CN115600014B - Personalized power distribution configuration method and system based on electricity utilization characteristics - Google Patents
Personalized power distribution configuration method and system based on electricity utilization characteristics Download PDFInfo
- Publication number
- CN115600014B CN115600014B CN202211602617.1A CN202211602617A CN115600014B CN 115600014 B CN115600014 B CN 115600014B CN 202211602617 A CN202211602617 A CN 202211602617A CN 115600014 B CN115600014 B CN 115600014B
- Authority
- CN
- China
- Prior art keywords
- electricity
- electricity consumption
- user
- utilization
- consumption data
- 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.)
- Active
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 514
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 130
- 238000005192 partition Methods 0.000 claims description 34
- 230000000737 periodic effect Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 18
- 238000012545 processing Methods 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 description 9
- 230000008901 benefit Effects 0.000 description 7
- 206010063385 Intellectualisation Diseases 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 239000002699 waste material Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a personalized power distribution configuration method and a personalized power distribution configuration system based on power utilization characteristics, and relates to the field of power utilization data processing, wherein the method comprises the following steps: obtaining a target electricity data set; carrying out special electricity data identification on the data to obtain a special electricity data set; inputting the target electricity utilization data set and the special electricity utilization data set into an electricity utilization characteristic analysis model to obtain target user characteristics; and obtaining a power consumption configuration adjustment scheme according to the characteristics of the target user, and performing power distribution configuration adjustment on the target user based on the power consumption configuration adjustment scheme. The invention solves the technical problems of poor analysis effect of the electricity utilization characteristics aiming at the user in the prior art, thereby causing low configuration degree of the meter reading individuation and the power distribution individuation of the user, and improving the quality of the electricity utilization characteristic analysis of the user; the configuration degree of meter reading individuation and power distribution individuation of the user is improved, and the technical effects of diversified power consumption requirements of the user and the like are met.
Description
Technical Field
The invention relates to the field of electricity data processing, in particular to a personalized power distribution configuration method and system based on electricity characteristics.
Background
The continuous development of science and technology promotes the informatization, automation and intellectualization processes of the power system. The accuracy and timeliness of the ammeter data copy have important influences on the development level, management decision-making, economic benefit and the like of the electric power system. In addition, the modern development of the life of the user improves the diversity of the electricity utilization characteristics of the user, and the electric meter data is continuously developed towards the personalized direction. The traditional meter reading configuration can not meet the requirements of modern ammeter data copy management, and the intelligent and personalized meter reading configuration method based on the user characteristics is researched and designed, so that the method has very important practical significance.
In the prior art, the technical problems of poor analysis effect of the power utilization characteristics of a user and low configuration degree of meter reading individuation and power distribution individuation of the user are caused.
Disclosure of Invention
The application provides a personalized power distribution configuration method and system based on power utilization characteristics. The method and the device solve the technical problems that in the prior art, the analysis effect of the electricity utilization characteristics aiming at the user is poor, and the configuration degree of meter reading individuation and power distribution individuation of the user is low.
In view of the above problems, the present application provides a personalized power distribution configuration method and system based on power consumption characteristics.
In a first aspect, the present application provides a personalized power distribution configuration method based on electricity consumption characteristics, where the method is applied to a personalized power distribution configuration system based on electricity consumption characteristics, and the method includes: determining a target user; collecting electricity utilization data of the target user in a plurality of preset time periods to obtain a target electricity utilization data set; carrying out special electricity utilization data identification on the target electricity utilization data set to obtain a special electricity utilization data set; constructing an electricity utilization characteristic analysis model; inputting the target electricity utilization data set and the special electricity utilization data set into the electricity utilization characteristic analysis model, and analyzing the electricity utilization characteristics of the target user to obtain target user characteristics; and obtaining a power consumption configuration adjustment scheme according to the characteristics of the target user, and performing power distribution configuration adjustment on the target user based on the power consumption configuration adjustment scheme.
In a second aspect, the present application further provides a personalized power distribution configuration system based on electricity utilization characteristics, wherein the system comprises: the user determining module is used for determining a target user; the power consumption data acquisition module is used for acquiring power consumption data of the target user in a plurality of preset time periods to obtain a target power consumption data set; the special electricity utilization data identification module is used for carrying out special electricity utilization data identification on the target electricity utilization data set to obtain a special electricity utilization data set; the construction module is used for constructing an electricity utilization characteristic analysis model; the electricity utilization characteristic analysis module is used for inputting the target electricity utilization data set and the special electricity utilization data set into the electricity utilization characteristic analysis model, analyzing the electricity utilization characteristics of the target user and obtaining the characteristics of the target user; and the user power distribution configuration adjustment module is used for obtaining a power utilization configuration adjustment scheme according to the target user characteristics and carrying out power distribution configuration adjustment on the target user based on the power utilization configuration adjustment scheme.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
acquiring electricity utilization data of a target user through a plurality of preset time periods to obtain a target electricity utilization data set; the special electricity utilization data set is obtained by carrying out special electricity utilization data identification on the target electricity utilization data set; constructing an electricity utilization characteristic analysis model; inputting the target electricity utilization data set and the special electricity utilization data set into an electricity utilization characteristic analysis model to obtain target user characteristics; and obtaining a power consumption configuration adjustment scheme through the characteristics of the target user, and carrying out power distribution configuration adjustment on the target user according to the power consumption configuration adjustment scheme. The method and the device achieve accurate electricity utilization characteristic analysis of the user through the electricity utilization characteristic analysis model, and improve the quality of the electricity utilization characteristic analysis of the user; the method has the advantages that informatization and intelligent meter reading configuration and power distribution management are realized, the configuration degree of user meter reading individuation and power distribution individuation is improved, and the diversified power consumption requirements of users are met; meanwhile, the scientificalness and the intellectualization of the power resource management are improved, and the technical effects of overhigh power grid load and power resource waste are avoided.
Drawings
Fig. 1 is a schematic flow chart of a personalized power distribution configuration method based on electricity utilization characteristics;
FIG. 2 is a schematic flow chart of obtaining a target electricity data set in a personalized power distribution configuration method based on electricity consumption characteristics;
FIG. 3 is a schematic flow chart of a method for obtaining a power consumption configuration adjustment scheme in a personalized power distribution configuration method based on power consumption characteristics;
fig. 4 is a schematic structural diagram of a personalized power distribution configuration system based on electricity utilization characteristics.
Reference numerals illustrate: the system comprises a user determining module 11, a power consumption data acquisition module 12, a special power consumption data identification module 13, a construction module 14, a power consumption characteristic analysis module 15 and a user power distribution configuration adjustment module 16.
Detailed Description
The application provides a personalized power distribution configuration method and system based on power utilization characteristics. The method and the device solve the technical problems that in the prior art, the analysis effect of the electricity utilization characteristics aiming at the user is poor, and the configuration degree of meter reading individuation and power distribution individuation of the user is low. The accurate electricity utilization characteristic analysis is carried out on the user through the electricity utilization characteristic analysis model, and the quality of the electricity utilization characteristic analysis of the user is improved; the method has the advantages that informatization and intelligent meter reading configuration and power distribution management are realized, the configuration degree of user meter reading individuation and power distribution individuation is improved, and the diversified power consumption requirements of users are met; meanwhile, the scientificalness and the intellectualization of the power resource management are improved, and the technical effects of overhigh power grid load and power resource waste are avoided.
Example 1
Referring to fig. 1, the present application provides a personalized power distribution configuration method based on electricity consumption characteristics, wherein the method is applied to a personalized power distribution configuration system based on electricity consumption characteristics, and the method specifically includes the following steps:
step S100: determining a target user;
specifically, first, the target user is specified. The target user is any user who performs intelligent electricity utilization characteristic analysis and meter reading personalized configuration by using the personalized electricity distribution configuration system based on electricity utilization characteristics. Illustratively, the target user may be a student dormitory of a university. The method achieves the technical effects of defining the target user and laying a foundation for carrying out intelligent electricity utilization characteristic analysis and meter reading personalized configuration on the target user.
Step S200: collecting electricity utilization data of the target user in a plurality of preset time periods to obtain a target electricity utilization data set;
further, as shown in fig. 2, step S200 of the present application further includes:
step S210: performing time section division on the preset time period to obtain a plurality of time sections;
step S220: acquiring electricity consumption data of the target user in the time sections in each preset time period, and acquiring a plurality of period electricity consumption data sets;
Step S230: and obtaining the target electricity utilization data set according to the plurality of periodic electricity utilization data sets.
Specifically, a plurality of preset time periods are obtained, and time section division is performed on each preset time period in the plurality of preset time periods to obtain a plurality of time sections. Further, based on a plurality of preset time periods and a plurality of time sections, the electricity consumption data of the target user are acquired, a plurality of period electricity consumption data sets are acquired, and then the target electricity consumption data sets are determined. Wherein the plurality of preset time periods are determined by the adaptive settings of the personalized power distribution configuration system based on the power consumption characteristics. The time sections comprise time section division is carried out on each preset time period in a plurality of preset time periods, and the obtained time section information is a plurality of time section information. The plurality of periodic electricity consumption data sets comprise a plurality of electricity consumption data of a target user in a plurality of time sections corresponding to a plurality of preset time periods. The target electricity usage data set includes a plurality of periodic electricity usage data sets. Illustratively, the plurality of preset time periods includes a preset time period a, which is 1 day. And the time section is 3 hours, and the time section of the preset time period A is divided according to the time section of 3 hours, so that a plurality of time sections corresponding to the preset time period A can be obtained. The plurality of periodic electricity data sets comprises an electricity data set of a preset time period A. The electricity consumption data set of the preset time period A comprises a plurality of electricity consumption data of the target user under a plurality of time sections corresponding to the preset time period A. The electricity consumption data may be collected based on an ammeter of a unit where the target user resides, for example, collecting electricity consumption of the target user in a plurality of time sections within each preset time period, to obtain a target electricity consumption data set.
Through the technical content, the method and the device achieve the technical effects that the electricity consumption data of the target user is acquired according to a plurality of preset time periods and a plurality of time sections, a reliable and accurate target electricity consumption data set is obtained, and reliable data support is provided for intelligent electricity consumption characteristic analysis and meter reading personalized configuration of the target user.
Step S300: carrying out special electricity utilization data identification on the target electricity utilization data set to obtain a special electricity utilization data set;
further, step S300 of the present application further includes:
step S310: constructing a special electricity data identification model;
further, step S310 of the present application further includes:
step S311: randomly selecting power consumption data from a plurality of power consumption data in the plurality of periodic power consumption data sets as a first dividing threshold;
step S312: constructing a first partition node of the special electricity data identification model by adopting the first partition threshold;
step S313: randomly selecting power consumption data from a plurality of power consumption data in the plurality of periodic power consumption data sets as a second dividing threshold value;
step S314: constructing a second partition node of the special electricity data identification model by adopting the two partition thresholds;
Step S315: continuously constructing multi-level partition nodes of the special electricity consumption data identification model;
step S316: setting special electricity consumption data output nodes according to the multi-stage dividing nodes, wherein the single electricity consumption data output by the special electricity consumption data output nodes and the dividing nodes below are special electricity consumption data;
step S317: and obtaining the special electricity utilization data identification model according to the multi-stage dividing nodes and the special electricity utilization data output nodes.
Step S320: and inputting a plurality of electricity consumption data in the plurality of periodic electricity consumption data sets into the special electricity consumption data identification model to obtain the special electricity consumption data set.
The embodiment of the application builds the special electricity consumption data identification model based on the thought of an isolated forest algorithm, specifically, performs random selection of electricity consumption data on an obtained target electricity consumption data set, namely, performs random selection of electricity consumption data in an obtained plurality of period electricity consumption data sets, and obtains a first division threshold value and a second division threshold value. Further, the first division threshold is set as a first division node of the special electricity consumption data identification model, and the second division threshold is set as a second division node of the special electricity consumption data identification model. The first dividing node can conduct two classifications on input electricity consumption data, the classification is conducted to the two classifications that are larger than the first dividing threshold value and not larger than the first dividing threshold value, the second dividing node can conduct further classification on the classification result of the first dividing node, and the like, and the obtained multiple period electricity consumption data sets are continuously conducted to conduct random selection of electricity consumption data and setting of the dividing nodes until the multi-level dividing nodes of the special electricity consumption data identification model are obtained. Further, the obtained multi-stage dividing nodes are set with special electricity consumption data output nodes, the special electricity consumption data output nodes are obtained, and the special electricity consumption data identification model is determined by combining the multi-stage dividing nodes. The special electricity consumption data identification model is constructed to form a decision tree algorithm structure, and then the target electricity consumption data set is input into the special electricity consumption data identification model, namely, a plurality of electricity consumption data in a plurality of period electricity consumption data sets are used as input information, and the special electricity consumption data identification model is input, so that the special electricity consumption data set is obtained.
The first dividing threshold and the second dividing threshold are any power consumption data in a plurality of period power consumption data sets. And, the first division threshold is different from the second division threshold. The first partition node is a first partition threshold. The second partition node is a second partition threshold. The multi-stage dividing node comprises a plurality of dividing thresholds, wherein the dividing thresholds are arbitrary and different power consumption data in a plurality of period power consumption data sets. The special electricity data output node can be subjected to custom setting and determination according to the number of the multi-stage dividing nodes. Optionally, the setting is performed according to the distribution situation of the multiple power consumption data in the multiple period power consumption data set, if the distribution of the multiple power consumption data is relatively uniform, the partition node with a higher level is set as the special power consumption data output node, and if the distribution deviation of the multiple power consumption data is relatively large, the partition node with a higher level is set as the special power consumption data output node, for example, the partition node in the middle position of the multi-level partition node may be preferably set as the special power consumption data output node.
The special electricity utilization data identification model comprises multi-stage dividing nodes and special electricity utilization data output nodes. The special electricity consumption data set comprises a plurality of electricity consumption data corresponding to the special electricity consumption data output nodes and the dividing nodes below the special electricity consumption data output nodes in the target electricity consumption data set.
Based on the constructed special electricity consumption data identification model, a plurality of electricity consumption data in a plurality of period electricity consumption data sets are input into the special electricity consumption data identification model, a final plurality of classification results are obtained through the classification of the multi-stage classification nodes, the single electricity consumption data obtained through the classification of the special electricity consumption data output nodes and the classification nodes below are used as the special electricity consumption data, the characteristic electricity consumption data set is further obtained, the difference between the part of electricity consumption data and other normal electricity consumption data is considered to be larger, the part of electricity consumption data is extremely small or extremely large, the isolated data points are formed, the single electricity consumption data is formed after the classification of the small number of the classification nodes below the characteristic electricity consumption data output nodes, other electricity consumption data form a dense data cluster, the single data is not formed yet through the classification of the multiple classification nodes, and therefore, the identification of the unsupervised characteristic electricity consumption data is carried out based on the characteristics of the plurality of the electricity consumption data, the special electricity consumption data is accurately identified through the special electricity consumption data identification model, the characteristic electricity consumption data set is obtained, the user-specific electricity consumption data is accurately analyzed, the user-oriented characteristic electricity consumption data is accurately analyzed, and the user-oriented electricity consumption data is improved.
Step S400: constructing an electricity utilization characteristic analysis model;
further, step S400 of the present application further includes:
step S410: constructing an electricity habit characteristic analysis path;
further, step S410 of the present application further includes:
step S411: acquiring target electricity utilization data sets of a plurality of sample users as a plurality of sample electricity utilization data sets;
step S412: marking the electricity consumption habit characteristics of the plurality of sample users to obtain the electricity consumption habit characteristics of the plurality of sample users;
step S413: constructing the power consumption habit characteristic analysis path based on a BP neural network;
step S414: and carrying out cross supervision training and verification on the electricity habit feature analysis path by adopting the plurality of sample electricity data sets and the electricity habit features of the plurality of sample users to obtain the electricity habit feature analysis path with the accuracy meeting the preset requirement.
Specifically, based on a plurality of preset time periods and a plurality of time sections, collecting electricity consumption data of a plurality of sample users, obtaining target electricity consumption data sets of the plurality of sample users, and setting the target electricity consumption data sets as the plurality of sample electricity consumption data sets. And then, based on a plurality of preset time periods and a plurality of time sections, carrying out power consumption habit analysis, evaluation and power consumption habit feature marking on a plurality of sample users to obtain power consumption habit features of the plurality of sample users. Furthermore, the data of the plurality of sample power consumption data sets and the plurality of sample user power consumption habit features can be divided to obtain the plurality of training sample power consumption data sets, the plurality of training sample user power consumption habit features, the plurality of test sample power consumption data sets and the plurality of test sample user power consumption habit features. And the plurality of training sample electricity consumption data sets and the plurality of training sample user electricity consumption habit characteristics have corresponding relations, and the plurality of test sample electricity consumption data sets and the plurality of test sample user electricity consumption habit characteristics have corresponding relations. And then, based on the BP neural network, the power consumption habit characteristic analysis path is obtained by performing cross supervision training and verification on a plurality of training sample power consumption data sets. When the accuracy of the electricity consumption habit feature analysis path meets the preset requirement, namely, the similarity degree between the output information corresponding to the electricity consumption habit feature of the plurality of training sample electricity consumption data sets and the electricity consumption habit features of the plurality of training sample users meets the preset requirement, the supervision training is finished. And then, taking the electricity consumption data sets of the plurality of test samples as input information, inputting the electricity consumption habit characteristic analysis path, and verifying the electricity consumption habit characteristic analysis path. And when the accuracy of the electricity habit feature analysis path meets the preset requirement, namely, the similarity degree between the output information corresponding to the electricity habit data sets of the plurality of test samples and the electricity habit features of the plurality of test sample users meets the preset requirement, obtaining the electricity habit feature analysis path with the accuracy meeting the preset requirement.
The plurality of sample users are determined by the personalized power distribution configuration system based on the power utilization characteristics according to the actual situation self-adaptive setting. For example, the target user is a C university's gramineous dormitory a. The plurality of sample users may be a plurality of other gramineous dormitories of university C, gramineous dormitory b, gramineous dormitory C, gramineous dormitory d, and the like. The target electricity consumption data set of the plurality of sample users comprises a plurality of electricity consumption data of the plurality of sample users in a plurality of preset time periods and a plurality of time sections. The plurality of sample electricity utilization data sets are target electricity utilization data sets of a plurality of sample users. The electricity consumption habit characteristics of the plurality of sample users comprise data information such as a plurality of electricity consumption times of the plurality of sample users and the electricity consumption amount corresponding to each electricity consumption time in a plurality of preset time periods and a plurality of time sections. The BP neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm. The BP neural network comprises an input layer, a plurality of layers of neurons and an output layer. The BP neural network can perform forward calculation and backward calculation. When calculating in the forward direction, the input information is processed layer by layer from the input layer through a plurality of layers of neurons and is turned to the output layer, and the state of each layer of neurons only affects the state of the next layer of neurons. If the expected output cannot be obtained at the output layer, the reverse calculation is carried out, the error signal is returned along the original connecting path, and the weight of each neuron is modified to minimize the error signal. In addition, the obtained electricity habit characteristic analysis path can be regarded as an intelligent electricity habit characteristic analysis model meeting the BP neural network. The accuracy comprises the similarity degree between the output information corresponding to the plurality of training sample electricity consumption data sets and the electricity consumption habit characteristics of the plurality of training sample users, and the similarity degree between the output information corresponding to the plurality of test sample electricity consumption data sets and the electricity consumption habit characteristics of the plurality of test sample users. The preset requirements comprise preset accuracy, and the preset accuracy is determined by the customized setting of the personalized power distribution configuration system based on the power utilization characteristics. The method has the advantages that the power consumption habit characteristic analysis path is built through the BP neural network, the power consumption habit characteristic analysis path is subjected to cross supervision training and verification through a plurality of sample power consumption data sets and a plurality of sample user power consumption habit characteristics, the power consumption habit characteristic analysis path with high accuracy meeting the preset requirements is obtained, and the technical effects of reliability and generalization capability are achieved, so that the accuracy of the power consumption characteristic analysis model is improved.
Step S420: constructing an electricity peak characteristic analysis path;
step S430: and obtaining an electricity consumption characteristic analysis model according to the electricity consumption habit characteristic analysis path and the electricity consumption peak characteristic analysis path, wherein input data of the electricity consumption habit characteristic analysis path is an electricity consumption data set, output data is a user electricity consumption habit characteristic, input data of the electricity consumption peak characteristic analysis path is a special electricity consumption data set, output data is a user electricity consumption peak characteristic, and the user electricity consumption habit characteristic and the user electricity consumption peak characteristic form a user characteristic.
Specifically, special electricity data identification is performed on the plurality of sample electricity data sets through a special electricity data identification model, and the plurality of sample special electricity data sets are obtained. And further, marking the electricity consumption peak value characteristics of the plurality of sample users based on a plurality of preset time periods and a plurality of time sections, so as to obtain the electricity consumption peak value characteristics of the plurality of sample users. Further, based on the BP neural network, cross supervision training and verification are carried out on the special electricity consumption data sets of a plurality of samples and electricity consumption peak characteristics of a plurality of sample users, so that an electricity consumption peak characteristic analysis path is obtained, and an electricity consumption habit characteristic analysis path is combined, so that an electricity consumption characteristic analysis model is obtained. The specific construction process of the electricity consumption peak characteristic analysis path is the same as the specific construction process of the electricity consumption habit characteristic analysis path, and is not repeated here for the sake of brevity of the description. The special electricity consumption data sets of the samples are included in the plurality of sample electricity consumption data sets, and the plurality of sample electricity consumption data sets are divided into a single plurality of electricity consumption data with the special electricity consumption data output nodes and the dividing nodes below the special electricity consumption data output nodes. The electricity consumption peak characteristics of the plurality of sample users comprise a plurality of preset time periods and a plurality of time sections, and the electricity consumption peak values of the plurality of sample users, the time corresponding to the electricity consumption peak values, the electricity consumption load parameters corresponding to the electricity consumption peak values and other data information. The electricity consumption characteristic analysis model comprises an electricity consumption habit characteristic analysis path and an electricity consumption peak characteristic analysis path. And the input data of the electricity consumption habit characteristic analysis path is an electricity consumption data set, and the output data is the electricity consumption habit characteristic of the user. The input data of the electricity consumption peak characteristic analysis path is a special electricity consumption data set, and the output data is the electricity consumption peak characteristic of a user. And the user electricity consumption habit characteristics and the user electricity consumption peak characteristics form user characteristics. The method achieves the technical effects of constructing an accurate and reliable electricity utilization characteristic analysis model, and improving the quality of electricity utilization characteristic analysis of a target user.
Step S500: inputting the target electricity utilization data set and the special electricity utilization data set into the electricity utilization characteristic analysis model, and analyzing the electricity utilization characteristics of the target user to obtain target user characteristics;
specifically, a target electricity data set and a special electricity data set of a target user are used as input information, and an electricity characteristic analysis model is input, wherein the electricity characteristic analysis model comprises an electricity habit characteristic analysis path and an electricity peak characteristic analysis path. And the target electricity consumption data set is transmitted to an electricity consumption habit feature analysis path, and electricity consumption habit feature analysis is carried out on the target electricity consumption data set through the electricity consumption habit feature analysis path, so that electricity consumption habit features of the target user are obtained. The special electricity consumption data set is transmitted to an electricity consumption peak characteristic analysis path, electricity consumption peak characteristic analysis is carried out on the special electricity consumption data set through the electricity consumption peak characteristic analysis path, electricity consumption peak characteristics of a target user are obtained, and the characteristics of the target user are obtained by combining the electricity consumption habit characteristics of the target user. The target user characteristics comprise target user electricity consumption habit characteristics and target user electricity consumption peak characteristics. The target user electricity consumption habit characteristics comprise a plurality of electricity consumption times of the target user corresponding to the target electricity consumption data set, and data information such as electricity consumption quantity corresponding to each electricity consumption time. The electricity consumption peak value characteristics of the target users comprise data information such as electricity consumption peak values, electricity consumption peak value time, electricity consumption load parameters and the like of the target users corresponding to the special electricity consumption data sets. The comprehensive and reliable electricity utilization characteristic analysis is carried out on the target user through the electricity utilization characteristic analysis model, the accurate characteristics of the target user are obtained, and the technical effects of adapting degree and rationality of power distribution configuration adjustment of the target user in the follow-up process are improved.
Step S600: and obtaining a power consumption configuration adjustment scheme according to the characteristics of the target user, and performing power distribution configuration adjustment on the target user based on the power consumption configuration adjustment scheme.
Further, as shown in fig. 3, step S600 of the present application further includes:
step S610: acquiring a plurality of sample user features;
step S620: acquiring a plurality of sample electricity utilization configuration adjustment schemes according to the plurality of sample user characteristics;
step S630: constructing mapping relations between the user characteristics of the plurality of samples and the power utilization configuration adjustment schemes of the plurality of samples;
step S640: and inputting the target user characteristics into the mapping relation to obtain the electricity utilization configuration adjustment scheme.
Specifically, a plurality of sample user characteristics are obtained based on a plurality of sample user electricity usage habit characteristics and a plurality of sample user electricity usage peak characteristics. Furthermore, based on the plurality of sample user characteristics, a plurality of sample power utilization configuration adjustment schemes for distributing power to the plurality of sample user characteristics are obtained through means such as big data inquiry. Further, the corresponding relation between the user characteristics of the plurality of samples and the power utilization configuration adjustment schemes of the plurality of samples is analyzed, and a mapping relation is obtained. And further, inputting the characteristics of the target user into the mapping relation to obtain a power utilization configuration adjustment scheme, and performing power distribution configuration adjustment on the target user according to the power utilization configuration adjustment scheme. The plurality of sample user characteristics comprise a plurality of sample user electricity consumption habit characteristics and a plurality of sample user electricity consumption peak characteristics. The multiple sample power utilization configuration adjustment scheme comprises data information for adjusting distribution parameters such as distribution time adjustment, distribution quantity adjustment and the like for multiple sample users. Illustratively, the plurality of sample user characteristics indicate that the electricity consumption of the C university's gramineous dormitory b is the least in the time section h, and the plurality of sample electricity consumption configuration adjustment schemes obtained are included in the time section h to reduce the electricity consumption of the C university's gramineous dormitory b. The mapping relation comprises a plurality of sample user characteristics, a plurality of sample power utilization configuration adjustment schemes and a corresponding relation between the plurality of sample user characteristics and the plurality of sample power utilization configuration adjustment schemes. For example, when the power utilization configuration adjustment scheme is obtained, the target user feature may be input into the mapping relationship, and similarity evaluation may be performed on the target user feature and a plurality of sample user features in the mapping relationship, so as to obtain a plurality of target user feature similarities. Maximum value screening is carried out on the feature similarities of the plurality of target users, the maximum target user feature similarity is obtained, the maximum target user feature similarity is matched with various sample electricity utilization configuration adjustment schemes in the mapping relation, the sample electricity utilization configuration adjustment scheme corresponding to the maximum target user feature similarity is determined, and the sample electricity utilization configuration adjustment scheme corresponding to the maximum target user feature similarity is output as the electricity utilization configuration adjustment scheme. The method and the device achieve the technical effects that various sample electricity utilization configuration adjustment schemes are screened according to the characteristics of the target user, the electricity utilization configuration adjustment scheme with higher adaptability is obtained, the adaptation degree of power distribution configuration adjustment of the target user is improved, and the diversified electricity utilization requirements of the target user are met.
In summary, the personalized power distribution configuration method based on the power consumption characteristics has the following technical effects:
1. acquiring electricity utilization data of a target user through a plurality of preset time periods to obtain a target electricity utilization data set; the special electricity utilization data set is obtained by carrying out special electricity utilization data identification on the target electricity utilization data set; constructing an electricity utilization characteristic analysis model; inputting the target electricity utilization data set and the special electricity utilization data set into an electricity utilization characteristic analysis model to obtain target user characteristics; and obtaining a power consumption configuration adjustment scheme through the characteristics of the target user, and carrying out power distribution configuration adjustment on the target user according to the power consumption configuration adjustment scheme. The accurate electricity utilization characteristic analysis is carried out on the user through the electricity utilization characteristic analysis model, and the quality of the electricity utilization characteristic analysis of the user is improved; the method has the advantages that informatization and intelligent meter reading configuration and power distribution management are realized, the configuration degree of user meter reading individuation and power distribution individuation is improved, and the diversified power consumption requirements of users are met; meanwhile, the scientificalness and the intellectualization of the power resource management are improved, and the technical effect of avoiding the waste of the power resource is achieved.
2. And carrying out special electricity data identification on the target electricity data set through the special electricity data identification model to obtain an accurate special electricity data set, so that the accuracy of electricity characteristic analysis on a target user is improved, and the distribution individuation adaptation degree of the user is improved.
3. Through the BP neural network, a power consumption habit feature analysis path is constructed, cross supervision training and verification are carried out on the power consumption habit feature analysis path through a plurality of sample power consumption data sets and a plurality of sample user power consumption habit features, the accuracy meets the preset requirements, the power consumption habit feature analysis path with high reliability and generalization capability is obtained, and the accuracy of a power consumption feature analysis model is improved.
Example two
Based on the same inventive concept as the personalized power distribution configuration method based on the power consumption characteristics in the foregoing embodiment, the present invention further provides a personalized power distribution configuration system based on the power consumption characteristics, referring to fig. 4, the system includes:
a user determination module 11, the user determination module 11 being configured to determine a target user;
the electricity consumption data acquisition module 12 is used for acquiring electricity consumption data of the target user in a plurality of preset time periods, and obtaining a target electricity consumption data set;
the special electricity data identification module 13 is used for carrying out special electricity data identification on the target electricity data set to obtain a special electricity data set;
A building module 14, wherein the building module 14 is used for building an electricity utilization characteristic analysis model;
the electricity utilization characteristic analysis module 15 is used for inputting the target electricity utilization data set and the special electricity utilization data set into the electricity utilization characteristic analysis model, and analyzing the electricity utilization characteristics of the target user to obtain the characteristics of the target user;
and the user power distribution configuration adjustment module 16 is used for obtaining a power utilization configuration adjustment scheme according to the target user characteristics, and performing power distribution configuration adjustment on the target user based on the power utilization configuration adjustment scheme.
Further, the system further comprises:
the time zone dividing module is used for dividing the time zone of the preset time period to obtain a plurality of time zones;
the periodic electricity consumption data set determining module is used for acquiring electricity consumption data of the target user in the plurality of time sections in each preset time period and obtaining a plurality of periodic electricity consumption data sets;
and the target electricity consumption data set determining module is used for obtaining the target electricity consumption data set according to the plurality of periodic electricity consumption data sets.
Further, the system further comprises:
the first execution module is used for constructing a special electricity utilization data identification model;
and the special electricity consumption data set determining module is used for inputting the multiple electricity consumption data in the multiple period electricity consumption data sets into the special electricity consumption data identification model to obtain the special electricity consumption data set.
Further, the system further comprises:
the first division threshold determining module is used for randomly selecting power consumption data from a plurality of power consumption data in the plurality of periodic power consumption data sets to serve as a first division threshold;
the first partition node determining module is used for constructing a first partition node of the special electricity utilization data identification model by adopting the partition threshold value;
the second division threshold determining module is used for randomly selecting power consumption data from a plurality of power consumption data in the plurality of periodic power consumption data sets again to serve as a second division threshold;
the second partition node determining module is used for constructing a second partition node of the special electricity utilization data identification model by adopting the two partition thresholds;
The multi-stage partition node determining module is used for continuously constructing multi-stage partition nodes of the special electricity utilization data identification model;
the special electricity consumption data output node determining module is used for setting special electricity consumption data output nodes according to the multi-stage dividing nodes, wherein single electricity consumption data output by the special electricity consumption data output nodes and the dividing nodes below are special electricity consumption data;
and the second execution module is used for obtaining the special electricity utilization data identification model according to the multi-stage dividing nodes and the special electricity utilization data output nodes.
Further, the system further comprises:
the habit path construction module is used for constructing an electricity utilization habit characteristic analysis path;
the peak value path construction module is used for constructing an electricity consumption peak value characteristic analysis path;
the third execution module is used for obtaining an electricity consumption characteristic analysis model according to the electricity consumption habit characteristic analysis path and the electricity consumption peak characteristic analysis path, wherein input data of the electricity consumption habit characteristic analysis path is an electricity consumption data set, output data of the electricity consumption habit characteristic analysis path is a user electricity consumption habit characteristic, input data of the electricity consumption peak characteristic analysis path is a special electricity consumption data set, output data of the electricity consumption peak characteristic analysis path is a user electricity consumption peak characteristic, and the user electricity consumption habit characteristic and the user electricity consumption peak characteristic form a user characteristic.
Further, the system further comprises:
the system comprises a sample electricity utilization data set determining module, a sample electricity utilization data set generating module and a sample electricity utilization data set generating module, wherein the sample electricity utilization data set determining module is used for acquiring target electricity utilization data sets of a plurality of sample users and taking the target electricity utilization data sets as a plurality of sample electricity utilization data sets;
the sample user electricity habit feature determining module is used for marking the electricity habit features of the plurality of sample users to obtain the electricity habit features of the plurality of sample users;
the fourth execution module is used for constructing the power utilization habit characteristic analysis path based on the BP neural network;
and the fifth execution module is used for performing cross supervision training and verification on the power consumption habit characteristic analysis path by adopting the plurality of sample power consumption data sets and the power consumption habit characteristics of the plurality of sample users to obtain the power consumption habit characteristic analysis path with the accuracy meeting the preset requirement.
Further, the system further comprises:
a sample user feature determination module for obtaining a plurality of sample user features;
the sample electricity utilization configuration adjustment scheme determining module is used for obtaining various sample electricity utilization configuration adjustment schemes according to the user characteristics of the plurality of samples;
The mapping relation determining module is used for constructing mapping relation between the user characteristics of the plurality of samples and the power utilization configuration adjustment scheme of the plurality of samples;
and the electricity utilization configuration adjustment scheme determining module is used for inputting the target user characteristics into the mapping relation to obtain the electricity utilization configuration adjustment scheme.
The application provides a personalized power distribution configuration method based on electricity utilization characteristics, wherein the method is applied to a personalized power distribution configuration system based on the electricity utilization characteristics, and the method comprises the following steps: acquiring electricity utilization data of a target user through a plurality of preset time periods to obtain a target electricity utilization data set; the special electricity utilization data set is obtained by carrying out special electricity utilization data identification on the target electricity utilization data set; constructing an electricity utilization characteristic analysis model; inputting the target electricity utilization data set and the special electricity utilization data set into an electricity utilization characteristic analysis model to obtain target user characteristics; and obtaining a power consumption configuration adjustment scheme through the characteristics of the target user, and carrying out power distribution configuration adjustment on the target user according to the power consumption configuration adjustment scheme. The method and the device solve the technical problems that in the prior art, the analysis effect of the electricity utilization characteristics aiming at the user is poor, and the configuration degree of meter reading individuation and power distribution individuation of the user is low. The accurate electricity utilization characteristic analysis is carried out on the user through the electricity utilization characteristic analysis model, and the quality of the electricity utilization characteristic analysis of the user is improved; the method has the advantages that informatization and intelligent meter reading configuration and power distribution management are realized, the configuration degree of user meter reading individuation and power distribution individuation is improved, and the diversified power consumption requirements of users are met; meanwhile, the scientificalness and the intellectualization of the power resource management are improved, and the technical effect of avoiding the waste of the power resource is achieved.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The specification and drawings are merely exemplary illustrations of the present application, and the present invention is intended to cover such modifications and variations if they fall within the scope of the invention and its equivalents.
Claims (2)
1. A personalized power distribution configuration method based on electricity utilization characteristics, the method comprising:
determining a target user;
collecting electricity utilization data of the target user in a plurality of preset time periods to obtain a target electricity utilization data set;
carrying out special electricity utilization data identification on the target electricity utilization data set to obtain a special electricity utilization data set;
constructing an electricity utilization characteristic analysis model;
inputting the target electricity utilization data set and the special electricity utilization data set into the electricity utilization characteristic analysis model, and analyzing the electricity utilization characteristics of the target user to obtain target user characteristics;
according to the characteristics of the target user, a power consumption configuration adjustment scheme is obtained, and power distribution configuration adjustment is carried out on the target user based on the power consumption configuration adjustment scheme;
Collecting electricity consumption data of the target user in a plurality of preset time periods, wherein the electricity consumption data comprises:
performing time section division on the preset time period to obtain a plurality of time sections;
acquiring electricity consumption data of the target user in the time sections in each preset time period, and acquiring a plurality of period electricity consumption data sets;
obtaining the target electricity utilization data set according to the plurality of periodic electricity utilization data sets; performing special electricity data identification on the target electricity data set, including:
constructing a special electricity data identification model;
inputting a plurality of electricity consumption data in the plurality of periodic electricity consumption data sets into the special electricity consumption data identification model to obtain the special electricity consumption data set;
the construction of the special electricity consumption data identification model comprises the following steps:
randomly selecting power consumption data from a plurality of power consumption data in the plurality of periodic power consumption data sets as a first dividing threshold;
constructing a first partition node of the special electricity consumption data identification model by adopting the first partition threshold;
randomly selecting power consumption data from a plurality of power consumption data in the plurality of periodic power consumption data sets as a second dividing threshold value;
Constructing a second partition node of the special electricity consumption data identification model by adopting the second partition threshold;
continuously constructing multi-level partition nodes of the special electricity consumption data identification model;
setting special electricity consumption data output nodes according to the multi-stage dividing nodes, wherein the single electricity consumption data output by the special electricity consumption data output nodes and the dividing nodes below are special electricity consumption data;
according to the multistage dividing nodes and the special electricity data output nodes, the special electricity data identification model is obtained;
the construction of the electricity utilization characteristic analysis model comprises the following steps:
constructing an electricity habit characteristic analysis path;
constructing an electricity peak characteristic analysis path;
obtaining an electricity consumption characteristic analysis model according to the electricity consumption habit characteristic analysis path and the electricity consumption peak characteristic analysis path, wherein input data of the electricity consumption habit characteristic analysis path is an electricity consumption data set, output data is a user electricity consumption habit characteristic, input data of the electricity consumption peak characteristic analysis path is a special electricity consumption data set, output data is a user electricity consumption peak characteristic, and the user electricity consumption habit characteristic and the user electricity consumption peak characteristic form a user characteristic;
The construction of the electricity habit characteristic analysis path comprises the following steps:
acquiring target electricity utilization data sets of a plurality of sample users as a plurality of sample electricity utilization data sets;
marking the electricity consumption habit characteristics of the plurality of sample users to obtain the electricity consumption habit characteristics of the plurality of sample users;
constructing the power consumption habit characteristic analysis path based on a BP neural network;
performing cross supervision training and verification on the electricity habit feature analysis path by adopting the plurality of sample electricity utilization data sets and the electricity habit features of the plurality of sample users to obtain the electricity habit feature analysis path with accuracy meeting preset requirements;
and according to the target user characteristics, performing user power distribution configuration adjustment to obtain a power utilization configuration adjustment scheme, wherein the power utilization configuration adjustment scheme comprises the following steps of:
acquiring a plurality of sample user features;
acquiring a plurality of sample electricity utilization configuration adjustment schemes according to the plurality of sample user characteristics;
constructing mapping relations between the user characteristics of the plurality of samples and the power utilization configuration adjustment schemes of the plurality of samples;
and inputting the target user characteristics into the mapping relation to obtain the electricity utilization configuration adjustment scheme.
2. A personalized power distribution configuration system based on electricity usage characteristics, the system comprising:
The user determining module is used for determining a target user;
the power consumption data acquisition module is used for acquiring power consumption data of the target user in a plurality of preset time periods to obtain a target power consumption data set;
the special electricity utilization data identification module is used for carrying out special electricity utilization data identification on the target electricity utilization data set to obtain a special electricity utilization data set;
the construction module is used for constructing an electricity utilization characteristic analysis model;
the electricity utilization characteristic analysis module is used for inputting the target electricity utilization data set and the special electricity utilization data set into the electricity utilization characteristic analysis model, analyzing the electricity utilization characteristics of the target user and obtaining the characteristics of the target user;
the user power distribution configuration adjustment module is used for obtaining a power utilization configuration adjustment scheme according to the target user characteristics and carrying out power distribution configuration adjustment on the target user based on the power utilization configuration adjustment scheme;
the time zone dividing module is used for dividing the time zone of the preset time period to obtain a plurality of time zones;
The periodic electricity consumption data set determining module is used for acquiring electricity consumption data of the target user in the plurality of time sections in each preset time period and obtaining a plurality of periodic electricity consumption data sets;
the target electricity consumption data set determining module is used for obtaining the target electricity consumption data set according to the plurality of periodic electricity consumption data sets;
the first execution module is used for constructing a special electricity utilization data identification model;
the special electricity consumption data set determining module is used for inputting a plurality of electricity consumption data in the plurality of periodic electricity consumption data sets into the special electricity consumption data identification model to obtain the special electricity consumption data set;
the first division threshold determining module is used for randomly selecting power consumption data from a plurality of power consumption data in the plurality of periodic power consumption data sets to serve as a first division threshold;
the first partition node determining module is used for constructing a first partition node of the special electricity utilization data identification model by adopting the first partition threshold value;
The second division threshold determining module is used for randomly selecting power consumption data from a plurality of power consumption data in the plurality of periodic power consumption data sets again to serve as a second division threshold;
the second partition node determining module is used for constructing a second partition node of the special electricity consumption data identification model by adopting the second partition threshold value;
the multi-stage partition node determining module is used for continuously constructing multi-stage partition nodes of the special electricity utilization data identification model;
the special electricity consumption data output node determining module is used for setting special electricity consumption data output nodes according to the multi-stage dividing nodes, wherein single electricity consumption data output by the special electricity consumption data output nodes and the dividing nodes below are special electricity consumption data;
the second execution module is used for obtaining the special electricity utilization data identification model according to the multi-stage dividing nodes and the special electricity utilization data output nodes;
the habit path construction module is used for constructing an electricity utilization habit characteristic analysis path;
The peak value path construction module is used for constructing an electricity consumption peak value characteristic analysis path;
the third execution module is used for obtaining an electricity consumption characteristic analysis model according to the electricity consumption habit characteristic analysis path and the electricity consumption peak characteristic analysis path, wherein input data of the electricity consumption habit characteristic analysis path is an electricity consumption data set, output data is a user electricity consumption habit characteristic, input data of the electricity consumption peak characteristic analysis path is a special electricity consumption data set, output data is a user electricity consumption peak characteristic, and the user electricity consumption habit characteristic and the user electricity consumption peak characteristic form a user characteristic;
the system comprises a sample electricity utilization data set determining module, a sample electricity utilization data set generating module and a sample electricity utilization data set generating module, wherein the sample electricity utilization data set determining module is used for acquiring target electricity utilization data sets of a plurality of sample users and taking the target electricity utilization data sets as a plurality of sample electricity utilization data sets;
the sample user electricity habit feature determining module is used for marking the electricity habit features of the plurality of sample users to obtain the electricity habit features of the plurality of sample users;
the fourth execution module is used for constructing the power utilization habit characteristic analysis path based on the BP neural network;
The fifth execution module is used for performing cross supervision training and verification on the power consumption habit feature analysis path by adopting the plurality of sample power consumption data sets and the power consumption habit features of the plurality of sample users to obtain the power consumption habit feature analysis path with accuracy meeting preset requirements;
a sample user feature determination module for obtaining a plurality of sample user features;
the sample electricity utilization configuration adjustment scheme determining module is used for obtaining various sample electricity utilization configuration adjustment schemes according to the user characteristics of the plurality of samples;
the mapping relation determining module is used for constructing mapping relation between the user characteristics of the plurality of samples and the power utilization configuration adjustment scheme of the plurality of samples;
and the electricity utilization configuration adjustment scheme determining module is used for inputting the target user characteristics into the mapping relation to obtain the electricity utilization configuration adjustment scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211602617.1A CN115600014B (en) | 2022-12-14 | 2022-12-14 | Personalized power distribution configuration method and system based on electricity utilization characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211602617.1A CN115600014B (en) | 2022-12-14 | 2022-12-14 | Personalized power distribution configuration method and system based on electricity utilization characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115600014A CN115600014A (en) | 2023-01-13 |
| CN115600014B true CN115600014B (en) | 2024-02-20 |
Family
ID=84854243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211602617.1A Active CN115600014B (en) | 2022-12-14 | 2022-12-14 | Personalized power distribution configuration method and system based on electricity utilization characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600014B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116894552A (en) * | 2023-06-28 | 2023-10-17 | 浙江海亮科技有限公司 | Students' dormitory distribution method, device, electronic device and storage medium |
| CN117057666B (en) * | 2023-09-07 | 2024-02-06 | 浙江万胜智通科技有限公司 | Distribution quality evaluation method and system for digital distribution network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122864A (en) * | 2017-04-28 | 2017-09-01 | 国网山东省电力公司泰安供电公司 | Power consumer requirement analysis method and device |
| CN108462173A (en) * | 2018-04-23 | 2018-08-28 | 黄宇松 | A kind of electric energy control method, device and equipment based on user power utilization custom |
| CN113591899A (en) * | 2021-06-10 | 2021-11-02 | 国网河北省电力有限公司营销服务中心 | Power customer portrait recognition method and device and terminal equipment |
| CN113962508A (en) * | 2021-09-03 | 2022-01-21 | 国网北京市电力公司 | Identification method and identification device for electricity object and electronic equipment |
| CN114298863A (en) * | 2022-03-11 | 2022-04-08 | 浙江万胜智能科技股份有限公司 | Data acquisition method and system of intelligent meter reading terminal |
| CN114492994A (en) * | 2022-01-25 | 2022-05-13 | 南方电网大数据服务有限公司 | Power information processing system, method and device based on power big data |
| CN115471122A (en) * | 2022-10-10 | 2022-12-13 | 宁波边缘物联科技有限公司 | Energy consumption evaluation method and system based on metadata model |
-
2022
- 2022-12-14 CN CN202211602617.1A patent/CN115600014B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122864A (en) * | 2017-04-28 | 2017-09-01 | 国网山东省电力公司泰安供电公司 | Power consumer requirement analysis method and device |
| CN108462173A (en) * | 2018-04-23 | 2018-08-28 | 黄宇松 | A kind of electric energy control method, device and equipment based on user power utilization custom |
| CN113591899A (en) * | 2021-06-10 | 2021-11-02 | 国网河北省电力有限公司营销服务中心 | Power customer portrait recognition method and device and terminal equipment |
| CN113962508A (en) * | 2021-09-03 | 2022-01-21 | 国网北京市电力公司 | Identification method and identification device for electricity object and electronic equipment |
| CN114492994A (en) * | 2022-01-25 | 2022-05-13 | 南方电网大数据服务有限公司 | Power information processing system, method and device based on power big data |
| CN114298863A (en) * | 2022-03-11 | 2022-04-08 | 浙江万胜智能科技股份有限公司 | Data acquisition method and system of intelligent meter reading terminal |
| CN115471122A (en) * | 2022-10-10 | 2022-12-13 | 宁波边缘物联科技有限公司 | Energy consumption evaluation method and system based on metadata model |
Non-Patent Citations (1)
| Title |
|---|
| BP神经网络在用电用户分类中的应用;李秋硕;王岩;孙宇军;肖勇;欧阳涛;;现代电子技术;20170501(09);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115600014A (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115600014B (en) | Personalized power distribution configuration method and system based on electricity utilization characteristics | |
| Donate et al. | Time series forecasting by evolving artificial neural networks with genetic algorithms, differential evolution and estimation of distribution algorithm | |
| Hvidsten et al. | Predicting gene function from gene expressions and ontologies | |
| CN111199016A (en) | DTW-based improved K-means daily load curve clustering method | |
| CN110515364B (en) | Cutter wear state detection method based on variational modal decomposition and LS-SVM | |
| CN109685277A (en) | Electricity demand forecasting method and device | |
| CN111178611B (en) | Method for predicting daily electric quantity | |
| CN108960488B (en) | Saturated load spatial distribution accurate prediction method based on deep learning and multi-source information fusion | |
| CN110348608A (en) | A kind of prediction technique for improving LSTM based on fuzzy clustering algorithm | |
| CN111028100A (en) | Refined short-term load prediction method, device and medium considering meteorological factors | |
| CN116913435B (en) | High-strength engineering plastic evaluation method and system based on component analysis | |
| CN112288137A (en) | LSTM short-term load prediction method and device considering electricity price and Attention mechanism | |
| CN110633859A (en) | Hydrological sequence prediction method for two-stage decomposition integration | |
| CN113642652A (en) | Method, device and equipment for generating fusion model | |
| CN114462683A (en) | Cloud edge collaborative multi-residential area load prediction method based on federal learning | |
| CN110517774A (en) | A method of prediction abnormal body temperature | |
| Mansor et al. | Modified Artificial Immune System Algorithm with Elliot Hopfield Neural Network For 3-Satisfiability Programming. | |
| CN115470862A (en) | Dynamic self-adaptive load prediction model combination method | |
| CN117291069A (en) | LSTM sewage water quality prediction method based on improved DE and attention mechanism | |
| Al Shami et al. | Unified knowledge based economy hybrid forecasting | |
| Papavlasopoulos et al. | A non-linear index to evaluate a journal’s scientific impact | |
| CN118183886A (en) | Neural network-based water quality model basic parameter dynamic tuning method and device | |
| CN112149870B (en) | Pig house ammonia concentration combination prediction method based on ISODATA clustering and Elman neural network | |
| CN115619028A (en) | Clustering algorithm fusion-based power load accurate prediction method | |
| Anand et al. | Hybrid data mining systems: the next generation |
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 | ||
| CB02 | Change of applicant information |
Address after: No. 109, Yongchang Road, Shifeng Street, Tiantai County, Taizhou City, Zhejiang Province 317200 Applicant after: ZHEJIANG WELLSUN INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 317200 15 Xingye East Third Street, Fuxi street, Tiantai County, Taizhou, Zhejiang Applicant before: ZHEJIANG WELLSUN INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |