CN115994778A - Behavior fine portrait method for multiple users - Google Patents
Behavior fine portrait method for multiple users Download PDFInfo
- Publication number
- CN115994778A CN115994778A CN202211544430.0A CN202211544430A CN115994778A CN 115994778 A CN115994778 A CN 115994778A CN 202211544430 A CN202211544430 A CN 202211544430A CN 115994778 A CN115994778 A CN 115994778A
- Authority
- CN
- China
- Prior art keywords
- energy
- service
- user
- value
- utility
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for finely portraying the energy consumption behavior of a plurality of users, which belongs to the technical field of comprehensive energy systems and realizes the comprehensive energy service demand analysis of the plurality of users, on one hand, the method can help the users to know the energy consumption demands of the users, on the other hand, can help service providers to screen potential service objects, and avoids the cost and the manpower waste caused by blind marketing. The method can match the optimal comprehensive energy service for the user, and exert the effect of the comprehensive energy service to the maximum extent. The method is beneficial to the marketing service center to accurately identify differentiated value-added service demand potential of multiple users, improves service efficiency, widens service channels and explores new profit growth points. The comprehensive energy service company can be facilitated to formulate a service scheme with optimal comprehensive benefit, different user energy utilization modes can be matched, the user energy utilization efficiency is improved, and the user is helped to save the energy utilization cost. And in the development direction of the value-added service, the market competitiveness of enterprises per se is improved in the market, and the operating efficiency and the operating benefit are improved.
Description
Technical Field
The invention belongs to the technical field of comprehensive energy systems, and particularly relates to an energy behavior fine portrait method for multiple users.
Background
The core of developing comprehensive energy service is to meet the energy demand of users as much as possible while realizing quick, efficient and large-scale popularization, thereby attracting users to actively participate and actively purchase. With the continuous opening of the energy market, the energy consumption requirements of users gradually show differentiated and diversified characteristics. At present, the application of the comprehensive energy service generally has the problems of single function, unclear profit, ambiguous user energy consumption behavior and the like. The main causes of these problems are the following: first, the user energy consumption characteristics are not clear, and the user demands are not clear. The user can not know the energy consumption situation of the user, and can not carry out comparison analysis on the user with other users in the horizontal direction and the vertical direction, and can not determine whether the user needs comprehensive energy service. Second, the existing comprehensive energy service has single function and poor market potential. For users with multiple energy consumption requirements, the existing comprehensive energy service has narrow coverage, the depth and width of the service architecture can not meet the requirements, and the users can not be helped to realize the expected energy utility and value. Third, the existing comprehensive energy service is not clear. The method lacks scientific and reasonable analysis methods to help the two parties to definitely integrate the economic benefits brought by the energy service. For an energy service provider providing services, it is necessary to define the profitability of the energy service for the energy service; for a user purchasing a service, it is necessary to clarify the energy saving benefit of the energy service. The scientific and reasonable analysis method can improve the investment courage and purchase willingness of users, improve the enthusiasm of energy service providers in the aspect of comprehensive energy service, release the market demand of the comprehensive energy service and promote the benign operation of the comprehensive energy service.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a behavior fine portrait method for multiple users, which is based on user energy data and realizes visual behavior fine portrait for users; the method helps users to clearly determine whether the users are worth participating in the comprehensive energy service and provides a comprehensive energy service potential assessment method.
The purpose of the invention is realized in the following way: a behavior fine portrait method for multiple users comprises the following steps:
s1: establishing a multi-dimensional user energy feature and a multi-element user energy behavior portrait model;
s2: establishing a comprehensive energy service utility and value evaluation model;
s3: and analyzing the comprehensive energy service requirements and the potential thereof.
Further, the multi-dimensional energy utilization characteristics of the users are characterized in that the energy supply level of the area where the users are located is comprehensively estimated based on marketing big data and multi-element user energy utilization behavior information, the multi-dimensional energy utilization characteristics of the users are extracted from a time-frequency domain by combining signal processing methods such as FFT, S transformation and HHT transformation, the multi-element energy utilization requirements of industrial users are quantitatively analyzed, the fine image of the multi-element user energy utilization behavior is clarified, and the development path of the energy saving and efficiency improvement of the users and the comprehensive energy service is cleared.
Furthermore, the multi-user behavior portraits are characterized in that a feature optimization model is built based on an AHP-TOPSIS method as a user behavior feature quantification method and a FISHER criterion method, user categories are divided in a self-adaptive mode, high-quality features are effectively selected as portrayal labels, various user behavior portraits are built, and the user behavior features and the contrast between the user behavior features are displayed through a radar chart and a histogram.
Further, the comprehensive energy service utility is that firstly, a service architecture comprising four layers of value-added functions, a technical scheme, a service mode and a service level is constructed based on the multi-user energy fine image; the value-added function layer reflects the type of value-added energy requirements of the service, which can meet the requirements of the user, and comprises energy saving cost, low carbon cleaning and energy utilization efficiency; the technical scheme layer embodies main terminal energy supply equipment, energy management means or related technical measures adopted by the service, and the differentiated technical scheme aims at matching different energy utilization modes and energy utilization habits of users; the service mode layer comprises an investment construction mode, an operation mode and a tariff mode which are related in the implementation process of the service; the service level layer provides service time limit, energy supply equipment capacity or service expected targets of different gears so as to meet the actual demands of users with different energy consumption levels; secondly, a basic utility model and a value-added utility model are established based on a utility theory, and economic cost corresponding to the total energy of electricity, gas, heat, water, oil and the like is calculated to obtain the basic utility model; calculating the capacity of describing the value-added functions such as carbon emission, energy saving, equipment cost saving and the like, and quantifying the satisfaction degree of the user on each value-added service by combining the subjective requirements of the user to obtain a value-added utility model; and finally, obtaining a utility model of the comprehensive energy service by considering the service level, and quantifying the subjective evaluation condition of the user on the comprehensive energy service.
Further, the value evaluation is that subjective utility value connotation definition and characteristic analysis of the comprehensive energy source by multiple users are based on the utility value theory, objective economic conditions of an operation mode, a tariff mode and an investment mode are considered, and the subjective factors and objective factors are combined by using an AHP and entropy weight method, so that the comprehensive energy source service utility value evaluation of the multiple users is provided.
Further, the analysis of the comprehensive energy service requirement and the potential thereof comprises the following steps: the connotation and extension of the user energy consumption requirements are clarified, the three types of user energy consumption demand characteristics are analyzed according to the multi-element user energy consumption behavior characteristics, the external factors of season climate and policy subsidy, the internal intrinsic characteristic factors of production activities and demand types are combined, the comprehensive energy service utility value is considered, and a comprehensive energy service demand quantification model considering multi-dimensional factors is constructed; step two: according to the comprehensive, objective, representative and acquirability evaluation principles, a comprehensive energy service potential evaluation index system is constructed, a TOPSIS function model is introduced, the comprehensive energy service potential evaluation method is researched by taking energy demand as a core guide, and dynamic analysis and accurate adjustment are carried out on potential evaluation results by considering the variability of user energy consumption behaviors and season climate.
Further, the score of each label of each type of user of the portrait label is obtained by the following formula:
wherein: g i,j A j-th tag score for a i-th class of users;
the average value of the jth label belonging to all users in the ith class; r is (r) j,max ，r j,min The maximum and minimum values of the jth tag, respectively.
Further, the model of the utility of the comprehensive energy service is expressed as:
U＝u+v
wherein: u is the utility of comprehensive energy service; u is the base utility; v is the value-added utility. The comprehensive energy service utilities include basic utilities and value added utilities.
The model of the underlying utility is expressed as:
wherein: u (u) i,j Basic functional utility of the comprehensive energy service j to the user i; y represents the energy category consumed by the user, and y=1, 2,3,4 represent electric energy, gas, heat energy, cold energy respectively; t represents service time limit, which is selected by the user according to the service time limit gear provided by the energy supplier, and the year;
the unit price of Y energy is purchased for a user i at the moment t through the traditional energy service, and ten thousand yuan/(kW.h); />
The available energy is the Y energy supply amount, kW, provided by service j at time t and which can be fully utilized by user i. />
The model of the added value utility is expressed as:
wherein: v i,j The value-added utility of the comprehensive energy service j to the user i is ten thousand yuan; a=1, 2,3, … represent the user's energy saving cost, clean low carbon, energy efficiency improvement, energy safety improvement and other value-added energy satisfaction;
the value-added function capability of the A of the service j is the degree that the service j meets the value-added satisfaction degree A of the user i, and ten thousand yuan; />
For user i's intensity for satisfaction a, +.>
The larger the user's need for satisfaction a is, the stronger; when->
When the user considers that satisfaction a is necessary satisfaction; when->
When the user does not have satisfaction a, he considers it to be available or not. />
The fuzzy membership is constructed and characterized by a scale method according to subjective consciousness of a user.
The invention has the beneficial effects that: the comprehensive energy service demand analysis of the multiple users is realized, so that the users can be helped to know the energy demand of the users, and the service providers can be helped to screen potential service objects, and the cost and manpower waste caused by blind marketing are avoided. And on the basis of defining the service object, the optimal comprehensive energy service can be matched for the user, and the effect of the comprehensive energy service can be exerted to the maximum extent. The method is beneficial to the marketing service center to accurately identify differentiated value-added service demand potential of multiple users, improves service efficiency, widens service channels and explores new profit growth points. The comprehensive energy service company can be facilitated to formulate a service scheme with optimal comprehensive benefit, different user energy utilization modes can be matched, the user energy utilization efficiency is improved, and the user is helped to save the energy utilization cost. The method is beneficial to reasonable value-added service investment decision making by users, provides decision support for the service company to make different business strategies of different clients, defines the development direction of the value-added service, improves the market competitiveness of the enterprise in the market, and improves the business efficiency and the business benefit.
Drawings
FIG. 1 is a schematic diagram of a mechanism of formation of utility of integrated energy services;
fig. 2 is a general route schematic.
Detailed Description
The present invention will be further explained in more detail below with reference to the accompanying drawings.
As shown in fig. 1-2, the present embodiment discloses a behavior refinement portrait method for multiple users, comprising the following steps:
s1: establishing a multi-dimensional user energy feature and a multi-element user energy behavior portrait model; the multi-dimensional energy utilization characteristics of the users are characterized in that the energy supply level of the area where the users are located is comprehensively estimated based on marketing big data and multi-element user energy utilization behavior information, the multi-dimensional energy utilization characteristics of the users are extracted from a time-frequency domain by combining signal processing methods such as FFT, S conversion, HHT conversion and the like, the multi-element energy utilization requirements of industrial users are quantitatively analyzed, the fine image of the multi-element user energy utilization behavior is clear, and the development path of the energy conservation and synergy and comprehensive energy service of the users is cleared. The multi-user behavior portraits are characterized in that a characteristic optimization model is built based on an AHP-TOPSIS method as a user behavior feature quantification method and a FISHER criterion method, user categories are divided in a self-adaptive mode, high-quality features are effectively selected as portraits labels, various user behavior portraits are built, and the user behavior features and the inter-category feature comparison are displayed through a radar chart and a histogram.
The method for establishing the multi-dimensional energy utilization characteristic model of the user comprises the following steps: because of the influence of signal interference, software faults, equipment performance and other conditions, the phenomenon that the energy supply data of users are not fully collected or distorted often occurs, and therefore the data needs to be cleaned, corrected and screened at first. And then performing data mining algorithm design (comprising decision trees, neural networks, clustering, support vector machines and the like). And finally, mining and analyzing the user load data according to a designed data mining algorithm. Currently, data mining techniques mainly include: data integration management techniques, data storage management techniques, high performance computing techniques, analysis mining techniques, and the like. Under the energy internet background, the number of samples at the user side is large, the feature vector dimension is large, and if a data method is adopted independently, the effect is often not ideal. Therefore, in order to more objectively and accurately identify the sample type and improve the classification efficiency, one or more mining algorithms which can be suitable for large samples and high dimensionality must be found to perform load characteristic analysis. Traditional power load characteristic analysis is generally classified by electricity price or industry. Under the energy internet, the energy supply and utilization characteristics of individuals/groups of multiple types of users are subjected to multi-dimensional information extraction from time dimension, generic dimension and response dimension, and are subjected to fine analysis by combining big data statistical analysis methods such as clustering method, fuzzy processing and data mining, so that a flexible information processing analysis method which can adapt to different scenes, different services and different user demands is formed. Firstly, analyzing the correlation among multi-dimensional data of statistics, correlation and causality research of user energy supply data information, secondly, mining energy supply behavior and psychological characteristics of the user individuals, and establishing a multi-type energy supply characteristic set multi-dimensional mathematical matrix model of the individual energy users in a plurality of time scales of short-term, long-term, real-time and the like. And finally, based on the energy supply characteristic model of the individual energy users, establishing an energy supply aggregation characteristic model of the user group, and researching an energy supply characteristic analysis technology under the condition of 'energy supply-energy storage-energy utilization' data information sharing by taking multi-scenario application as a target of the multi-type user individuals/groups.
The large data of the user side mass data classification comprehensive energy service relates to the mass data in the whole life cycle of energy resources, production, consumption, transmission, processing conversion, storage, emission, efficiency, finance and other relevant fields. Because of the numerous data bodies and complex content, the data are suitable for being classified by the mass data for the user side:
and the comprehensive energy sources such as user side combined cooling, heating and power supply, heat pump, industrial waste heat and residual pressure and the like are utilized.
Distributed renewable energy access metering and synergy with distributed energy such as natural gas, hydrogen, etc.
Multiple types of centralized or decentralized energy storage access, such as electricity storage, heat storage, cold storage, etc.
Comprehensive energy consumption of intelligent homes, intelligent buildings, intelligent factories, etc.
Various traffic energy consumption such as charging pile, gas station, port yard head and the like.
In the performance analysis, the performance characteristics derived from the performance curve are typically used to characterize the user performance. The commonly used energy utilization characteristics can be divided into two main types, wherein one type is visual description type, and the two main types comprise daily energy, daily maximum load, daily minimum load, daily average load, daily peak-valley difference and the like; the other type is a ratio description type, which comprises a daily load rate, a daily peak Gu Chalv, a peak time energy consumption rate, a normal period energy consumption percentage and the like. The original feature set may be composed of a combination of the two types of features described above.
The maximum correlation minimum redundancy criterion is a filtered feature selection method. The core idea is to maximize the correlation between the features and the classification variables and minimize the redundancy between the features. The method is applied to the selection of the user energy characteristics, and the feature set with the strongest correlation and the lowest redundancy is obtained and used for representing the user energy characteristics. The correlation of the feature and the classification variable takes the mutual information value between the feature and the classification variable as a measurement index, and the measurement index characterizes the degree of reduction of the uncertainty of the category when the feature is known. In the solving process, in order to make each characteristic variable have more statistical significance, variable domain discretization processing is needed to be carried out on each variable, namely, the numerical sequence of each variable is converted into a probability distribution interval. The invention firstly carries out normalization processing on the characteristics, then evenly disperses the variable intervals to obtain probability distribution of each characteristic variable, and then completes mutual information calculation of each characteristic quantity and user category.
The solution of the optimal feature set S can be converted into an optimization problem and can be divided into an incremental search method and a group intelligent algorithm. However, the incremental search method may have a problem of improper first feature selection, and the swarm intelligence algorithm is prone to be locally optimized. Considering that the initial feature quantity of the user behavior is not large, the invention can obtain the global optimal solution by adopting a traversal method.
Let f i For the set membership indicating function, 0-1 coding is carried out on the set membership indicating function, f i =1 indicates that the feature is present in S, then indicates that the tag t is not present in S i . To simplify the expression, the mutual information and the correlation coefficient are respectively expressed by a i And b ij The expression is that:
and synthesizing a maximum correlation minimum redundancy criterion to obtain a formula:
obtain the product I mRMR And the maximum f vector is decoded to obtain the optimal feature set S.
The method for establishing the behavior fine portrait model for the multiple users comprises the following steps:
the first step of the representation of the behavior of multiple users is to perform a cluster analysis on the behavior data samples. The invention adopts a k-means clustering algorithm which is an unsupervised learning algorithm and can realize the rapid and efficient classification of a large-scale data set. However, the k-means algorithm has the problem that the category number k is difficult to determine, and currently, the commonly used solutions can be roughly divided into the following categories: a method of transition by a canopy algorithm; a method of constructing a decision graph based on density; a binary iteration optimizing method; a method based on cloud model theory and a method controlled by clustering effectiveness indexes. The method for controlling k value selection by using the cluster effectiveness index is to evaluate the cluster quality and determine the optimal cluster number by establishing the cluster effectiveness index, has simple idea, is not greatly influenced by sample distribution, and does not need to manually set a threshold value. The present invention thus uses this type of method to determine the k value. The invention obtains the error reduction coefficient index based on the error square sum (sum of squared error, SSE), combines the error reduction coefficient index with the contour coefficient to construct an aggregate return index, comprehensively considers the aggregation degree and the separation degree of the clusters, and realizes the automatic determination of the category number k.
First, the error sum of squares (sum of squared error, SSE) is defined as follows:
wherein: i SSE Is the sum of squares of the errors; c (C) i Is the i-th category; x is C i Sample points in (a); m is m i Is C i I.e. the average of all samples.
When the k value is smaller than the optimal cluster number, the increase of the k value greatly increases the aggregation degree of each cluster, so that the descending amplitude of the SSE value is increased sharply, and when the k value reaches the optimal cluster number, the aggregation degree return obtained by increasing the k value is reduced rapidly, and the descending amplitude of the SSE value is reduced sharply. To quantify the return of the aggregation level, an error reduction coefficient beta is defined SSE Is that
For sample point x i Assuming that it is clustered into cluster a, its contour coefficients are as follows:
wherein: i SC Is a contour coefficient; a (x) i ) For sample x i Average Euclidean distance to other sample points of cluster A; for cluster B, let D (x i B) is sample x i Average euclidean distance from all samples in cluster B, then B (x i ) I.e. sample x i Minimum of average distance to other clusters.
The average contour coefficients of the sample set can be obtained by obtaining the contour coefficients of all samples and then taking the average value:
wherein:
is the average profile coefficient; c is the total sample set; n is the total number of samples.
The error reduction coefficient reflects the cluster concentration, and the average contour coefficient reflects the cluster separation. Thus, combining the two coefficients defines an aggregate return index I Re ：
And when the aggregate return value is the largest, the clustering result is the best. Thus, by defining the aggregate return index, the automatic determination of the k value of the optimal cluster number is realized.
After the optimal k value is determined, a k-means algorithm is adopted to conduct clustering analysis on the samples, and category labels of all users are obtained.
The user behavior label consists of two parts: category labels and behavior labels. The class labels are obtained from the clustering analysis result, and the behavior labels are the high-quality characteristics obtained above. Most of user behavior data are numerical data, and the user behavior data can be converted into labels which are convenient for business personnel to understand through a certain conversion rule. The invention adopts scoring system, the full score is 10, and the energy consumption characteristics of each class of users are measured by the score of each label of each class of users. The score for each tag for each class of users is given by:
wherein: g i,j A j-th tag score for a i-th class of users;
the average value of the jth label belonging to all users in the ith class; r is (r) j,max ，r j,min The maximum and minimum values of the jth tag, respectively.
In order to enable business personnel to intuitively grasp the energy consumption characteristics of various users, the obtained energy consumption labels of the users are visually displayed, so that the energy consumption behavior portraits of different types of users are formed. The visual presentation is divided into two parts: the user behavior portraits in the class are compared with the energy consumption characteristics between the classes. The user behavior portraits in the classes show the energy characteristics of various users through radar images and the like, and the energy characteristics of the classes are compared with each other by taking a histogram as a representation form, so that the comparison of the same label quantity of various users is highlighted. The service personnel can know the commonality and individuality of the behavior of the multiple users more accurately and conveniently by combining the service personnel.
Based on marketing big data, multi-source information such as multi-user energy consumption behavior information and the like, comprehensively evaluating the energy supply level of the area where the user is located, extracting multi-dimensional characteristics of the user energy consumption, quantitatively analyzing multi-user energy consumption requirements of industrial users, and determining fine figures of the multi-user energy consumption behavior on the basis is one of key points.
The marketing big data driven user multidimensional feature calculating method comprises the following steps:
step 1: comprehensively evaluating the energy supply level of the area where the user is located according to marketing big data and multi-source information of energy consumption behavior information of multiple users; reducing data dimension based on NJW clustering method, and extracting user energy multidimensional features from water, heat, electricity, gas, oil and other energy consumption data according to wavelet transformation, S transformation, HHT and other methods; and combining the industry division of users, and quantitatively analyzing the multi-element energy consumption requirements of industrial users based on the comprehensive energy demand response theory.
Step 2: according to the energy supply data of the multiple types of user individuals/groups, carrying out multidimensional information extraction on the energy supply data from a time dimension, a generic dimension and a response dimension; based on a hierarchical fuzzy clustering method, the method performs fine analysis, starts from the energy utilization characteristics, risk preference and benefit appeal of different types of users, clarifies the development paths of energy conservation and synergy and comprehensive energy services of the users, and provides multidimensional characteristic quantization indexes of the users.
The behavior fine portrait method for multiple users comprises the following steps:
step 1: according to the multidimensional characteristics of the users, the categories of the users are adaptively divided based on an AHP-TOPSIS method, and the high-quality characteristics are effectively selected as portrait tags, so that various user behavior portraits are constructed; the method comprises the steps of analyzing the correlation among multi-dimensional data of statistics, correlation and causality research of user energy supply data information, extracting morphological characteristics of a load curve according to a differential algorithm, defining a demand response scheme type applicable to different loads, displaying comparison of user energy consumption characteristics and inter-class characteristics through a radar chart and a histogram, combing main business of a comprehensive energy service main body, researching main varieties and time-space characteristics of the main varieties participating in energy market transaction, and qualitatively and quantitatively obtaining an energy market behavior capability portrait; and establishing cost-benefit functions of different energy market main bodies, and carrying out quantitative comparison analysis on the multipotent behaviors of each main body based on the multi-main-body incomplete information non-cooperative game model.
Step 2: aiming at a user individual, mining the behavior and psychological characteristics of energy supply, and performing system modeling on a comprehensive energy system involved in the existing research to form a comprehensive energy system full life cycle modeling simulation method from a device model to system planning and then to optimization operation; analyzing comprehensive energy planning potential of a user, establishing a comprehensive energy planning model and carrying out instance simulation; on the basis, analyzing the complementary relation existing among energy sources, and establishing a multi-type energy supply characteristic set multi-dimensional characteristic model of an individual energy user in a plurality of time scales of short term, long term, real time and the like; based on the energy supply characteristic model of the individual energy users, an energy supply aggregation characteristic model of the user group is established, and an energy supply behavior fine portrait method under the condition of 'energy supply-energy storage-energy utilization' data information sharing of the multi-type user individuals/groups with multi-scene application as a target is researched.
S2: establishing a comprehensive energy service utility and value evaluation model; firstly, constructing a service architecture comprising four layers of value-added functions, a technical scheme, a service mode and a service level based on a multi-user energy-consumption fine image; the value-added function layer reflects the type of value-added energy requirements of the service, which can meet the requirements of the user, and comprises energy saving cost, low carbon cleaning and energy utilization efficiency; the technical scheme layer embodies main terminal energy supply equipment, energy management means or related technical measures adopted by the service, and the differentiated technical scheme aims at matching different energy utilization modes and energy utilization habits of users; the service mode layer comprises an investment construction mode, an operation mode and a tariff mode which are related in the implementation process of the service; the service level layer provides service time limit, energy supply equipment capacity or service expected targets of different gears so as to meet the actual demands of users with different energy consumption levels; secondly, a basic utility model and a value-added utility model are established based on a utility theory, and economic cost corresponding to the total energy of electricity, gas, heat, water, oil and the like is calculated to obtain the basic utility model; calculating the capacity of describing the value-added functions such as carbon emission, energy saving, equipment cost saving and the like, and quantifying the satisfaction degree of the user on each value-added service by combining the subjective requirements of the user to obtain a value-added utility model; and finally, obtaining a utility model of the comprehensive energy service by considering the service level, and quantifying the subjective evaluation condition of the user on the comprehensive energy service. The value evaluation is that subjective utility value connotation definition and characteristic analysis of the comprehensive energy source by multiple users are based on utility value theory, objective economic conditions of an operation mode, a tariff mode and an investment mode are considered, and the subjective factors and objective factors are combined by using an AHP and entropy weight method, so that the comprehensive energy source service utility value evaluation of the multiple users is provided.
Utility is generally used for measuring the capability of goods or services to meet consumer demands, is an important evaluation index for consumer to make consumption decisions, and based on utility theory, the utility of the integrated energy service can be defined as the degree to which the integrated energy service meets the multiple user satisfaction, namely the sum of the satisfaction degree of the user basic satisfaction degree and the value-added satisfaction degree obtained from the integrated energy service, and the model of the utility of the integrated energy service is expressed as:
U＝u+v
wherein: u is the utility of comprehensive energy service; u is the base utility; v is the value-added utility.
The comprehensive energy service has the characteristics of complex technical category, diversified service contents and differentiated service functions, and can be considered in two cases: the technical scheme relies on the comprehensive energy service of the terminal energy supply equipment to have the functions of energy supply and value-added service, and has basic utility and value-added utility; the technical scheme only comprises energy management and operation means (not related to the construction and operation of terminal energy supply equipment), and the comprehensive energy service generally has no energy supply function, so that the comprehensive energy service has only value-added utility.
Basic utility model
The comprehensive energy service with the energy supply function can partially or even completely replace the energy consumption of the user in the traditional energy service. Thus, the underlying utility characterizes how satisfactory the integrated energy service meets the user's underlying energy usage, essentially the economic cost to which the service is able to provide the user with the total amount of energy. The underlying utility of the user i purchasing the integrated energy service j can be expressed as
Wherein: u (u) i,j Basic functional utility of the comprehensive energy service j to the user i; y represents the energy category consumed by the user, and y=1, 2,3,4 represent electric energy, gas, heat energy, cold energy respectively; t represents service time limit, which is selected by the user according to the service time limit gear provided by the energy supplier, and the year;
the unit price of Y energy is purchased for a user i at the moment t through the traditional energy service, and ten thousand yuan/(kW.h); />
The available energy is the Y energy supply amount, kW, provided by service j at time t and which can be fully utilized by user i.
Value-added utility model
The value-added utility characterizes the degree of satisfaction of the comprehensive energy service to the value-added energy of the user, and is related to the value-added function capability of the service and the strong degree of satisfaction of the user to the value-added energy, and can be expressed as
Wherein: v i,j The value-added utility of the comprehensive energy service j to the user i is ten thousand yuan; a=1, 2,3, … represent the user's energy saving cost, clean low carbon, energy efficiency improvement, energy safety improvement and other value-added energy satisfaction;
the value-added function capability of the A of the service j is the degree that the service j meets the value-added satisfaction degree A of the user i, and ten thousand yuan; />
For user i's intensity for satisfaction a, +. >
The larger the user's need for satisfaction a is, the stronger; when->
When the user considers that satisfaction a is necessary satisfaction; when->
When the user does not have satisfaction a, he considers it to be available or not. />
As determined by the subjective consciousness of the user, there is semantic ambiguity,the fuzzy membership can be constructed by a scale method for depiction.
According to the difference of the value-added satisfaction degree class A, the value-added function capability
Different calculation methods are needed: the energy-saving cost capability of the service can be quantified by the difference value of total energy cost required before and after using the comprehensive energy service under the condition that the total energy consumption of various types is unchanged; the clean low-carbon capacity can be calculated according to the reduced carbon emission of the comprehensive energy service and by combining the carbon emission right trade condition of the user and the market carbon price; the energy efficiency improving capability can be characterized from the angles of energy saving, lagging productivity improving condition, advanced energy saving technology popularization and effect and the like realized by the comprehensive energy service within the service time limit; the energy utilization safety promotion can be analyzed based on the economic loss reduction value caused by the energy utilization safety accidents before and after the user uses the service, the cost-saving condition of the operation and maintenance work of the energy utilization equipment and the like.
The integrated energy service has significant commodity attributes. Users can voluntarily select comprehensive energy service products meeting the demands and benefits of the users as rational investors, and the evaluation method of the users on the comprehensive energy service is not available at present. Therefore, how to establish a comprehensive energy service utility value index system by satisfying the satisfaction of multiple users and considering the energy consumption of electric energy, fuel gas, heat energy, cold energy and the like is important.
Comprehensive energy service utility quantization model based on user energy consumption condition:
step 1: based on the fine portrait data of each energy consumption of multiple users, from the market promotion practice, a service architecture comprising four layers of value-added functions, technical schemes, service modes and service orders can be constructed, and a service framework is provided for energy suppliers. And the association relation among the four layers of the service architecture is given by taking three types of value-added functions of saving energy cost, cleaning low carbon and improving energy efficiency as an example, and the mathematical description model of the association relation is provided based on a rough set and the like.
Step 2: and establishing a basic utility model by taking the economic cost corresponding to the total energy which can be provided by the service to the user as a reference so as to represent the degree of satisfaction of the comprehensive energy service for meeting the basic energy consumption of the user. And establishing a value-added utility model by taking the value-added function capacity of the service and the satisfaction degree of the user on the value-added energy as references so as to represent the satisfaction degree of the comprehensive energy service on the value-added energy of the user. Based on the two, the total utility of purchasing the comprehensive energy service by the user is calculated, and the comprehensive energy service utility quantification model is obtained by taking electric energy, fuel gas, heat energy and cold energy as targets.
The utility value evaluation method for the comprehensive energy service of the multiple users comprises the following steps:
step 1: calculating subjective utility value of the comprehensive energy service of the multiple users according to the comprehensive energy service utility model; based on the utility value theory, from subjective utility value connotation definition and characteristic analysis of the comprehensive energy by multiple users, an objective economic condition such as an operation mode, a tariff mode, an investment mode and the like is combined to construct a multi-distance comprehensive service utility evaluation index system, and the objective value of the comprehensive energy service is quantified.
Step 2: based on the established comprehensive energy service utility value evaluation system, an expert experience judgment matrix is constructed by using a hierarchical analysis method, the weights of subjective value factors and objective value factors are calculated by combining an entropy weight method, and the subjective and objective value factors are aggregated based on a difference coefficient method to obtain the comprehensive energy service utility value of multiple users.
S3: and analyzing the comprehensive energy service requirements and the potential thereof. The analysis of the comprehensive energy service requirements and the potential thereof comprises the following steps: the connotation and extension of the user energy consumption requirements are clarified, the three types of user energy consumption demand characteristics are analyzed according to the multi-element user energy consumption behavior characteristics, the external factors of season climate and policy subsidy, the internal intrinsic characteristic factors of production activities and demand types are combined, the comprehensive energy service utility value is considered, and a comprehensive energy service demand quantification model considering multi-dimensional factors is constructed; step two: according to the comprehensive, objective, representative and acquirability evaluation principles, a comprehensive energy service potential evaluation index system is constructed, a TOPSIS function model is introduced, the comprehensive energy service potential evaluation method is researched by taking energy demand as a core guide, and dynamic analysis and accurate adjustment are carried out on potential evaluation results by considering the variability of user energy consumption behaviors and season climate.
The TOPSIS method is a method for analyzing target decision by a limited scheme in the system process, and the basic idea is that the optimal scheme has the smallest distance from a positive ideal scheme and the largest distance from a negative ideal scheme. In recent years, the method is also gradually applied to multi-index comprehensive evaluation in the economic and commercial field. The TOPSIS model basic evaluation steps are as follows:
the n evaluation indexes are comprehensively evaluated by selecting p evaluation indexes (if the p indexes have reverse indexes or moderate indexes, the reverse indexes or moderate indexes are forward-oriented), and the original data matrix is as follows:
normalizing the original data to obtain
Wherein:
the optimal value vector Z is respectively formed by the optimal value and the worst value of each index + And a worst value vector Z - 。
Wherein:
calculating the distance between each evaluation unit and the optimal value and the worst value
Calculating the relative proximity of each evaluation unit to the optimal value
Ordered by relative proximity, C i The larger the i-th evaluation unit, the closer to the optimum level.
The construction of the comprehensive energy service potential evaluation index system is key and core for realizing the scientific and accurate evaluation of the service potential. Therefore, ensuring the comprehensiveness of the coverage of the potential evaluation index and whether the index can fully characterize a certain dimension characteristic of the service potential is one of key points.
Comprehensive energy service demand quantization model considering multidimensional factors:
step 1: the meaning and extension of the energy consumption requirement of the user are clear, and the energy consumption requirement (the simple requirement on certain energy sources such as electricity, heat, gas, cold and the like) is based on the traditional energy consumption requirement, so that the comprehensive benefit of the energy source is maximized, the comprehensive utilization efficiency of the energy source is improved, and the fundamental requirement of the energy source use cost is reduced.
Step 2: according to the energy consumption behavior characteristics of the multiple users, the energy consumption demand characteristics of three types of users are defined: active, passive, and latent. The active type mainly aims at objectively using comprehensive energy service for users; the passive type is mainly that the user does not know the effect of comprehensive energy service, and early marketing of the service is needed; the potential type is mainly that the user has no clear knowledge of the user, although the user has a service requirement objectively.
Step 3: and (3) combining external uncertainty factors such as season climate, policy subsidy and the like with internal essential characteristic factors such as production activities, demand types and the like, considering the utility value of the comprehensive energy service, and constructing a comprehensive energy service demand quantification model considering multidimensional factors based on different types of energy demand characteristics.
The comprehensive energy service potential evaluation method taking energy consumption requirements as guidance comprises the following steps:
Step 1: and constructing a comprehensive energy service potential evaluation index system from the aspects of energy indexes, information indexes, benefit indexes, service indexes and the like according to the evaluation principles of comprehensiveness, objectivity, representativeness and availability.
Step 2: the TOPSIS function model is introduced, the comprehensive energy service potential evaluation index system is relied on, the energy consumption requirement is used as a core guide, and the comprehensive energy service potential evaluation method is researched, so that the reasonable depiction of the relative requirement potential of a single user on different comprehensive energy services is realized.
Step 3: in consideration of the variability of user behavior and seasonal climate, a sensitivity analysis method is applied on the basis of the demand evaluation result, a plurality of space variables and economic variables are comprehensively considered, and dynamic analysis and accurate adjustment are carried out on the potential evaluation result.
By analyzing the marketing data, the electricity utilization characteristics and the electricity utilization behaviors of the user are extracted, and then the electricity utilization image of the user is depicted, so that the foundation of subsequent research is laid. And establishing a matching relation between the service capacity of the comprehensive service and the user energy consumption condition in the time dimension and the generic dimension, and qualitatively and quantitatively predicting and evaluating the value and the utility of the comprehensive energy service to the user. And analyzing the comprehensive energy demand of the user, and definitely optimizing the comprehensive energy service by taking the comprehensive energy service cost, the self consumption capability of the user and the like as constraints. The invention can further guide users with different purchasing power and consumption level to purchase comprehensive energy service suitable for the users, and the energy suppliers specify reasonable market operation strategies to promote the development of comprehensive energy service.
The invention provides an energy feature selection and behavior portrayal method for multiple users. Automatically determining an optimal classification number by constructing an aggregate return index considering both the aggregation degree and the separation degree, and completing k-means clustering based on the optimal classification number; then, mRMR is used for constructing a user energy feature set, the effectiveness and the simplicity of the selected feature set are reflected more comprehensively and uniformly, and a traversal method is adopted to solve the mRMR, so that an optimal feature set meeting criteria is obtained; and finally, quantifying the selected features, forming a user-used behavior portrait tag, realizing visualization through a radar chart, a histogram and the like, and intuitively displaying the user-used energy characteristics. The comprehensive energy service utility value evaluation model provided by the invention is based on the degree that marketing big data drive quantized service meets the user basic energy satisfaction degree and the value-added energy satisfaction degree, so that the perceived benefit of the user on the comprehensive energy service is clear, and the user is facilitated to make a purchase decision and an energy provider to make a market operation strategy. Meanwhile, a key foundation is provided for realizing the large-scale development of comprehensive energy service. The knowledge of the traditional single energy demand spans the comprehensive energy demand to the full energy flow level. The energy consumption requirement of the user is not limited by the cognitive inertia in the aspect of the traditional energy service requirement, the availability of comprehensive energy service is fully considered, and the fundamental requirement of the energy consumption of the user is met. Secondly, on the basis of analysis of the traditional energy demand, a comprehensive energy service demand quantification model considering multi-dimensional factors is provided, and one-sided performance of the traditional energy demand analysis is compensated. And finally, providing a comprehensive energy service potential evaluation method taking energy consumption requirements as guidance, and filling the blank of the existing research in the aspect.
And selecting an optimal feature set according to the user energy data to form a user energy behavior portrait tag. The invention provides a method for evaluating the utility value of the comprehensive energy service of multiple users, which establishes a model for evaluating the utility of the comprehensive energy service based on the utility value theory, realizes quantitative evaluation of the satisfaction degree of the diversified energy consumption of the users, fills up the gap of domestic and foreign research, and promotes the large-scale development and application of the comprehensive energy service. An integrated energy service potential evaluation method taking energy consumption requirements as a guide is provided. According to the comprehensive, objective, representative and acquirability evaluation principles, a comprehensive energy service potential evaluation index system is constructed, a TOPSIS function model is introduced, the comprehensive energy service potential evaluation method is researched by taking energy demand as a core guide, and dynamic analysis and accurate adjustment are carried out on potential evaluation results by considering the variability of user energy consumption behaviors and season climate.
And selecting an optimal feature set according to the user performance data to form a user performance portrait tag, and providing a multi-user performance fine portrait method. The problem of lacking objective and effective evaluation tools in the development of comprehensive energy services in China exists, so that users generally judge the comprehensive energy services from the perspective of traditional energy supply and marketing business, the cognitive level of the users is severely restricted, and the market demand of the services is suppressed. The invention provides an evaluation model of the utility value of the comprehensive energy service of the user, helps the user to recognize the value of the service, is beneficial to improving the participation enthusiasm and the marketing efficiency of the user, and defines the marketing thinking of the service.
The present invention is not limited to the above-mentioned embodiments, and any person skilled in the art, based on the technical solution of the present invention and the concept thereof, can be replaced or changed equally within the scope of the present invention.
Claims (10)
1. The behavior fine image-drawing method for the multiple users is characterized by comprising the following steps of:
s1: establishing a multi-dimensional user energy feature and a multi-element user energy behavior portrait model;
s2: establishing a comprehensive energy service utility and value evaluation model;
s3: and analyzing the comprehensive energy service requirements and the potential thereof.
2. The multi-user behavior fine imaging method according to claim 1, wherein: the multi-dimensional energy utilization characteristics of the users are characterized in that the energy supply level of the area where the users are located is comprehensively estimated based on marketing big data and multi-element user energy utilization behavior information, the multi-dimensional energy utilization characteristics of the users are extracted from a time-frequency domain by combining signal processing methods such as FFT, S conversion, HHT conversion and the like, the multi-element energy utilization requirements of industrial users are quantitatively analyzed, the fine image of the multi-element user energy utilization behavior is clear, and the development path of the energy conservation and synergy and comprehensive energy service of the users is cleared.
3. The multi-user behavior fine imaging method according to claim 1, wherein: the multi-user behavior portraits are characterized in that a characteristic optimization model is built based on an AHP-TOPSIS method as a user behavior feature quantification method and a FISHER criterion method, user categories are divided in a self-adaptive mode, high-quality features are effectively selected as portraits labels, various user behavior portraits are built, and the user behavior features and the inter-category feature comparison are displayed through a radar chart and a histogram.
4. The multi-user behavior fine imaging method according to claim 1, wherein: the utility of the comprehensive energy service is that,
firstly, constructing a service architecture comprising four layers of value-added functions, technical schemes, service modes and service orders based on fine images of multiple users; the value-added function layer reflects the type of value-added energy requirements of the service, which can meet the requirements of the user, and comprises energy saving cost, low carbon cleaning and energy utilization efficiency; the technical scheme layer embodies main terminal energy supply equipment, energy management means or related technical measures adopted by the service, and the differentiated technical scheme aims at matching different energy utilization modes and energy utilization habits of users; the service mode layer comprises an investment construction mode, an operation mode and a tariff mode which are related in the implementation process of the service; the service level layer provides service time limit, energy supply equipment capacity or service expected targets of different gears so as to meet the actual demands of users with different energy consumption levels;
Secondly, a basic utility model and a value-added utility model are established based on a utility theory, and economic cost corresponding to the total energy of electricity, gas, heat, water, oil and the like is calculated to obtain the basic utility model; calculating the capacity of describing the value-added functions such as carbon emission, energy saving, equipment cost saving and the like, and quantifying the satisfaction degree of the user on each value-added service by combining the subjective requirements of the user to obtain a value-added utility model;
and finally, obtaining a utility model of the comprehensive energy service by considering the service level, and quantifying the subjective evaluation condition of the user on the comprehensive energy service.
5. The multi-user behavior fine imaging method according to claim 1, wherein: the value evaluation is that subjective utility value connotation definition and characteristic analysis of the comprehensive energy source by multiple users are based on utility value theory, objective economic conditions of an operation mode, a tariff mode and an investment mode are considered, and the subjective factors and objective factors are combined by using an AHP and entropy weight method, so that the comprehensive energy source service utility value evaluation of the multiple users is provided.
6. The multi-user behavior fine imaging method according to claim 1, wherein: the analysis of the comprehensive energy service requirements and the potential thereof comprises the following steps: the connotation and extension of the user energy consumption requirements are clarified, the three types of user energy consumption demand characteristics are analyzed according to the multi-element user energy consumption behavior characteristics, the external factors of season climate and policy subsidy, the internal intrinsic characteristic factors of production activities and demand types are combined, the comprehensive energy service utility value is considered, and a comprehensive energy service demand quantification model considering multi-dimensional factors is constructed; step two: according to the comprehensive, objective, representative and acquirability evaluation principles, a comprehensive energy service potential evaluation index system is constructed, a TOPSIS function model is introduced, the comprehensive energy service potential evaluation method is researched by taking energy demand as a core guide, and dynamic analysis and accurate adjustment are carried out on potential evaluation results by considering the variability of user energy consumption behaviors and season climate.
7. The multi-user behavior refinement method of claim 3, wherein: the score of each label of each type of user of the portrait label is obtained by the following formula:
wherein: g i,j A j-th tag score for a i-th class of users;
the average value of the jth label belonging to all users in the ith class; r is (r) j,max ，r j,min The maximum and minimum values of the jth tag, respectively.
8. The multi-user behavior refinement method of claim 4, wherein: the model of the comprehensive energy service utility is expressed as:
U＝u+v
wherein: u is the utility of comprehensive energy service; u is the base utility; v is the value-added utility.
9. The multi-user behavior refinement method of claim 8, wherein: the comprehensive energy service utilities include basic utilities and value added utilities.
10. The multi-user behavior refinement method of claim 9, wherein: the model of the underlying utility is expressed as:
wherein: u (u) i,j Basic functional utility of the comprehensive energy service j to the user i; y represents the energy category consumed by the user, and y=1, 2,3,4 represent electric energy, gas, heat energy, cold energy respectively; t represents service time limit, which is selected by the user according to the service time limit gear provided by the energy supplier, and the year; 
The unit price of Y energy is purchased for a user i at the moment t through the traditional energy service, and ten thousand yuan/(kW.h); />
The available energy is the Y energy supply amount, kW, provided by service j at time t and which can be fully utilized by user i.
The model of the added value utility is expressed as:
wherein: v i,j The value-added utility of the comprehensive energy service j to the user i is ten thousand yuan; a=1, 2,3, … represent the user's energy saving cost, clean low carbon, energy efficiency improvement, energy safety improvement and other value-added energy satisfaction;
the value-added function capability of the A of the service j is the degree that the service j meets the value-added satisfaction degree A of the user i, and ten thousand yuan; />
For user i's intensity for satisfaction a, +.>
The larger the user's need for satisfaction a is, the stronger; when->
When the user considers that satisfaction a is necessary satisfaction; when->
When the user does not have satisfaction a, he considers it to be available or not. />
The fuzzy membership is constructed and characterized by a scale method according to subjective consciousness of a user. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211544430.0A CN115994778A (en) | 2022-12-04 | 2022-12-04 | Behavior fine portrait method for multiple users |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211544430.0A CN115994778A (en) | 2022-12-04 | 2022-12-04 | Behavior fine portrait method for multiple users |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115994778A true CN115994778A (en) | 2023-04-21 |
Family
ID=85989652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211544430.0A Pending CN115994778A (en) | 2022-12-04 | 2022-12-04 | Behavior fine portrait method for multiple users |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115994778A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117557299A (en) * | 2024-01-11 | 2024-02-13 | 天津慧聪科技有限公司 | Marketing planning method and system based on computer assistance |
| CN118152830A (en) * | 2024-05-09 | 2024-06-07 | 国网山东省电力公司营销服务中心(计量中心) | User carbon emission characteristic image drawing method and system based on mean value clustering algorithm |
-
2022
- 2022-12-04 CN CN202211544430.0A patent/CN115994778A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117557299A (en) * | 2024-01-11 | 2024-02-13 | 天津慧聪科技有限公司 | Marketing planning method and system based on computer assistance |
| CN117557299B (en) * | 2024-01-11 | 2024-03-22 | 天津慧聪科技有限公司 | Marketing planning method and system based on computer assistance |
| CN118152830A (en) * | 2024-05-09 | 2024-06-07 | 国网山东省电力公司营销服务中心(计量中心) | User carbon emission characteristic image drawing method and system based on mean value clustering algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111582911B (en) | Friendly interactive power utilization system for multiple users and power grid | |
| Li et al. | Impact factors analysis on the probability characterized effects of time of use demand response tariffs using association rule mining method | |
| CN115994778A (en) | Behavior fine portrait method for multiple users | |
| CN107480856A (en) | Based on the sale of electricity company power customer appraisal procedure for improving similarity to ideal solution ranking method | |
| CN108805443A (en) | Comprehensive evaluation method and system for power grid performance | |
| CN103632203A (en) | Distribution network power supply area division method based on comprehensive evaluation | |
| CN113344449B (en) | Method for predicting monthly industrial water demand | |
| CN112465286A (en) | Method for evaluating service capability of electric vehicle charging network | |
| CN109241190A (en) | Electric power big data mixes computing architecture | |
| CN115330555A (en) | IES comprehensive benefit evaluation method based on digital portrait | |
| CN117172530A (en) | Enterprise operation risk assessment system and method based on data mining algorithm | |
| CN116777616A (en) | Probability density distribution-based future market new energy daily transaction decision method | |
| Wang et al. | Research on energy consumption in household sector: a comprehensive review based on bibliometric analysis | |
| CN113780686A (en) | Distributed power supply-oriented virtual power plant operation scheme optimization method | |
| Shiyun et al. | Data analysis and cloud computing of power grid infrastructure projects under the background of informatization | |
| CN117236532B (en) | Load data-based electricity consumption peak load prediction method and system | |
| CN112348066A (en) | Line uninterrupted power rating evaluation method based on gray clustering algorithm | |
| CN112308340A (en) | Power data processing method and device | |
| CN116362828B (en) | Thermal power generating unit quotation decision method based on similarity scene and particle swarm algorithm | |
| Kong et al. | User group portrait method of integrated energy system based on multi-source big data | |
| Huynh | Business intelligence in the electrical power industry | |
| Chen et al. | A Multi-Dimensional Fine Portrait of Residential Power Users’ Interactive Behaviors | |
| Li et al. | State Evaluation Method, Monitoring Method and Monitoring Analysis of Small and Medium-Sized Enterprises Based on Power Data | |
| Zhang et al. | A decision model of three—Endpoint interval method based on grey theory | |
| Belov et al. | A Model of Classification of Consumers on the Retail Electricity Market |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |