CN116596640A - Recommendation method, system, equipment and storage medium for electric power retail electric charge package - Google Patents
Recommendation method, system, equipment and storage medium for electric power retail electric charge package Download PDFInfo
- Publication number
- CN116596640A CN116596640A CN202310882913.XA CN202310882913A CN116596640A CN 116596640 A CN116596640 A CN 116596640A CN 202310882913 A CN202310882913 A CN 202310882913A CN 116596640 A CN116596640 A CN 116596640A
- Authority
- CN
- China
- Prior art keywords
- electricity
- retail
- user
- package
- electric
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 230000005611 electricity Effects 0.000 claims abstract description 351
- 239000011159 matrix material Substances 0.000 claims abstract description 31
- 238000004364 calculation method Methods 0.000 claims description 41
- 230000008569 process Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000004308 accommodation Effects 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of package recommendation, and provides a recommendation method, a system, equipment and a storage medium for an electric power retail electric charge package. Dividing users in a sample set into different user basic electricity utilization types according to electricity utilization attributes; according to the package selection, the selection times of the power retail electric charge packages are used as scoring basis, and a user preference scoring matrix of the basic electricity utilization type of the user is constructed; on the basis of the basic electricity utilization type of the user, carrying out secondary classification on the user according to the load data of the user, and establishing user subdivision categories; adjusting a user preference scoring matrix, sequencing the electric power retail electric charge packages, and selecting N high scoring packages; and determining the basic electricity utilization type of the user according to the electricity utilization attribute of the target user, calculating the distance between the target user and the clustering center of each subdivision category, selecting the subdivision category closest to the target user, and taking N high-scoring packages corresponding to the subdivision category as candidate package sets of the target user.
Description
Technical Field
The invention relates to the field of electric power marketing work electric charge package recommendation, in particular to a recommendation method, a system, equipment and a storage medium for electric power retail electric charge packages.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Compared with the traditional marketized retail business, the retail price is changed from a one-household monovalent mode to a package mode, and the current electric quantity price of the electric retail package can be divided into a fixed price type, a step price type, a market rate type and a mixed type according to a price forming mode, and more electric charge packages are further provided subsequently.
Fixed price class: the price per day for each period is fixed during the contract period.
Step price class: the initial stage of the market can set 2-4 levels of step prices according to the monthly electricity consumption (gradually transiting to time-sharing electricity consumption), and the electricity price in each level of step is fixed. The user time period electricity consumption sequentially executes the step electricity prices from the first stage according to the grading standard. The market main body is a group of households, and when the step over-gear occurs, the partial electric quantity of the over-gear is distributed according to the actual electric quantity proportion in the settlement period of each household (sub) of each household.
Market rate class: the time period electricity price floats monthly with reference to a certain reference price. The initial reference price is temporarily executed according to the monthly arithmetic average value of the price of the electricity side of the electricity spot market in time intervals, and the reference price type can be properly increased according to the needs after the market is mature.
Mixing: the time period electric quantity is divided into a fixed rate part (1-99%) and a market rate part (99-1%) according to the proportion by adopting a fixed price and market rate mixed mode.
After the electric retail package service is introduced, for a wide range of retail users, the user often has no clear idea how to select what package is most suitable for the self-electricity-consumption characteristics, facing the various retail packages on the market. The user wants to select the best suitable self situation from hundreds of packages, which is a complex intellectual engineering.
The current retail platform for each power supply only provides related retail package science popularization level instructions for the retail power supply consumers, intelligent package recommendation cannot be made according to actual power consumption conditions of the consumers, guidance of electric charge packages on power consumption behavior is difficult to be exerted, peak clipping and valley filling of a power grid cannot be really realized, and supply and demand balance pressure of the power grid is solved.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a recommendation method, a system, equipment and a storage medium for electric power retail packages, which are used for calculating and comparing electric power consumption retail packages under different electric power packages by combining similar users with objective scores according to different electric power packages, characteristics of users and actual electricity consumption conditions, assisting users to more scientifically complete the selection of the electric power retail packages, and guiding the users to adjust electricity consumption strategies on the premise of meeting the minimum spending of the users as much as possible, so as to realize peak clipping and valley filling of a power grid.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the first aspect of the invention provides a recommendation method of an electric retail electric charge package for a target user.
The recommendation method of the electric power retail electric charge package comprises the following steps:
taking the users who have used the electric power retail electric charge package as a sample set, and acquiring package selection, electricity utilization attribute and load data of each user in the sample set;
dividing users in the sample set into different user basic electricity utilization types according to electricity utilization attributes;
according to the package selection, the selection times of the power retail electric fee packages are used as scoring basis, and a power retail electric fee package user preference scoring matrix of the basic power consumption type of the user is constructed;
on the basis of the basic electricity utilization type of the user, carrying out secondary classification on the user according to the load data of the user, and establishing user subdivision categories;
adjusting the preference scoring matrix of the electric power retail electric power fare packages based on the user subdivision types, sorting the electric power retail electric power fare packages according to scores in the adjusted preference scoring matrix of the electric power retail electric power fare packages, and selecting N high-score packages;
determining a basic electricity utilization type of a user according to the electricity utilization attribute of the target user, calculating the distance between the target user and each subdivision class clustering center under the basic electricity utilization type of the user, selecting the subdivision class with the nearest distance, and taking N high-scoring packages corresponding to the subdivision class as candidate package sets of the target user;
And calculating the expected electric charges corresponding to the N high-scoring packages, and recommending the electric retail electric charge packages corresponding to the minimum value of the expected electric charges to the target user.
Further, the process of classifying the users secondarily according to the load data of the users on the basis of the basic electricity utilization type of the users by considering the load data of the sample users comprises the following steps:
processing load data of users to obtain typical daily load curves of the users;
extracting characteristics of typical daily load curves of all users to obtain a plurality of electricity utilization characteristics;
determining an initialized clustering center, and calculating the distance between the electricity utilization characteristics of each user and the clustering center;
updating the clustering center, and repeating the clustering process until the condition of clustering termination is met.
Further, the power retail electricity fee package includes: fixed price class, step electricity price class, market rate class, and mix class.
Further, when the electricity fee package of the power retail is a fixed price type, the electricity fee is calculated by:
loading daily clear electric quantity data according to the marketized metering points;
summarizing the daily clear electricity quantity data according to the retail package users to obtain the total electricity quantity of each retail package user in each period;
Summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
calculating the electricity charge of each time period of the retail package user according to the electricity price of each time period in the fixed package;
collecting the electricity quantity and electricity charge of each period of the retail package user to obtain the total daily electricity quantity and the total retail transaction electricity charge;
weighted average = total retail transaction electricity fee +.d. total daily electricity;
retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price.
Further, when the electricity retail electricity fee package is of the step electricity price type, the electricity fee calculating process is as follows:
summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
summarizing the monthly electricity quantity according to the market main body to obtain the monthly total electricity quantity of each market main body;
calculating the monthly electricity quantity proportion of the retail package users under the market subject according to the corresponding relation between the market subject and the retail package users;
calculating the electric quantity of each grade of the market main body according to the ladder electric quantity range and the moon total electric quantity of the market main body;
the electricity quantity of each grade of the market main body is apportioned according to the moon electricity quantity proportion of the retail package users;
and multiplying the electricity quantity of each grade of the retail package user by the electricity price of each grade to obtain the electricity fee of each grade.
Further, when the electric power retail electric charge package is a market rate type, the electric charge calculation process is as follows:
loading daily clear electric quantity data according to the marketized metering points;
summarizing the daily clear electricity quantity data according to the retail package users to obtain the total electricity quantity of each retail package user in each period;
summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
then according to the calculation mode of the reference price, judging the calculation of the day-ahead price or the real-time price, wherein the reference price is the arithmetic average value of the day-ahead price or the real-time price;
multiplying the electric quantity, the electricity price and the price adjustment coefficient to obtain the electricity fee of each period of the retail package user;
collecting the electricity quantity and electricity charge of each period of the retail package user to obtain the total daily electricity quantity and the total retail transaction electricity charge;
weighted average = total retail transaction electricity fee +.d. total daily electricity;
retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price.
Further, when the electric power retail electric charge package is a mixed type, the electric charge calculating process is as follows:
loading daily clear electric quantity data according to the marketized metering points;
summarizing the daily clear electricity quantity data according to the retail package users to obtain the total electricity quantity of each retail package user in each period;
Summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
calculating the actual electricity consumption of each period of the fixed package part of the retail package user according to the fixed package settlement electricity proportion;
multiplying the electric quantity of each time period of the fixed package part by the electric price to obtain the electric charge of each time period;
subtracting the electric quantity of the fixed package part from the total electric quantity of each time period to obtain the actual electric quantity of each time period of the rate class part;
calculating the reference price of each time period according to the reference price calculation mode and the price adjustment coefficient, multiplying the reference price by the electric quantity of the corresponding time period, and obtaining the electric charge of each time period;
summarizing the electric quantity and the electric charge of the fixed part and the charge rate part to obtain the total daily electricity quantity and the total retail transaction electric charge;
weighted average = total retail transaction electricity fee +.d. total daily electricity;
retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price.
A second aspect of the present invention provides a recommendation system for an electricity retail electricity fee package.
A recommendation system for an electricity retail electricity rate package, comprising:
a data acquisition module configured to: taking the users who have used the electric power retail electric charge package as a sample set, and acquiring package selection, electricity utilization attribute and load data of each user in the sample set;
A primary classification module configured to: dividing users in the sample set into different user basic electricity utilization types according to electricity utilization attributes;
a user preference scoring matrix construction module configured to: according to the package selection, the selection times of the power retail electric fee packages are used as scoring basis, and a power retail electric fee package user preference scoring matrix of the basic power consumption type of the user is constructed;
a secondary classification module configured to: on the basis of the basic electricity utilization type of the user, carrying out secondary classification on the user according to the load data of the user, and establishing user subdivision categories;
a package ordering module configured to: adjusting the preference scoring matrix of the electric power retail electric power fare packages based on the user subdivision types, sorting the electric power retail electric power fare packages according to scores in the adjusted preference scoring matrix of the electric power retail electric power fare packages, and selecting N high-score packages;
an alternative package determination module configured to: determining a basic electricity utilization type of a user according to the electricity utilization attribute of the target user, calculating the distance between the target user and each subdivision class clustering center under the basic electricity utilization type of the user, selecting the subdivision class with the nearest distance, and taking N high-scoring packages corresponding to the subdivision class as candidate package sets of the target user;
A recommendation module configured to: and calculating the expected electric charges corresponding to the N high-scoring packages, and recommending the electric retail electric charge packages corresponding to the minimum value of the expected electric charges to the target user.
A third aspect of the present invention provides a computer-readable storage medium.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps in the method of recommending an electricity retail package according to the first aspect described above.
A fourth aspect of the invention provides a computer device.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the method of recommending an electricity retail package according to the first aspect above when the program is executed.
Compared with the prior art, the invention has the beneficial effects that:
according to the electricity consumption characteristics of users (called target users in the invention), the retail electricity charge package collection which is most willing to select by the similar users is screened out, the electricity charge of the users is calculated on trial for each package in the collection, comparison is carried out according to the trial calculation result, scientific data support is provided for the selection of the retail packages by the users, the retail electricity users are assisted to fully know the electricity charge cost under various package modes before trading, the retail users are promoted to develop and produce planning according to own enterprises, reasonable electricity trading schemes are formulated, the guiding function of the electricity charge packages is effectively exerted, the electricity consumption elasticity of the users is fully excavated, the users are guided to adopt more reasonable electricity consumption strategies, and the supply and demand balance pressure of a power grid is helped to be relieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a flowchart of a recommendation method of an electricity retail electricity rate package shown in the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
It is noted that the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems according to various embodiments of the present disclosure. It should be noted that each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the logical functions specified in the various embodiments. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by special purpose hardware-based systems which perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.
Example 1
As shown in fig. 1, the present embodiment provides a recommendation method for an electricity fee package for power retail, and the present embodiment is illustrated by applying the method to a server, and it can be understood that the method may also be applied to a terminal, and may also be applied to a system and a terminal, and implemented through interaction between the terminal and the server. The server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, security services CDNs, basic cloud computing services such as big data and artificial intelligent platforms and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, etc. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the present application is not limited herein. In this embodiment, the method includes the steps of:
taking the users who have used the electric power retail electric charge package as a sample set, and acquiring package selection, electricity utilization attribute and load data of each user in the sample set;
Dividing users in the sample set into different user basic electricity utilization types according to electricity utilization attributes;
according to the package selection, the selection times of the power retail electric fee packages are used as scoring basis, and a power retail electric fee package user preference scoring matrix of the basic power consumption type of the user is constructed;
on the basis of the basic electricity utilization type of the user, carrying out secondary classification on the user according to the load data of the user, and establishing user subdivision categories;
adjusting the preference scoring matrix of the electric power retail electric power fare packages based on the user subdivision types, sorting the electric power retail electric power fare packages according to scores in the adjusted preference scoring matrix of the electric power retail electric power fare packages, and selecting N high-score packages;
determining a basic electricity utilization type of a user according to the electricity utilization attribute of the target user, calculating the distance between the target user and each subdivision class clustering center under the basic electricity utilization type of the user, selecting the subdivision class with the nearest distance, and taking N high-scoring packages corresponding to the subdivision class as candidate package sets of the target user;
and calculating the expected electric charges corresponding to the N high-scoring packages, and recommending the electric retail electric charge packages corresponding to the minimum value of the expected electric charges to the target user.
The present embodiment is described in detail below:
1. sample user primary classification
The electricity consumption properties of the power consumers are different, and the electricity consumption properties and the electricity consumption preferences are also different. In the past, power consumers have been divided into four major categories: residential electricity, general industry electricity, large industry electricity and agricultural production electricity, but only the electricity consumption performance of users is considered, and with the development of the electric market and the popularization of retail packages, the electric users should be further classified according to industry attributes so as to better describe the electricity consumption preference. According to the national economy industry electricity classification (NB/T33030-2018), the embodiment performs the following primary classification on sample users: (1) farmer, forest, pasture, fishery users; (2) mining industry users; (3) manufacturing users; (4) Electric, thermal, gas and water production and supply industry users; (5) building business users; (6) transportation, warehousing and postal service users; (7) Information transmission, software and information technology service industry users; (8) wholesale and retail customers; (9) accommodation and catering users; (10) financial industry users; (11) residential industry users; (12) lease and business service users; (13) public service and management organization users.
2. User preference scoring matrix
Post-determination for primary classificationAnd setting a certain class of users of the basic electricity utilization type, taking the selection times of the users on the electric power retail electric charge packages as a scoring basis, establishing a user preference scoring matrix, and taking the time change of the cognition and consumption preference of the users on the packages into consideration, wherein statistics of the selection times of the users on the packages take quarterly as a period. Meanwhile, as the electricity-measuring cost in the use process of the package directly influences the preference of the user to the package, the reciprocal of the electricity-measuring cost is taken as the weight of the package selection behavior, and the lower the electricity-measuring cost is, the higher the package score is, namely the user set is obtainedAnd package set->Preference scoring matrix->Element->The calculation mode of (2) is as follows:
(1)
wherein:for user->Selecting a package during a statistical period>Is>Is->The electrical cost of the package is selected a second time.
3. Sample user secondary classification
Based on the basic power utilization category, the load data of the users are considered, and the sample users in the sub-set are secondarily classified by adopting a clustering method. The embodiment adopts a k-means clustering algorithm, and the specific flow is as follows:
(3-1) data preprocessing
Firstly, processing user load data to obtain a typical daily load curve of each user, and secondly, extracting characteristics of the user load curve to realize data dimension reduction, wherein the power utilization characteristics extracted by the embodiment comprise:
(3-1-1) daily average load;
(3-1-2) load factor: average load to maximum load ratio;
(3-1-3) the maximum number of hours of use: ratio of total power consumption to maximum load;
(3-1-4) peak Gu Chalv: the ratio of the difference between the maximum and minimum loads to the maximum load;
(3-1-5) peak load rate: peak period load mean to daily average load ratio, wherein peak period refers to 08:00-11:00, 18:00-21:00;
(3-1-6) flat load rate: average period load mean to daily average load ratio, wherein average period refers to 06:00-08:00, 11:00-18:00, 21:00-22:00;
(3-1-7) valley load rate: the ratio of valley period load mean to daily average load, wherein valley period refers to 22:00-24:00, 00:00-06:00.
(3-2) initialization stage: setting the cluster class number toRandomly select->Individual users, initialize them as cluster center +.>Initializing the error threshold to +.>。
(3-3) classification stage: assigning each user to the cluster closest theretoThe heart belongs to the category. In this step, the horse-type distance is used as the distance measure. Wherein for a user vector characterized by a power consumption characteristicAnd clustering center vector->（/>Number of electrical features), the mahalanobis distance of the two is expressed as:
(2)
Wherein:is->Individual user vectors and->Inverse of covariance matrix between different dimensions of each cluster center vector.
The covariance matrix is calculated as follows:
(3-3-1) pairThe method comprises the following steps:
(3)
wherein:is->Average of the individual dimensions.
(3-3-2) calculating covariance between dimensions, the firstCovariance between dimensions is expressed as:
(4)
(3-3-3) obtaining a covariance matrix:
(5)
(3-4) update stage: updating cluster centersThe new cluster center is the average value of all the users' power consumption characteristics in the class, and is marked as +.>。
(3-5) ending stage: calculating a cluster error DB indexWhen->Let->And jumping to step (3); if->And ending the clustering. The DB index is calculated in the following manner:
(6)
wherein:、/>respectively is a kind->、/>Average distance within.
The mahalanobis distance not only considers the correlation between the features, but also eliminates the difference of the dimensions of different features through the covariance matrix, so that the data does not need to be standardized when the data preprocessing in the step (3-1) is performed.
4、High-scoring power retail electricity fee package acquisition
Based on the user preference scoring matrix, sorting packages selected by each user according to the scoring level, and taking the packages before taking the packages And one as the user's top scoring package. After finishing the user's secondary classification +.>Counting the selection times of each package in the top scoring packages and sorting the packages from high to low according to the times, and taking the previous +.>And the power retail electric charge package is used as the high-scoring power retail electric charge package of the user.
5. Target userIndividual alternative package acquisition
Firstly, carrying out electricity utilization attribute judgment and load feature extraction on a target user, after primary classification is obtained, calculating the mahalanobis distance between the target user and each cluster center of a subdivision class under the basic electricity utilization type, and determining the class to which the cluster center closest to the target user belongsA high-score power retail electric charge package serving as the target userAlternative package sets.
6. Target user expected electricity charge calculation
Respectively calculating according to the target user load dataThe expected electricity fee of the target user under each recommended package is calculated in the following manner.
(6-1) fixed price class
The fixed price retail packages or retail contracts have fixed price per day in each period, and are divided into full-period unified price, time-period price packages and month packages, and whichever one of the fixed price retail packages or retail contracts has specified effective month and time-period electricity prices. The specific calculation steps are as follows:
(6-1-1) loading daily electricity clearing amount data according to the marketized metering points;
(6-1-2) summarizing the daily electricity consumption according to the retail package users to obtain the total electricity consumption of each retail package user in each period;
(6-1-3) summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
(6-1-4) calculating the electricity charge of each period of the retail package user according to the electricity price of each period of the fixed package;
(6-1-5) summarizing the electricity quantity and the electricity charge of each period of the retail package user to obtain the total daily electricity quantity and the total retail transaction electricity charge;
(6-1-6) weighted average price = total retail transaction electricity fee/(total daily electricity amount);
(6-1-7) retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price;
(6-2) step-by-step electricity prices
In the initial stage of retail market construction, setting 2-4 levels of step prices according to the monthly electricity consumption, wherein the price in each step is fixed, and the electricity consumption in each period sequentially executes the step prices from the first step according to the step division standard. After the retail market matures, preliminary transition is made to time-division ladder electricity quantity according to time period. The specific calculation steps are as follows:
(6-2-1) summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
(6-2-2) summarizing the monthly electricity quantity according to the market subjects to obtain the monthly electricity quantity of each market subject;
(6-2-3) calculating the monthly electricity proportion of the retail package users under the market subject according to the corresponding relation between the market subject and the retail package users;
(6-2-4) calculating the electric quantity of each grade of the market subject according to the ladder electric quantity range and the total moon electric quantity of the market subject;
(6-2-5) apportioning the electricity of each grade of the market subject according to the lunar electricity proportion of the retail package users;
(6-2-6) the electricity quantity of each grade of the retail package user multiplied by the electricity price of each grade to obtain the electricity fee of each grade. (each grade of electric charge stores a total electric charge and an electric charge detail)
(6-3) market rate class
The electric quantity price of each period of the market rate class calculation method floats according to months by referring to a certain reference price, and the daily or real-time price month arithmetic average value at the spot market user side is used as the reference price in the initial stage of retail market construction. The specific calculation steps are as follows:
(6-3-1) loading daily electricity consumption data according to the marketized metering points;
(6-3-2) summarizing the daily electricity consumption according to the retail package users to obtain the total electricity consumption of each retail package user in each period;
(6-3-3) summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
(6-3-4) then judging whether the price is calculated according to the day-ahead price or the real-time price according to the calculation mode of the reference price, wherein the reference price is the arithmetic average value of the day-ahead price or the real-time price; (each time period has corresponding reference price, the arithmetic average value in one month is calculated, the calculation is completed firstly when the archives are recorded, the arithmetic is directly carried out by taking the arithmetic average value, and the performance of wasting the calculation is avoided when the calculation is repeated)
The real-time settlement price is a reference price: zt=kx Pt. real-time averaging
Zt: retail price;
k: price adjustment coefficients;
pt. real-time average: the spot market settles the arithmetic average value of the price month in real time.
The day-ahead settlement price is a reference price: zt=kx Pt. real-time averaging
Zt: retail price;
k: price adjustment coefficients;
pt. real-time average: the daily settlement price month arithmetic average value of the spot market.
(6-3-5) multiplying the electric quantity, the electricity price and the price adjustment coefficient to obtain the electricity fee of each period of the retail package user;
(6-3-6) summarizing the electricity quantity and the electricity charge of each period of the retail package user to obtain the total daily electricity quantity and the total retail transaction electricity charge;
(6-3-7) weighted average price = total retail transaction electricity fee/(total daily electricity amount);
(6-3-8) retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price;
(6-4) Mixed class
The mixed package is characterized in that the electric quantity proportion of part of fixed price class and market rate class is contracted in the package, and the weighted average price of the two parts is the package settlement price. Wherein the mixed package is firstly contracted with a fixed package electric quantity proportion (more than 1% and less than 99%), and the rest proportion is settled according to the market rate. The specific calculation steps are as follows:
(6-4-1) loading daily electricity consumption data according to the marketized metering points;
(6-4-2) summarizing the daily electricity consumption according to the retail package users to obtain the total electricity consumption of each retail package user in each period;
(6-4-3) summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
(6-4-4) calculating the actual electricity consumption of each period of the fixed package part of the retail package user according to the fixed package settlement electricity quantity proportion;
(6-4-5) multiplying the electricity quantity of each time period of the fixed package part by the electricity price to obtain the electricity fee of each time period;
(6-4-6) subtracting the electric quantity of the fixed package part from the total electric quantity of each time period to obtain the actual electric quantity of each time period of the rate class part;
(6-4-7) calculating the reference price of each time period according to the reference price calculation mode and the price adjustment coefficient, multiplying the reference price by the electric quantity of the corresponding time period, and obtaining the electric charge of each time period;
(6-4-8) summarizing the electric quantity and the electric charge of the fixed part and the rate part to obtain total daily electricity quantity and total retail transaction electric charge;
(6-4-9) weighted average price = total retail transaction electricity fee/(total daily electricity amount);
(6-4-10) retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price.
User X is now planning to participate in a marketized retail market transaction at some 35 kv. And the electric power cost of various packages is calculated according to the electric quantity information of 2 months, so that proper electric power selling companies and packages can be selected. The user settles the electricity in 2 months for 63278990 kilowatt hours, and the electricity in each period of the whole month is shown in table 1. Note that: the case is provided with the difference between the total daily electricity quantity and the monthly electricity quantity, so that the actual fee calculation process can be understood conveniently.
TABLE 1 user X2 month day purge
Currently, the electricity-selling company provides 5 kinds of packages, which are respectively: full cycle fixed price packages (as shown in table 2), monthly and time-division fixed price packages (as shown in table 3), step price packages (as shown in table 4), market rate packages (as shown in table 5), and mixed packages. For simplifying the calculation, various packages are not provided with additional conditions such as deviation assessment, illegal deposit and the like.
Table 2 full period fixed price details
Table 3 fixed price details in month and time slots
Table 4 step price details
The rate package is divided into a day-ahead price and a real-time price, and the calculation processes of the two modes are similar, but the price formation modes are different. To simplify the calculation, the present case is illustrated with real-time prices as an example.
Table 5 rate class price details
The mixed package provided by the electricity selling company is formed by combining a monthly and time-sharing fixed-price package and a rate package, wherein 80% of monthly electricity quantity is used for executing the monthly and time-sharing fixed-price package price, and the rest part is used for executing the rate package price.
Because the calculation modes of the basic electric charge and the power adjustment electric charge are not influenced by the market transaction modes, the basic electric charge and the power adjustment electric charge are not considered in the measurement case, and only deduction calculation is carried out on each package electric charge.
If the user X and the A electricity selling company sign a full-period unified price package retail package, the settlement electricity price of each period of the checking day is 0.3758 yuan/kilowatt-hour, and finally the retail transaction electricity fee is 23780244.44 yuan. The calculation process is as follows:
(1) First, the daily electricity clearing rate of the user X in all the time periods of the month is calculated, wherein the daily electricity clearing rate of the user X in all the time periods of the month is=the daily electricity clearing amount of the user X the package price of the user X in all the time periods.
TABLE 6 user X time-of-day electric charge details for each time period of full month
(2) And (5) collecting the electricity quantity and the electricity charge of each time period of the user to obtain the total daily electricity quantity and the total retail transaction electricity charge. As can be seen from the calculation in table 6, the total electric quantity 63282926 at the time of day clearing and the total electric charge 23781723.60 at the time of day clearing.
(3) And calculating the month settlement weighted average price according to the daily clear time-sharing total electric charge and the daily clear total electric quantity. I.e. monthly settlement weighted average = daily total electricity charge/daily total electricity charge = 23781723.60/63282926 = 0.3758.
(4) Retail transaction electricity fee = monthly total electricity amount x monthly settlement weighted average price = 63278990 x 0.3758 = 23780244.44
If the user X and the A electricity selling company sign a full-period unified price package retail package, the retail transaction electricity fee 23386142.89 yuan is finally calculated. The calculation process is as follows:
(1) Firstly, acquiring package price of each period of 2 months from package information, and calculating the daily electricity clearing rate of each period of the whole month of the user X, wherein the daily electricity clearing rate of each period of the whole month is=daily electricity clearing amount of each period of the whole month×package price of each period.
TABLE 7 details of daily clear electric charge for user X throughout the month
(2) And (5) collecting the electricity quantity and the electricity charge of each time period of the user to obtain the total daily electricity quantity and the total retail transaction electricity charge. As can be seen from the calculation in table 7, the total electric quantity 63282926 at the time of day clearing and the total electric charge 23387575.15 at the time of day clearing.
(3) And calculating the month settlement weighted average price according to the daily clear time-sharing total electric charge and the daily clear total electric quantity. I.e. monthly settlement weighted average = daily total electricity charge/daily total electricity charge = 23387575.15/63282926 = 0.369572.
(4) Retail transaction electricity fee = monthly total electricity amount x monthly settlement weighted average price = 63278990 x 0.369572 = 23386142.89
As can be seen from the ladder package, the package executes two-gear electricity prices, and the ladder first gear and the ladder second gear execute full-period fixed prices, wherein the electric quantity of the first gear is 50000000. If the user X and the A electricity selling company sign a full-period unified price package retail package, the price details of the step electricity fees of the A electricity selling company are shown in a table 8, and finally 23548034.34 yuan of retail transaction electricity fees are calculated. The calculation process is as follows:
(1) And comparing the lunar junction electric quantity with the step gear, wherein the lunar junction electric quantity 63278990 is larger than the first gear 50000000. It can be calculated that: first gear step charge=50000000, second gear step charge= 63278990-50000000 = 13278990.
Table 8A price details of step charges of electricity for electricity-selling companies
(2) And respectively calculating first and second grade step electricity fees according to the package step electricity price.
First step electricity charge=first step electricity quantity x first step electricity price=50000000 x 0.3685 = 18425000
Second-gear step electricity charge=second-gear step electricity quantity×second-gear step electricity price= 13278990 × 0.3858 = 5123034.34
(3) Calculating retail package transaction electricity fee=first step electricity fee+second step electricity fee= 23548034.34
To facilitate subsequent calculation of the quote, the rate package price shows a real-time arithmetic average price for each period of the whole month. In practice, the arithmetic average price is obtained by calculating the arithmetic average of 24 real-time prices per day, and the calculation process will not be described in detail herein, if the user X and the a electric company sign up for a rate type retail package, the retail transaction electric charge 34790915.26 yuan is finally calculated. The calculation process is as follows:
(1) Firstly, calculating the settlement price of each period according to the arithmetic real-time price average price of 2 months and the price adjustment coefficient. Settlement price = 2 months month arithmetic real-time price average price x price adjustment coefficient. Taking 0100 period as an example, when the real-time price average of 2 months is 0.350742 and the price adjustment coefficient is 1.4, the settlement price= 0.350742 ×1.4= 0.491039. And so on to calculate the settlement prices for other periods.
TABLE 9 details of daily clear electric charge for user X throughout the month for each period
(2) And calculating the daily clear electricity charge of each period according to the settlement price and the daily clear electricity quantity of each period, and summarizing the daily clear electricity charge of 24 points. The total daily electricity charge was 34793105.2 yuan as calculated in table 9.
(3) And calculating the month settlement weighted average price according to the total daily electricity clearing quantity and the total daily electricity clearing charge. I.e. monthly settlement weighted average = daily total electricity charge/daily total electricity charge = 34793105.2/63282926 = 0.549802.
(4) Retail transaction electricity fee = monthly total electricity amount x monthly settlement weighted average price = 63278990 x 0.549802 = 34790915.26
The mixed package provided by the electricity selling company is formed by combining a monthly and time-period fixed-price package and a rate package, wherein 80% of monthly electricity quantity is used for executing the monthly and time-period fixed-price package, and the rest is used for executing the rate package. If the user X and the A electricity selling company sign a full-period unified price package retail package, the retail transaction electricity fee 25667097.37 yuan is finally calculated. The calculation process is as follows:
(1) Firstly, according to the package contract proportion of 80%, calculating the total daily clearing electric quantity of the package with fixed price and the daily clearing electric quantity of each time period, removing the fixed package electric quantity from the total daily clearing electric quantity of each time period, and obtaining the daily clearing electric quantity of each time period of the rate package. The specific calculation process and the results are shown in Table 10:
table 10 user X rate package daily clear quantity details of each time period
(2) And calculating the daily electricity clearing charge of each time period of the fixed package part according to the daily electricity clearing quantity of each time period of the fixed package and the price of the fixed package. From Table 11, it can be seen that the total electric charge of the fixed package solar heat collector is 18710060.21 yuan.
TABLE 11 user X fixed package part daily clear electric charge details for each time period
(3) And calculating the daily electricity clearing charge of each time period of the rate package part according to the daily electricity clearing quantity of each time period of the rate package, the price adjustment coefficient and the settlement price of each time period. From Table 12, it can be seen that the fixed package daily clear total electricity charge is 6958622.03 yuan.
Table 12 user X rate plan part daily clear electric charge details of each time period
(4) Through the two steps, the total daily electricity clearing rate of the mixed package=the daily electricity clearing rate of the fixed package+the daily electricity clearing rate of the rate package=18710060.21+6958022.03= 25668682.24 yuan can be calculated.
(5) And calculating the month settlement weighted average price according to the daily clear time-sharing total electric charge and the daily clear total electric quantity. Namely, monthly settlement weighted average price=total electricity charge when daily clearing/total electricity quantity when daily clearing= 25668682.24/63282926 = 0.405618
(6) Retail transaction electricity fee = monthly total electricity amount x monthly settlement weighted average price = 63278990 x 0.405618 = 25667097.37
Through the above measurement, the retail transaction fee for the user X2 month power under various packages is shown in table 13. It can be seen that the different types of package choices have significant cost expenditure differences. Wherein, the highest fee is the rate set meal, and the lowest fee is the monthly and time-sharing price set meal. Thus, from the retail transaction electricity rates of the user alone, it is recommended to select a monthly time period price package for the electricity-selling company.
Table 13 user X various packages electric charge trial calculation results contrast
Example two
The embodiment provides a recommendation system for electric power retail electric charge packages.
A recommendation system for an electricity retail electricity rate package, comprising:
a data acquisition module configured to: taking the users who have used the electric power retail electric charge package as a sample set, and acquiring package selection, electricity utilization attribute and load data of each user in the sample set;
a primary classification module configured to: dividing users in the sample set into different user basic electricity utilization types according to electricity utilization attributes;
a user preference scoring matrix construction module configured to: according to the package selection, the selection times of the power retail electric fee packages are used as scoring basis, and a power retail electric fee package user preference scoring matrix of the basic power consumption type of the user is constructed;
a secondary classification module configured to: on the basis of the basic electricity utilization type of the user, carrying out secondary classification on the user according to the load data of the user, and establishing user subdivision categories;
a package ordering module configured to: adjusting the preference scoring matrix of the electric power retail electric power fare packages based on the user subdivision types, sorting the electric power retail electric power fare packages according to scores in the adjusted preference scoring matrix of the electric power retail electric power fare packages, and selecting N high-score packages;
An alternative package determination module configured to: determining a basic electricity utilization type of a user according to the electricity utilization attribute of the target user, calculating the distance between the target user and each subdivision class clustering center under the basic electricity utilization type of the user, selecting the subdivision class with the nearest distance, and taking N high-scoring packages corresponding to the subdivision class as candidate package sets of the target user;
a recommendation module configured to: and calculating the expected electric charges corresponding to the N high-scoring packages, and recommending the electric retail electric charge packages corresponding to the minimum value of the expected electric charges to the target user.
It should be noted that, the data acquisition module, the primary classification module, the user preference scoring matrix construction module, the secondary classification module, the package ordering module, the alternative package determining module, and the recommendation module are the same as the examples and application scenarios implemented by the steps in the first embodiment, but are not limited to those disclosed in the first embodiment. It should be noted that the modules described above may be implemented as part of a system in a computer system, such as a set of computer-executable instructions.
Example III
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the recommendation method for electric power retail packages as described in the above embodiment one.
Example IV
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to implement the steps in the recommendation method for the electric retail electric fare package according to the embodiment.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random access Memory (Random AccessMemory, RAM), or the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The recommendation method of the electric power retail electric charge package is characterized by comprising the following steps:
taking the users who have used the electric power retail electric charge package as a sample set, and acquiring package selection, electricity utilization attribute and load data of each user in the sample set;
dividing users in the sample set into different user basic electricity utilization types according to electricity utilization attributes;
according to the package selection, the selection times of the power retail electric fee packages are used as scoring basis, and a power retail electric fee package user preference scoring matrix of the basic power consumption type of the user is constructed;
on the basis of the basic electricity utilization type of the user, carrying out secondary classification on the user according to the load data of the user, and establishing user subdivision categories;
adjusting the preference scoring matrix of the electric power retail electric power fare packages based on the user subdivision types, sorting the electric power retail electric power fare packages according to scores in the adjusted preference scoring matrix of the electric power retail electric power fare packages, and selecting N high-score packages;
Determining a basic electricity utilization type of a user according to the electricity utilization attribute of the target user, calculating the distance between the target user and each subdivision class clustering center under the basic electricity utilization type of the user, selecting the subdivision class with the nearest distance, and taking N high-scoring packages corresponding to the subdivision class as candidate package sets of the target user;
and calculating the expected electric charges corresponding to the N high-scoring packages, and recommending the electric retail electric charge packages corresponding to the minimum value of the expected electric charges to the target user.
2. The recommendation method of electric power retail electric power fare packages according to claim 1, wherein the process of secondarily classifying the users according to the load data of the users based on the basic electricity type of the users comprises:
processing load data of users to obtain typical daily load curves of the users;
extracting characteristics of typical daily load curves of all users to obtain a plurality of electricity utilization characteristics;
determining an initialized clustering center, and calculating the distance between the electricity utilization characteristics of each user and the clustering center;
updating the clustering center, and repeating the clustering process until the condition of clustering termination is met.
3. The recommendation method for an electricity retail electricity fee package according to claim 1, wherein the electricity retail electricity fee package comprises: fixed price class, step electricity price class, market rate class, and mix class.
4. The recommendation method for electric power retail electric power rate packages according to claim 3, wherein when the packages are of a fixed price type, the electric power rate calculation process is as follows:
loading daily clear electric quantity data according to the marketized metering points;
summarizing the daily clear electricity quantity data according to the retail package users to obtain the total electricity quantity of each retail package user in each period;
summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
calculating the electricity charge of each time period of the retail package user according to the electricity price of each time period in the fixed package;
collecting the electricity quantity and electricity charge of each period of the retail package user to obtain the total daily electricity quantity and the total retail transaction electricity charge;
weighted average = total retail transaction electricity fee +.d. total daily electricity;
retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price.
5. The recommendation method for electric power retail electric power rate packages according to claim 3, wherein when the packages are of the step electricity rate type, the electric power rate calculation process is as follows:
summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
summarizing the monthly electricity quantity according to the market main body to obtain the monthly total electricity quantity of each market main body;
Calculating the monthly electricity quantity proportion of the retail package users under the market subject according to the corresponding relation between the market subject and the retail package users;
calculating the electric quantity of each grade of the market main body according to the ladder electric quantity range and the moon total electric quantity of the market main body;
the electricity quantity of each grade of the market main body is apportioned according to the moon electricity quantity proportion of the retail package users;
and multiplying the electricity quantity of each grade of the retail package user by the electricity price of each grade to obtain the electricity fee of each grade.
6. The recommendation method for electric power retail electric power rate packages according to claim 3, wherein when the packages are market rate categories, the electric power rate calculation process is as follows:
loading daily clear electric quantity data according to the marketized metering points;
summarizing the daily clear electricity quantity data according to the retail package users to obtain the total electricity quantity of each retail package user in each period;
summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
then according to the calculation mode of the reference price, judging the calculation of the day-ahead price or the real-time price, wherein the reference price is the arithmetic average value of the day-ahead price or the real-time price;
multiplying the electric quantity, the electricity price and the price adjustment coefficient to obtain the electricity fee of each period of the retail package user;
Collecting the electricity quantity and electricity charge of each period of the retail package user to obtain the total daily electricity quantity and the total retail transaction electricity charge;
weighted average = total retail transaction electricity fee +.d. total daily electricity;
retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price.
7. The recommendation method for electric power retail electric charge packages according to claim 3, wherein when the packages are of mixed type, the electric charge calculation process is as follows:
loading daily clear electric quantity data according to the marketized metering points;
summarizing the daily clear electricity quantity data according to the retail package users to obtain the total electricity quantity of each retail package user in each period;
summarizing the monthly electricity quantity according to the retail package users to obtain the monthly electricity quantity of each retail package user;
calculating the actual electricity consumption of each period of the fixed package part of the retail package user according to the fixed package settlement electricity proportion;
multiplying the electric quantity of each time period of the fixed package part by the electric price to obtain the electric charge of each time period;
subtracting the electric quantity of the fixed package part from the total electric quantity of each time period to obtain the actual electric quantity of each time period of the rate class part;
calculating the reference price of each time period according to the reference price calculation mode and the price adjustment coefficient, multiplying the reference price by the electric quantity of the corresponding time period, and obtaining the electric charge of each time period;
Summarizing the electric quantity and the electric charge of the fixed part and the charge rate part to obtain the total daily electricity quantity and the total retail transaction electric charge;
weighted average = total retail transaction electricity fee +.d. total daily electricity;
retail package user retail transaction electricity fee = monthly total electricity amount x weighted average price.
8. Recommendation system of electric power retail electric charge package, characterized by comprising:
a data acquisition module configured to: taking the users who have used the electric power retail electric charge package as a sample set, and acquiring package selection, electricity utilization attribute and load data of each user in the sample set;
a primary classification module configured to: dividing users in the sample set into different user basic electricity utilization types according to electricity utilization attributes;
a user preference scoring matrix construction module configured to: according to the package selection, the selection times of the power retail electric fee packages are used as scoring basis, and a power retail electric fee package user preference scoring matrix of the basic power consumption type of the user is constructed;
a secondary classification module configured to: on the basis of the basic electricity utilization type of the user, carrying out secondary classification on the user according to the load data of the user, and establishing user subdivision categories;
a package ordering module configured to: adjusting the preference scoring matrix of the electric power retail electric power fare packages based on the user subdivision types, sorting the electric power retail electric power fare packages according to scores in the adjusted preference scoring matrix of the electric power retail electric power fare packages, and selecting N high-score packages;
An alternative package determination module configured to: determining a basic electricity utilization type of a user according to the electricity utilization attribute of the target user, calculating the distance between the target user and each subdivision class clustering center under the basic electricity utilization type of the user, selecting the subdivision class with the nearest distance, and taking N high-scoring packages corresponding to the subdivision class as candidate package sets of the target user;
a recommendation module configured to: and calculating the expected electric charges corresponding to the N high-scoring packages, and recommending the electric retail electric charge packages corresponding to the minimum value of the expected electric charges to the target user.
9. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the recommendation method for an electricity retail package according to any one of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method of recommending an electricity retail package according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310882913.XA CN116596640B (en) | 2023-07-19 | 2023-07-19 | Recommendation method, system, equipment and storage medium for electric power retail electric charge package |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310882913.XA CN116596640B (en) | 2023-07-19 | 2023-07-19 | Recommendation method, system, equipment and storage medium for electric power retail electric charge package |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116596640A true CN116596640A (en) | 2023-08-15 |
| CN116596640B CN116596640B (en) | 2024-06-21 |
Family
ID=87594156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310882913.XA Active CN116596640B (en) | 2023-07-19 | 2023-07-19 | Recommendation method, system, equipment and storage medium for electric power retail electric charge package |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596640B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117252636A (en) * | 2023-11-17 | 2023-12-19 | 国网山东省电力公司营销服务中心(计量中心) | Electricity fee package type optimization method and system based on user |
| CN117521898A (en) * | 2023-11-10 | 2024-02-06 | 国网山东省电力公司营销服务中心(计量中心) | Electric charge settlement optimization method and system based on association analysis |
Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013105215A (en) * | 2011-11-10 | 2013-05-30 | Ntt Docomo Inc | Recommendation information generation device, recommendation information generation method, and recommendation information generation program |
| CN103942606A (en) * | 2014-03-13 | 2014-07-23 | 国家电网公司 | Residential electricity consumption customer segmentation method based on fruit fly intelligent optimization algorithm |
| CN104463637A (en) * | 2014-12-23 | 2015-03-25 | 北京石油化工学院 | Commodity recommendation method and device based on electronic business platform and server |
| KR20160064447A (en) * | 2014-11-28 | 2016-06-08 | 이종찬 | A recommendation method for new users by using preference prediction based on collaborative filtering algorithm |
| CN108563690A (en) * | 2018-03-15 | 2018-09-21 | 中山大学 | A kind of collaborative filtering recommending method based on object-oriented cluster |
| US20180293674A1 (en) * | 2017-04-11 | 2018-10-11 | Erik Joseph Bartone | System and Method for Retail Consumers to Purchase Dynamically Priced Wholesale Electricity Generation Services |
| US20180330192A1 (en) * | 2017-05-15 | 2018-11-15 | International Business Machines Corporation | Load-Balancing Training of Recommender System for Heterogeneous Systems |
| CN108830460A (en) * | 2018-05-23 | 2018-11-16 | 重庆邮电大学 | A method of recommender system Deta sparseness is alleviated based on substep dynamic filling |
| CN110210914A (en) * | 2019-06-17 | 2019-09-06 | 华北电力大学 | Residential electricity consumption demand response method based on intelligent recommendation |
| CN111798336A (en) * | 2020-07-09 | 2020-10-20 | 山东大学 | Typical user-based resident electricity fee package recommendation method and system |
| CN112017069A (en) * | 2020-07-08 | 2020-12-01 | 广东电力交易中心有限责任公司 | Power market electricity price package recommendation method and terminal based on electricity utilization characteristics |
| US20210150378A1 (en) * | 2018-04-12 | 2021-05-20 | Boe Technology Group Co., Ltd. | Recommendation method, recommendation apparatus, recommendation device, recommendation system and storage medium |
| CN112950322A (en) * | 2021-03-11 | 2021-06-11 | 昆明电力交易中心有限责任公司 | Power retail package recommendation method and system based on collaborative filtering optimization |
| CN112967108A (en) * | 2021-03-09 | 2021-06-15 | 昆明电力交易中心有限责任公司 | BP-ANN-based electric power retail package searching and sequencing simulation system and method |
| CN113538041A (en) * | 2021-06-29 | 2021-10-22 | 广东电力交易中心有限责任公司 | Power package recommendation method and device based on load curve clustering analysis |
| CN113538093A (en) * | 2021-07-16 | 2021-10-22 | 四川大学 | High-quality power package recommendation method based on improved collaborative filtering algorithm |
| CN113947444A (en) * | 2021-11-17 | 2022-01-18 | 浙江理工大学 | Electricity selling package recommending method considering multi-granularity hesitation fuzzy set and incomplete weight |
| CN113962414A (en) * | 2020-07-02 | 2022-01-21 | 国网能源研究院有限公司 | Method and system for quantifying retail electricity price package of industrial and commercial users |
| CN114037161A (en) * | 2021-11-10 | 2022-02-11 | 国网四川省电力公司经济技术研究院 | Modeling method of retail electricity price package optimization model for maximizing social welfare |
| CN114969520A (en) * | 2022-05-16 | 2022-08-30 | 重庆大学 | Commodity recommendation method, system and equipment based on label information and commodity attributes |
| CN115578163A (en) * | 2022-10-18 | 2023-01-06 | 李倩文 | Personalized pushing method and system for combined commodity information |
| CN115994807A (en) * | 2021-10-15 | 2023-04-21 | 第四范式（北京）技术有限公司 | Material recommendation method, device and system |
| CN115994271A (en) * | 2023-01-12 | 2023-04-21 | 武汉大学 | Recommendation method of psychological assessment |
| CN116127201A (en) * | 2023-02-27 | 2023-05-16 | 安徽大学 | Large-scale user recommendation method based on evolutionary multitasking |
| CN116187808A (en) * | 2022-12-13 | 2023-05-30 | 华电电力科学研究院有限公司 | Electric power package recommendation method based on virtual power plant user-package label portrait |
-
2023
- 2023-07-19 CN CN202310882913.XA patent/CN116596640B/en active Active
Patent Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013105215A (en) * | 2011-11-10 | 2013-05-30 | Ntt Docomo Inc | Recommendation information generation device, recommendation information generation method, and recommendation information generation program |
| CN103942606A (en) * | 2014-03-13 | 2014-07-23 | 国家电网公司 | Residential electricity consumption customer segmentation method based on fruit fly intelligent optimization algorithm |
| KR20160064447A (en) * | 2014-11-28 | 2016-06-08 | 이종찬 | A recommendation method for new users by using preference prediction based on collaborative filtering algorithm |
| CN104463637A (en) * | 2014-12-23 | 2015-03-25 | 北京石油化工学院 | Commodity recommendation method and device based on electronic business platform and server |
| US20180293674A1 (en) * | 2017-04-11 | 2018-10-11 | Erik Joseph Bartone | System and Method for Retail Consumers to Purchase Dynamically Priced Wholesale Electricity Generation Services |
| US20180330192A1 (en) * | 2017-05-15 | 2018-11-15 | International Business Machines Corporation | Load-Balancing Training of Recommender System for Heterogeneous Systems |
| CN108563690A (en) * | 2018-03-15 | 2018-09-21 | 中山大学 | A kind of collaborative filtering recommending method based on object-oriented cluster |
| US20210150378A1 (en) * | 2018-04-12 | 2021-05-20 | Boe Technology Group Co., Ltd. | Recommendation method, recommendation apparatus, recommendation device, recommendation system and storage medium |
| CN108830460A (en) * | 2018-05-23 | 2018-11-16 | 重庆邮电大学 | A method of recommender system Deta sparseness is alleviated based on substep dynamic filling |
| CN110210914A (en) * | 2019-06-17 | 2019-09-06 | 华北电力大学 | Residential electricity consumption demand response method based on intelligent recommendation |
| CN113962414A (en) * | 2020-07-02 | 2022-01-21 | 国网能源研究院有限公司 | Method and system for quantifying retail electricity price package of industrial and commercial users |
| CN112017069A (en) * | 2020-07-08 | 2020-12-01 | 广东电力交易中心有限责任公司 | Power market electricity price package recommendation method and terminal based on electricity utilization characteristics |
| CN111798336A (en) * | 2020-07-09 | 2020-10-20 | 山东大学 | Typical user-based resident electricity fee package recommendation method and system |
| CN112967108A (en) * | 2021-03-09 | 2021-06-15 | 昆明电力交易中心有限责任公司 | BP-ANN-based electric power retail package searching and sequencing simulation system and method |
| CN112950322A (en) * | 2021-03-11 | 2021-06-11 | 昆明电力交易中心有限责任公司 | Power retail package recommendation method and system based on collaborative filtering optimization |
| CN113538041A (en) * | 2021-06-29 | 2021-10-22 | 广东电力交易中心有限责任公司 | Power package recommendation method and device based on load curve clustering analysis |
| CN113538093A (en) * | 2021-07-16 | 2021-10-22 | 四川大学 | High-quality power package recommendation method based on improved collaborative filtering algorithm |
| CN115994807A (en) * | 2021-10-15 | 2023-04-21 | 第四范式（北京）技术有限公司 | Material recommendation method, device and system |
| CN114037161A (en) * | 2021-11-10 | 2022-02-11 | 国网四川省电力公司经济技术研究院 | Modeling method of retail electricity price package optimization model for maximizing social welfare |
| CN113947444A (en) * | 2021-11-17 | 2022-01-18 | 浙江理工大学 | Electricity selling package recommending method considering multi-granularity hesitation fuzzy set and incomplete weight |
| CN114969520A (en) * | 2022-05-16 | 2022-08-30 | 重庆大学 | Commodity recommendation method, system and equipment based on label information and commodity attributes |
| CN115578163A (en) * | 2022-10-18 | 2023-01-06 | 李倩文 | Personalized pushing method and system for combined commodity information |
| CN116187808A (en) * | 2022-12-13 | 2023-05-30 | 华电电力科学研究院有限公司 | Electric power package recommendation method based on virtual power plant user-package label portrait |
| CN115994271A (en) * | 2023-01-12 | 2023-04-21 | 武汉大学 | Recommendation method of psychological assessment |
| CN116127201A (en) * | 2023-02-27 | 2023-05-16 | 安徽大学 | Large-scale user recommendation method based on evolutionary multitasking |
Non-Patent Citations (5)
| Title |
|---|
| MIN ZHANG等: "Recommendation algorithm based on user attributes and tag preferences", 《 JOURNAL OF PHYSICS: CONFERENCE SERIES》, vol. 1684, pages 012081 * |
| 周世平主编: "《音频音乐与计算机的交融 音频音乐技术》", 江苏凤凰科学技术出版社, pages: 342 * |
| 张承畅等: "基于云计算和改进K-means算法的海量用电数据分析方法", 《计算机应用》, no. 01, 10 January 2018 (2018-01-10), pages 165 - 170 * |
| 曲朝阳等: "基于电力交易用户最优特征子集的售电套餐推荐方法", 《电网技术》, no. 10, 19 July 2018 (2018-07-19), pages 220 - 227 * |
| 李峰: "《基于聚类与信任关系的混合推荐算法研究》", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, no. 6, pages 138 - 1199 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117521898A (en) * | 2023-11-10 | 2024-02-06 | 国网山东省电力公司营销服务中心(计量中心) | Electric charge settlement optimization method and system based on association analysis |
| CN117252636A (en) * | 2023-11-17 | 2023-12-19 | 国网山东省电力公司营销服务中心(计量中心) | Electricity fee package type optimization method and system based on user |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116596640B (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116596640B (en) | Recommendation method, system, equipment and storage medium for electric power retail electric charge package | |
| Cai et al. | Real-time bidding by reinforcement learning in display advertising | |
| CN109063945A (en) | A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system | |
| US20160364807A1 (en) | Electric power business profit and loss calculation system and electric power business profit and loss calculation method | |
| US10346862B2 (en) | Migration system to migrate users to target services | |
| CN108596467B (en) | Market operation simulation transaction simulation system suitable for electricity selling company | |
| CN107895241A (en) | A kind of sale of electricity company purchase sale of electricity operational decision making and methods of risk assessment | |
| CN111724039B (en) | Recommendation method for recommending customer service personnel to power users | |
| CN106485578A (en) | Smart home quick modularity quotation system and method | |
| CN108154311A (en) | Top-tier customer recognition methods and device based on random forest and decision tree | |
| CN107480907A (en) | The optimization method of provincial power network power purchase proportioning containing wind-powered electricity generation under a kind of time-of-use tariffs | |
| CN109657998A (en) | A kind of resource allocation methods, device, equipment and storage medium | |
| Bompard et al. | A game theory simulator for assessing the performances of competitive electricity markets | |
| CN105281959B (en) | A kind of mobile communication subscriber attrition prediction method based on hidden Markov model | |
| CN116402362A (en) | Electricity fee charging method and device based on user portrait | |
| CN112037049A (en) | Bank card charging method and device | |
| CN115130811A (en) | Method and device for establishing power user portrait and electronic equipment | |
| CN114757710A (en) | Evaluation method for load aggregator bidding | |
| Ali et al. | Integrating forecasting service and Gen2 blockchain into a local energy trading platform to promote sustainability goals | |
| CN110413722A (en) | Address choice method, apparatus and non-transient storage medium | |
| CN116894156A (en) | MCMC algorithm-based power acquisition terminal data preprocessing method | |
| CN115080639B (en) | Internet of things connection management platform operation method and system | |
| CN116542490A (en) | Virtual power plant day-ahead dispatching encapsulation model and dispatching ex-definition model construction method | |
| CN114155032B (en) | Calculation scheme for retailers to collect commodity sales rebate fees from suppliers | |
| CN109711735A (en) | A kind of auditing method and device of basic charge as per installed capacity |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |