Electricity user classification method, device and system and storage medium

Abstract

The invention relates to a power consumption user classification method, device and system and a storage medium, relates to the technical field of power data analysis, and aims to at least solve the problem that a power selling company lacks an accurate user portrait for a power consumption user in the related technology. The method comprises the following steps of: according to a first index, a second index, a third index, a fourth index and a fifth index in power utilization load characteristics of power utilization users, classifying load types, value types, power utilization operation modes, power utilization capabilities and festival sensitivity degrees of the power utilization users in sequence; obtaining a first classification result, a second classification result, a third classification result, a fourth classification result and a fifth classification result, and comprehensively determining the user portrait of each power user based on the five classification results.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, device, system and storage medium for classifying electricity users. Background Art

[0002] Currently, the core business of power sales companies is to purchase electricity from the medium- and long-term markets and the spot market on the wholesale side, and sell it to retail users on the retail side to earn the difference. In order to ensure that the power sales strategies formulated by power sales companies and the operating profits of spot declarations are maximized, it is necessary to fully understand the electricity consumption characteristics of electricity users. However, at present, the analysis of electricity consumption characteristics of power users is limited to the marketing and metering field of power grid companies, and there is no in-depth analysis of the retail trading platform from the perspective of power sales companies. As a result, power sales companies lack accurate user portraits of electricity users. Summary of the Invention

[0003] The present invention provides a method, device, system, and storage medium for classifying electricity users to at least address the problem in related technologies where electricity sales companies lack accurate user profiles of electricity users. The technical solutions of the present invention are as follows:

[0004] According to a first aspect of an embodiment of the present invention, a method for classifying electricity users is provided. The method includes: classifying the load types of multiple electricity users according to multiple first indicators of their electricity load characteristics to obtain a first classification result; evaluating the value categories of the multiple electricity users according to multiple second indicators of the economic value of their electricity loads to obtain a second classification result; classifying the electricity operation models of the multiple electricity users according to a third indicator of their electricity load characteristics to obtain a third classification result; evaluating the electricity consumption capabilities of the multiple electricity users according to multiple fourth indicators of their interactive technology levels to obtain a fourth classification result; and classifying the holiday sensitivity levels of the multiple electricity users according to their holiday sensitivity information to obtain a fifth classification result. Based on the first, second, third, fourth, and fifth classification results, a user profile for each electricity user is determined.

[0005] As an implementation method, the plurality of first indicators include: daily average load, daily peak-to-valley difference rate, peak load rate, valley load rate, daily load rate, and maximum load factor.

[0006] The load types of multiple electricity users are classified according to multiple first indicators in the electricity load characteristics of the electricity users to obtain a first classification result, including: determining first weights representing the relative influence between each first indicator in the multiple first indicators based on the analytic hierarchy process and the entropy weight method; obtaining a second indicator matrix representing the relative influence between each first indicator based on a first indicator matrix constructed from the multiple first indicators and the first weights; and classifying each element in the second indicator matrix to obtain the first classification result. The first classification result includes single-peak load, bi-peak load, peak-avoiding load, and flat-peak load.

[0007] As a means of implementation, multiple secondary indicators include: contract capacity, average annual electricity consumption, electricity growth rate and transaction price acceptance level.

[0008] The value categories of multiple electricity users are evaluated based on multiple second indicators of the economic value of their electricity loads to obtain a second classification result, including: determining respective second weights representing the relative influence of each of the multiple second indicators based on the analytic hierarchy process and the entropy weight method. The economic value of the user loads is evaluated based on each second weight based on the principle of maximum membership to obtain a second classification result; the second classification result includes a first level, a second level, a third level, a fourth level, and a fifth level, indicating the degree of economic value of the user loads.

[0009] As an implementation method, the plurality of third indicators include a daily load rate and a maximum load factor.

[0010] The electricity operation models of multiple electricity users are classified according to the third indicator in the electricity load characteristics to obtain a third classification result, including determining any third indicator in the third indicator for which the daily load rate is greater than the first daily load rate threshold and the maximum load factor is less than the second load factor threshold as a shutdown indicator corresponding to a shutdown day. The total shutdown days for each electricity user are determined based on the number of shutdown indicators included in the third indicator corresponding to each electricity user. The third classification result for each electricity user is determined based on the shutdown range to which the total shutdown days of each electricity user fall.

[0011] As an implementation method, the third classification results include: full operation mode, intermittent shutdown mode and complete shutdown mode.

[0012] Determining the third classification result for each electricity user based on the outage range to which the total outage days of each electricity user fall, including: determining that any electricity user's total outage days are less than a first outage threshold, determining that the user is in full operation mode; determining that any electricity user's total outage days are greater than or equal to the first outage threshold and less than or equal to the second outage threshold, determining that the user is in intermittent outage mode; and determining that any electricity user's total outage days are greater than the second outage threshold, determining that the user is in complete outage mode.

[0013] As an implementation method, the plurality of fourth indicators include: an auxiliary service level indicator parameter and a demand response level indicator parameter.

[0014] The electricity consumption capabilities of multiple electricity users are evaluated based on multiple fourth indicators of their interactive technology levels, resulting in a fourth classification result, including: determining the ratio of each electricity user's interruptible load value to the user's annual maximum load as the ancillary service level indicator parameter for each electricity user; and determining the ratio of the duration of interruptible load provided by each electricity user to the number of interruptions as the demand response level indicator parameter for each electricity user. The fourth classification result is determined based on the service indicator range to which each electricity user's ancillary service level indicator parameter belongs and the response indicator range to which each electricity user's demand response level indicator parameter belongs. The fourth classification result includes a first level, a second level, a third level, a fourth level, and a fifth level, indicating the level of a user's ability to participate in the ancillary service market and the demand response market.

[0015] As an implementation method, the holiday sensitivity of multiple electricity users is classified according to their holiday sensitivity information to obtain a fifth classification result, including: determining the total downtime days of each electricity user based on the downtime days corresponding to each electricity user having a daily load rate greater than a second daily load rate threshold and a maximum load factor less than the second load factor threshold. Determining the total holidays included in the total downtime days of each electricity user. For any electricity user, the ratio between the total holidays of any electricity user and the total downtime days of any electricity user is determined as the holiday work ratio of any electricity user. Determining the fifth classification result of any electricity user based on the holiday proportion range to which the holiday work ratio of any electricity user belongs, the fifth classification result includes a first sensitive type, a second sensitive type, and a third sensitive type that characterize the user's holiday sensitivity.

[0016] According to a second aspect of an embodiment of the present invention, a device for classifying electricity users is provided, the device comprising:

[0017] The classification unit is configured to classify multiple electricity users by load type based on multiple first indicators in the electricity load characteristics of the electricity users, thereby obtaining a first classification result. Furthermore, the value categories of the multiple electricity users are evaluated based on multiple second indicators in the economic value of the electricity loads of the electricity users, thereby obtaining a second classification result. Furthermore, the electricity operation models of the multiple electricity users are classified based on a third indicator in the electricity load characteristics, thereby obtaining a third classification result. Furthermore, the electricity consumption capabilities of the multiple electricity users are evaluated based on multiple fourth indicators in the interactive technology levels of the electricity users, thereby obtaining a fourth classification result. Furthermore, the holiday sensitivity levels of the multiple electricity users are classified based on the holiday sensitivity information of the electricity users, thereby obtaining a fifth classification result.

[0018] The determining unit is configured to determine a user portrait of each electricity user based on the first classification result, the second classification result, the third classification result, the fourth classification result and the fifth classification result.

[0019] According to a third aspect of an embodiment of the present invention, a system for classifying electricity users is provided. The system is configured to execute the method for classifying electricity users according to the first aspect and any possible implementation thereof.

[0020] According to a fourth aspect of the embodiments of the present invention, there is provided an electricity user classification device, which is configured to execute the electricity user classification method according to the first aspect and any possible implementation manner thereof.

[0021] According to a fifth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the electricity user classification method such as the first aspect and any possible implementation thereof.

[0022] According to a sixth aspect of an embodiment of the present disclosure, a computer program product is provided, which includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the electricity user classification method of the above-mentioned first aspect and any possible implementation thereof.

[0023] The technical solutions provided by the embodiments of the present invention bring at least the following beneficial effects: In order to more accurately determine the electricity load characteristics of each user, the load type of each electricity user is accurately identified according to the first indicator, so as to ensure that the first classification result can fully reflect the user's load type. In order to more clearly highlight the economic characteristics of the user's electricity consumption, the economic value of the electricity load of each electricity user is identified according to the second indicator, so as to ensure that the second classification result more accurately evaluates the economic value of the user's load. In order to make the classification of user business models more reasonable, the electricity load of each electricity user is analyzed according to the third indicator, so as to ensure that the third classification result can accurately reflect the user's business model. In order to more accurately reflect the interactive technology level of each user, the electricity consumption capacity of each electricity user is accurately evaluated according to the fourth indicator, so as to ensure that the fourth classification result can accurately reflect the user's electricity consumption capacity. In order to more accurately reflect the holiday sensitivity of each user, the holiday sensitivity of multiple electricity users is reasonably divided according to the user's holiday sensitivity information, so as to ensure that the fifth classification result can fully reflect the user's holiday sensitivity.

[0024] This application accurately classifies the user load information of each electricity user according to five different dimensions, and makes a comprehensive evaluation of each electricity user based on the five classification results obtained by the above classification, so as to obtain a user portrait that can fully characterize the user's electricity usage and improve the accuracy of the user portrait.

[0025] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0027] Figure 1 is a schematic diagram of a system for classifying electricity users according to an exemplary embodiment;

[0028] Figure 2 is a diagrammatic diagram illustrating a portrait of an electricity user according to an exemplary embodiment;

[0029] Figure 3 This is a flow chart of a method for classifying electricity users according to an exemplary embodiment. Figure 1 ;

[0030] Figure 4 This is a flow chart of a method for classifying electricity users according to an exemplary embodiment. Figure 2 ;

[0031] Figure 5This is a flow chart of a method for classifying electricity users according to an exemplary embodiment. Figure 3 ;

[0032] Figure 6 is a schematic diagram of a user business model classification result chart according to an exemplary embodiment;

[0033] Figure 7 is a schematic diagram of a chart showing interactive technology level classification results according to an exemplary embodiment;

[0034] Figure 8 This is a flow chart of a method for classifying electricity users according to an exemplary embodiment. Figure 4 ;

[0035] Figure 9 is a schematic diagram of a holiday sensitivity classification result chart according to an exemplary embodiment;

[0036] Figure 10 is a block diagram of a device for classifying electricity users according to an exemplary embodiment;

[0037] Figure 11 The figure is a schematic diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0038] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0039] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.

[0040] Before introducing in detail the electricity user classification method provided in the embodiment of the present application, a brief introduction to the application scenarios and implementation environment involved in the embodiment of the present application is first given.

[0041] First, a brief introduction to the application scenarios involved in this application is given.

[0042] Research has found that with the deepening of electricity market reforms and the rapid implementation of spot electricity settlement trials in the southern region, competition among power retail companies has intensified. In this competitive power market, the core business of power retail companies is to purchase electricity from the medium- and long-term markets and the spot market at the wholesale level, and sell it to retail users to profit from the price difference. This mitigates the risks of user load uncertainty and spot price fluctuations. Determining power purchasing strategies at the wholesale level and designing appropriate retail packages at the retail level to maximize profits and minimize risks are key to the success of power retail companies. Therefore, it is very important for power sales companies to fully understand the electricity consumption characteristics of agent users, which plays a vital role in formulating power purchasing strategies, participating in spot declarations, and improving operating profits. However, the current analysis of electricity consumption characteristics of power users only stays in the scope of marketing measurement for power grid companies, and generally does not consider the reference value of electricity consumption characteristics of power users from the perspective of power sales companies in the power market for power sales companies to formulate power sales strategies and participate in spot declarations. Therefore, a method and system are designed to assist power sales companies in intelligently identifying electricity consumption characteristics of power users, establish a multi-dimensional load characteristic index system, and comprehensively analyze user electricity consumption habits and load characteristics through scientific means, so as to help power sales companies fully understand user characteristics and customize differentiated and personalized electricity retail packages for them. At the same time, the load complementary characteristics of users with different characteristics are used to optimize spot quotations, thereby reducing power purchase costs and operating risks of power sales companies.

[0043] In response to the above problems, this application proposes a method for classifying electricity users, which accurately classifies the user load information of each electricity user according to different dimensions, and makes a comprehensive evaluation of each electricity user based on the classification results obtained by the above classification, so as to obtain a user portrait that can fully characterize the electricity consumption of different users and improve the accuracy of the user portrait.

[0044] Next, the implementation architecture involved in this application is briefly introduced below.

[0045] Figure 1 This is a schematic diagram of an electricity user classification system 10 provided by this application. Figure 1 As shown, the electricity user classification system includes a load feature classifier 11, a load economic value classifier 12, a user operation mode classifier 13, an interactive technology level classifier 14, and a holiday sensitivity classifier 15.

[0046] The load feature classifier 11 , the load economic value classifier 12 , the user operation mode classifier 13 , the interactive technology level classifier 14 , and the holiday sensitivity classifier 15 are connected to each other via a wired network or a wireless network.

[0047] The load characteristic classifier 11 is configured to classify load types of multiple electricity users to obtain a first classification result.

[0048] The load economic value classifier 12 is configured to evaluate the value categories of a plurality of electricity users to obtain a second classification result.

[0049] The user operation mode classifier 13 is configured to classify the electricity operation modes of a plurality of electricity users to obtain a third classification result.

[0050] The interactive skill level classifier 14 is configured to evaluate the power consumption capabilities of multiple power users to obtain a fourth classification result.

[0051] The holiday sensitivity classifier 15 is configured to classify the holiday sensitivity of multiple electricity users to obtain a fifth classification result.

[0052] In some embodiments, the electricity user classification system 10 is configured to perform the following three stages.

[0053] (1) In the index calculation stage, the electricity user classification system 10 receives the information authorization application initiated by the user. After the user agrees, the system automatically extracts relevant data from the user's profile and transaction behavior, calculates the user index characteristic results according to the index definition, and pushes them.

[0054] (2) In the characteristic classification stage, a comprehensive evaluation is conducted on the various characteristics within the index system. The electricity consumption data of the intended users and the users who have signed contracts with the current power sales company are combined to determine the load type of the intended users based on the load characteristic cluster analysis. The load economic value level, user operation model, interactive technology level, and holiday sensitivity of the intended users are then evaluated in turn.

[0055] (3) In the image output stage, such as Figure 2 As shown in (diagram of electricity user portrait), the above-mentioned evaluation results are received and a portrait model of potential contract users is established, and the comprehensive evaluation results of potential contract users are displayed to the power sales company to assist the power sales company in making good decisions on purchasing and selling electricity.

[0056] Specifically, first, in the load characteristic dimension, based on the comprehensive calculation of relevant indicator weights based on the hierarchical analysis method and the entropy weight method, the fuzzy c-means clustering algorithm is used to divide user load characteristics into four categories, namely, unimodal load, bimodal load, peak-avoiding load, and flat-peak load.

[0057] Second, in terms of operating model, the basic classification statistical method is used to calculate the number of days of user shutdown throughout the year, and the user operating models are divided into three categories according to quantitative rules, namely full-time operation mode, intermittent shutdown mode and complete shutdown mode.

[0058] Third, in the dimension of load economic value level, based on the comprehensive calculation of relevant indicator weights based on the hierarchical analysis method and the entropy weight method, the user value score is solved according to the maximum membership principle to divide the user load economic value level into five categories, namely high, relatively high, medium, relatively low, and low.

[0059] Fourth, in terms of the level of interactive technology, user interactive technology is divided into five categories according to the indicator quantification rules, namely high, relatively high, medium, relatively low and low levels.

[0060] Fifth, in the dimension of holiday sensitivity, users' holiday sensitivity is divided into three categories according to the quantitative rule of proportion, namely insensitive, balanced, and sensitive.

[0061] Ultimately, a five-dimensional profile of the electricity user is generated for the electricity retail company. The multi-dimensional user characteristic mining and evaluation technology proposed in this application provides a more comprehensive, integrated, refined, and operational user profile. This can help the electricity retail company customize electricity retail packages based on the provided user profile, assisting the company in making better decisions in areas such as demand response, electricity purchase and sales, spot declaration, and value-added services.

[0062] The electricity user classification method provided in the embodiment of the present application can be applied to the aforementioned Figure 1 The electricity user classification system in the illustrated implementation architecture. For ease of understanding, the electricity user classification method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0063] Figure 3 is a flow chart showing a method for classifying electricity users according to an exemplary embodiment. Figure 3 As shown, the electricity user classification method includes the following steps.

[0064] S21 , classifying load types of a plurality of electricity users according to a plurality of first indicators in electricity load characteristics of the electricity users to obtain a first classification result.

[0065] The characterization of electricity load characteristics focuses on users' electricity consumption behavior.

[0066] Multiple first-level indicators include daily average load, daily peak-to-valley difference rate, peak load rate, valley load rate, daily load rate, and maximum load factor.

[0067] When a power sales company supplies power to multiple potential subscribers, it needs to investigate their electricity usage characteristics. In this step, the first categorization of the multiple subscribers is performed based on the first dimension of their load information (i.e., multiple first indicators). This allows the company to identify the first dimensional characteristics of the multiple subscribers.

[0068] Further, as follows Figure 4As shown, the above step S21 specifically includes:

[0069] S211 , determining first weights of relative influences between first indicators in a plurality of first indicators according to the analytic hierarchy process and the entropy weight method.

[0070] In one embodiment, the process of determining the first weight according to the following formulas (1) to (15) is as follows.

[0071] As a method for determining the first weight, the first indicator is first determined, and then the weights of the first indicators of the hierarchical analysis method and the entropy weight method are determined based on the relative influence between the first indicators. Finally, the first weight is further determined by combining the weight of the first indicator of the hierarchical analysis method and the weight of the first indicator of the entropy weight method.

[0072] Specifically, first, each first index is obtained based on formula (1) to formula (6).

[0073] The specific calculation formula for daily load utilization level is as follows.

[0074]

[0075] Among them, α is the daily average load; Q d is the daily electricity consumption; d is the number of days.

[0076] The specific calculation formula for the ratio of the maximum daily peak-to-valley difference to the daily maximum load is as follows.

[0077]

[0078] Among them, β is the daily peak-to-valley difference rate; is the maximum daily load; This is the minimum daily load.

[0079] The specific calculation formula for the ratio of the average load during peak hours to the average daily load is as follows.

[0080]

[0081] Where, χ is the peak load factor; is the average load during the daily peak period; is the average daily load.

[0082] The specific calculation formula for the ratio of the average load during the off-peak period to the average daily load is as follows.

[0083]

[0084] Where, γ is the valley load rate; is the average daily load; It is the average load during the daily off-peak period.

[0085] The specific calculation formula for the ratio of daily average load to daily maximum load is as follows.

[0086]

[0087] Where, δ is the daily load rate; is the average daily load; The maximum daily load.

[0088] The specific calculation formula for the ratio of daily maximum load to annual maximum load is as follows.

[0089]

[0090] Where, ε is the maximum load factor; is the maximum daily load; The maximum annual load.

[0091] Secondly, the weight of the first indicator of the hierarchical analysis method is determined based on formula (7) and formula (8).

[0092] The specific calculation formula for determining the relative impact between each first indicator using the paired comparison method is as follows.

[0093]

[0094] Among them, A is the judgment matrix, a ij It is the relative weight element between different indicators.

[0095] The specific calculation formula for determining the weight of the first indicator of the hierarchical analysis method is as follows.

[0096]

[0097] Among them, w i is the weight coefficient of the first indicator of the i-th analytic hierarchy process, m is the number of indicators (m = 6), a ij are the elements in the above matrix.

[0098] Again, the first indicator weight of the entropy weight method is determined based on formulas (9) to (14).

[0099] According to the amount of information and degree of differentiation of each feature, the impact of the indicator on the total value is determined, and the specific calculation formula of the first indicator matrix is determined as follows.

[0100]

[0101] Among them, n is the daily load data of users; m is the number of indicators; x nm Refers to the value of the mth first indicator of the nth user.

[0102] In order to eliminate the influence of different dimensions, the specific calculation formula of the matrix after the first indicator is normalized is as follows.

[0103]

[0104] Among them, x ij is an element in the matrix; z ij are the elements in the normalized matrix.

[0105] The specific calculation formula for determining the first indicator probability matrix is as follows.

[0106]

[0107] Among them, z ij is the element in the normalized matrix; p ij Elements in the first indicator probability matrix.

[0108] The specific calculation formula for determining the information entropy of each first indicator is as follows.

[0109]

[0110] Among them, e i is the information entropy of the first indicator of item i; p ij Elements in the first indicator probability matrix.

[0111] The specific calculation formula for determining the information utility value is as follows.

[0112] d i =1-e i (13).

[0113] Among them, d i is the information utility value of the first indicator of item i; e i is the information entropy of the first indicator of the i-th item.

[0114] The specific calculation formula for determining the first indicator weight of the entropy weight method is as follows.

[0115]

[0116] Among them, d i is the utility value of the i-th information; w i ′ is the weight of the first indicator of the i-th entropy weight method.

[0117] Finally, the first weight is further determined based on formula (15).

[0118] The specific calculation formula for determining the first weight is as follows.

[0119]

[0120] Among them, w is the second weight; w i is the weight of the first indicator of the i-th analytic hierarchy process; w′ i is the weight of the first indicator of the i-th entropy weight method.

[0121] In this step, in order to make the classification of each electricity user more scientific and accurate, the subjective and objective combined weighting model that integrates the hierarchical analysis method and the entropy weight method defines the weights of each first indicator, and accurately processes the huge and complex user electricity consumption data to ensure the accuracy of the first weight.

[0122] S212: Obtain a second indicator matrix representing the relative influence between the first indicators based on the first indicator matrix constructed from the plurality of first indicators and the first weights.

[0123] In one embodiment, the process of determining the second indicator matrix according to the following formulas (16) to (18) is as follows.

[0124] Specifically, first, the first indicator matrix is determined based on formula (16).

[0125] X=(x1,x2,…,x n ) (16).

[0126] Among them, X is the first indicator matrix; x n is the first indicator matrix element.

[0127] Secondly, the normalized matrix is determined based on formula (17).

[0128] Z=(z1,z2,…,z n ) (17).

[0129] Among them, Z is the matrix after normalization; z n are the matrix elements after normalization.

[0130] Finally, based on formula (18), a second indicator matrix is determined that combines the first weights to characterize the relative influence between the first indicators.

[0131]

[0132] Where W is the second indicator matrix; wmxnm is the element of the second indicator matrix.

[0133] S213: Classify each element in the second indicator matrix to obtain a first classification result.

[0134] In one embodiment, the second indicator matrix is used as input data, and the fuzzy c-means clustering algorithm is called to perform clustering calculation. After investigating a given number of clusters, four types of load characteristics are obtained, which are verified by user load curves to finally obtain four types of classification results.

[0135] The above first classification results include single-peak load, double-peak load, peak-avoiding load and flat-peak load.

[0136] S22, evaluating the value categories of the plurality of electricity users according to the plurality of second indicators in the economic value of the electricity load of the electricity users to obtain a second classification result.

[0137] The economic value characterization of electric load focuses on the economic characteristics of users' electricity consumption.

[0138] The multiple secondary indicators of the economic value of electricity load of electricity users include contract capacity, average annual electricity consumption, electricity growth rate and transaction price acceptance level.

[0139] When a power sales company provides power to multiple potential subscribers, it needs to investigate the economic value of their loads. In this step, the multiple subscribers are classified into a second category based on the second dimension of their load information (i.e., multiple second indicators). This allows the company to identify the second-dimensional characteristics of each subscriber.

[0140] Further, as follows Figure 5 As shown, the above step S22 specifically includes:

[0141] S221 , determining second weights of relative influences between the second indicators in the plurality of second indicators according to the analytic hierarchy process and the entropy weight method.

[0142] In one embodiment, the process of determining the second weight according to the following formulas (19) to (28) is as follows.

[0143] As a method for determining the second weight, the second indicator is first determined, and then the weights of the second indicators of the hierarchical analysis method and the entropy weight method are determined based on the relative influence between the second indicators. Finally, the second weight is further determined by combining the weight of the second indicator of the hierarchical analysis method and the weight of the second indicator of the entropy weight method.

[0144] Specifically, first, the second indicator is determined.

[0145] Select the user's contract capacity, average annual power consumption in the past year, and daily power consumption Q from the user's authorization information and transaction data. d , monthly retail transaction prices and other data determine the second indicator.

[0146] The contract capacity is the total capacity of the user's transformer, reflecting the user's overall electricity consumption scale.

[0147] The average annual electricity consumption reflects the overall electricity consumption level of users.

[0148] The price acceptance level is the weighted average price of the user's contract price in the past year based on actual electricity consumption.

[0149] The electricity consumption growth rate reflects the user's electricity consumption growth potential. The specific formula is as follows.

[0150]

[0151] Among them, ω is the growth rate of electricity; Q d is the daily electricity consumption; Q d-1 The electricity consumption for the previous day.

[0152] Secondly, the weight of the second indicator of the hierarchical analysis method is determined based on formula (20) and formula (21).

[0153] The specific calculation formula for determining the relative impact between each first indicator using the paired comparison method is as follows.

[0154]

[0155] Among them, A is the judgment matrix, a ij It is the relative weight element between different indicators.

[0156] The specific calculation formula for determining the weight of the second indicator of the hierarchical analysis method is as follows.

[0157]

[0158] Among them, w i is the weight coefficient of the second indicator of the i-th analytic hierarchy process, m is the number of indicators, a ij are the elements in the above matrix.

[0159] Again, the second indicator weight of the entropy weight method is determined based on formulas (22) to (27).

[0160] According to the amount of information and degree of differentiation of each feature, the impact of the indicator on the total value is determined, and the specific calculation formula of the second indicator matrix is determined as follows.

[0161]

[0162] Among them, n is the daily load data of users; m is the number of indicators; x nm Refers to the value of the mth second indicator of the nth user.

[0163] In order to eliminate the influence of different dimensions, the specific calculation formula of the matrix after the second index is normalized is as follows.

[0164]

[0165] Among them, x ij is an element in the matrix; z ij are the elements in the normalized matrix.

[0166] The specific calculation formula for determining the second indicator probability matrix is as follows.

[0167]

[0168] Among them, z ij is the element in the normalized matrix; p ij Elements in the second indicator probability matrix.

[0169] The specific calculation formula for determining the information entropy of each second indicator is as follows.

[0170]

[0171] Among them, e i is the information entropy of the second indicator of item i; p ij Elements in the second indicator probability matrix.

[0172] The specific calculation formula for determining the information utility value is as follows.

[0173] d i =1-e i (26).

[0174] Among them, d i is the information utility value of the first indicator of item i; e i is the information entropy of the first indicator of the i-th item.

[0175] The specific calculation formula for the second indicator weight of the entropy weight method is as follows.

[0176]

[0177] Among them, d i is the utility value of the i-th information, w i ′ is the weight of the second indicator of the i-th entropy weight method.

[0178] Finally, the second weight is further determined based on formula (28).

[0179] The specific calculation formula of the second weight is as follows.

[0180]

[0181] Among them, w is the second weight; w i is the weight of the second indicator of the i-th analytic hierarchy process; w′ i is the weight of the second indicator of the i-th entropy weight method.

[0182] S222: Evaluate the economic value of the user load for each second weight according to the maximum membership principle to obtain a second classification result.

[0183] In one embodiment, the second classification result is determined according to the following formulas (29) to (32).

[0184] Specifically, first, the value assessment matrix is determined based on formula (29).

[0185] The economic value of user load is divided into five levels: high, relatively high, medium, relatively low, and low, and a value assessment matrix is constructed.

[0186] V={V1,V2,V3,V4,V5}(29).

[0187] Among them, V is the value assessment matrix; V1, V2, V3, V4, V5 are the value assessment ranges.

[0188] Secondly, the value assessment matrix elements affected by the second weight are determined based on formula (30).

[0189]

[0190] Among them, c i is the second weighted impact factor of the i-th factor, V i The value of the second weighted impact evaluation matrix element retV i For value assessment level.

[0191] Again, the value evaluation operator of the second weight influence is determined based on formula (31).

[0192]

[0193] Among them, c i is the second weighted impact factor of the i-th factor, V i The value of the second weighted impact evaluation matrix element.

[0194] Finally, according to the maximum membership principle, the value evaluation matrix elements of the second weight influence determined by formula (30) and the value evaluation operator of the second weight influence determined by formula (31) are substituted into formula (32) to determine the economic value evaluation level of the user load, thereby obtaining the second classification result.

[0195]

[0196] Among them, retV is the value assessment level, c i is the second weighted impact factor of the i-th factor, V i is the value evaluation matrix element of the second weight impact, σ kThe value evaluation operator for the second weighted influence.

[0197] The above-mentioned second classification results include a first level, a second level, a third level, a fourth level and a fifth level indicating the degree of economic value of the user load.

[0198] In one embodiment, the economic value of user load is divided into five levels, and retV1 is defined as a low level with a proportion of 0; retV2 is a lower level with a proportion of 70; retV3 is a medium level with a proportion of 80; retV4 is a higher level with a proportion of 90; and retV5 is a high level with a proportion of 100.

[0199] Specifically, the higher the level, the higher the economic level of the user.

[0200] In this step, in order to make the classification results of each user more intuitive, the maximum membership principle is adopted to clearly classify the economic value of user loads, ensuring that the second classification result is more accurate in evaluating the economic value of user loads.

[0201] S23, classifying the electricity consumption operation modes of the plurality of electricity users according to the third indicator in the electricity load characteristic to obtain a third classification result.

[0202] The characterization of electricity load characteristics focuses on users' electricity consumption behavior.

[0203] The various third indicators include daily load factor and maximum load factor.

[0204] Any electricity sales company will supply electricity to multiple potential contract users and needs to investigate their electricity usage patterns. In this step, multiple electricity users are classified into a third category based on the third dimension of their load information (i.e., multiple third indicators). This allows the company to identify the third-dimensional characteristics of each user.

[0205] In one embodiment, a shutdown index is determined based on the third index, shutdown days are determined based on the shutdown index, and a third classification result is determined based on the shutdown range to which the total shutdown days belong.

[0206] First, determine the third indicator.

[0207] Specifically, the process of determining the third indicator according to the following formula (33) and formula (34) is as follows.

[0208] Determine the ratio of the daily maximum load to the annual maximum load.

[0209]

[0210] Where, δ is the daily load rate; is the average daily load; The maximum daily load.

[0211] Determine the ratio of the maximum load to the annual maximum load.

[0212]

[0213] Where ε is the maximum load factor is the maximum daily load; The maximum annual load.

[0214] Secondly, the shutdown index is determined based on the third index, and the total shutdown days of each electricity user is determined based on the shutdown index.

[0215] Specifically, any third indicator whose daily load factor is greater than the first daily load factor threshold and whose maximum load factor is less than the second load factor threshold is determined as a shutdown indicator corresponding to a shutdown day. The total number of shutdown days for each electricity user is determined based on the number of shutdown indicators included in the third indicator corresponding to each electricity user.

[0216] Based on the above embodiment, illustratively, the first daily load factor threshold is 0.8, the second load factor threshold is 0.3, the first shutdown threshold is 100, and the second shutdown threshold is 300. A day with a load factor greater than 0.8 and a maximum load factor less than 0.3 is considered a shutdown day.

[0217] Finally, the third classification result of each electricity user is determined based on the shutdown range to which the total shutdown days of each electricity user belong.

[0218] The above third classification results include full operation mode, intermittent shutdown mode and complete shutdown mode.

[0219] Specifically, if the total downtime days of any electricity user is less than a first downtime threshold, the electricity user is determined to be in full operation mode. If the total downtime days of any electricity user is greater than or equal to the first downtime threshold and less than or equal to a second downtime threshold, the electricity user is determined to be in intermittent downtime mode. If the total downtime days of any electricity user is greater than a second downtime threshold, the electricity user is determined to be in full downtime mode.

[0220] For example, Figure 6 As shown in the figure, the total number of downtime days can also be called the annual downtime days. A yearly downtime of less than 100 days is considered full operation mode, a yearly downtime of 100 to 300 days is considered intermittent downtime mode, and a yearly downtime of more than 300 days is considered complete downtime mode.

[0221] In this step, the basic classification statistics method is used to calculate the total downtime days of users and quantify the user's business model to make the classification results more reasonable.

[0222] S24, evaluating the electricity consumption capabilities of the plurality of electricity users according to the plurality of fourth indicators of the interactive technology levels of the electricity users to obtain a fourth classification result;

[0223] The interactive technology level characterization focuses on the user's ability to cooperate with power sales companies in the spot market environment.

[0224] The plurality of fourth indicators include auxiliary service level indicator parameters and demand response level indicator parameters.

[0225] Any electricity sales company will provide power to multiple potential users and needs to investigate their interaction technology levels. In this step, multiple electricity users are classified into a fourth category based on the fourth dimension of their load information (i.e., multiple fourth indicators). This allows the company to identify the fourth dimension characteristics of each user.

[0226] First, the ratio of the interruptible load value of each electricity user to the user's annual maximum load is determined as the auxiliary service level index parameter of each electricity user, and the ratio of the duration of the interruptible load provided by each electricity user to the number of interruptions is determined as the demand response level index parameter of each electricity user.

[0227] Specifically, the ratio of the user's interruptible load value to the user's annual maximum load is determined according to the following formula.

[0228]

[0229] Where η is the auxiliary service level; P 可中断 is the interruption load value; The maximum annual load.

[0230] The ratio of the duration of interruptible load provided by the user to the number of interruptions is determined according to the following formula.

[0231]

[0232] Where λ is the demand response level; P 可中断 is the interruption load value, P 最大负荷 is the annual maximum load value, n is the number of interruptible loads in a day, T is the average duration of interruptible loads, and t is the reaction time for participating in demand response.

[0233] In this step, the potential peak-shaving and reserve capacity of electricity users and their ability to participate in demand response are reflected.

[0234] Finally, the fourth classification result is determined according to the service index range to which the auxiliary service level index parameter of each electricity user belongs and the response index range to which the demand response level index parameter of each electricity user belongs.

[0235] In one embodiment, both the auxiliary service level and the demand response level indicators reflect the user's ability and technology to participate in the auxiliary service market and the demand response market, and therefore have equal weights. The two indicators are further quantified to determine the fourth classification result.

[0236] The fourth classification results include the first level, the second level, the third level, the fourth level and the fifth level, which indicate the user's ability to participate in the ancillary service market and the demand response market.

[0237] In some embodiments, the higher the interactive technology level, the higher the user's power usage capacity.

[0238] The results of the interactive technology level classification are as follows Figure 7 shown.

[0239] Specifically, the auxiliary service level range for electricity users is divided into five indicator ranges: less than 10, greater than or equal to 10 and less than 20, greater than or equal to 20 and less than 40, greater than or equal to 40 and less than 80, and greater than 80. The demand response level range for electricity users is divided into five indicator ranges: less than 10, greater than or equal to 10 and less than 20, greater than or equal to 20 and less than 40, greater than or equal to 40 and less than 80, and greater than 80. The first, second, third, fourth, and fifth levels of the interactive technology level classification results correspond to the five levels of low, lower, medium, higher, and high, respectively.

[0240] S25 , classifying the holiday sensitivity of the plurality of electricity users according to the holiday sensitivity information of the electricity users, and obtaining a fifth classification result.

[0241] Holiday sensitivity information represents the proportion of holidays in the total shutdown days and determines the electricity demand of electricity users.

[0242] A power sales company will supply power to multiple potential customers and needs to investigate their holiday sensitivity. In this step, multiple customers are classified into a fifth category based on the fifth dimension of their load information (i.e., multiple fifth indicators). This allows the company to identify the fifth dimension characteristics of each customer.

[0243] Further, if Figure 8 As shown, the above step S25 specifically includes:

[0244] S251, determining the holiday working ratio of electricity users.

[0245] First, the total downtime days of each electricity user are determined based on downtime days corresponding to each electricity user having a daily load rate greater than a second daily load rate threshold and a maximum load factor less than a second load factor threshold.

[0246] Secondly, determine the total number of holidays included in the total downtime days for each electricity user

[0247] Finally, for any electricity user, the ratio between the total holidays of any electricity user and the total work stoppage days of any electricity user is determined as the holiday work ratio of any electricity user.

[0248] Exemplarily, the second daily load rate threshold is 0.8, and the second load factor threshold is 0.3.

[0249] The holiday working ratio of electricity users is determined according to the following formula.

[0250]

[0251] Where ω is the holiday work ratio D′ δ>0.8,ε<0.3 The number of days in the past year that were holidays when the daily load factor was greater than 0.8 and the maximum load factor was less than 0.3; D δ>0.8,ε<0.3 The number of days in a year when the daily load factor is greater than 0.8 and the maximum load factor is less than 0.3.

[0252] S252: Determine a fifth classification result based on the holiday working ratio of electricity users.

[0253] The fifth classification result of any electricity user is determined according to the holiday proportion range to which the holiday work ratio of any electricity user belongs.

[0254] The fifth classification result includes a first sensitive type, a second sensitive type, and a third sensitive type that characterize the user's holiday sensitivity.

[0255] In some embodiments, the holiday proportion classification results are as follows: Figure 9 shown.

[0256] Specifically, the first sensitive type is the insensitive type, the second sensitive type is the balanced type, and the third sensitive type is the sensitive type. If the holiday ratio is less than 30%, it is the insensitive type; if the holiday ratio is between 30% and 60%, it is the balanced type; and if the holiday ratio is greater than 60%, it is the sensitive type.

[0257] In this step, the user's holiday sensitivity is classified using a proportion quantification rule to ensure that the classification result is more in line with the user's actual situation.

[0258] S26, determining a user profile of each electricity user based on the first classification result, the second classification result, the third classification result, the fourth classification result, and the fifth classification result.

[0259] Through the above steps, five classification results are obtained through comprehensive analysis of the five dimensions of load characteristics, economic value level, business model, interactive technology level, and holiday sensitivity, thereby forming a user portrait that can accurately reflect the user's electricity consumption characteristics. Different user characteristics are evaluated from multiple dimensions to obtain a more comprehensive, integrated, refined, and differentiated user portrait.

[0260] In order to realize the above functions, the electricity user classification device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0261] The present disclosure also provides a Figure 10 The device for classifying electricity users shown includes: a classification unit 301 and a determination unit 302 .

[0262] The classification unit 301 is configured to classify the load types of multiple electricity users according to multiple first indicators in the electricity load characteristics of the electricity users to obtain a first classification result, and to evaluate the value categories of multiple electricity users according to multiple second indicators in the economic value of the electricity load of the electricity users to obtain a second classification result, and to classify the electricity operation models of multiple electricity users according to the third indicator in the electricity load characteristics to obtain a third classification result, and to evaluate the electricity consumption capabilities of multiple electricity users according to multiple fourth indicators in the interactive technology level of the electricity users to obtain a fourth classification result, and to classify the holiday sensitivity of multiple electricity users according to the holiday sensitivity information of the electricity users to obtain a fifth classification result.

[0263] The determining unit 302 is configured to determine a user portrait of each electricity user based on the first classification result, the second classification result, the third classification result, the fourth classification result, and the fifth classification result.

[0264] As an implementation method, the plurality of first indicators include: daily average load, daily peak-to-valley difference rate, peak load rate, valley load rate, daily load rate, and maximum load factor.

[0265] The classification unit 301 is specifically configured to classify the load types of multiple electricity users according to multiple first indicators in the electricity load characteristics of the electricity users to obtain a first classification result, including: determining each first weight representing the relative influence between each first indicator in the multiple first indicators based on the hierarchical analysis method and the entropy weight method; obtaining a second indicator matrix representing the relative influence between each first indicator based on a first indicator matrix constructed from the multiple first indicators and the first weights; and classifying each element in the second indicator matrix to obtain the first classification result. The first classification result includes unimodal load, bimodal load, peak-avoiding load, and flat-peak load.

[0266] As a means of implementation, multiple secondary indicators include: contract capacity, average annual electricity consumption, electricity growth rate and transaction price acceptance level.

[0267] The classification unit 301 is specifically configured to evaluate the value categories of multiple electricity users based on multiple second indicators of the economic value of their electricity loads to obtain a second classification result, including: determining second weights representing the relative influence of each second indicator among the multiple second indicators based on the analytic hierarchy process and the entropy weight method. Evaluating the economic value of the user loads based on each second weight based on the maximum membership principle to obtain a second classification result; the second classification result includes a first level, a second level, a third level, a fourth level, and a fifth level indicating the degree of economic value of the user loads.

[0268] As an implementation method, the plurality of third indicators include a daily load rate and a maximum load factor.

[0269] The classification unit 301 is specifically configured to classify the electricity operation models of multiple electricity users according to a third indicator in the electricity load characteristics, thereby obtaining a third classification result, including determining any third indicator in the third indicator for which the daily load rate is greater than the first daily load rate threshold and the maximum load factor is less than the second load factor threshold as a shutdown indicator corresponding to a shutdown day. The total number of shutdown days for each electricity user is determined based on the number of shutdown indicators included in the third indicator corresponding to each electricity user. The third classification result for each electricity user is determined based on the shutdown range to which the total number of shutdown days for each electricity user belongs.

[0270] As an implementation method, the third classification results include: full operation mode, intermittent shutdown mode and complete shutdown mode.

[0271] The classification unit 301 is specifically configured to determine a third classification result for each electricity user based on the outage range to which the total outage days of each electricity user belong, including: determining that the total outage days of any electricity user are less than a first outage threshold, determining that the electricity user is in full operation mode; determining that the total outage days of any electricity user are greater than or equal to the first outage threshold and less than or equal to the second outage threshold, determining that the electricity user is in intermittent outage mode; and determining that the total outage days of any electricity user are greater than the second outage threshold, determining that the electricity user is in full outage mode.

[0272] As an implementation method, the plurality of fourth indicators include: an auxiliary service level indicator parameter and a demand response level indicator parameter.

[0273] The classification unit 301 is specifically configured to evaluate the electricity consumption capabilities of multiple electricity users based on multiple fourth indicators of the electricity user's interactive technology level, thereby obtaining a fourth classification result, including: determining the ratio of each electricity user's interruptible load value to the user's annual maximum load as the auxiliary service level indicator parameter for each electricity user; and determining the ratio of the duration of interruptible load provided by each electricity user to the number of interruptions as the demand response level indicator parameter for each electricity user. The fourth classification result is determined based on the service indicator range to which each electricity user's auxiliary service level indicator parameter belongs and the response indicator range to which each electricity user's demand response level indicator parameter belongs. The fourth classification result includes a first level, a second level, a third level, a fourth level, and a fifth level, indicating the level of a user's ability to participate in the ancillary service market and the demand response market.

[0274] As an implementation method, the classification unit 301 is specifically configured to classify the holiday sensitivity of multiple electricity users according to the holiday sensitivity information of the electricity users, and obtain a fifth classification result, including: determining the total downtime days of each electricity user based on the downtime days corresponding to each electricity user whose daily load rate is greater than the second daily load rate threshold and whose maximum load factor is less than the second load factor threshold. Determine the total holidays included in the total downtime days of each electricity user. For any electricity user, determine the ratio between the total holidays of any electricity user and the total downtime days of any electricity user as the holiday work ratio of any electricity user. Determine the fifth classification result of any electricity user based on the holiday proportion range to which the holiday work ratio of any electricity user belongs, and the fifth classification result includes the first sensitive type, the second sensitive type, and the third sensitive type that characterize the user's holiday sensitivity.

[0275] Regarding the device in the above embodiment, the specific manner in which each unit module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0276] Figure 11This is a schematic diagram of an electronic device provided by this application. Figure 11 The electronic device 50 may include at least one processor 501 and a memory 503 for storing processor-executable instructions. The processor 501 is configured to execute instructions in the memory 503 to implement the electricity user classification method in the following embodiment.

[0277] In addition, the electronic device 50 may further include a communication bus 502 , at least one communication interface 504 , an input device 506 , and an output device 505 .

[0278] The processor 501 may be a central processing unit (CPU), a microprocessor unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0279] The communication bus 502 may include a pathway for transmitting information between the aforementioned components.

[0280] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0281] The input device 506 is used to receive input signals and the output device 505 is used to output signals.

[0282] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be independent and connected to the processing unit via a bus. The memory may also be integrated with the processing unit.

[0283] The memory 503 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the instructions stored in the memory 503, thereby realizing the functions of the method of the present application.

[0284] In a specific implementation, as an embodiment, the processor 501 may include one or more CPUs, such as Figure 11 CPU0 and CPU1 in.

[0285] In a specific implementation, as an embodiment, the electronic device 50 may include multiple processors, such as Figure 11 1 and 507. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0286] The electronic equipment Figure 11 The system includes a processor 501 and a memory 503 for storing executable instructions of the processor 501. The processor 501 is configured to execute the executable instructions to implement the electricity user classification method according to any of the above possible implementations. The methods can achieve the same technical effects and are not described here in detail to avoid repetition.

[0287] The present application also provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a processor of an electricity user classification device or electronic device, the device or electronic device can perform the electricity user classification method according to any of the above possible implementations. To avoid repetition, the above description will not be repeated.

[0288] The present application also provides a computer program product including a computer program or instructions, wherein the computer program or instructions are executed by a processor to implement the electricity user classification method according to any of the above possible implementations. The same technical effects can be achieved, and to avoid repetition, they are not described here.

[0289] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0290] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for classifying electricity users, characterized in that: The method comprises: Classifying the load types of multiple electricity users according to multiple first indicators in the electricity load characteristics of the electricity users to obtain a first classification result; and evaluating the value categories of the multiple electricity users according to multiple second indicators in the economic value of the electricity load of the electricity users to obtain a second classification result; and classifying the electricity operation models of the multiple electricity users according to a third indicator in the electricity load characteristics to obtain a third classification result; and evaluating the electricity consumption capabilities of the multiple electricity users according to multiple fourth indicators in the interactive technology levels of the electricity users to obtain a fourth classification result; and classifying the holiday sensitivity of the multiple electricity users according to the holiday sensitivity information of the electricity users to obtain a fifth classification result; Based on the first classification result, the second classification result, the third classification result, the fourth classification result and the fifth classification result, a user profile of each electricity user is determined.

2. The method for classifying electricity users according to claim 1, characterized in that: The plurality of first indicators include: daily average load, daily peak-to-valley difference rate, peak load rate, valley load rate, daily load rate, and maximum load factor; The classifying the load types of the plurality of electricity users according to the plurality of first indicators in the electricity load characteristics of the electricity users to obtain a first classification result includes: Determine, according to the hierarchical analysis method and the entropy weight method, first weights of the relative influence between the first indicators in the plurality of first indicators; A second indicator matrix representing the relative influence between the first indicators is obtained based on the first indicator matrix constructed by the multiple first indicators and the first weights. Each element in the second indicator matrix is classified to obtain the first classification result; the first classification result includes single-peak load, double-peak load, peak-avoiding load and flat-peak load.

3. The method for classifying electricity users according to claim 1, characterized in that: The multiple second indicators include: contract capacity, average annual electricity consumption, electricity growth rate and transaction price acceptance level; The value categories of the plurality of electricity users are evaluated according to the plurality of second indicators in the economic value of the electricity load of the electricity users to obtain a second classification result, including: Determine, according to the hierarchical analysis method and the entropy weight method, respective second weights of the relative influence between the respective second indicators in the plurality of second indicators; According to the maximum membership principle, the economic value of the user load is evaluated for each second weight to obtain the second classification result; the second classification result includes a first level, a second level, a third level, a fourth level and a fifth level indicating the degree of the economic value of the user load.

4. The method for classifying electricity users according to claim 1, characterized in that: The plurality of third indicators include a daily load rate and a maximum load factor; and the electricity operation modes of the plurality of electricity users are classified according to the third indicator in the electricity load characteristics to obtain a third classification result, including: Determine any third indicator among the third indicators whose daily load rate is greater than the first daily load rate threshold and whose maximum load factor is less than the second load factor threshold as a shutdown indicator corresponding to one shutdown day; Determining the total downtime days of each electricity user according to the number of downtime indicators included in the third indicator corresponding to each electricity user; The third classification result of each electricity user is determined according to the shutdown range to which the total shutdown days of each electricity user belong.

5. The method for classifying electricity users according to claim 4, characterized in that: The third classification result includes: full operation mode, intermittent shutdown mode and complete shutdown mode; the third classification result of each electricity user is determined according to the shutdown range to which the total shutdown days of each electricity user belong, including: Determining that the total downtime days of any electricity user is less than a first downtime threshold, and determining that the any electricity user is in a full-operation mode; Determining that the total shutdown days of any electricity user is greater than or equal to the first shutdown threshold and less than or equal to the second shutdown threshold, and determining that the any electricity user belongs to the intermittent shutdown mode; It is determined that the total shutdown days of any electricity user is greater than the second shutdown threshold, and it is determined that any electricity user is in a complete shutdown mode.

6. The method for classifying electricity users according to claim 1, characterized in that: The plurality of fourth indicators include: auxiliary service level indicator parameters and demand response level indicator parameters; The power consumption capabilities of the plurality of power users are evaluated according to a plurality of fourth indicators of the interactive technology levels of the power users to obtain a fourth classification result, including: Determine the ratio of the interruptible load value of each electricity user to the user's annual maximum load as the auxiliary service level indicator parameter of each electricity user; and determine the ratio of the duration of the interruptible load provided by each electricity user to the number of interruptions as the demand response level indicator parameter of each electricity user; The fourth classification result is determined based on the service indicator range to which the auxiliary service level indicator parameters of each electricity user belong and the response indicator range to which the demand response level indicator parameters of each electricity user belong; the fourth classification result includes the first level, the second level, the third level, the fourth level and the fifth level indicating the user's ability to participate in the auxiliary service market and the demand response market.

7. The method for classifying electricity users according to claim 1, characterized in that: The fifth classification result is obtained by classifying the holiday sensitivity of the plurality of electricity users according to the holiday sensitivity information of the electricity users, including: Determine the total downtime days of each electricity user based on downtime days corresponding to each electricity user having a daily load rate greater than a second daily load rate threshold and a maximum load factor less than a second load factor threshold; Determine the total number of holidays included in the total number of downtime days for each electricity user; For any electricity user, determining the ratio between the total holidays of the any electricity user and the total work stoppage days of the any electricity user as the holiday work ratio of the any electricity user; The fifth classification result of any electricity user is determined according to the holiday proportion range to which the holiday working ratio of any electricity user belongs, and the fifth classification result includes a first sensitive type, a second sensitive type and a third sensitive type that characterize the user's holiday sensitivity.

8. A device for classifying electricity users, characterized in that: The device comprises: The classification unit is configured to classify a plurality of electricity load types according to a plurality of first indicators in the electricity load characteristics of the electricity users to obtain a first classification result; and evaluate the value categories of the plurality of electricity users according to a plurality of second indicators in the economic value of the electricity load of the electricity users to obtain a second classification result; and classify the electricity operation models of the plurality of electricity users according to a third indicator in the electricity load characteristics to obtain a third classification result; and evaluate the electricity consumption capabilities of the plurality of electricity users according to a plurality of fourth indicators in the interactive technology levels of the electricity users to obtain a fourth classification result; and classify the holiday sensitivity of the plurality of electricity users according to the holiday sensitivity information of the electricity users to obtain a fifth classification result; The determining unit is configured to determine a user portrait of each electricity user based on the first classification result, the second classification result, the third classification result, the fourth classification result and the fifth classification result.

9. A power system, characterized in that: The method is configured to execute the electricity user classification method according to any one of claims 1 to 7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for classifying electricity users according to any one of claims 1 to 7.

Images