Industrial load flexibility evaluation method and device, computer equipment and storage medium

Abstract

The invention relates to an industrial load flexibility evaluation method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring multiple pieces of industrial load flexibility index data; determining a subjective weight and an objective weight of each piece of industrial load flexibility index data; determining a comprehensive weight of each industrial load flexibility index data based on the subjective weight and the objective weight; determining an industrial load flexibility evaluation grade based on the industrial load flexibility index data and the comprehensive weight of the industrial load flexibility index data; wherein the industrial load flexibility index data comprises load characteristic index data, control characteristic index data, response characteristic index data, adjustment characteristic index data and response intention index data. The method is beneficial to improving the accuracy of industrial load flexibility evaluation.

Description

Technical Field

[0001] The present application relates to the technical field of electric power, and particularly to an industrial load flexibility evaluation method, device, computer device, computer-readable storage medium, and computer program product. Background Art

[0002] With the large-scale grid connection of new energy mainly based on wind power, the uncertainty and reverse peak shaving characteristics faced by the power system are continuously increasing. It is necessary to fully exploit the flexible regulation ability of the power system to improve the consumption of renewable energy while meeting the peak shaving requirements.

[0003] In the domestic electricity consumption structure, compared with users of other types such as commercial and residential users, industrial users have characteristics such as large energy consumption capacity and strong energy consumption logic. By adjusting production plans, starting and stopping equipment, etc. to respond to the regulation signals of the power grid and fully utilizing the flexibility space in their production, the stable operation of the power system can be effectively supported.

[0004] However, due to the diverse production logics and different production habits of industrial users, it is usually necessary to analyze which industries have the greatest potential based on industry load data, and then conduct specific analyses on users in each industry to select industries and users with demand response potential from a large number of users, that is, to conduct a hierarchical quantification evaluation of industrial load flexibility. The current industrial load flexibility evaluation methods have the problem of low evaluation accuracy. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide an industrial load flexibility evaluation method, device, computer device, computer-readable storage medium, and computer program product that can improve the accuracy of industrial load flexibility evaluation.

[0006] In a first aspect, the present application provides an industrial load flexibility evaluation method, including:

[0007] Obtaining a plurality of industrial load flexibility index data;

[0008] Determining the subjective weight and objective weight of each industrial load flexibility index data;

[0009] Based on the subjective weight and objective weight, determining the comprehensive weight of each industrial load flexibility index data;

[0010] Based on each industrial load flexibility index data and the comprehensive weight of each industrial load flexibility index data, determining the industrial load flexibility evaluation level;

[0011] Wherein, the industrial load flexibility index data includes load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data.

[0012] In one embodiment, determining the objective weight of each industrial load flexibility index data includes:

[0013] Obtain multiple index data sample sets, where each index data sample set includes multiple industrial load flexibility index data samples;

[0014] Perform data preprocessing on each index data sample set, and the data preprocessing includes at least one of dimensionless processing and standardization processing;

[0015] Based on multiple index data sample sets, determine the information entropy of each industrial load flexibility index data;

[0016] According to each industrial load flexibility index data, determine the Pearson correlation coefficient between each industrial load flexibility index data;

[0017] For each industrial load flexibility index data, determine the degree of influence of the industrial load flexibility index data according to the Pearson correlation coefficient;

[0018] According to the information entropy and the degree of influence of each industrial load flexibility index, determine the objective weight of each industrial load flexibility index data.

[0019] In one embodiment, determining the subjective weight of each industrial load flexibility index data includes:

[0020] Obtain the criterion layer matrix, and the elements in the criterion layer matrix are the importance difference values between different industrial load flexibility index data;

[0021] When the criterion layer matrix passes the consistency check, solve the eigenvector corresponding to the maximum eigenvalue of the criterion layer matrix to obtain the subjective weight of each industrial load flexibility index data.

[0022] In one embodiment, based on the subjective weight and the objective weight, determining the comprehensive weight of each industrial load flexibility index includes:

[0023] Taking the goal of maximizing the difference in scores between different index data sample sets, through the particle swarm optimization algorithm, solve the weight coefficients corresponding to the subjective weight and the objective weight of the industrial load flexibility index respectively. The score of the index data sample set is determined according to the subjective weight and the objective weight of each industrial load flexibility index data and each industrial load flexibility index data sample;

[0024] Based on the weight coefficients corresponding to the subjective weight and the objective weight respectively, determine the comprehensive weight of the industrial load flexibility index.

[0025] In one embodiment, based on the comprehensive weights of each industrial load flexibility index, an industrial load flexibility evaluation level is determined, including:

[0026] Determine the membership degree of each industrial load flexibility index data for different evaluation levels;

[0027] Based on the comprehensive weights of each industrial load flexibility index data and the membership degrees of each industrial load flexibility index data for different evaluation levels, construct an evaluation matrix;

[0028] Based on the objective weights of each industrial load flexibility index data and the evaluation matrix, obtain the comprehensive evaluation values of each industrial load flexibility index data, and determine the evaluation level to which the maximum comprehensive evaluation value belongs as the industrial load flexibility evaluation level.

[0029] In one embodiment, the load characteristic index data includes a load matching degree, and the load matching degree is obtained based on the power consumption data during the peak load period of the day;

[0030] The power consumption data during the peak load period of the day is obtained based on the following method:

[0031] Obtain multiple grid daily load time series data;

[0032] Determine the similarity between each grid daily load time series data, and screen out the target grid daily load time series data with a similarity greater than a preset similarity threshold;

[0033] Extract the peak load period data from the target grid daily load time series data, and perform a clustering operation on the peak load period data to obtain multiple peak load period clusters;

[0034] Determine the class center of each peak load period cluster, and integrate each class center to obtain the power consumption data during the peak load period of the day.

[0035] In a second aspect, the present application also provides an industrial load flexibility evaluation device, including:

[0036] A data acquisition module for acquiring multiple industrial load flexibility index data;

[0037] A weight determination module for determining the subjective weight and objective weight of each industrial load flexibility index data; based on the subjective weight and objective weight, determine the comprehensive weight of each industrial load flexibility index data;

[0038] A level evaluation module for determining the industrial load flexibility evaluation level based on each industrial load flexibility index data and the comprehensive weight of each industrial load flexibility index data; wherein, the industrial load flexibility index data includes load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data.

[0039] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps in any of the above-mentioned embodiments of the industrial load flexibility evaluation method are implemented.

[0040] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above-mentioned embodiments of the industrial load flexibility evaluation method are implemented.

[0041] In a fifth aspect, the present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps in any of the above-mentioned embodiments of the industrial load flexibility evaluation method are implemented.

[0042] For the above-mentioned industrial load flexibility evaluation method, device, computer device, computer-readable storage medium, and computer program product, on the one hand, it fully considers the impact of industrial loads when accessing the power grid, takes into account the fast response ability, reliability, and economy of flexible loads, and conducts industrial load flexibility evaluation on multi-dimensional index data such as flexible load potential, regulation effect, load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data, improving the accuracy of industrial load evaluation; on the other hand, it respectively determines the subjective weight and objective weight of each industrial load flexibility index data, determines the comprehensive weight of each industrial load flexibility index data through the subjective weight and objective weight, reduces the deviation of a single method, is conducive to enhancing the adaptability and flexibility of the evaluation, and at the same time improves the effectiveness of the evaluation. Thus, the industrial load flexibility evaluation level is determined according to each industrial load flexibility index data and the corresponding comprehensive weight, providing a relatively perfect evaluation system, further improving the accuracy of industrial load flexibility evaluation, and then being conducive to industrial demand-side response management according to the industrial load flexibility evaluation level, guiding peak shaving and valley filling, improving the flexibility of the power system, ensuring the safe and stable operation of the power system, and promoting the consumption of renewable energy power. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a diagram of the application environment of the industrial load flexibility evaluation method in an embodiment;

[0045] Figure 2 It is a schematic flow chart of an industrial load flexibility evaluation method in an embodiment;

[0046] Figure 3 It is a schematic flow chart of an industrial load flexibility evaluation method in another embodiment;

[0047] Figure 4 It is a schematic flow chart of an industrial load flexibility evaluation method in yet another embodiment;

[0048] Figure 5 It is a structural block diagram of an industrial load flexibility evaluation device in an embodiment;

[0049] Figure 6 It is an internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0050] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] The industrial load flexibility evaluation method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 . Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers.

[0052] Specifically, it can be that an operator uploads the collected multiple industrial load flexibility index data to the server 104 through the terminal 102, and then sends an industrial load flexibility evaluation message to the server 104 through the terminal 102. The server 104 obtains the multiple industrial load flexibility index data. The industrial load flexibility index data includes load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index and response willingness index data. Secondly, determine the subjective weight and objective weight of each industrial load flexibility index data. Then, based on the subjective weight and objective weight, determine the comprehensive weight of each industrial load flexibility index data. Finally, based on each industrial load flexibility index data and the comprehensive weight of each industrial load flexibility index data, determine the industrial load flexibility evaluation level.

[0053] Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, etc. The server 104 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0054] In an exemplary embodiment, as Figure 2 shown, an industrial load flexibility evaluation method is provided. Taking the method applied to Figure 1 the server 104 in it as an example for illustration, it includes the following steps (hereinafter simply referred to as S) S100 to S400. Among them:

[0055] S100, obtain multiple industrial load flexibility index data. Among them, the industrial load flexibility index data includes load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data.

[0056] In practical applications, for different industrial types, such as industries like cement, steel, ferroalloy, silicon carbide, electrolytic aluminum, electrolytic magnesium, etc., industrial load flexibility index data including load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data can be obtained respectively as the to-be-evaluated scheme to facilitate the evaluation of industrial load flexibility. Specifically:

[0057] (1) The load characteristic index data can be calculated from the industrial load data. The load characteristic index data can include the load rate and the peak-valley difference rate.

[0058] Among them, the load rate is used to reflect the volatility of the load on working days. The daily load time series data can be obtained through the energy management system, the daily load average value and the daily maximum load can be determined according to the daily load time series data, and the load rate can be obtained through the following formula:

[0059]

[0060] The peak-valley difference rate is used to characterize the load transfer ability and is obtained through the following formula:

[0061]

[0062] (2) The control characteristic index data can include three types of index data: power grid dispatching mode, load regulation mode, and equipment control mode. Among them:

[0063] The dispatching method is used to reflect whether the user has signed an agreement with the power grid and whether a control device is installed. Whether the user has signed an agreement with the power grid and whether a control device is installed can be obtained through means such as power supply contracts and equipment lists. Direct control and non-direct control can be the ways for the power grid operator to manage and adjust the power load on the user side. The dispatching method is obtained through the following formula:

[0064]

[0065] The load regulation method is used to characterize the characteristics of user equipment. The equipment regulation method can be divided into power regulation and switching regulation, and is obtained through the following formula:

[0066]

[0067] The equipment control method is used to characterize the form in which the equipment participates in the interaction with the power grid. Among them, the automated control method represents higher flexibility. The equipment control method is obtained through the following formula:

[0068]

[0069] (3) The response characteristic index data can include three types of index data: the proportion of adjustable capacity, adjustable duration, and response speed. It mainly characterizes the demand response ability of industrial loads.

[0070] The proportion of adjustable capacity is used to reflect the ratio of the user's maximum adjustable capacity to the maximum power consumption load. The total adjustable capacity of the equipment can be the power consumption that can be flexibly adjusted (reduced) by a device without affecting its main function, indicating the potential of this device to participate in demand response. The calculation formula for the proportion of adjustable capacity is as follows:

[0071]

[0072] The adjustable duration is used to reflect the longest callable time of the user's maximum adjustable power.

[0073] The response speed is used to reflect the ramp rate of the load from the start of demand response to reaching the maximum adjustment power. It can be obtained through the following formula. Among them, the maximum adjustable capacity represents the maximum power consumption reduction that the equipment can provide during a single demand response time, which can be obtained through load curve analysis; the execution required time represents the duration from receiving the demand response instruction to the equipment reaching the predetermined adjustment power. Specifically:

[0074]

[0075] (4)The adjustable characteristic index data may include three types of index data: preparation duration, recovery duration, and suitable service type. Among them, the preparation time may be the time required for the user to enter the demand response state from the normal production state. The recovery time may be the time required for the user to return to the normal production state from the demand response end state. The suitable service type represents the number of user types suitable for participation in regulation among industrial users for load flexibility evaluation.

[0076] (5)The adjustable characteristic index data may include three types of index data: service marginal cost, subsidy intensity, and marginal carbon emissions. Among them:

[0077] The service marginal cost is used to reflect the relationship between the response cost and the response power consumption, and is calculated by the following formula. Among them, the annual output value of the user represents the total income or added value obtained by the enterprise through production and sales of products in one year, and can be obtained from an industry analysis report released by a third party; the user's response power consumption represents the power consumption actually adjusted (usually reduced) by the user according to the requirements of the demand response project within a specific time period, and can be obtained through a power monitoring system. Specifically:

[0078]

[0079] The subsidy intensity is used to reflect the income that the user can gain by saving one degree of electricity compared to using one degree of electricity. The subsidy for each degree of electricity in response refers to the economic compensation per degree of electricity obtained by power users from the power grid company or relevant management agencies after reducing or adjusting their power consumption according to the agreement within a specific time in the demand response project. The cost per degree of electricity is the cost required to consume one degree of electricity (if the peak-valley electricity price is implemented, the peak-time electricity price is adopted). The subsidy intensity is calculated by the following formula:

[0080]

[0081] The marginal carbon emissions are used to reflect the relationship between the carbon emissions and the response power consumption. The carbon emissions during user response may be the change in direct or indirect carbon emissions caused when the power user adjusts its power usage behavior according to the instructions of the demand response project. The user's response power consumption may be the power consumption used by the power user during the participation in the demand response project. The marginal carbon emissions are calculated by the following formula:

[0082]

[0083] Through the above methods, a plurality of industrial load flexibility index data are obtained.

[0084] S200. Determine the subjective weight and objective weight of each industrial load flexibility index data.

[0085] Among them, the subjective weight can be the weight obtained from a subjective perspective determined by the knowledge and experience of the decision maker, such as obtained through expert judgment. The objective weight can be the weight determined from an objective perspective through data analysis.

[0086] In practical applications, the subjective weight for determining each industrial load flexibility index data can be obtained by using the subjective weighting method, where professionals assign weights to different industrial load flexibility index data through scoring. The subjective weighting method can include the fuzzy analytic hierarchy process, the ordered graph method, the Delphi method, etc. The objective weight can be obtained by analyzing the index data through objective weighting methods such as the principal component analysis method, the factor analysis method, the vector similarity method, the independent weight, and the information content weight.

[0087] S300. Based on the subjective weight and the objective weight, determine the comprehensive weight of each industrial load flexibility index data.

[0088] In practical applications, weight coefficients can be assigned to the subjective weight and the objective weight respectively to obtain the comprehensive weight of each industrial load flexibility index data, or the comprehensive weight can be determined according to the subjective weight and the objective weight through the comprehensive weighting method. The comprehensive weighting method can be a weighting method based on addition synthesis or multiplication synthesis normalization, or a weighting method based on range maximization, based on matrix thinking, based on distance function method. Exemplarily, the weighting method based on addition synthesis or multiplication synthesis normalization can be to add or multiply the subjective weight and the objective weight of the industrial load flexibility index data and perform normalization processing to obtain the comprehensive weight of each industrial load flexibility index data.

[0089] S400. Based on each industrial load flexibility index data and the comprehensive weight of each industrial load flexibility index data, determine the industrial load flexibility evaluation level.

[0090] In practical applications, the weighted score of each industrial load flexibility index data can be obtained according to each industrial load flexibility index data and its corresponding comprehensive weight, and the comprehensive score can be obtained according to the sum of the weighted scores of all industrial load flexibility index data. According to prior knowledge, different levels of comprehensive score thresholds are preset in advance, and the industrial load flexibility evaluation level to which it belongs is determined according to the comprehensive score.

[0091] In the above industrial load flexibility assessment method, on the one hand, the impact of industrial loads when connected to the power grid is fully considered. By taking into account the fast response ability, reliability, and economy of flexible loads, the potential and regulation effect of flexible loads are evaluated. Multi-dimensional index data such as load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data are used for industrial load flexibility assessment, improving the accuracy of industrial load assessment. On the other hand, the subjective weight and objective weight of each industrial load flexibility index data are determined separately, and the comprehensive weight of each industrial load flexibility index data is determined through the subjective weight and objective weight, reducing the deviation of a single method, which is beneficial to enhancing the adaptability and flexibility of the assessment. At the same time, the effectiveness of the assessment is improved. Then, the industrial load flexibility evaluation level is determined according to each industrial load flexibility index data and the corresponding comprehensive weight, providing a relatively perfect assessment system, further improving the accuracy of industrial load flexibility assessment, and thus being beneficial to industrial demand-side response management according to the industrial load flexibility evaluation level, guiding peak shaving and valley filling, improving the flexibility of the power system, ensuring the safe and stable operation of the power system, and promoting the consumption of renewable energy power.

[0092] In an exemplary embodiment, as Figure 3 shown, determining the objective weight of each industrial load flexibility index data includes S221 to S226. Among them:

[0093] In this embodiment, in order to improve the accuracy of index data weighting, the present application considers the mutual influence between index data and designs an improved entropy weight method to determine the objective weight of each industrial load flexibility index data.

[0094] S221, obtain multiple index data sample sets, and each index data sample set includes multiple industrial load flexibility index data samples.

[0095] In practical applications, it can be to obtain multiple industrial load flexibility index data within different time periods as the index data sample set. The steps of obtaining the index data sample set can refer to the steps of the method for obtaining multiple industrial load flexibility index data in the above embodiment and will not be elaborated here. After obtaining multiple index data sample sets, an m×n index matrix is established according to the multiple index data sample sets, where m is the total number of index data sample sets and n is the total number of industrial load flexibility index data.

[0096] S222, perform data preprocessing on each index data sample set, and the data preprocessing includes at least one of dimensionless processing and standardization processing.

[0097] In practical applications, considering that there are dimensions among different industrial load flexibility index data, making them incomparable. Therefore, the dimensional influence is eliminated by dimensionless processing of the index data sample set. Specifically, the dimensionless processing methods can include processing methods such as the threshold method, the standardization method, or the proportion method, etc. The standardization processing can be Z-score standardization, min-max standardization, etc. After data preprocessing of each index data sample set, a standardized matrix X is obtained.

[0098] S223. Based on multiple index data sample sets, determine the information entropy of each industrial load flexibility index data.

[0099] Among them, the information entropy characterizes the amount of information of the index data.

[0100] In practical applications, for each industrial load flexibility index data in the standardized matrix X, determine the weight value of this industrial load flexibility index data in each index data sample, and determine its information entropy according to the weight of this industrial load flexibility index data in different index data sample sets. Specifically:

[0101] ‌

[0102]

[0103] In the formula, represents the value of the j-th industrial load flexibility index in the i-th index data sample set in the standardized matrix X (i.e., the industrial load flexibility index data); represents the proportion of the j-th industrial load flexibility index data in the i-th index data sample set in the sum of all the j-th industrial load flexibility index data in all index data sample sets in the standardized matrix X; represents the information entropy of the j-th industrial load flexibility index data.

[0104] S224. According to each industrial load flexibility index data, determine the Pearson correlation coefficient between each industrial load flexibility index data.

[0105] In practical applications, the Pearson correlation coefficient between different industrial load flexibility index data in the standardized matrix X is determined by the following formula:

[0106]

[0107] The formula, represents the correlation coefficient between the j-th industrial load flexibility index data and the k-th industrial load flexibility index data, where, ; X, Y are vectors composed of the values of the same index in different scenarios, is the covariance of vector Y and vector Z, , are the standard deviations of vector Y and vector Z, respectively.

[0108] S225. For each industrial load flexibility index data, according to the Pearson correlation coefficient, determine the degree of influence of the industrial load flexibility index data.

[0109] Among them, the degree of influence of the industrial load flexibility index data characterizes the degree of influence of this industrial load flexibility index data by other industrial load flexibility index data.

[0110] In practical applications, to measure the overall influence of each industrial load flexibility index data by other industrial load flexibility index data, it is calculated by the following formula:

[0111]

[0112] Among them, The larger it is, the greater the influence of this industrial load flexibility index data by other industrial load flexibility index data, that is, this industrial load flexibility index data cannot directly provide information for the evaluation of industrial load flexibility, which means that its weight can be appropriately weakened.

[0113] S226. Determine the objective weights of each industrial load flexibility index data according to the information entropy and the degree of influence of each industrial load flexibility index.

[0114] In practical applications, according to the information entropy and the degree of influence of each industrial load flexibility index, the objective weights of each industrial load flexibility index data are determined by the following formula:

[0115]

[0116] In the formula, is the objective weight of the j-th industrial load flexibility index data.

[0117] In this embodiment, the mutual influence between different industrial load flexibility index data is considered, and a more scientific method for assigning objective weights is proposed, thereby improving the accuracy of objective weight assignment, and further facilitating the improvement of the accuracy of industrial load flexibility evaluation.

[0118] In an exemplary embodiment, determining the subjective weight of each industrial load flexibility index data includes S242 to S244. Among them:

[0119] S242. Obtain the criterion layer matrix, and the elements in the criterion layer matrix are the importance difference values between different industrial load flexibility index data.

[0120] Among them, the importance difference value characterizes the relative importance degree of different industrial load flexibility index data for the evaluation of industrial load flexibility in the decision-making process.

[0121] In practical applications, it can be that the decision maker or expert compares the importance of each index relative to the evaluation of industrial load flexibility pairwise according to their own knowledge and experience, and uses a preset ratio scale (such as the ratio scale in the following table) to represent the difference in importance, obtaining the criterion layer matrix. It can be that by obtaining the criterion layer matrix data uploaded by the terminal, the criterion layer matrix is obtained, and its form is as follows:

[0122]

[0123] Among them, , its size is determined by odd numbers from 1 to 9, and its specific meaning is as follows:

[0124] Scale Meaning 1 When comparing the two factors, they have the same importance 3 When comparing the two factors, the former is slightly more important than the latter 5 When comparing the two factors, the former is significantly more important than the latter 7 When comparing the two factors, the former is strongly more important than the latter 9 When comparing the two factors, the former is extremely more important than the latter

[0125] S244, when the criterion layer matrix passes the consistency check, solve the eigenvector corresponding to the maximum eigenvalue of the criterion layer matrix to obtain the subjective weight of each industrial load flexibility index data.

[0126] In practical applications, to ensure the rationality of the elements in the judgment matrix, before solving the subjective weight, a consistency check is performed on the criterion layer matrix. Specifically, the consistency index CI is calculated by the following formula:

[0127]

[0128] Among them, is the maximum eigenvalue of the criterion layer matrix (judgment matrix), and n is the number of rows of the judgment matrix.

[0129] Determine the random consistency index RI corresponding to the number of rows n of the judgment matrix, which can be determined by looking up the standard table of RI values. Calculate the consistency ratio: CR = CI / RI. If the consistency check fails (the consistency ratio is greater than or equal to 0.1, that is, CR >= 0.1), then a new criterion layer matrix needs to be obtained. Otherwise, it is determined that the consistency check passes. When the consistency check passes, it can be that by solving the eigenvector corresponding to the maximum eigenvalue of the criterion layer matrix and normalizing the eigenvector, the components in the normalized eigenvector are respectively determined as the subjective weights of each industrial load flexibility index data. Exemplarily, determine the maximum eigenvalue λ max and the corresponding eigenvector v. The normalization process can be to divide each component in the eigenvector v by the sum of all components in the eigenvector v, and the obtained result is the vector W = (W1, W2,..., W) composed of the subjective weights of each industrial load flexibility index data.n ).

[0130] In other embodiments, when passing the consistency check, it can also be to obtain the subjective weights of the industrial load flexibility index data by the arithmetic mean method or the geometric mean method.

[0131] In this embodiment, the subjective weights are obtained by obtaining the criterion layer matrix. Since the criterion layer matrix is obtained by quantifying the relative importance between various indicators through pairwise comparison in combination with the knowledge and experience of domain experts, the subjective weight distribution is more in line with the actual situation, and the decision-making quality is improved through consistency check, thereby improving the reliability and logical rationality of the subjective weight distribution.

[0132] To improve the evaluation accuracy, in an exemplary embodiment, as Figure 4 shown, S300 includes S320 to S340. Among them:

[0133] S320 aims to maximize the difference in scores between different indicator data sample sets, and through the particle swarm optimization algorithm, solve the weight coefficients corresponding to the subjective weights and objective weights of the industrial load flexibility indicators. The scores of the indicator data sample sets are determined according to the subjective weights and objective weights of the industrial load flexibility indicator data and the industrial load flexibility indicator data samples.

[0134] S340 determines the comprehensive weight of the industrial load flexibility indicators based on the weight coefficients corresponding to the subjective weights and objective weights respectively.

[0135] In practical applications, after obtaining the subjective weight ω a and the objective weight ω b , based on the particle swarm algorithm, determine the weight coefficients corresponding to the subjective weights and objective weights of each industrial load flexibility indicator. Let the weight coefficient of the subjective weight be k1, and the weight coefficient of the objective weight be k2. The comprehensive weight ω is:

[0136]

[0137] In the formula, n is the number of industrial load flexibility indicators, ω an , ω bn are the subjective weight and objective weight of the nth indicator respectively.

[0138] Based on the particle swarm algorithm to calculate the optimal combination of weight coefficients of the subjective weight and objective weight, it should be achieved that the selected weight coefficients can reflect the gap between different indicator data sample sets to the greatest extent. Therefore, aiming at maximizing the score difference (difference) between different indicator data sample sets, solve the optimal weight coefficients k1 and k2. Among them, the fitness function is the maximum value of the sum of the score differences of different indicator data sample sets. The specific expression is as follows:

[0139]

[0140] Among them, C1, C2,...., C r , C m are the scores of the first, second,..., r-th, and m-th index data sample sets to be evaluated respectively:

[0141]

[0142] Among them, X represents the matrix storing the industrial load flexibility index data in the index data sample set, and T represents the transpose of the X matrix.

[0143] Using the particle swarm optimization algorithm process, the solution that maximizes the fitness function is calculated, which is the optimal weight coefficients k1 and k2 sought, and thus the comprehensive weight ω corresponding to each industrial load flexibility index data is obtained.

[0144] In this embodiment, with the goal of maximizing the score difference, the optimal weight coefficients of each industrial load flexibility index data are obtained through the particle swarm algorithm, so as to obtain a more accurate comprehensive weight, which is beneficial to improving the accuracy of industrial load flexibility evaluation.

[0145] In an exemplary embodiment, the load characteristic index data includes load matching degree, and the load matching degree is obtained based on the power consumption data during the daily load peak period. The power consumption data during the daily load peak period is obtained based on the following steps S120 to S180:

[0146] S120, Obtain multiple pieces of grid daily load time series data.

[0147] In practical applications, it can be obtained by collecting grid load data through an energy management system to obtain multiple days of grid daily load time series data.

[0148] S140, Determine the similarity between each piece of grid daily load time series data, and filter out the target grid daily load time series data whose similarity is greater than a preset similarity threshold.

[0149] In practical applications, the similarity between each piece of grid daily load time series data can be determined based on methods such as Euclidean distance, Manhattan distance, or Dynamic Time Warping (DTW). In this embodiment, the similarity between each piece of grid daily load time series data is determined by Dynamic Time Warping. Assuming that there are 24 sampling points (each sampling point collects 15 minutes of data) for the grid daily load time series data every day, then its warping distance matrix is (24×24), and its specific calculation method is:

[0150]

[0151]

[0152] It can be to preset a similarity threshold according to experience (such as 0.7), screen out the grid daily load time series data with a similarity greater than the similarity threshold, and determine the screened grid daily load time series data as the target grid daily load time series data.

[0153] S160. Extract the peak period load data from the target grid daily load time series data, and perform a clustering operation on the peak period load data to obtain multiple peak period load clusters.

[0154] Among them, the peak period load data is the load data during the peak electricity consumption period. The peak period can refer to the peak electricity consumption period within a day, such as from 8:30 to 10:30 in the morning, from 6:00 to 7:00 in the afternoon, and from 9:00 to 11:00 in the evening.

[0155] In practical applications, according to the time period included in the peak period, extract the time series data within the peak period from the target grid daily load time series data to obtain the peak period load data. It can be to perform clustering processing on the peak period load data through a clustering algorithm to obtain multiple peak period load clusters. The clustering algorithms include but are not limited to the K-means algorithm, the PAM (Partitioning Around Medoids) partitioning algorithm around the center point, etc.

[0156] S180. Determine the class center of each peak period load cluster, and integrate each class center to obtain the electricity consumption data of the daily load peak period.

[0157] In practical applications, according to the clustering processing method, adopt the corresponding class center determination method to determine the class center of each peak period load cluster. For each class center, perform integration through a numerical integration method to obtain the electricity consumption data within the daily load peak period. The numerical integration methods can include the rectangle method, the trapezoid method, the Simpson method, as well as Gaussian integration and adaptive integration, etc.

[0158] In this embodiment, on the one hand, the interaction mode between the user load and the grid load is considered, and introducing the load matching degree index data is beneficial to improving the accuracy of industrial load flexibility evaluation; on the other hand, by performing similarity calculation, clustering processing, and integration calculation on multiple grid daily load time series data to obtain the peak period electricity consumption, it is beneficial to reduce the influence of the random fluctuation of the daily load time series data and improve the representativeness, accuracy, and effectiveness of the electricity consumption data.

[0159] By comprehensively weighing and evaluating the industrial load flexibility index data, in an exemplary embodiment, S400 includes S420 to S460. Among them:

[0160] S420. Determine the membership degree of each industrial load flexibility index data for different evaluation levels.

[0161] Among them, the evaluation levels can include excellent, good, and average. The membership degree represents the degree to which the industrial load flexibility index data belongs to different evaluation levels.

[0162] In this embodiment, for the industrial load flexibility assessment based on fuzzy evaluation, the membership functions of each industrial load flexibility index data for the evaluation levels of excellent, good, and average are preset respectively. Specifically, the membership functions are set as follows:

[0163] (1) Load characteristic index data

[0164] ① The specific expressions of the membership functions of the load rate index data for the evaluation levels of excellent, good, and average are as follows:

[0165]

[0166] Among them, x represents the specific value of the load rate, represents the membership degree of this index data for the excellent level, represents the membership degree of this index data for the good level, represents the membership degree of this index data for the average level.

[0167] ② The specific expressions of the membership functions of the peak-valley difference rate index data for the evaluation levels of excellent, good, and average are as follows:

[0168]

[0169] Among them, x represents the specific value of the peak-valley difference rate, represents the membership degree of this index data for the excellent level, represents the membership degree of this index data for the good level, represents the membership degree of this index data for the average level.

[0170] ③ The specific expressions of the membership functions of the load matching degree index data for the evaluation levels of excellent, good, and average are as follows:

[0171]

[0172] Among them, x represents the specific value of the load matching degree, represents the membership degree of this index data for the excellent level, represents the membership degree of this index data for the good level, represents the membership degree of this index data for the average level.

[0173] (2) Control characteristic index data

[0174] ① The specific expressions of the membership functions of the scheduling method index data for excellent, good, and average are as follows:

[0175]

[0176] Among them, direct control and non-direct control represent the specific values of the scheduling method, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the average level.

[0177] ② The specific expressions of the membership functions of the adjustment method index data for excellent, good, and average are as follows:

[0178]

[0179] Among them, power adjustment and opening / closing adjustment represent the specific values of the adjustment method, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the average level.

[0180] ③ The specific expressions of the membership functions of the control method index for excellent, good, and average are as follows:

[0181]

[0182] Among them, automation and manual represent the specific values of the control method, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the average level.

[0183] (3) Response characteristic index data

[0184] ① The specific expressions of the membership functions of the adjustable capacity ratio index data for excellent, good, and average evaluation levels are as follows:

[0185]

[0186] Among them, x represents the specific value of the index data, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the average level.

[0187] ② The specific expressions of the membership functions of the adjustable duration index data for the excellent, good, and general evaluation levels are as follows:

[0188]

[0189] Among them, x represents the specific value of the index data, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the general level.

[0190] ③ The specific expressions of the membership functions of the response speed index data for the excellent, good, and general evaluation levels are as follows:

[0191]

[0192] Among them, x represents the specific value of the index data, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the general level.

[0193] (4)Adjustment characteristic index data

[0194] ① The specific expressions of the membership functions of the preparation duration index data for the excellent, good, and general evaluation levels are as follows:

[0195]

[0196] Among them, x represents the specific value of the index, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the general level.

[0197] ② The specific expressions of the membership functions of the recovery duration index data for the excellent, good, and general evaluation levels are as follows:

[0198]

[0199] Among them, x represents the specific value of the index data, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the general level.

[0200] ③ The specific expressions of the membership functions of the suitable service type index data for the excellent, good, and average evaluation levels are as follows:

[0201]

[0202] Among them, x represents the specific value of the index data, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the average level.

[0203] (5)Response willingness index data

[0204] ① The specific expressions of the membership functions of the service marginal cost index data for the excellent, good, and average evaluation levels are as follows:

[0205]

[0206] Among them, x represents the specific value of the index data, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the average level.

[0207] ② The specific expressions of the membership functions of the subsidy intensity index data for the excellent, good, and average levels are as follows:

[0208]

[0209] Among them, x represents the specific value of the index data, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the average level.

[0210] ③ The specific expressions of the membership functions of the marginal carbon emission index data for the excellent, good, and average levels are as follows:

[0211]

[0212] Among them, x represents the specific value of the index data, represents the membership degree of the index data for the excellent level, represents the membership degree of the index data for the good level, represents the membership degree of the index data for the average level.

[0213] In practical applications, substitute the flexibility index data of each industrial load into the corresponding membership function to obtain the membership degrees of the flexibility index data of each industrial load for the excellent, good, and average levels.

[0214] S440. Based on the comprehensive weights of the flexibility index data of each industrial load and the membership degrees of the flexibility index data of each industrial load for different evaluation levels, construct an evaluation matrix.

[0215] In practical applications, after obtaining the membership degrees of the flexibility index data of each industrial load for the excellent, good, and average levels, based on the comprehensive weights of the flexibility index data of each industrial load and the membership degrees of the flexibility index data of each industrial load for different evaluation levels, for the load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic, and response willingness index data, set 5 standard layers, which correspond one by one to the above-mentioned 5 types of industrial load flexibility index data. Determine the membership degree V of each standard layer for different evaluation levels through the following formula bq , and its specific calculation method is:

[0216]

[0217] where, ω q is a vector composed of the comprehensive weights of each flexibility index data of industrial load contained in the standard layer q, and Z q is a vector composed of the membership degrees of each flexibility index data of industrial load contained in the standard layer q for the excellent, good, and average evaluation levels. q is an integer and 0 < q ≤ 5.

[0218] After obtaining the membership degrees V bq of each standard layer for different evaluation levels, the membership degrees V bq of each standard layer for different evaluation levels form an evaluation matrix, where the evaluation matrix is a 5×3 matrix.

[0219] S460. Based on the objective weights of the flexibility index data of each industrial load and the evaluation matrix, obtain the comprehensive evaluation values of the flexibility index data of each industrial load, and determine the evaluation level to which the largest comprehensive evaluation value belongs as the industrial load flexibility evaluation level.

[0220] In practical applications, based on the objective weights of the flexibility index data of each industrial load and the evaluation matrix, through the following formula, obtain the comprehensive evaluation values of the flexibility index data of each industrial load:

[0221]

[0222] In the formula, V qis the membership degree of the q-th criterion layer in the evaluation matrix for the excellent, good, and general evaluation levels, ω b is a vector composed of the objective weights of the industrial load flexibility index data contained in this criterion layer. Through the above formula, the comprehensive evaluation value of each industrial load flexibility index data is obtained, and the element values in the evaluation matrix are replaced with the comprehensive evaluation values of each industrial load flexibility index data. Determine the industrial load flexibility index data corresponding to the largest comprehensive evaluation value among them, and determine the evaluation level to which this industrial load flexibility index data belongs as the industrial load flexibility evaluation level of the entire industrial load flexibility index data set.

[0223] In this embodiment, membership functions for different evaluation levels are set considering the nature of different industrial load flexibility index data, and their membership degrees for different evaluation levels are determined. Through the comprehensive weights and objective weights of each index data, as well as the membership degrees for different evaluation levels, the comprehensive evaluation values of each index data are determined. According to the comprehensive evaluation values of each index data, the final industrial load flexibility evaluation level is determined, forming a more scientific and perfect evaluation strategy, and improving the accuracy of industrial load flexibility assessment.

[0224] To make a clearer description of the industrial load flexibility assessment method provided in this application, a specific embodiment is described below. This specific embodiment includes the following steps:

[0225] S1, Obtain multiple industrial load flexibility index data, where the industrial load flexibility index data includes load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic, and response willingness index data.

[0226] S2, The load characteristic index data includes load matching degree, which is obtained based on the electricity consumption data during the daily load peak period. The acquisition method of the electricity consumption data during the daily load peak period: Obtain multiple grid daily load time series data, determine the similarity between each grid daily load time series data, screen out the target grid daily load time series data with a similarity greater than the preset similarity threshold, extract the peak period load data from the target grid daily load time series data, perform a clustering operation on the peak period load data to obtain multiple peak period load clusters, determine the class center of each peak period load cluster, and integrate each class center to obtain the electricity consumption data during the daily load peak period.

[0227] S3. Obtain multiple sets of index data samples. Each set of index data samples includes multiple industrial load flexibility index data samples. Perform data preprocessing on each set of index data samples. The data preprocessing includes at least one of dimensionless processing and standardization processing. Based on the multiple sets of index data samples, determine the information entropy of each industrial load flexibility index data. According to each industrial load flexibility index data, determine the Pearson correlation coefficient between each industrial load flexibility index data. For each industrial load flexibility index data, determine the degree of influence of the industrial load flexibility index data according to the Pearson correlation coefficient. According to the information entropy and the degree of influence of each industrial load flexibility index, determine the objective weight of each industrial load flexibility index data.

[0228] S4. Obtain the criterion layer matrix. The elements in the criterion layer matrix are the importance difference values between different industrial load flexibility index data. When the criterion layer matrix passes the consistency check, solve the eigenvector corresponding to the maximum eigenvalue of the criterion layer matrix to obtain the subjective weight of each industrial load flexibility index data.

[0229] S5. With the goal of maximizing the difference in scores between different sets of index data samples, use the particle swarm optimization algorithm to solve the weight coefficients corresponding to the subjective weight and the objective weight of the industrial load flexibility index respectively. The score of the set of index data samples is determined according to the subjective weight and the objective weight of each industrial load flexibility index data and each industrial load flexibility index data sample. Based on the weight coefficients corresponding to the subjective weight and the objective weight respectively, determine the comprehensive weight of the industrial load flexibility index.

[0230] S6. Determine the membership degree of each industrial load flexibility index data for different evaluation grades. Based on the comprehensive weight of each industrial load flexibility index data and the membership degree of each industrial load flexibility index data for different evaluation grades, construct an evaluation matrix. Based on the objective weight of each industrial load flexibility index data and the evaluation matrix, obtain the comprehensive evaluation value of each industrial load flexibility index data. Determine the evaluation grade to which the largest comprehensive evaluation value belongs as the industrial load flexibility evaluation grade.

[0231] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indication of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0232] In an exemplary embodiment, as Figure 5 shown, an industrial load flexibility evaluation device 600 is provided, including: a data acquisition module 610, a weight determination module 620, and a level evaluation module 630, where:

[0233] The data acquisition module 610 is configured to acquire multiple industrial load flexibility index data.

[0234] The weight determination module 620 is configured to determine the subjective weight and objective weight of each industrial load flexibility index data; based on the subjective weight and objective weight, determine the comprehensive weight of each industrial load flexibility index data.

[0235] The level evaluation module 630 is configured to determine the industrial load flexibility evaluation level based on each industrial load flexibility index data and the comprehensive weight of each industrial load flexibility index data; wherein, the industrial load flexibility index data includes load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data.

[0236] In an exemplary embodiment, the weight determination module 620 is further configured to acquire multiple index data sample sets, each index data sample set includes multiple industrial load flexibility index data samples, perform data preprocessing on each index data sample set, and the data preprocessing includes at least one of dimensionless processing and standardization processing. Based on the multiple index data sample sets, determine the information entropy of each industrial load flexibility index data, determine the Pearson correlation coefficient between each industrial load flexibility index data according to each industrial load flexibility index data, for each industrial load flexibility index data, determine the degree of influence of the industrial load flexibility index data according to the Pearson correlation coefficient, and determine the objective weight of each industrial load flexibility index data according to the information entropy and degree of influence of each industrial load flexibility index.

[0237] In an exemplary embodiment, the weight determination module 620 is further configured to obtain a criterion layer matrix, where the elements in the criterion layer matrix are the importance difference values between different industrial load flexibility index data. When the criterion layer matrix passes the consistency check, solve the eigenvector corresponding to the maximum eigenvalue of the criterion layer matrix to obtain the subjective weight of each industrial load flexibility index data.

[0238] In an exemplary embodiment, the weight determination module 620 is further configured to aim at maximizing the difference in scores between different index data sample sets, and solve the weight coefficients corresponding to the subjective weight and the objective weight of the industrial load flexibility index through a particle swarm optimization algorithm. The score of the index data sample set is determined according to the subjective weight and the objective weight of each industrial load flexibility index data and each industrial load flexibility index data sample. Based on the weight coefficients corresponding to the subjective weight and the objective weight respectively, determine the comprehensive weight of the industrial load flexibility index.

[0239] In an exemplary embodiment, the level evaluation module 630 is further configured to determine the membership degree of each industrial load flexibility index data to different evaluation levels, construct an evaluation matrix based on the comprehensive weight of each industrial load flexibility index data and the membership degree of each industrial load flexibility index data to different evaluation levels, and obtain the comprehensive evaluation value of each industrial load flexibility index data based on the objective weight of each industrial load flexibility index data and the evaluation matrix. Determine the evaluation level to which the largest comprehensive evaluation value belongs as the industrial load flexibility evaluation level.

[0240] In an exemplary embodiment, the module 640 is further configured to obtain load characteristic index data based on the power consumption data during the daily load peak period;

[0241] The industrial load flexibility evaluation device 600 further includes a load data acquisition module 640 and a power consumption data acquisition module 650, where:

[0242] The load data acquisition module 640 is configured to obtain multiple pieces of grid daily load time series data;

[0243] The power consumption data acquisition module 650 is configured to determine the similarity between each grid daily load time series data, screen out the target grid daily load time series data whose similarity is greater than a preset similarity threshold; extract the peak period load data from the target grid daily load time series data, perform a clustering operation on the peak period load data to obtain multiple peak period load clusters, determine the class center of each peak period load cluster, and integrate each class center to obtain the power consumption data during the daily load peak period.

[0244] Each module in the above industrial load flexibility evaluation device 600 can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0245] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements an industrial load flexibility evaluation method.

[0246] Those skilled in the art can understand that Figure 6 the structure shown in

[0247] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0248] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in any one of the above embodiments of the industrial load flexibility evaluation method.

[0249] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, it implements the steps in any one of the above embodiments of the industrial load flexibility evaluation method.

[0250] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0251] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, artificial intelligence (AI) processors, etc., and are not limited thereto.

[0252] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope recorded in this application.

[0253] The above-described embodiments only represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application should be subject to the appended claims.

Claims

1. An industrial load flexibility assessment method, characterized in that The method includes: Obtaining multiple industrial load flexibility index data; Determining the subjective weight and objective weight of each of the industrial load flexibility index data; Based on the subjective weight and the objective weight, determining the comprehensive weight of each of the industrial load flexibility index data; Based on each of the industrial load flexibility index data and the comprehensive weight of each of the industrial load flexibility index data, determining the industrial load flexibility evaluation level; Wherein, the industrial load flexibility index data includes load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data.

2. The method according to claim 1, characterized in that Determining the objective weight of each of the industrial load flexibility index data includes: Obtaining multiple index data sample sets, each of the index data sample sets including multiple industrial load flexibility index data samples; Performing data preprocessing on each of the index data sample sets, the data preprocessing including at least one of dimensionless processing and standardization processing; Based on the multiple index data sample sets, determining the information entropy of each of the industrial load flexibility index data; According to each of the industrial load flexibility index data, determining the Pearson correlation coefficient between each of the industrial load flexibility index data; For each of the industrial load flexibility index data, according to the Pearson correlation coefficient, determining the degree of influence of the industrial load flexibility index data; According to the information entropy and the degree of influence of each of the industrial load flexibility index data, determining the objective weight of each of the industrial load flexibility index data.

3. The method according to claim 1, wherein Determining the subjective weight of each of the industrial load flexibility index data includes: Obtaining a criterion layer matrix, the elements in the criterion layer matrix being the importance difference values between different industrial load flexibility index data; In the case where the criterion layer matrix passes the consistency check, solving the eigenvector corresponding to the maximum eigenvalue of the criterion layer matrix to obtain the subjective weight of each of the industrial load flexibility index data.

4. The method according to claim 2, wherein Based on the subjective weight and the objective weight, determining the comprehensive weight of each of the industrial load flexibility index includes: Taking the maximization of the difference in scores between different index data sample sets as the goal, through the particle swarm optimization algorithm, solving the weight coefficients corresponding to the subjective weight and the objective weight of the industrial load flexibility index, the score of the index data sample set being determined according to the subjective weight and the objective weight of each of the industrial load flexibility index data and each of the industrial load flexibility index data samples; Based on the weight coefficients corresponding to the subjective weight and the objective weight, determining the comprehensive weight of the industrial load flexibility index.

5. The method according to claim 4, wherein Based on the comprehensive weight of each of the industrial load flexibility index, determining the industrial load flexibility evaluation level includes: Determining the membership degree of each of the industrial load flexibility index data for different evaluation levels; Based on the comprehensive weight of each of the industrial load flexibility index data and the membership degree of each of the industrial load flexibility index data for different evaluation levels, constructing an evaluation matrix; Based on the objective weights and the evaluation matrix of the industrial load flexibility index data, obtain the comprehensive evaluation values of the industrial load flexibility index data, and determine the evaluation level to which the maximum comprehensive evaluation value belongs as the industrial load flexibility evaluation level.

6. The method according to any one of claims 1 to 5, characterized in that, The load characteristic index data includes a load matching degree, and the load matching degree is obtained based on the power consumption data during the daily load peak period; The power consumption data during the daily load peak period is obtained based on the following method: Obtain multiple grid daily load time series data; Determine the similarity between the grid daily load time series data, and filter out the target grid daily load time series data with a similarity greater than a preset similarity threshold; Extract the peak period load data from the target grid daily load time series data, and perform a clustering operation on the peak period load data to obtain multiple peak period load clusters; Determine the class center of each peak period load cluster, and integrate the class centers to obtain the power consumption data during the daily load peak period.

7. An industrial load flexibility evaluation device, characterized in that, The device includes: A data acquisition module for acquiring multiple industrial load flexibility index data; A weight determination module for determining the subjective weights and objective weights of each industrial load flexibility index data, and determining the comprehensive weights of each industrial load flexibility index data based on the subjective weights and the objective weights; A level evaluation module for determining the industrial load flexibility evaluation level based on each industrial load flexibility index data and the comprehensive weights of each industrial load flexibility index data; wherein, the industrial load flexibility index data includes load characteristic index data, control characteristic index data, response characteristic index data, regulation characteristic index, and response willingness index data.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images