evaluated, the flexibility and accuracy of power grid dispatching are ensured, and the consumption of new energy and the safe operation of a power system are promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated energy systems, and in particular to a method for quantitatively evaluating control performance of flexible controllable resources. Background Art

[0002] With the rapid development of flexible controllable resources and their large-scale access to the power grid, the power system is gradually shifting towards a cleaner and more sustainable direction. However, the traditional power system architecture has certain limitations for the large-scale integration and dispatching of new energy sources, and the operation of the power system is also facing higher complexity and challenges. In order to effectively respond to these challenges and achieve the maximum absorption of new energy sources, a large number of studies have proposed optimal dispatching methods for flexible controllable resources. However, most of the current studies have ignored the consideration of the control performance of flexible controllable resources, making the proposed dispatching plan inconsistent with the actual output of flexible controllable resources, which seriously affects the absorption of new energy sources and the safe and stable operation of the power system.

[0003] At present, there is no unified standard for the control performance evaluation method of flexible controllable resources, and the existing technologies are often limited to specific resource types or lack systematic considerations. In order to solve the above problems, it is necessary to propose an effective control performance quantitative evaluation method for flexible controllable resources such as wind power, photovoltaics, and flexible loads, so as to improve the consumption of new energy in the power grid and provide effective data support for the real-time coordinated control of the power grid. Summary of the invention

[0004] The present invention aims to at least solve the technical problem that existing research has neglected the consideration of the control performance of flexible controllable resources, resulting in the proposed scheduling plan being inconsistent with the actual output of flexible controllable resources, seriously affecting the absorption of new energy and the safe and stable operation of the power system.

[0005] To this end, an object of the present invention is to provide a method for quantitatively evaluating the control performance of flexible controllable resources, comprising the following steps:

[0006] The following steps are involved:

[0007] The improved grey wolf algorithm is used to optimize the support vector machine method to process the historical data of flexible controllable resources of the power grid, and the historical valid data set of flexible controllable resources is obtained;

[0008] Considering the maximum consumption of new energy and the safe operation of the power grid, the control characteristics of different resources are analyzed, and the historical effective data set of flexible controllable resources is divided into new energy clusters, output complementary clusters and flexible load clusters;

[0009] Considering the differences in regulation characteristics and dispatching stages among the new energy cluster, the output complementary cluster and the flexible load cluster, a spatiotemporal response control performance index system and a special index system for different cluster characteristics are established. The spatiotemporal response control performance index system is used to reflect the requirements of power grid regulation for the multivariate response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of power grid regulation for a certain type of flexible adjustable resources. The dispatching stage includes: the first stage, dispatching the output complementary cluster to preliminarily absorb the new energy cluster; the second stage, dispatching the flexible load cluster to supplement the new energy cluster;

[0010] For the spatiotemporal response control performance index system and the special index system, the entropy weight method is used to perform weighted calculation to obtain the quantitative control performance indicators of the new energy cluster, the output complementary cluster and the flexible load cluster respectively; based on the quantitative control performance indicators, the comprehensive quantitative control performance indicators of flexible controllable resources are obtained.

[0011] Furthermore, considering the differences in regulation characteristics and dispatching stages among the new energy cluster, the output complementary cluster and the flexible load cluster, a spatiotemporal response control performance index system and a special index system for different cluster characteristics are established. The spatiotemporal response control performance index system is used to reflect the requirements of power grid regulation for the multivariate response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of power grid regulation for a certain type of flexible adjustable resources. The dispatching stage includes: the first stage, dispatching the output complementary cluster to preliminarily absorb the new energy cluster; the second stage, dispatching the flexible load cluster to supplement the new energy cluster; wherein,

[0012] The evaluation indicators of the spatiotemporal response control performance indicator system include:

[0013] The time response control performance index is used to characterize the time taken by the flexible adjustable resource from receiving the adjustment instruction to the actual output reaching the set percentage of the target value for the first time;

[0014] The spatial response control performance index is used to characterize the power capacity of flexible adjustable resources that can be dispatched by the power grid within a set period of time;

[0015] The evaluation indicators of the special indicator system include:

[0016] New energy prediction performance indicators and spinning reserve capacity indicators used to reflect the special requirements of power grid regulation for new energy clusters; the new energy prediction performance indicators are used to characterize the uncertainty of new energy, indicating the degree of deviation between the predicted maximum output value of new energy and the actual maximum output value; the spinning reserve capacity indicator is the probability of insufficient output after the spinning reserve is configured, which is used to characterize the ability of new energy units to respond to faults and ensure the stable operation of the power system;

[0017] The first-stage optimal absorption rate of new energy and the power plant electricity execution rate indicators are used to reflect the special requirements of the power grid regulation for the output complementary cluster; the first-stage optimal absorption rate of new energy is used to characterize the absorption degree of the first-stage output complementary cluster for new energy; the power plant electricity execution rate indicator is used to characterize the execution degree of the power plant for the dispatch plan;

[0018] The second-stage optimal absorption rate and load execution rate indicators of new energy are used to reflect the special requirements of power grid regulation for flexible load clusters. The second-stage optimal absorption rate of new energy is used to characterize the degree of absorption of new energy by the second-stage output complementary cluster of scheduling; the load execution rate indicator is used to characterize the responsiveness of flexible adjustable resources to the scheduling plan.

[0019] Furthermore, for the spatiotemporal response control performance index system and the special index system, the quantitative control performance indexes of the new energy cluster, the output complementary cluster and the flexible load cluster are obtained by weighted calculation using the entropy weight method; based on the quantitative control performance index, the comprehensive quantitative control performance index of the flexible controllable resources is obtained, and the calculation of the comprehensive quantitative control performance index includes the following steps:

[0020] Standardizing the original data of the new energy cluster, the output complementary cluster and the flexible load cluster under the spatiotemporal response control performance index system and the special index system;

[0021] Using the standardized data, the information entropy of each evaluation indicator under different indicator systems is calculated;

[0022] By utilizing the information entropy of each evaluation index under different index systems, the spatiotemporal response control performance sub-index and the special performance sub-index corresponding to each cluster are aggregated;

[0023] The weight values ​​of the spatiotemporal response control performance sub-indicators and special performance sub-indicators corresponding to each cluster are set respectively, and the quantitative control performance indicators corresponding to the new energy cluster, the output complementary cluster and the flexible load cluster are obtained respectively by using the spatiotemporal response control performance sub-indicators, special performance sub-indicators and weight values ​​corresponding to each cluster.

[0024] Furthermore, the original data of the new energy cluster, the output complementary cluster and the flexible load cluster under the spatiotemporal response control performance index system and the special index system are standardized. Considering that all indicators are positive indicators, the standardized formula is:

[0025]

[0026] Where: is the index data value after the jth evaluation index of the flexible controllable load cluster k under the i-th index system is standardized, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; is the original data value of the index before normalization of the jth evaluation index of the flexible controllable load cluster k under the i-th index system, X i,j is the set of original data values ​​of the jth evaluation index of all flexible controllable load clusters under the i-th index system, max(X i,j ) is the maximum value of the original data value of the jth evaluation index of all flexible controllable load clusters under the i-th index system, min(X i,j ) is the minimum value of the original data value of the jth evaluation index of all flexible controllable load clusters under the i-th index system.

[0027] Furthermore, the standardized data is used to calculate the information entropy of each evaluation indicator under different indicator systems, including:

[0028] Assume that the information entropy of the jth evaluation index of the flexible controllable load cluster k under the i-th index system is Its expression is:

[0029]

[0030] Where: is the proportion of the jth evaluation index of the flexible controllable load cluster k in the i-th index system in the evaluation index column; It is the index data value after the jth evaluation index of the flexible controllable load cluster k under the i-th index system is standardized; k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; n is the number of evaluation indicators.

[0031] Furthermore, the information entropy of each evaluation index under different index systems is used to aggregate the spatiotemporal response control performance sub-index and special performance sub-index corresponding to each cluster, including:

[0032] The sub-indicators obtained by aggregating the i-th indicator system of the flexible controllable load cluster k for:

[0033]

[0034] Where: is the weight of the jth evaluation index of controllable load cluster k under the i-th index system; is the information entropy of the jth evaluation index of the flexible controllable load cluster k under the i-th index system, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; n is the number of evaluation indicators; It is the index data value after standardization of the jth evaluation index of the flexible controllable load cluster k under the i-th index system.

[0035] Furthermore, the weight values ​​of the spatiotemporal response control performance sub-indicators and special performance sub-indicators corresponding to each cluster are set respectively, and the spatiotemporal response control performance sub-indicators, special performance sub-indicators and weight values ​​corresponding to each cluster are used to obtain the comprehensive real-time control performance indicators corresponding to the new energy cluster, the output complementary cluster and the flexible load cluster respectively. The expression is:

[0036]

[0037] x k +y k =1

[0038] Where: S c,k is the control performance index corresponding to the flexible controllable load cluster k; and are the spatiotemporal response control performance index and special performance index of the flexible controllable load cluster k, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; x k is the spatiotemporal response control performance index of the flexible controllable load cluster k; y k It is the special performance index of the flexible controllable load cluster k.

[0039] Furthermore, the improved grey wolf algorithm is used to optimize the support vector machine method to process the historical data of the flexible controllable resources of the power grid to obtain a historical valid data set of the flexible controllable resources, including the following steps:

[0040] Preprocess the historical data of flexible and controllable resources of the power grid;

[0041] Use the improved grey wolf algorithm to solve the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm;

[0042] The optimal penalty factor and the optimal kernel function parameter are used to train a classification model, and the historical data set of the flexible controllable resources of the power grid is classified by the classification model to obtain a historical valid data set of the flexible controllable resources.

[0043] Furthermore, the improved grey wolf algorithm is used to solve the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm, including:

[0044] Set the mirror factor, maximum and minimum number of iterations of the improved gray wolf algorithm, and encode the penalty factor and kernel function parameters of the support vector machine algorithm in two dimensions of the position in the gray wolf;

[0045] Calculate the individual fitness values ​​of the gray wolves, select three gray wolves whose fitness values ​​meet the requirements and record them as α wolf, β wolf and γ wolf in turn, and use the error rate as the fitness value of α wolf, β wolf and γ wolf;

[0046] Perform pinhole imaging reverse learning on the optimal individual at the current position to generate a reverse solution; when the reverse solution is better than the current solution, replace the reverse solution with the optimal solution, update the global optimal solution and fitness value; update the coefficient vector of the improved gray wolf algorithm to optimize the support vector machine method, the fitness values ​​of α wolf, β wolf and γ wolf;

[0047] Verify whether the maximum number of iterations has been reached. If so, output the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm. Otherwise, continue the iterative calculation.

[0048] Furthermore, considering the maximum consumption of new energy and the safe operation of the power grid, the control characteristics of different resources are analyzed, and the historical effective data set of flexible controllable resources is divided into new energy clusters, output complementary clusters and flexible load clusters, among which,

[0049] The new energy cluster includes wind power and photovoltaic resources, the output complementary cluster includes adjustable hydropower, thermal power and energy storage, and the flexible load cluster includes electric vehicles and temperature control loads typically represented by air conditioners.

[0050] The invention provides a method for quantitatively evaluating the control performance of flexible controllable resources, which has the following beneficial effects:

[0051] In view of the problem that existing research has neglected the consideration of the control performance of flexible controllable resources, resulting in the proposed scheduling plan being inconsistent with the actual output of flexible controllable resources, seriously affecting the consumption of new energy and the safe and stable operation of the power system, the present invention takes into account the maximum consumption of new energy, accurately and effectively evaluates the control performance of flexible controllable resources, ensures the flexibility and accuracy of power grid scheduling, and promotes the consumption of new energy and the safe operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0053] Figure 1 A flowchart of a method for quantitatively evaluating control performance of flexible controllable resources according to the present invention;

[0054] Figure 2 A flowchart of a historical valid data set of flexible controllable resources in a method for quantitatively evaluating control performance of flexible controllable resources according to the present invention;

[0055] Figure 3 A schematic diagram of real-time control performance evaluation indicators of flexible controllable resources in a method for quantitatively evaluating control performance of flexible controllable resources of the present invention. DETAILED DESCRIPTION

[0056] Various aspects and features of the present invention are described herein with reference to the accompanying drawings.

[0057] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of the embodiments. Other modifications within the scope and spirit of the present invention will occur to those skilled in the art.

[0058] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the general description of the invention given above and the detailed description of the embodiments given below, serve to explain the principles of the invention.

[0059] These and other characteristics of the invention will become apparent from the following description of a preferred form of embodiment given as a non-limiting example, with reference to the accompanying drawings.

[0060] It should also be understood that, although the invention has been described with reference to some specific examples, those skilled in the art will be able to realize many other equivalent forms of the invention that have the characteristics recited in the claims and are therefore within the scope of protection defined thereby.

[0061] The above and other aspects, features and advantages of the present invention will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0062] Specific embodiments of the present invention are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments claimed are merely examples of the present invention, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid obscuring the present invention with unnecessary or redundant details. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present invention in a variety of ways with substantially any suitable detailed structure.

[0063] In the description of the present invention, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0064] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0065] Example

[0066] like Figure 1 and Figure 3 As shown, this embodiment provides a method for quantitatively evaluating the control performance of flexible controllable resources, including the following steps:

[0067] Step S1: using an improved gray wolf algorithm to optimize support vector machine method (Improved Gray Wolf Optimizing Support Vector Machine, IGWO-SVM) to process historical data of flexible controllable resources of the power grid to obtain a historical valid data set of flexible controllable resources;

[0068] Step S2: Considering the maximum consumption of new energy and the safe operation of the power grid, the control characteristics of different resources are analyzed, and the historical effective data set of flexible controllable resources is divided into new energy clusters, output complementary clusters and flexible load clusters;

[0069] Step S3: Considering the differences in regulation characteristics and dispatching stages among the new energy cluster, the output complementary cluster and the flexible load cluster, a spatiotemporal response control performance index system and a special index system for different cluster characteristics are established. The spatiotemporal response control performance index system is used to reflect the requirements of power grid regulation for the multivariate response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of power grid regulation for a certain type of flexible adjustable resources. The dispatching stage includes: the first stage, dispatching the output complementary cluster to preliminarily absorb the new energy cluster; the second stage, dispatching the flexible load cluster to supplement the absorption of the new energy cluster;

[0070] Step S4: For the spatiotemporal response control performance index system and the special index system, the entropy weight method is used to perform weighted calculation to obtain the quantitative control performance indicators of the new energy cluster, the output complementary cluster and the flexible load cluster respectively; based on the quantitative control performance indicators, the comprehensive quantitative control performance indicators of the flexible controllable resources are obtained.

[0071] like Figure 2 As shown, according to another specific embodiment of the present invention, on the basis of step S1, an improved grey wolf algorithm is used to optimize a support vector machine method to process historical data of flexible controllable resources of a power grid to obtain a historical valid data set of flexible controllable resources, including the following steps:

[0072] Preprocess the historical data of flexible and controllable resources of the power grid;

[0073] Use the improved grey wolf algorithm to solve the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm;

[0074] The classification model is trained using the optimal penalty factor and the optimal kernel function parameter, and the preprocessed historical data set of the flexible controllable resources of the power grid is classified by the classification model to obtain a historical valid data set of the flexible controllable resources.

[0075] According to another specific embodiment of the present invention, on the basis of the above embodiment, the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm are solved by using the improved grey wolf algorithm;

[0076] Set the mirror factor, maximum and minimum number of iterations of the improved gray wolf algorithm, and encode the penalty factor and kernel function parameters of the support vector machine algorithm in two dimensions of the position in the gray wolf;

[0077] Calculate the individual fitness values ​​of the gray wolves, select three gray wolves whose fitness values ​​meet the requirements and record them as α wolf, β wolf and γ wolf in turn, and use the error rate as the fitness value of α wolf, β wolf and γ wolf;

[0078] Perform pinhole imaging reverse learning on the optimal individual at the current position to generate a reverse solution; when the reverse solution is better than the current solution, replace the reverse solution with the optimal solution, update the global optimal solution and fitness value; update the coefficient vector of the improved gray wolf algorithm to optimize the support vector machine method, the fitness values ​​of α wolf, β wolf and γ wolf;

[0079] Verify whether the maximum number of iterations has been reached. If so, output the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm. Otherwise, continue the iterative calculation.

[0080] In step S1, the improved grey wolf algorithm is used to optimize the support vector machine method to process the historical data of the flexible controllable resources, and obtain the historical effective data set of the flexible controllable resources. Support vector machine (SVM) is a classic binary classification algorithm, which is suitable for nonlinear data, can avoid the dimensionality disaster, and has good generalization ability; dividing the historical effective data set of flexible controllable resources requires dividing the high-dimensional complex data of flexible controllable resources into normal and abnormal categories; when the support vector machine is used as a classification tool, its performance is closely related to the support vector machine parameters, including the penalty factor C and the kernel function parameter g.

[0081] The penalty factor C represents the degree of importance the algorithm places on outliers, that is, the tolerance for errors. The kernel function parameter g is a parameter of the Gaussian Radial Basis Function (RBF), which affects the performance of the kernel function. The larger the penalty factor C and the kernel function parameter g, the less tolerant the model is to errors, and it pays particular attention to relatively distant outliers, which will cause the model to have more support vectors, making the support vector machine model more complicated and prone to over-learning. The smaller the penalty factor C and the kernel function parameter g, the more tolerant the model is to errors, and some outliers can be discarded to obtain a simpler model, but it may cause the model to be underfitted.

[0082] Gray Wolf Optimizer (GWO) has been successfully applied in the fields of image processing, intrusion detection and abnormal data detection due to its simple principle, small number of parameters and good convergence. Therefore, the present invention selects the GWO algorithm to find the penalty factor C and kernel function parameter g of the support vector machine. The traditional GWO algorithm is prone to premature convergence and easy to fall into local optimality. Therefore, in order to reasonably select the parameters of SVM, the present invention improves GWO and proposes an improved Gray Wolf Optimizer (IGWO) algorithm for optimizing the parameters of the support vector machine.

[0083] An initial population with good diversity and uniform distribution is crucial to the swarm intelligence optimization algorithm, which can maximize the scope of search optimization and enhance the effect of global optimization. The standard gray wolf optimization algorithm usually solves the optimization problem by randomly generating gray wolf populations, which causes gray wolf individuals to gather in a small area and makes it difficult to maintain population diversity, or the generated population is unevenly distributed, causing gray wolf individuals to blindly conduct invalid searches in the solution space, converge slowly, and have low precision. Therefore, it is necessary to find an initial population with good diversity and uniform distribution to expand the search range of the gray wolf population and improve the overall performance of the algorithm. At present, there are many chaotic maps commonly used in the field of swarm intelligence optimization, and different maps produce different population distributions. The present invention uses Tent mapping to initialize the population, improve the quality of the initial population, and reduce the impact of the initial value on the algorithm optimization. The Tent mapping method avoids the problem of unevenly generated populations caused by other mapping methods, which usually have a high probability of taking values ​​at the edge and a low probability of taking values ​​in the middle segment. It generates a relatively uniformly distributed population in the [0,1] interval and has strong traversal and optimization efficiency. Tent mapping expression:

[0084]

[0085] At the same time, in order to avoid the algorithm falling into local extreme values, the pinhole imaging reverse learning strategy is used to optimize GWO. In one-dimensional space, the projection x0 of a flame on the x-axis is the global optimal individual. The upper and lower limits of the coordinate axis are X and Y. A pinhole screen with a small hole is placed at the center point. The flame can be reflected on the receiving screen through the small hole. Its projection on the x-axis is x best x represents the independent variable of the T(x) function, that is, the value of the Tent mapping function on the x-axis. Therefore, the global optimal individual x0 generates a reverse solution x on the x-axis through reverse learning of pinhole imaging. best The expression is:

[0086]

[0087] Where n is the mirror factor. The improved algorithm uses a larger n value in the early iteration to enhance the algorithm's ability to find the best solution in a wide space and increase the diversity of the best location. A smaller n is used in the later iteration to gradually approach the group to the optimal individual area, quickly conduct local exploration, and improve the algorithm's search performance. The mirror factor n is calculated using linear decrement:

[0088]

[0089] Where: I max is the maximum number of iterations, n max and n min are the maximum and minimum values ​​of the mirror factor n respectively.

[0090] The present invention uses an improved grey wolf algorithm to optimize the support vector machine method to optimize the parameters of the support vector, removes invalid data in the historical data of the flexible controllable resources, and obtains the historical valid data of the flexible controllable resources.

[0091] According to another specific embodiment of the present invention, on the basis of step S2, the maximum consumption of new energy and the safe operation of the power grid are considered, the control characteristics of different resources are analyzed, and the historical effective data set of flexible controllable resources is divided into new energy clusters, output complementary clusters and flexible load clusters, wherein:

[0092] The new energy cluster includes wind power and photovoltaic resources, the output complementary cluster includes adjustable hydropower, thermal power and energy storage, and the flexible load cluster includes electric vehicles and temperature control loads typically represented by air conditioners.

[0093] The regulation characteristics of each flexible controllable resource are as follows:

[0094] New Energy Cluster:

[0095] The output of solar photovoltaic generators is mainly affected by light intensity, battery junction temperature and ambient temperature. The mathematical model of photovoltaic output can be expressed as:

[0096]

[0097] Where: P PV (t) is the output power of the photovoltaic unit at time t (W), k T is the temperature coefficient (% / ℃), P SET is the rated output power of the photovoltaic unit (W), S SET is the standard light intensity of the photovoltaic unit (kw / m 2 ), S(t) is the light intensity of the photovoltaic unit at time t (kw / m 2 ), T(t) is the ambient temperature at time t (℃), T SET is the standard ambient temperature (℃).

[0098] Wind power generation is one of the main forms of wind energy utilization. It converts wind energy into electrical energy through wind turbines. The basic principle is that wind energy drives the blades on the wind turbine to rotate, converting wind energy into mechanical energy. The rotating blades drive the main shaft of the generator to rotate, and then convert it into electrical energy. According to the principle of power generation, the mechanical output power of the wind turbine is mainly affected by parameters such as wind speed, blade radius and air density. Its mathematical expression is:

[0099]

[0100] Where: P M is the mechanical output power of the fan (W), is the blade sweep area (m 2 ), where RWT is the blade radius (m), ρ is the air density (kg / m 3 ), ν is wind speed (m / s), C p is the wind energy utilization coefficient.

[0101] Output complementary cluster:

[0102] The factors that affect the output power of a hydropower station include not only the total amount of water required at each moment and the change in the water level of the reservoir, but also the head of the turbine and the efficiency of the hydroelectric generator. The output power model of a hydropower station can be expressed according to the law of conservation of energy, that is, the potential energy difference between the upstream and downstream water bodies is the corresponding output electrical energy.

[0103]

[0104] Where: P h,t is the output power of the hydropower unit during period t; A is the hydropower conversion constant, usually 9.81; Q h,t h is the power generation flow of the hydropower station during period t; t is the net water head of the turbine in period t; η is the efficiency of the hydropower station.

[0105] The various parameters of thermal power units during peak load regulation can be calculated by the following formula:

[0106]

[0107] Where: P Gi The rated capacity of the units participating in conventional peak load regulation; is the rated capacity of the deep peak-shaving unit; N G1 With N G2 are the number of conventional peak-shaving units and deep peak-shaving units respectively; P Gi,max With P Gi,min分别 is the maximum and minimum output power of thermal power unit i; P Gi,n P is the minimum output power of thermal power unit i in the deep peak regulation stage without oil injection; Gi,m is the minimum output power of thermal power unit i during the oil-added deep peak-shaving stage; and are the maximum and minimum load rates of thermal power unit i respectively; and are the minimum load rates of thermal power unit i when no oil is added and when oil is added during the deep peak regulation stage, respectively.

[0108] The key parameter of the energy storage resource is the system frequency f, and the output power of the resource is P out5 , P out5 is the battery output power, P out5 <0 means the battery is charged, P out5 >0 means the battery is discharged.out5 The expression is:

[0109]

[0110] Where P BS is the rated power of the battery; K EA Adjust the power per unit; Δf b and Δf a These are the upper and lower limits of the energy storage battery's participation in frequency regulation output.

[0111] Flexible load cluster:

[0112] Air conditioning load is a typical temperature control load. Air conditioning resources are generally adjusted in cluster form. Suppose the air conditioning cluster consists of N air conditioners, and its key parameter is the start state S of generator i at time t. t,i and air conditioner rated power P t,i , power P ac for:

[0113]

[0114] Electric vehicle loads are generally adjusted in clusters. Assume that an electric vehicle cluster consists of N vehicles, and its key parameter is the required charge amount Q of the jth vehicle. need,j , output power P EV for

[0115]

[0116] Where: i,j is the i-th charging time period of the j-th electric vehicle, and M is the number of charging time periods.

[0117] The present invention is based on the principle of achieving multi-energy output complementarity and source-load interaction, and divides flexible controllable resources into new energy clusters, output complementarity clusters and flexible load clusters. The output complementarity clusters and flexible load clusters are optimized and dispatched in two stages. In the first stage, the output complementarity clusters are dispatched to preliminarily absorb the new energy clusters, and in the second stage, the flexible load clusters are dispatched to supplement the new energy clusters.

[0118] According to another specific embodiment of the present invention, on the basis of step S3, considering the differences in the regulation characteristics and dispatching stages of the new energy cluster, the output complementary cluster and the flexible load cluster, a spatiotemporal response control performance index system and a special index system for different cluster characteristics are established, the spatiotemporal response control performance index system is used to reflect the requirements of the power grid regulation for the multivariate response control performance of all flexible adjustable resources, the special index system is used to reflect the special requirements of the power grid regulation for a certain type of flexible adjustable resources, the dispatching stage includes: the first stage, dispatching the output complementary cluster to preliminarily absorb the new energy cluster; the second stage, dispatching the flexible load cluster to supplement the new energy cluster; wherein,

[0119] The evaluation indicators of the spatiotemporal response control performance indicator system include:

[0120] The time response control performance index is used to characterize the time taken by the flexible adjustable resource from receiving the adjustment instruction to the actual output reaching 90% of the target value for the first time;

[0121] The spatial response control performance index is used to characterize the power capacity of flexible adjustable resources that can be dispatched by the power grid within a set period of time;

[0122] The evaluation indicators of the special indicator system include:

[0123] New energy prediction performance indicators and spinning reserve capacity indicators used to reflect the special requirements of power grid regulation for new energy clusters; the new energy prediction performance indicators are used to characterize the uncertainty of new energy, indicating the degree of deviation between the predicted maximum output value of new energy and the actual maximum output value; the spinning reserve capacity indicator is the probability of insufficient output after the spinning reserve is configured, which is used to characterize the ability of new energy units to respond to faults and ensure the stable operation of the power system;

[0124] The first-stage optimal absorption rate of new energy and the power plant electricity execution rate indicators are used to reflect the special requirements of the power grid regulation for the output complementary cluster; the first-stage optimal absorption rate of new energy is used to characterize the absorption degree of the first-stage output complementary cluster for new energy; the power plant electricity execution rate indicator is used to characterize the execution degree of the power plant for the dispatch plan;

[0125] The second-stage optimal absorption rate and load execution rate indicators of new energy are used to reflect the special requirements of power grid regulation for flexible load clusters. The second-stage optimal absorption rate of new energy is used to characterize the degree of absorption of new energy by the second-stage output complementary cluster of scheduling; the load execution rate indicator is used to characterize the responsiveness of flexible adjustable resources to the scheduling plan.

[0126] The details are as follows:

[0127] Since new energy has strong uncertainty and the units need to reserve sufficient spinning reserve capacity to maintain the system at a good reliability standard, the special indicator system for new energy clusters includes the following indicators:

[0128] New energy prediction performance indicators:

[0129] New energy prediction performance index E adj Characterizes the uncertainty of new energy, indicating the degree of deviation between the predicted maximum output value of new energy and the actual maximum output value, and the expression is:

[0130]

[0131] Where: is the actual maximum output value of new energy, Predict the maximum output value for new energy.

[0132] Spinning reserve capacity indicators:

[0133] Spinning reserve capacity index L RB To represent the probability of insufficient output after configuring spinning reserve, and to characterize the ability of new energy units to cope with faults and ensure stable operation of the power system, the expression is:

[0134] L RB =P[P fau +(P real,s -P pre,s )-(P real,l -P pre,l )≥R]

[0135] Where: P fau is the outage capacity of new energy units due to failure, P real,l is the actual load value of the flexible load, P pre,l is the predicted load value of flexible load, R is the spinning reserve capacity of new energy units, and P is the probability of occurrence of the subsequent expression in [].

[0136] The output complementary cluster is used to initially absorb new energy in the first stage of dispatch. In the first stage of dispatch, the output of the new energy cluster and the output complementary cluster in each period is optimized, and an optimization dispatch model with the goal of minimizing the total load variance of the power system and minimizing the operating cost of the power system is established. The model is solved to obtain the output value of the output complementary cluster in each period, and further obtain the optimal absorption rate and optimal grid-connected power of the new energy cluster in the first stage. Based on the dispatching objectives of the first stage, the special indicator system for the output complementary cluster includes the following indicators:

[0137] The optimal absorption rate of new energy in the first phase:

[0138] The first-stage dispatch obtained the optimal dispatch plan for the new energy units in the first stage with the goal of minimizing the total load variance of the power system and minimizing the operating cost of the power system. Less than its actual maximum output The optimal absorption rate index C1 of new energy is defined to represent the absorption degree of new energy by the output complementary cluster in the first stage of dispatch. The expression is as follows:

[0139]

[0140] Power plant electricity execution rate indicators:

[0141] The power plant power execution rate index represents the degree of execution of the power plant on the dispatch plan, and the expression is:

[0142]

[0143] Where: P real is the actual output value of the power plant, P she Plan the output value for the power plant.

[0144] Flexible load clusters are used to supplement and absorb new energy in the second stage of dispatch. In the second stage of dispatch, the output of flexible load clusters in each period is optimized, and an optimization dispatch model with the goal of minimizing the total load variance of the power system and minimizing the electricity cost of flexible load clusters is established. The load value of the flexible load cluster in each period is solved, and the optimal absorption rate of new energy and the optimal grid-connected power in the second stage are further obtained. Based on the second stage dispatch target, the special indicator system for flexible load clusters includes the following indicators:

[0145] The optimal absorption rate of new energy in the second phase:

[0146] The second-stage dispatch obtained the optimal dispatch plan for the second stage of new energy units with the goal of minimizing the total load variance of the power system, maximizing the consumption of new energy and minimizing the electricity cost of the flexible load cluster. Less than its actual maximum output The optimal absorption rate index C2 of new energy is defined to represent the absorption degree of new energy by the output complementary cluster in the second stage of scheduling. The expression is as follows:

[0147]

[0148] Load execution rate index:

[0149] Load execution rate index E L Characterize the responsiveness of flexible adjustable resources to the scheduling plan, the expression is:

[0150]

[0151] Where: ΔP real is the change in actual power of the flexible load, ΔP she is the planned change of flexible load.

[0152] According to another specific embodiment of the present invention, on the basis of step S4, for the spatiotemporal response control performance index system and the special index system, the quantitative control performance indexes of the new energy cluster, the output complementary cluster and the flexible load cluster are respectively obtained by weighted calculation using the entropy weight method; based on the quantitative control performance index, the comprehensive quantitative control performance index of the flexible controllable resources is obtained, and the calculation of the quantitative control performance index includes the following steps:

[0153] Standardizing the original data of the new energy cluster, the output complementary cluster and the flexible load cluster under the spatiotemporal response control performance index system and the special index system;

[0154] Using the standardized data, the information entropy of each evaluation indicator under different indicator systems is calculated;

[0155] By utilizing the information entropy of each evaluation index under different index systems, the spatiotemporal response control performance sub-index and the special performance sub-index corresponding to each cluster are aggregated;

[0156] The weight values ​​of the spatiotemporal response control performance sub-indicators and special performance sub-indicators corresponding to each cluster are set respectively, and the quantitative control performance indicators corresponding to the new energy cluster, the output complementary cluster and the flexible load cluster are obtained respectively by using the spatiotemporal response control performance sub-indicators, special performance sub-indicators and weight values ​​corresponding to each cluster.

[0157] According to another specific embodiment of the present invention, on the basis of the above embodiment, the original data of the new energy cluster, the output complementary cluster and the flexible load cluster under the spatiotemporal response control performance index system and the special index system are standardized. Considering that all indicators are positive indicators, the standardized formula is:

[0158]

[0159] Where: is the index data value after the jth evaluation index of the flexible controllable load cluster k under the i-th index system is standardized, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; is the original data value of the index before normalization of the jth evaluation index of the flexible controllable load cluster k under the i-th index system, X i,jis the set of original data values ​​of the jth evaluation index of all flexible controllable load clusters under the i-th index system, max(X i,j ) is the maximum value of the original data value of the jth evaluation index of all flexible controllable load clusters under the i-th index system, min(X i,j ) is the minimum value of the original data value of the jth evaluation index of all flexible controllable load clusters under the i-th index system.

[0160] According to another specific embodiment of the present invention, on the basis of the above embodiment, the information entropy of each evaluation index under different index systems is calculated by using the standardized data, including:

[0161] Assume that the information entropy of the jth evaluation index of the flexible controllable load cluster k under the i-th index system is Its expression is:

[0162]

[0163] Where: is the proportion of the jth evaluation index of the flexible controllable load cluster k in the i-th index system in the evaluation index column; It is the index data value after the jth evaluation index of the flexible controllable load cluster k under the i-th index system is standardized; k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; n is the number of evaluation indicators.

[0164] According to another specific embodiment of the present invention, on the basis of the above embodiment, the information entropy of each evaluation index under different index systems is used to aggregate and obtain the spatiotemporal response control performance sub-index and special performance sub-index corresponding to each cluster, including:

[0165] The sub-indicators obtained by aggregating the i-th indicator system of the flexible controllable load cluster k for:

[0166]

[0167] Where: is the weight of the jth evaluation index of controllable load cluster k under the i-th index system; is the information entropy of the jth evaluation index of the flexible controllable load cluster k under the i-th index system, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; n is the number of evaluation indicators; It is the index data value after standardization of the jth evaluation index of the flexible controllable load cluster k under the i-th index system.

[0168] According to another specific embodiment of the present invention, on the basis of the above, the weight values ​​of the spatiotemporal response control performance sub-indicators and special performance sub-indicators corresponding to each cluster are set respectively, and the spatiotemporal response control performance sub-indicators, special performance sub-indicators and weight values ​​corresponding to each cluster are used to obtain the comprehensive real-time control performance indicators corresponding to the new energy cluster, the output complementary cluster and the flexible load cluster respectively. The expression is:

[0169]

[0170] x k +y k =1

[0171] Where: S c,k is a quantitative control performance indicator corresponding to the flexible controllable load cluster k (the new energy cluster, the output complementary cluster or the flexible load cluster); and are the spatiotemporal response control performance index and special performance index of the flexible controllable load cluster k, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; x k is the spatiotemporal response control performance index of the flexible controllable load cluster k; y k is the special performance index of the flexible controllable load cluster k; S c,1 is a comprehensive real-time control performance index corresponding to the new energy cluster; S c,2 is a comprehensive real-time control performance index corresponding to the output complementary cluster; S c,3 is a comprehensive real-time control performance indicator corresponding to the flexible load cluster.

[0172] The weights ω of the three flexible controllable resources in the temporal and spatial response control performance sub-indicators and special performance sub-indicators are shown in Table 1:

[0173] Table 1 Weights of control performance indicators under three time scales

[0174] Temporal and spatial response control performance indicators Special performance index New Energy Cluster <![CDATA[x1]]> <![CDATA[y1]]> Output complementary cluster <![CDATA[x2]]> <![CDATA[y2 <!-- 13 -->]]> Flexible load cluster <![CDATA[x3]]> <![CDATA[y3]]>

[0175] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0176] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0177] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

[0178] Multiple embodiments of the present disclosure are described in detail above, but the present disclosure is not limited to these specific embodiments. Those skilled in the art can make various variations and modifications to the embodiments based on the concepts of the present disclosure, and these variations and modifications should all fall within the scope of protection required by the present disclosure.

Claims

1. A method for quantitatively evaluating the control performance of flexible controllable resources, characterized in that: The following steps are involved: The improved grey wolf algorithm is used to optimize the support vector machine method to process the historical data of flexible controllable resources of the power grid, and the historical valid data set of flexible controllable resources is obtained; Considering the maximum consumption of new energy and the safe operation of the power grid, the control characteristics of different resources are analyzed, and the historical effective data set of flexible controllable resources is divided into new energy clusters, output complementary clusters and flexible load clusters; Taking into account the differences in regulation characteristics and dispatching stages of the new energy cluster, the output complementary cluster and the flexible load cluster, a spatiotemporal response control performance index system and a special index system for different cluster characteristics are established. The spatiotemporal response control performance index system is used to reflect the requirements of power grid regulation for the multivariate response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of power grid regulation for a certain type of flexible adjustable resources. The dispatching stage includes: the first stage, dispatching the complementary output cluster to preliminarily absorb the new energy cluster; the second stage, dispatching the flexible load cluster to supplement the new energy cluster; For the spatiotemporal response control performance index system and the special index system, the entropy weight method is used to perform weighted calculation to obtain the quantitative control performance indicators of the new energy cluster, the output complementary cluster and the flexible load cluster respectively; based on the quantitative control performance indicators, the comprehensive quantitative control performance indicators of flexible controllable resources are obtained.

2. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 1 is characterized in that: Taking into account the differences in regulation characteristics and dispatching stages among the new energy cluster, the output complementary cluster and the flexible load cluster, a spatiotemporal response control performance index system and a special index system for different cluster characteristics are established. The spatiotemporal response control performance index system is used to reflect the requirements of power grid regulation for the multivariate response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of power grid regulation for a certain type of flexible adjustable resources. The dispatching stage includes: the first stage, dispatching the output complementary cluster to preliminarily absorb the new energy cluster; the second stage, dispatching the flexible load cluster to supplement the new energy cluster; wherein, The evaluation indicators of the spatiotemporal response control performance indicator system include: The time response control performance index is used to characterize the time taken by the flexible adjustable resource from receiving the adjustment instruction to the actual output reaching the set percentage of the target value for the first time; The spatial response control performance index is used to characterize the power capacity of flexible adjustable resources that can be dispatched by the power grid within a set period of time; The evaluation indicators of the special indicator system include: New energy prediction performance indicators and spinning reserve capacity indicators used to reflect the special requirements of power grid regulation for new energy clusters; the new energy prediction performance indicators are used to characterize the uncertainty of new energy, indicating the degree of deviation between the predicted maximum output value of new energy and the actual maximum output value; the spinning reserve capacity indicator is the probability of insufficient output after the spinning reserve is configured, which is used to characterize the ability of new energy units to respond to faults and ensure the stable operation of the power system; The first-stage optimal absorption rate of new energy and the power plant electricity execution rate indicators are used to reflect the special requirements of the power grid regulation for the output complementary cluster; the first-stage optimal absorption rate of new energy is used to characterize the absorption degree of the first-stage output complementary cluster for new energy; the power plant electricity execution rate indicator is used to characterize the execution degree of the power plant for the dispatch plan; The second-stage optimal absorption rate and load execution rate indicators of new energy are used to reflect the special requirements of power grid regulation for flexible load clusters. The second-stage optimal absorption rate of new energy is used to characterize the degree of absorption of new energy by the second-stage output complementary cluster of scheduling; the load execution rate indicator is used to characterize the responsiveness of flexible adjustable resources to the scheduling plan.

3. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 2 is characterized in that: For the spatiotemporal response control performance index system and the special index system, the quantitative control performance indexes of the new energy cluster, the output complementary cluster and the flexible load cluster are obtained by weighted calculation using the entropy weight method; based on the quantitative control performance index, the comprehensive quantitative control performance index of the flexible controllable resources is obtained, and the calculation of the quantitative control performance index includes the following steps: Standardizing the original data of the new energy cluster, the output complementary cluster and the flexible load cluster under the spatiotemporal response control performance index system and the special index system; Using the standardized data, the information entropy of each evaluation indicator under different indicator systems is calculated; By utilizing the information entropy of each evaluation index under different index systems, the spatiotemporal response control performance sub-index and the special performance sub-index corresponding to each cluster are aggregated; The weight values ​​of the spatiotemporal response control performance sub-indicators and special performance sub-indicators corresponding to each cluster are set respectively, and the quantitative control performance indicators corresponding to the new energy cluster, the output complementary cluster and the flexible load cluster are obtained respectively by using the spatiotemporal response control performance sub-indicators, special performance sub-indicators and weight values ​​corresponding to each cluster.

4. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 3 is characterized in that: The original data of the new energy cluster, the output complementary cluster and the flexible load cluster under the spatiotemporal response control performance index system and the special index system are standardized. Considering that all indicators are positive indicators, the standardized formula is: Where: is the index data value after the jth evaluation index of the flexible controllable load cluster k under the i-th index system is standardized, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; is the original data value of the index before normalization of the jth evaluation index of the flexible controllable load cluster k under the i-th index system, X i,j is the set of original data values ​​of the jth evaluation index of all flexible controllable load clusters under the i-th index system, max(X i,j ) is the maximum value of the original data value of the jth evaluation index of all flexible controllable load clusters under the i-th index system, min(X i,j ) is the minimum value of the original data value of the jth evaluation index of all flexible controllable load clusters under the i-th index system.

5. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 3 is characterized in that: Using the standardized data, the information entropy of each evaluation indicator under different indicator systems is calculated, including: Assume that the information entropy of the jth evaluation index of the flexible controllable load cluster k under the i-th index system is Its expression is: Where: is the proportion of the jth evaluation index of the flexible controllable load cluster k in the i-th index system in the evaluation index column; It is the index data value after the jth evaluation index of the flexible controllable load cluster k under the i-th index system is standardized; k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; n is the number of evaluation indicators.

6. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 3 is characterized in that: By using the information entropy of each evaluation index under different index systems, the spatiotemporal response control performance sub-index and special performance sub-index corresponding to each cluster are aggregated, including: The sub-indicators obtained by aggregating the i-th indicator system of the flexible controllable load cluster k for: Where: is the weight of the jth evaluation index of controllable load cluster k under the i-th index system; is the information entropy of the jth evaluation index of the flexible controllable load cluster k under the i-th index system, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; n is the number of evaluation indicators; It is the index data value after standardization of the jth evaluation index of the flexible controllable load cluster k under the i-th index system.

7. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 3 is characterized in that: The weight values ​​of the spatiotemporal response control performance sub-indicators and special performance sub-indicators corresponding to each cluster are set respectively. The spatiotemporal response control performance sub-indicators, special performance sub-indicators and weight values ​​corresponding to each cluster are used to obtain the comprehensive real-time control performance indicators corresponding to the new energy cluster, the output complementary cluster and the flexible load cluster respectively. The expression is: x k +y k =1 Where: S c,k is the quantitative control performance index corresponding to the flexible controllable load cluster k; and are the spatiotemporal response control performance index and special performance index of the flexible controllable load cluster k, k = 1, 2, 3, flexible controllable load cluster 1 represents the new energy cluster, flexible controllable load cluster 2 represents the output complementary cluster, and flexible controllable load cluster 3 represents the flexible load cluster; x k is the spatiotemporal response control performance index of the flexible controllable load cluster k; y k It is the special performance index of the flexible controllable load cluster k.

8. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 1 is characterized in that: The improved grey wolf algorithm is used to optimize the support vector machine method to process the historical data of the flexible controllable resources of the power grid, and the historical valid data set of the flexible controllable resources is obtained, which includes the following steps: Preprocess the historical data of flexible and controllable resources of the power grid; Use the improved grey wolf algorithm to solve the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm; The classification model is trained using the optimal penalty factor and the optimal kernel function parameter, and the preprocessed historical data set of the flexible controllable resources of the power grid is classified by the classification model to obtain a historical valid data set of the flexible controllable resources.

9. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 8 is characterized in that: The improved grey wolf algorithm is used to solve the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm, including: Set the mirror factor, maximum and minimum number of iterations of the improved gray wolf algorithm, and encode the penalty factor and kernel function parameters of the support vector machine algorithm in two dimensions of the position in the gray wolf; Calculate the individual fitness values ​​of the gray wolves, select three gray wolves whose fitness values ​​meet the requirements and record them as α wolf, β wolf and γ wolf in turn, and use the error rate as the fitness value of α wolf, β wolf and γ wolf; Perform pinhole imaging reverse learning on the optimal individual at the current position to generate a reverse solution; when the reverse solution is better than the current solution, replace the reverse solution with the optimal solution, update the global optimal solution and fitness value; update the coefficient vector of the improved gray wolf algorithm to optimize the support vector machine method, the fitness values ​​of α wolf, β wolf and γ wolf; Verify whether the maximum number of iterations has been reached. If so, output the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm. Otherwise, continue the iterative calculation.

10. The method for quantitatively evaluating the control performance of flexible controllable resources according to claim 1, characterized in that: Considering the maximum consumption of new energy and the safe operation of the power grid, the control characteristics of different resources are analyzed, and the historical effective data set of flexible controllable resources is divided into new energy clusters, output complementary clusters and flexible load clusters, among which, The new energy cluster includes wind power and photovoltaic resources, the output complementary cluster includes adjustable hydropower, thermal power and energy storage, and the flexible load cluster includes electric vehicles and temperature control loads typically represented by air conditioners.

Images