A flexible controllable resource control performance quantification evaluation method

Abstract

The present application relates to the technical field of power grid dispatching, and discloses a flexible controllable resource control performance quantification 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 new energy clusters, output complementary clusters and flexible load clusters; establishing a time-space response control performance index system and a special index system for different cluster characteristics; and using an entropy weight method to weight and calculate the comprehensive quantitative control performance index of the new energy clusters, the output complementary clusters and the flexible load clusters according to the time-space response control performance index system and the special index system. The present application is beneficial to accurately and effectively evaluating the control performance of flexible controllable resources, ensuring the flexibility and accuracy of power grid dispatching, and promoting the consumption of new energy and the safe operation of a power system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of integrated energy systems, in particular to a flexible controllable resource control performance quantification evaluation method. BACKGROUND

[0002] With the rapid development and large-scale access of flexible controllable resources to the power grid, the power system is gradually changing towards a cleaner and more sustainable direction, but at the same time, the traditional power system architecture has certain limitations for the large-scale integration and dispatch of new energy, and the operation of the power system also faces higher complexity and challenges. In order to effectively cope with these challenges and achieve the maximum consumption of new energy, a large number of studies have proposed optimal scheduling methods for flexible controllable resources. However, most of the current research ignores the consideration of the control performance of flexible controllable resources, which makes the proposed scheduling plan not consistent 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.

[0003] Currently, there is no unified standard for the control performance evaluation method of flexible controllable resources, and existing technologies are often limited to specific resource types or lack systematic consideration. In order to solve the above problems, an effective control performance quantification evaluation method needs to be proposed for flexible controllable resources such as wind power, photovoltaic, flexible load, etc., to improve the consumption of new energy in the power grid and provide effective data support for real-time coordination control links in the power grid. SUMMARY

[0004] The present application aims to at least solve the technical problem that existing research ignores the consideration of the control performance of flexible controllable resources, which makes the proposed scheduling plan not consistent 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.

[0005] To this end, one object of the present application is to propose a flexible controllable resource control performance quantification evaluation method, comprising the following steps:

[0006] comprising the following steps:

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

[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 the flexible controllable resources is divided into a new energy cluster, a complementary output cluster and a flexible load cluster;

[0009] In view of the different adjustment characteristics of the new energy cluster, the output complementary cluster and the flexible load cluster and different scheduling stages, a space-time response control performance index system and a special index system for different cluster characteristics are established, the space-time response control performance index system is used to reflect the requirements of the grid regulation on the multi-response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of the grid regulation on certain flexible adjustable resources; the scheduling stages include: a first stage of scheduling the output complementary cluster to preliminarily consume the new energy cluster; and a second stage of scheduling the flexible load cluster to supplementally consume the new energy cluster.

[0010] In view of the space-time response control performance index system and the special index system, the entropy weight method is used to weight and calculate to obtain the quantitative control performance indexes of the new energy cluster, the output complementary cluster and the flexible load cluster respectively; and based on the quantitative control performance indexes, a comprehensive quantitative control performance index of the flexible controllable resources is obtained.

[0011] Further, in view of the different adjustment characteristics of the new energy cluster, the output complementary cluster and the flexible load cluster and different scheduling stages, a space-time response control performance index system and a special index system for different cluster characteristics are established, the space-time response control performance index system is used to reflect the requirements of the grid regulation on the multi-response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of the grid regulation on certain flexible adjustable resources, the scheduling stages include: a first stage of scheduling the output complementary cluster to preliminarily consume the new energy cluster; and a second stage of scheduling the flexible load cluster to supplementally consume the new energy cluster; wherein,

[0012] The evaluation indexes of the space-time response control performance index system include:

[0013] A time response control performance index, which is used to represent the time used by the flexible adjustable resources to reach the set percentage of the target value from receiving the adjustment instruction to the actual output;

[0014] A space response control performance index, which is used to represent the power capacity of the flexible adjustable resources that can be accepted by the grid scheduling within a set period of time;

[0015] The evaluation indexes of the special index system include:

[0016] A new energy prediction performance index and a spinning reserve capacity index, which are used to reflect the special requirements of the grid regulation on the new energy cluster, the new energy prediction performance index is used to represent the uncertainty of the new energy, and represents the deviation degree between the predicted maximum output value and the actual maximum output value of the new energy; and the spinning reserve capacity index is the insufficient probability of the output after the spinning reserve is configured, and is used to represent the ability of the new energy unit to cope with faults and guarantee the stable operation of the power system.

[0017] a first-stage new energy optimal consumption rate for reflecting special requirements of the grid regulation on the output complementary cluster, the first-stage new energy optimal consumption rate being used to represent a consumption degree of the scheduled first-stage output complementary cluster on new energy; and a power plant power execution rate index for representing an execution degree of the power plant on the scheduling plan;

[0018] a second-stage new energy optimal consumption rate for reflecting special requirements of the grid regulation on the flexible load cluster, the second-stage new energy optimal consumption rate being used to represent a consumption degree of the scheduled second-stage output complementary cluster on new energy; and a load execution rate index for representing a response capability of the flexible adjustable resource on the scheduling plan.

[0019] Further, the quantified control performance indexes of the new energy cluster, the output complementary cluster and the flexible load cluster are respectively obtained by using an entropy weight method to weight the special index system and the space-time response control performance index system; a comprehensive quantified control performance index of the flexible controllable resource is obtained based on the quantified control performance indexes, and the calculation of the comprehensive quantified 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 space-time response control performance index system and the special index system;

[0021] using the standardized data to calculate the information entropy of each evaluation index under different index systems;

[0022] using the information entropy of each evaluation index under different index systems to aggregate the space-time response control performance sub-index and the special performance sub-index corresponding to each cluster;

[0023] weight values of the space-time response control performance sub-index and the special performance sub-index corresponding to each cluster are respectively set, and the quantified control performance indexes respectively corresponding to the new energy cluster, the output complementary cluster and the flexible load cluster are respectively obtained by using the space-time response control performance sub-index, the special performance sub-index and the weight values corresponding to each cluster.

[0024] Further, the original data of the new energy cluster, the output complementary cluster and the flexible load cluster under the space-time response control performance index system and the special index system are standardized, and the standardization formula is:

[0025]

[0026] In the formula, is the normalized index data value of the jth evaluation index of the flexible controllable load cluster k under the ith index system, k = 1, 2, 3, the flexible controllable load cluster 1 represents a new energy cluster, the flexible controllable load cluster 2 represents a complementary output cluster, and the flexible controllable load cluster 3 represents a flexible load cluster; is the original index data value of the jth evaluation index of the flexible controllable load cluster k before standardization under the ith index system, X i,j is a set of original index data values of the jth evaluation index of all flexible controllable load clusters under the ith index system, max(X i,j is the maximum value in the set of original index data values of the jth evaluation index of all flexible controllable load clusters under the ith index system, min(X i,j is the minimum value in the set of original index data values of the jth evaluation index of all flexible controllable load clusters under the ith index system.

[0027] Further, using the standardized data, the information entropy of each evaluation index under different index systems is calculated, including:

[0028] Let the information entropy of the jth evaluation index of the flexible controllable load cluster k under the ith index system be H The expression is:

[0029]

[0030] In the formula: is the proportion of the jth evaluation index of the flexible controllable load cluster k under the ith index system in the column of the evaluation index; is the normalized index data value of the jth evaluation index of the flexible controllable load cluster k under the ith index system; k = 1, 2, 3, the flexible controllable load cluster 1 represents a new energy cluster, the flexible controllable load cluster 2 represents a complementary output cluster, and the flexible controllable load cluster 3 represents a flexible load cluster; n is the number of evaluation indexes.

[0031] Further, using the information entropy of each evaluation index under different index systems, the time and space response control performance index and the special performance index corresponding to each cluster are aggregated, including:

[0032] The aggregated index of the flexible controllable load cluster k under the ith index system is:

[0033]

[0034] In the formula: is the weight of the jth evaluation index of the controllable load cluster k under the ith index system; ​H is the information entropy of the jth evaluation index of the flexible controllable load cluster k under the ith index system, k = 1, 2, 3, the flexible controllable load cluster 1 represents the new energy cluster, the flexible controllable load cluster 2 represents the output complementary cluster, and the flexible controllable load cluster 3 represents the flexible load cluster; n is the number of evaluation indexes; H is the index data value of the jth evaluation index of the flexible controllable load cluster k under the ith index system after standardization.

[0035] Further, the weight values of the space-time response control performance sub-index and the special performance sub-index corresponding to each cluster are set respectively, and the comprehensive real-time control performance index corresponding to the new energy cluster, the output complementary cluster and the flexible load cluster respectively is obtained by using the space-time response control performance sub-index, the special performance sub-index and the weight value corresponding to each cluster, and the expression is:

[0036]

[0037] x k +y k =1

[0038] In the formula, S c,k is the control performance index corresponding to the flexible controllable load cluster k; and are the space-time response control performance sub-index and the special performance sub-index of the flexible controllable load cluster k respectively, k = 1, 2, 3, the flexible controllable load cluster 1 represents the new energy cluster, the flexible controllable load cluster 2 represents the output complementary cluster, and the flexible controllable load cluster 3 represents the flexible load cluster; x k is the space-time response control performance sub-index of the flexible controllable load cluster k; y k is the special performance sub-index of the flexible controllable load cluster k.

[0039] Further, 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 effective data set of the flexible controllable resources is obtained, including the following steps:

[0040] The historical data of the flexible controllable resources of the power grid are preprocessed;

[0041] The improved grey wolf algorithm is used to solve the optimal penalty factor and the optimal kernel function parameter of the support vector machine algorithm;

[0042] The classification model is trained by using the optimal penalty factor and the optimal kernel function parameter, the historical data set of the flexible controllable resources of the power grid is classified by using the classification model, and the historical effective data set of the flexible controllable resources is obtained.

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

[0044] The mirror factor, the maximum and minimum iteration times of the improved grey wolf algorithm are set, and the two dimensions of the position of the grey wolf are used to encode the penalty factor and the kernel function parameter of the support vector machine algorithm.

[0045] The fitness value of the grey wolf individual is calculated, and the three grey wolves meeting the requirements of the fitness value are sequentially recorded as alpha wolf, beta wolf and gamma wolf, and the error rate is used as the fitness value of the alpha wolf, the beta wolf and the gamma wolf.

[0046] The current position optimal individual is subjected to pinhole imaging reverse learning to generate a reverse solution; when the reverse solution is better than the current solution, the reverse solution is replaced by the optimal solution, and the global optimal solution and the fitness value are updated; the coefficient vector of the improved grey wolf algorithm optimization support vector machine method, the fitness value of the alpha wolf, the beta wolf and the gamma wolf are updated.

[0047] Whether the maximum iteration times are reached is verified, if the maximum iteration times are reached, the optimal penalty factor and the optimal kernel function parameter of the support vector machine algorithm are output, otherwise the iteration calculation is continued.

[0048] Further, 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 the flexible controllable resource is divided into a new energy cluster, a complementary output cluster and a flexible load cluster, wherein,

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

[0050] The flexible controllable resource control performance quantification evaluation method has the following beneficial effects:

[0051] The present application considers the maximum consumption of new energy, accurately and effectively evaluates the control performance of the flexible controllable resource, ensures the flexibility and accuracy of the power grid dispatching, and promotes the consumption of new energy and the safe operation of the power system. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings that need to be used in the embodiments or prior art description. Obviously, the drawings in the following description only represent some of the embodiments of the present application. Those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0053] Figure 1 Flow chart of the flexible controllable resource control performance quantification evaluation method of the present application;

[0054] Figure 2 Flow chart of the historical effective data set of the flexible controllable resource of the flexible controllable resource control performance quantification evaluation method of the present application;

[0055] Figure 3 Schematic diagram of the real-time control performance evaluation index of the flexible controllable resource of the flexible controllable resource control performance quantification evaluation method of the present application. DETAILED DESCRIPTION

[0056] The various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0057] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be taken as limiting, but merely as exemplification of the embodiments. Other modifications in the scope and spirit of the application will occur to those skilled in the art upon reading the description of the embodiments.

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

[0059] These and other characteristics of the present application will become apparent from the following description of the preferred forms given, by way of non-limiting example only, with reference to the attached drawings.

[0060] It should also be understood that, although the present application has been described above with reference to certain specific examples, many modifications and variations of the described embodiments are possible and will be apparent to those skilled in the art, which have the characteristics as defined by the claims and therefore all fall within the protective scope of the present application.

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

[0062] Specific embodiments of the present application are described herein with reference to the accompanying drawings. However, it should be understood that the disclosed embodiments are merely examples of implementations of the application as claimed and can be carried out in various ways. Well-known and / or redundant functionality and structure are not described in detail to avoid obscuring the application unnecessarily. Therefore, specific structural and functional details disclosed herein are not intended to be limiting but are merely examples of the application as claimed and are used as a basis for the claims and as a representative basis for teaching one of ordinary skill in the art to variously employ the application in virtually any appropriate detailed structure.

[0063] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "certain embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples.

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

[0065] Embodiments

[0066] As shown in Figure 1 and Figure 3 The present embodiment provides a flexible controllable resource control performance quantification evaluation method, comprising the following steps:

[0067] Step S1: using an improved gray wolf algorithm optimizing support vector machine (IGWO-SVM) method to process the historical data of the flexible controllable resources of the power grid, to obtain a historical effective data set of the flexible controllable resources;

[0068] Step S2: considering the maximum consumption of new energy and the safe operation of the power grid, analyzing the control characteristics of different resources, and dividing the historical effective data set of the flexible controllable resources into a new energy cluster, an output complementary cluster and a flexible load cluster;

[0069] Step S3: considering the adjustment characteristics of the new energy cluster, the output complementary cluster and the flexible load cluster and different scheduling stages, a space-time response control performance index system and a special index system for different cluster characteristics are established, the space-time response control performance index system is used to reflect the requirements of the grid regulation on the multi-response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of the grid regulation on certain flexible adjustable resources; the scheduling stages include: a first stage of scheduling the output complementary cluster and preliminarily consuming the new energy cluster; and a second stage of scheduling the flexible load cluster and supplementally consuming the new energy cluster.

[0070] Step S4: the entropy weight method is used to weight and calculate the quantitative control performance indexes of the new energy cluster, the output complementary cluster and the flexible load cluster respectively according to the space-time response control performance index system and the special index system; and a comprehensive quantitative control performance index of the flexible controllable resources is obtained based on the quantitative control performance indexes.

[0071] As shown in Figure 2 According to another specific embodiment of the present application, on the basis of the step S1, the improved grey wolf algorithm is used to optimize the support vector machine method to process the historical data of the grid flexible controllable resources, and the historical effective data set of the flexible controllable resources is obtained, including the following steps:

[0072] The historical data of the grid flexible controllable resources is preprocessed;

[0073] The improved grey wolf algorithm is used to solve the optimal penalty factor and the optimal kernel function parameter of the support vector machine algorithm;

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

[0075] According to another specific embodiment of the present application, on the basis of the above embodiment, the improved grey wolf algorithm is used to solve the optimal penalty factor and the optimal kernel function parameter of the support vector machine algorithm;

[0076] The mirror factor, the maximum and minimum iteration numbers of the improved grey wolf algorithm are set, and the two dimensions of the position of the grey wolf are used to encode the penalty factor and the kernel function parameter of the support vector machine algorithm;

[0077] The fitness values of the grey wolves are calculated, three grey wolves whose fitness values meet the requirements are selected and sequentially recorded as alpha wolf, beta wolf and gamma wolf, and the error rate is used as the fitness value of the alpha wolf, the beta wolf and the gamma wolf;

[0078] The current position optimal individual is subjected to small hole imaging reverse learning to generate a reverse solution; when the reverse solution is better than the current solution, the reverse solution is replaced by the optimal solution, and the global optimal solution and the fitness value are updated; the fitness values of the coefficient vector, alpha wolf, beta wolf and gamma wolf of the improved gray wolf algorithm optimization support vector machine method are updated;

[0079] It is verified whether the maximum iteration number is reached, and if so, the optimal penalty factor and the optimal kernel function parameter of the support vector machine algorithm are output, otherwise the iteration calculation is continued.

[0080] In the step S1, the improved gray wolf algorithm optimization support vector machine method is used to process the historical data of the flexible controllable resource to obtain a historical effective data set of the flexible controllable resource. The support vector machine (SVM) is a classic binary classification algorithm, which is suitable for nonlinear data, can avoid the curse of dimensionality, and has good generalization ability; dividing the historical effective data set of the flexible controllable resource needs to divide the high-dimensional complex data of the flexible controllable resource into two categories of normal and abnormal; 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 importance of the algorithm to outliers, that is, the tolerance to errors. The kernel function parameter g is the parameter of the Gauss radial basis function (RBF), which affects the performance of the kernel function. The greater the values of the penalty factor C and the kernel function parameter g, the less tolerant the model is to errors, and it pays more attention to relatively distant outliers, which will cause the model to have more support vectors, making the support vector machine model complex and prone to over-learning. The smaller the values of the penalty factor C and the kernel function parameter g, the more tolerant the model is to errors, and some outliers can be discarded, so that a simpler model is obtained, but it may lead to underfitting of the model.

[0082] The gray wolf optimization algorithm (GWO) has been successfully applied in image processing, intrusion detection and anomaly data detection due to its simple principle, small number of parameters and good convergence. Therefore, the GWO algorithm is selected to find the penalty factor C and the kernel function parameter g of the support vector machine. The traditional GWO algorithm is prone to premature convergence and local optimum. Therefore, in order to reasonably select the parameters of the SVM, the GWO is improved, and the improved gray wolf optimization algorithm (IGWO) is proposed to optimize the parameters of the support vector machine.

[0083] Good diversity and uniform distribution of initial population is essential for swarm intelligence optimization algorithm, which can maximize the range of search optimization and enhance the effect of global optimization. The standard grey wolf optimization algorithm usually solves optimization problems by randomly generating grey wolf population, which leads to the aggregation of grey wolf individuals in a small area, making it difficult to maintain population diversity, or the uneven distribution of the generated population, resulting in blind search of grey wolf individuals in the solution space, slow convergence and low precision. Therefore, it is necessary to find an initial population with good diversity and uniform distribution, expand the search range of grey wolf population, and improve the overall performance of the algorithm. At present, there are many commonly used chaos mapping in the field of swarm intelligence optimization, and the population distribution generated by different mapping is different. The present application uses Tent mapping to initialize the population, improve the quality of the initial population, and reduce the influence of the initial value on the optimization of the algorithm. The Tent mapping method can well avoid the problem of uneven population generated by other mapping methods, which usually has a higher probability of taking values at the edge and a lower probability of taking values in the middle segment. The Tent mapping method generates a relatively uniform population in the [0,1] interval, and has strong ergodicity and optimization efficiency. The expression of Tent mapping is:

[0084]

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

[0086]

[0087] In the formula: n is the mirror factor. The improved algorithm uses a larger n value in the early iteration, which can enhance the optimization ability of the algorithm in a wide space and increase the diversity of the optimization position; a smaller n is used in the later iteration, which can make the population gradually approach the optimal individual area, quickly explore the local area, and improve the search performance of the algorithm. The mirror factor n is calculated by linearly decreasing:

[0088]

[0089] In the formula: I max is the maximum iteration number, n max and n min are the maximum and minimum values of the mirror factor n, respectively.

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

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

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

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

[0094] New energy cluster:

[0095] The output of a solar photovoltaic generator set is mainly affected by the light intensity, battery junction temperature and environmental temperature, and the mathematical model of the photovoltaic output can be expressed as

[0096]

[0097] In the formula, P PV (t) is the output power of the photovoltaic set at time t (W), k T is the temperature coefficient (% / ℃), P SET is the rated output power of the photovoltaic set (W), S SET is the standard light intensity of the photovoltaic set (kw / m 2 ), S(t) is the light intensity of the photovoltaic set at time t (kw / m 2 ), T(t) is the environmental temperature at time t (℃), and T SET is the standard environmental temperature (℃).

[0098] Wind power generation is one of the main forms of wind energy utilization, which converts wind energy into electric energy through a wind turbine. The basic principle is that wind energy drives the blades of the wind turbine to rotate, converts wind energy into mechanical energy, and the rotating blades drive the generator shaft to rotate and then convert into electric energy. According to the principle of power generation, the mechanical output power of the wind turbine is mainly affected by the wind speed, blade radius and air density, and its mathematical expression is:

[0099]

[0100] In the formula, P M is the mechanical output power of the wind turbine (W), is the swept area of the blade (m 2 ), wherein, RWT Where ρ is the blade radius (m), and ρ is the air density (kg / m³). 3 ), where ν is the wind speed (m / s), and C p This represents the wind energy utilization coefficient.

[0101] Complementary power clusters:

[0102] The factors affecting the output power of a hydropower station include not only the total water demand at various times and changes in reservoir water level, but also the turbine head and the efficiency of the generator. The output power model of a hydropower station can be represented by the law of energy conservation, where the potential energy difference between the upstream and downstream sections of the water body corresponds to the output electrical energy.

[0103]

[0104] In the formula: P h,t Let be the output power of the hydropower unit during time period t; A is the hydroelectric conversion constant, typically 9.81; Q h,t The flow rate used by the hydropower station for power generation during time period t; h t η is the net head of the turbine during time period t; η is the efficiency of the hydropower station.

[0105] The parameters during the peak-shaving process of thermal power units can be calculated using the following formula:

[0106]

[0107] In the formula: P Gi The rated capacity of units participating in conventional peak shaving; The rated capacity of a deep peak-shaving unit; N G1 With N G2 These represent the number of conventional peak-shaving units and the number of units capable of deep peak shaving; P Gi,max With P Gi,min分别 P represents the maximum and minimum output power of thermal power unit i; Gi,n P represents the minimum output power of thermal power unit i during the peak shaving phase without oil injection. Gi,m This represents the minimum output power of thermal power unit i during the peak shaving phase of oil injection depth. and These represent the maximum and minimum load rates of thermal power unit i, respectively. and These represent the minimum load rates of thermal power unit i during the deep peak shaving phase when it is not fueled and when it is fueled, respectively.

[0108] The key parameter for energy storage resources is the system frequency f, and the output power of the resource is P. out5 P out5 P is the battery output power. out5 <0 indicates battery charging, P out5 >0 indicates that the battery is discharged. Pout5 The expression is:

[0109]

[0110] In the formula P BS Rated power of the battery; K EA Unit adjustable power; Δf b and Δf a These are the upper and lower limits for the energy storage battery's output during frequency regulation.

[0111] Flexible load clustering:

[0112] Air conditioning load is a typical temperature-controlled load. Air conditioning resources are generally regulated in clusters. Let's assume the air conditioning cluster consists of N air conditioners, and its key parameter is the on / off state S of generator i at time t. t,i and the rated power P of the air conditioner t,i Power P ac for:

[0113]

[0114] Electric vehicle loads are typically regulated in clusters. Let the electric vehicle cluster consist of N vehicles, and its key parameter be the charging requirement Q for the j-th vehicle. need,j Output power P EV for

[0115]

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

[0117] This invention, based on the principle of achieving multi-energy complementarity and source-load interaction, divides flexible and controllable resources into new energy clusters, complementary energy clusters, and flexible load clusters. It performs two-stage optimized scheduling of the complementary energy clusters and the flexible load clusters. The first stage schedules the complementary energy clusters to initially absorb the new energy from the new energy clusters; the second stage schedules the flexible load clusters to supplement and absorb the new energy from the new energy clusters.

[0118] According to another specific embodiment of the present application, on the basis of the step S3, considering the adjustment characteristics and scheduling stages of the new energy cluster, the output complementary cluster and the flexible load cluster, a time-space response control performance index system and a special index system for different cluster characteristics are established, the time-space response control performance index system is used to reflect the requirements of the grid regulation on the multi-response control performance of all flexible adjustable resources, and the special index system is used to reflect the special requirements of the grid regulation on certain flexible adjustable resources, the scheduling stages include: a first stage, scheduling the output complementary cluster to preliminarily consume the new energy cluster; a second stage, scheduling the flexible load cluster to supplementally consume the new energy cluster; wherein,

[0119] The evaluation indexes of the time-space response control performance index system include:

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

[0121] a space response control performance index, used to represent the power capacity of the flexible adjustable resource that can be accepted by the grid scheduling within a set period of time;

[0122] The evaluation indexes of the special index system include:

[0123] a new energy prediction performance index and a spinning reserve capacity index used to reflect the special requirements of the grid regulation on the new energy cluster; the new energy prediction performance index is used to represent the uncertainty of the new energy, indicating the deviation degree between the predicted maximum output value and the actual maximum output value of the new energy; the spinning reserve capacity index is the insufficient probability of the output after the spinning reserve is configured, and is used to represent the ability of the new energy unit to cope with faults and ensure the stable operation of the power system;

[0124] a first-stage new energy optimal consumption rate and a power plant power execution rate index used to reflect the special requirements of the grid regulation on the output complementary cluster; the first-stage new energy optimal consumption rate is used to represent the consumption degree of the new energy by the output complementary cluster in the first stage of scheduling; and the power plant power execution rate index is used to represent the execution degree of the scheduling plan by the power plant;

[0125] a second-stage new energy optimal consumption rate and a load execution rate index used to reflect the special requirements of the grid regulation on the flexible load cluster, the second-stage new energy optimal consumption rate is used to represent the consumption degree of the new energy by the output complementary cluster in the second stage of scheduling; and the load execution rate index is used to represent the response ability of the flexible adjustable resource to the scheduling plan.

[0126] Specifically as follows:

[0127] Since new energy has strong uncertainty, and the unit needs to leave enough rotating reserve capacity to maintain the system always on a better reliability standard, the special index system for new energy cluster includes the following indexes:

[0128] New energy prediction performance index:

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

[0130]

[0131] In the formula: is the actual maximum output value of new energy, is the predicted maximum output value of new energy.

[0132] Rotating reserve capacity index:

[0133] Rotating reserve capacity index L RB The insufficient output probability after configuring rotating reserve, which characterizes the ability of new energy unit to deal with faults and ensure the stable operation of 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] In the formula: P fau is the fault outage capacity of new energy unit, P real,l is the actual load value of flexible load, P pre,l is the predicted load value of flexible load, R is the rotating reserve capacity of new energy unit, P is the probability of the expression in the subsequent [].

[0136] Output complementary cluster is used to preliminarily consume new energy in the first stage of scheduling. In the first stage of scheduling, the output of new energy cluster and output complementary cluster in each period is optimized, an optimization scheduling model is established to minimize the total load variance of power system and minimize the operation cost of power system, the output value of output complementary cluster in each period is obtained by solving the model, and the optimal consumption rate and optimal grid-connected power of new energy cluster in the first stage are further obtained. Based on the first stage scheduling target, the special index system for output complementary cluster includes the following indexes:

[0137] First stage new energy optimal consumption rate:

[0138] The first-stage scheduling obtains a first-stage optimal scheduling plan of the new energy unit with the minimum total load variance of the power system and the lowest operation cost of the power system as the target, and the optimal plan output is less than the actual maximum output The optimal consumption rate of new energy index C1 is defined to represent the consumption degree of the first-stage output complementary cluster of the scheduling to the new energy, and the expression is as follows:

[0139]

[0140] The power plant power execution rate index:

[0141] The power plant power execution rate index represents the execution degree of the power plant to the scheduling plan, and the expression is as follows:

[0142]

[0143] In the formula, P real is the actual output value of the power plant, P she is the planned output value of the power plant.

[0144] The flexible load cluster is used to supplement the consumption of the new energy in the second stage of the scheduling. In the second stage of the scheduling, the output of the flexible load cluster in each period is optimized, an optimal scheduling model with the minimum total load variance of the power system and the lowest electricity cost of the flexible load cluster as the target is established, the load value of the flexible load cluster in each period is solved, and the optimal consumption rate of the new energy in the second stage and the optimal grid-connected power are further solved. Based on the target of the second-stage scheduling, the special index system of the flexible load cluster includes the following indexes:

[0145] The optimal consumption rate of the new energy in the second stage:

[0146] The second-stage scheduling obtains a second-stage optimal scheduling plan of the new energy unit with the minimum total load variance of the power system, the highest consumption of the new energy and the lowest electricity cost of the flexible load cluster as the target, and the optimal plan output is less than the actual maximum output The optimal consumption rate of the new energy index C2 is defined to represent the consumption degree of the second-stage output complementary cluster of the scheduling to the new energy, and the expression is as follows:

[0147]

[0148] The load execution rate index:

[0149] The load execution rate index E L represents the response ability of the flexible adjustable resource to the scheduling plan, and the expression is as follows:

[0150]

[0151] ΔP real is a change amount of actual power of the flexible load, ΔP she is a planned change amount of the flexible load.

[0152] According to another specific embodiment of the present application, on the basis of the step S4, the quantitative control performance indexes of the new energy cluster, the output complementary cluster and the flexible load cluster are respectively obtained by using the entropy weight method to weight the space-time response control performance index system and the special index system; the comprehensive quantitative control performance index of the flexible controllable resource is obtained on the basis of the quantitative control performance indexes, and the calculation of the quantitative control performance indexes comprises the following steps:

[0153] The original data of the new energy cluster, the output complementary cluster and the flexible load cluster under the space-time response control performance index system and the special index system are standardized;

[0154] The information entropy of each evaluation index under different index systems is calculated by using the standardized data;

[0155] The space-time response control performance sub-index and the special performance sub-index corresponding to each cluster are aggregated by using the information entropy of each evaluation index under different index systems;

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

[0157] According to another specific embodiment of the present application, 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 space-time response control performance index system and the special index system are standardized, and the standardization formula is considered to be a positive index, that is:

[0158]

[0159] In the formula: is the index data value of the jth evaluation index of the flexible controllable load cluster k under the ith index system after standardization, k = 1, 2, 3, the flexible controllable load cluster 1 represents the new energy cluster, the flexible controllable load cluster 2 represents the output complementary cluster, and the flexible controllable load cluster 3 represents the flexible load cluster; is the index original data value of the jth evaluation index of the flexible controllable load cluster k under the ith index system before standardization, X i,jmax(X i,j ) is the maximum value of the set of the original data values of the jth evaluation index under the ith index system of all the flexible controllable load clusters. i,j ) is the minimum value of the set of the original data values of the jth evaluation index under the ith index system of all the flexible controllable load clusters.

[0160] According to another specific embodiment of the present application, on the basis of the above-mentioned embodiment, the data obtained by standardization is used to calculate the information entropy of each evaluation index under different index systems, including:

[0161] Let the information entropy of the jth evaluation index under the ith index system of the flexible controllable load cluster k be The expression is:

[0162]

[0163] In the formula: is the proportion of the jth evaluation index under the ith index system of the flexible controllable load cluster k in the column of the evaluation index; is the index data value of the jth evaluation index under the ith index system of the flexible controllable load cluster k after standardization; k = 1, 2, 3, the flexible controllable load cluster 1 represents a new energy cluster, the flexible controllable load cluster 2 represents a complementary output cluster, and the flexible controllable load cluster 3 represents a flexible load cluster; n is the number of evaluation indexes.

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

[0165] The sub-index obtained by aggregating the ith index system of the flexible controllable load cluster k is:

[0166]

[0167] In the formula: is the weight of the jth evaluation index under the ith index system of the controllable load cluster k; is the information entropy of the jth evaluation index under the ith index system of the flexible controllable load cluster k, k = 1, 2, 3, the flexible controllable load cluster 1 represents a new energy cluster, the flexible controllable load cluster 2 represents a complementary output cluster, and the flexible controllable load cluster 3 represents a flexible load cluster; n is the number of evaluation indexes. The standardized index data value of the flexible controllable load cluster k under the jth evaluation index of the ith index system.

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

[0169]

[0170] x k +y k =1

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

[0172] The weight values ω of the space-time response control performance sub-index and the special performance sub-index of the three kinds of flexible controllable resources are shown in Table 1:

[0173] Table 1 Weight values of control performance sub-indexes under three time scales

[0174] spatial-temporal response control performance sub-index special performance sub-index new energy cluster x1 [cdta] output complementary cluster x2 y2 <!-- 13 -->]] flexible load cluster x3 [cdta]

[0175] The above description merely illustrates the preferred embodiments of the disclosure and a principle of applied technologies. It should be understood by those skilled in the art that the disclosed range of the disclosure is not limited to the technical solutions formed by the specific combinations of the technical features described above, and should also cover other technical solutions formed by the combinations of the technical features described above or their equivalent features without departing from the above disclosed concept. For example, the technical solutions formed by the mutual replacement of the above features and the technical features with similar functions disclosed in the disclosure (but not limited to) should be covered.

[0176] Furthermore, although operations are depicted in a particular, sequential order, this should not be understood as requiring or implying that the operations are performed in the order illustrated or sequentially. In certain circumstances, multitasking and parallel processing can be advantageous. Likewise, although specific implementation details are included for the purpose of providing a thorough disclosure, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination.

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

[0178] The above has described in detail the multiple embodiments of the disclosure, but the disclosure is not limited to these specific embodiments, and those skilled in the art can make various modifications and embodiments on the basis of the concept of the disclosure, and these modifications and embodiments should fall within the scope of the disclosure claimed.

Claims

1. A method for quantitatively evaluating the control performance of flexible and controllable resources, characterized in that, Includes the following steps: An improved gray wolf algorithm-optimized support vector machine is used to process historical data of flexible and controllable resources of the power grid, resulting in a valid historical dataset of flexible and controllable resources. Considering the maximum absorption of new energy sources and the safe operation of the power grid, the control characteristics of different resources are analyzed, and the historical effective datasets of flexible and controllable resources are divided into new energy clusters, power output complementary clusters, and flexible load clusters. Considering the different regulation characteristics and scheduling stages of the new energy cluster, the power 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 multi-dimensional 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 scheduling phase includes: the first phase, scheduling complementary power output clusters to initially absorb the new energy clusters; and the second phase, scheduling flexible load clusters to supplement the absorption of the new energy clusters. For the spatiotemporal response control performance index system and the special index system, the quantitative control performance indexes of the new energy cluster, the power output complementary cluster and the flexible load cluster are obtained by weighted calculation using the entropy weight method; based on the quantitative control performance indexes, the comprehensive quantitative control performance index of flexible and controllable resources is obtained. The evaluation indicators of the spatiotemporal response control performance index system include: Time response control performance metrics are used to characterize the time taken for a flexible and adjustable resource to reach the set percentage of the target value for the first time from receiving an adjustment command to the actual output. Spatial response control performance indicators are used to characterize the power capacity of flexible and adjustable resources that can be dispatched by the power grid within a set time period.

2. The method for quantitatively evaluating the control performance of flexible and controllable resources according to claim 1, characterized in that, Considering the different regulation characteristics and scheduling stages of the aforementioned new energy clusters, power complementarity clusters, and flexible load clusters, 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 reflects the requirements of grid regulation for the multi-dimensional response control performance of all flexible adjustable resources, while the special index system reflects the special requirements of grid regulation for a certain type of flexible adjustable resource. The scheduling stage includes: a first stage, scheduling power complementarity clusters to initially absorb new energy clusters; and a second stage, scheduling flexible load clusters to supplement the absorption of new energy clusters. The evaluation indicators of the special indicator system include: The new energy prediction performance index and the spinning reserve capacity index are used to reflect the special requirements of grid regulation on new energy clusters. The new energy prediction performance index is used to characterize the uncertainty of new energy and to indicate the degree of deviation between the predicted maximum output value and the actual maximum output value of new energy. The spinning reserve capacity index is the probability of insufficient output after configuring spinning reserve and is used to characterize the ability of new energy units to cope with faults and ensure the stable operation of the power system. The first-stage optimal renewable energy absorption rate and power plant power execution rate are indicators used to reflect the special requirements of power grid regulation on the power complementarity cluster. The first-stage optimal renewable energy absorption rate is used to characterize the degree of renewable energy absorption by the first-stage power complementarity cluster in the dispatching process. The power plant power execution rate is used to characterize the degree of execution of the dispatching plan by the power plant. The second-stage optimal renewable energy absorption rate and load execution rate indicators are used to reflect the special requirements of power grid regulation for flexible load clusters. The second-stage optimal renewable energy absorption rate is used to characterize the degree of renewable energy absorption by the second-stage power complementary cluster of the dispatching system; the load execution rate indicator is used to characterize the responsiveness of flexible adjustable resources to the dispatching plan.

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

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

5. The method for quantitatively evaluating the control performance of flexible and controllable resources according to claim 3, characterized in that, Using standardized data, the information entropy of various evaluation indicators under different indicator systems is calculated, including: Let the information entropy of the j-th evaluation index of the flexible and controllable load cluster k under the i-th index system be . Its expression is: ， ， In the formula: The percentage of the j-th evaluation index in the i-th index system for the flexible and controllable load cluster k in this evaluation index column; The standardized index data value of the j-th evaluation index under the i-th index system for flexible and controllable load cluster k; k=1, 2, 3, where flexible and controllable load cluster 1 represents a new energy cluster, flexible and controllable load cluster 2 represents a power complementary cluster, and flexible and controllable load cluster 3 represents a flexible load cluster; n is the number of evaluation indicators.

6. The method for quantitatively evaluating the control performance of flexible and controllable resources according to claim 3, characterized in that, By utilizing the information entropy of various evaluation indicators under different indicator systems, spatiotemporal response control performance sub-indicators and special performance sub-indicators corresponding to each cluster are aggregated, including: The sub-indicators obtained by aggregating the i-th index system in the flexible and controllable load cluster k for: ， ， In the formula: Let be the weight of the j-th evaluation index of the controllable load cluster k under the i-th index system; Let k be the information entropy of the j-th evaluation index of the flexible and controllable load cluster k under the i-th index system, where k = 1, 2, 3. Flexible and controllable load cluster 1 represents a new energy cluster, flexible and controllable load cluster 2 represents a power complementary cluster, and flexible and controllable load cluster 3 represents a flexible load cluster; n is the number of evaluation indicators. The standardized index data value of the j-th evaluation index under the i-th index system for the flexible and controllable load cluster k.

7. The method for quantitatively evaluating the control performance of flexible and controllable resources according to claim 3, characterized in that, Weights are set for the spatiotemporal response control performance sub-indicators and special performance sub-indicators corresponding to each cluster. Using the spatiotemporal response control performance sub-indicators, special performance sub-indicators, and weights for each cluster, the comprehensive real-time control performance indices corresponding to the new energy cluster, the power output complementary cluster, and the flexible load cluster are obtained. Their expressions are as follows: ， ， In the formula: S c,k This refers to the quantitative control performance index corresponding to the flexible and controllable load cluster k; and These are the spatiotemporal response control performance sub-indicators and special performance sub-indicators of flexible and controllable load cluster k, respectively, k=1, 2, 3. Flexible and controllable load cluster 1 represents a new energy cluster, flexible and controllable load cluster 2 represents a power complementary cluster, and flexible and controllable load cluster 3 represents a flexible load cluster. The spatiotemporal response control performance index of flexible and controllable load cluster k; This is a special performance index for flexible and controllable load cluster k.

8. The method for quantitatively evaluating the control performance of flexible and controllable resources according to claim 1, characterized in that, An improved gray wolf algorithm is used to optimize the support vector machine method for processing historical data of flexible and controllable resources in the power grid, resulting in a valid historical dataset of flexible and controllable resources. This process includes the following steps: Preprocess historical data on the flexible and controllable resources of the power grid; The optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm are solved using the improved gray wolf algorithm; A classification model is trained using the optimal penalty factor and the optimal kernel function parameters. The classification model is then used to classify the preprocessed historical dataset of flexible and controllable resources in the power grid, thereby obtaining a valid historical dataset of flexible and controllable resources.

9. The method for quantitatively evaluating the control performance of flexible and controllable resources according to claim 8, characterized in that, The optimal penalty factor and optimal kernel function parameters for the Support Vector Machine (SVM) algorithm are solved using an improved Grey Wolf algorithm, including: The improved Grey Wolf algorithm is configured with a mirror factor, a maximum and minimum number of iterations, and the penalty factor and kernel function parameters of the support vector machine algorithm are encoded using two dimensions: the position in the Grey Wolf algorithm. Calculate the fitness value of individual gray wolves, select three gray wolves whose fitness values ​​meet the requirements and label them as α wolf, β wolf and γ wolf respectively, and use the error rate as the fitness value of α wolf, β wolf and γ wolf; The optimal individual at the current position is subjected to pinhole imaging back learning to generate a back solution; when the back solution is better than the current solution, the back solution is replaced with the optimal solution, and the global optimal solution and fitness value are updated; the coefficient vector, α wolf, β wolf and γ wolf fitness values ​​of the improved gray wolf algorithm for optimizing the support vector machine method are updated. Verify whether the maximum number of iterations has been reached. If it has, output the optimal penalty factor and optimal kernel function parameters of the support vector machine algorithm; otherwise, continue iterative calculation.

10. The method for quantitatively evaluating the control performance of flexible and controllable resources according to claim 1, characterized in that, Considering the maximum absorption of new energy sources and the safe operation of the power grid, the control characteristics of different resources are analyzed. The historical effective datasets of flexible and controllable resources are divided into new energy clusters, power complementarity clusters, and flexible load clusters. The new energy cluster includes wind power and photovoltaic resources, the power output complementary cluster includes adjustable hydropower, thermal power and energy storage, and the flexible load cluster includes electric vehicles and temperature-controlled loads, with air conditioning as a typical example.

Images