[go: up one dir, main page]

CN112884307A - Power consumption data-based standing population prediction model construction method - Google Patents

Power consumption data-based standing population prediction model construction method Download PDF

Info

Publication number
CN112884307A
CN112884307A CN202110149982.0A CN202110149982A CN112884307A CN 112884307 A CN112884307 A CN 112884307A CN 202110149982 A CN202110149982 A CN 202110149982A CN 112884307 A CN112884307 A CN 112884307A
Authority
CN
China
Prior art keywords
data
rate
prediction model
electricity
standing population
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110149982.0A
Other languages
Chinese (zh)
Inventor
杨波
王�华
杨明杰
高建勇
王栋
延亮
李杏丽
卓俊宇
高承敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Information and Communication Co of State Grid Gansu Electric Power Co Ltd
Original Assignee
Information and Communication Co of State Grid Gansu Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Information and Communication Co of State Grid Gansu Electric Power Co Ltd filed Critical Information and Communication Co of State Grid Gansu Electric Power Co Ltd
Priority to CN202110149982.0A priority Critical patent/CN112884307A/en
Publication of CN112884307A publication Critical patent/CN112884307A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0637Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G06Q10/06375Prediction of business process outcome or impact based on a proposed change
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a standing population prediction model construction method based on electricity consumption data, and belongs to the technical field of mathematical modeling. The method realizes the construction of the standing population prediction model by confirming the four steps of electric power behavior characteristics, data preprocessing, data training and model evaluation. According to the method, the electricity stealing samples are constructed, the prediction model is built on the voltage data set, and the prediction model is combined with the users with abnormal line loss, so that the recall rate and the accuracy of the lead-in line are improved, and a more accurate prediction effect is obtained. According to the method, the standing population is predicted, the accuracy rate of the incoming line loss rate is 52.69-74.11%, the recall rate of the incoming line loss rate is 71.37-99.49%, the metric value is 70.45-73.48%, and the prediction accuracy is high.

Description

Power consumption data-based standing population prediction model construction method
Technical Field
The invention belongs to the technical field of mathematical modeling, and particularly relates to a standing population prediction model construction method based on electricity consumption data.
Background
The population prediction model is a comprehensive system and a quantitative method which are established on the basis of the current population condition and on the condition of prediction parameters and used for measuring and calculating the future population. Population prediction methods can be divided into dynamic and static predictions. Population prediction models fall into the category of dynamic population prediction. The basic idea of establishing a population prediction model is as follows: the method comprises the steps of grasping main factors among a plurality of factors influencing population development, establishing a dynamic mathematical model describing population development process, enabling the dynamic mathematical model to accurately reflect the dynamic change process of future population development, and reasonably defining and describing various variables, indexes and mutual dependency relations among the variables and the indexes in the population development process.
The invention discloses a user electricity consumption deviation analysis method based on an intelligent algorithm, which is found through the search of the existing documents, and is disclosed in the patent application of Chinese patent publication No. CN109460849A, publication No. 2019, 03, 12 and mainly comprises the steps of calculating a Pearson coefficient of each deviation influence factor and the total annual electricity consumption of a prediction area through a two-dimensional scatter diagram of the prediction area in which the total annual electricity consumption is combined, establishing an electricity consumption prediction model by utilizing a grey neural network, and predicting the total annual electricity consumption of the prediction area by adopting an electricity consumption prediction model. Although the invention can improve the accuracy of prediction to a certain extent, the detection range is narrow.
Disclosure of Invention
The invention aims to provide a power consumption data-based standing population prediction model construction method which improves prediction accuracy and has a wide detection range.
In order to achieve the purpose, the invention adopts the following technical scheme:
a standing population prediction model construction method based on electricity utilization data comprises the following steps:
1) determining characteristics reflecting the electricity consumption behavior of a user, extracting data from an acquisition system, and acquiring economic parameters related to electricity prediction;
2) preprocessing the data extracted in the step 1), detecting whether missing values and abnormal values exist in the data, then cleaning the data, and converting a data format by using read thermal coding to convert the data into numerical data;
3) training the data by using a classification algorithm, constructing an anti-electricity-stealing model, then performing error removal processing on the data in the step 2) by using an Adam algorithm, calculating an average value of line loss rates of days before and after each line, and calculating the growth rate of each two average values;
4) and comparing and analyzing the experimental result of each model, evaluating the anti-electricity-stealing early warning model, generating a random number of positive-phase and negative-phase distribution by using the cloud generator, and calculating a specific input value of the cloud generator.
Further, the CNN layer is used to extract the data hiding features in step 3).
Further, the evaluation index in step 4) includes a recall rate and a precision rate, and the recall rate and the precision rate are proportional, wherein the recall rate is npre _ real/nreal, and the precision rate is npre _ real/npre.
And further, the voltage in the power distribution network is monitored in real time by using the power distribution network control center, and when the voltage out-of-limit condition occurs, the voltage is adjusted by using the AVC function of the power distribution network by the control center.
Compared with the prior art, the invention has the beneficial effects that:
1) according to the method, the electricity stealing samples are constructed, the prediction model is built on the voltage data set, and the prediction model is combined with the users with abnormal line loss, so that the recall rate and the accuracy of the lead-in line are improved, and a more accurate prediction effect is obtained.
2) According to the method, the standing population is predicted, the accuracy rate of the incoming line loss rate is 52.69-74.11%, the recall rate of the incoming line loss rate is 71.37-99.49%, the metric value is 70.45-73.48%, and the prediction accuracy is high.
Detailed Description
The following describes in further detail embodiments of the present invention. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
A standing population prediction model construction method based on electricity utilization data comprises the following steps:
1) determining characteristics reflecting the electricity consumption behavior of a user, extracting data from an acquisition system, and acquiring economic parameters related to electricity prediction;
2) preprocessing the data extracted in the step 1), detecting whether missing values and abnormal values exist in the data, then cleaning the data, and converting a data format by using read thermal coding to convert the data into numerical data;
3) training the data by using a classification algorithm, constructing an anti-electricity-stealing model, then performing error removal processing on the data in the step 2) by using an Adam algorithm, calculating an average value of line loss rates of days before and after each line, calculating the growth rate of each two average values, and extracting data hiding characteristics by using a CNN layer.
4) And comparing and analyzing the experimental result of each model, evaluating the anti-electricity-stealing early warning model, generating a random number of positive-phase and negative-phase distribution by using the cloud generator, and calculating a specific input value of the cloud generator. The evaluation index includes a recall rate and a precision rate, which are proportional to the recall rate, wherein the recall rate is npre _ real/nreal, and the precision rate is npre _ real/npre. The voltage in the power distribution network is monitored in real time by using the power distribution network control center, and when the voltage out-of-limit condition occurs, the voltage is adjusted by using the AVC function of the power distribution network by the control center.
Where nreal is the number of real electricity stealing users, npre is the number of model-predicted electricity stealing users, and npre _ real is the intersection of nreal and npre.
When the recall rate and the precision rate cannot be simultaneously considered, the quality of the model is measured by a metric value f 1:
f1 is 2 × (recall rate × precision)/(recall rate + precision) × 100%,
the following predictions of the standing population were made according to the method of the present invention, and the results of a number of algorithmic model evaluations based on voltage data are shown in table 1:
Figure BDA0002929612570000041
Figure BDA0002929612570000051
as can be seen from Table 1, the accuracy rate of the incoming line loss rate is 52.69-74.11%, the recall rate of the incoming line loss rate is 71.37-99.49%, the metric value is 70.45-73.48% and the prediction accuracy rate is high when the standing population is predicted.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.

Claims (4)

1. A standing population prediction model construction method based on electricity utilization data is characterized by comprising the following steps:
1) determining characteristics reflecting the electricity consumption behavior of a user, extracting data from an acquisition system, and acquiring economic parameters related to electricity prediction;
2) preprocessing the data extracted in the step 1), detecting whether missing values and abnormal values exist in the data, then cleaning the data, and converting a data format by using read thermal coding to convert the data into numerical data;
3) training the data by using a classification algorithm, constructing an anti-electricity-stealing model, then performing error removal processing on the data in the step 2) by using an Adam algorithm, calculating an average value of line loss rates of days before and after each line, and calculating the growth rate of each two average values;
4) and comparing and analyzing the experimental result of each model, evaluating the anti-electricity-stealing early warning model, generating a random number of positive-phase and negative-phase distribution by using the cloud generator, and calculating a specific input value of the cloud generator.
2. The method for constructing a standing population prediction model based on electricity consumption data as claimed in claim 1, wherein the step 3) utilizes a CNN layer to extract data hidden features.
3. The method as claimed in claim 1, wherein the evaluation index in step 4) includes a recall rate and a precision rate, and the recall rate and the precision rate are proportional, wherein the recall rate is npre _ real/nreal and the precision rate is npre _ real/npre.
4. The method for constructing the standing population prediction model based on the electricity consumption data according to claim 1, wherein a power distribution network control center is used for monitoring the voltage in the power distribution network in real time, and when the voltage exceeds the limit, the control center adjusts the voltage by using an AVC function of the power distribution network.
CN202110149982.0A 2021-02-02 2021-02-02 Power consumption data-based standing population prediction model construction method Pending CN112884307A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110149982.0A CN112884307A (en) 2021-02-02 2021-02-02 Power consumption data-based standing population prediction model construction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110149982.0A CN112884307A (en) 2021-02-02 2021-02-02 Power consumption data-based standing population prediction model construction method

Publications (1)

Publication Number Publication Date
CN112884307A true CN112884307A (en) 2021-06-01

Family

ID=76056977

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110149982.0A Pending CN112884307A (en) 2021-02-02 2021-02-02 Power consumption data-based standing population prediction model construction method

Country Status (1)

Country Link
CN (1) CN112884307A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115759430A (en) * 2022-11-23 2023-03-07 国网商用大数据有限公司 Method and device for predicting population mobility based on power data and government affair data

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070265713A1 (en) * 2006-02-03 2007-11-15 Michel Veillette Intelligent Monitoring System and Method for Building Predictive Models and Detecting Anomalies
US20080294558A1 (en) * 2007-05-23 2008-11-27 Masahiro Shimanuki Portable electronic appliance, data processor, data communication system, computer program, data processing method
CN107766979A (en) * 2017-10-23 2018-03-06 国网湖南省电力公司 Methods of electric load forecasting based on cloud model
CN109583680A (en) * 2018-09-30 2019-04-05 国网浙江长兴县供电有限公司 A kind of stealing discrimination method based on support vector machines
CN109740784A (en) * 2018-10-11 2019-05-10 云南电网有限责任公司 A kind of construction method of area power quantity predicting model
CN110137959A (en) * 2019-05-23 2019-08-16 国网湖北省电力有限公司黄冈供电公司 A kind of administering method of Rural Power Distribution Network voltage out-of-limit
US20200074325A1 (en) * 2018-08-29 2020-03-05 National Chiao Tung University Systems and Methods for Creating an Optimal Prediction Model and Obtaining Optimal Prediction Results Based on Machine Learning
CN111191909A (en) * 2019-12-26 2020-05-22 中国电力科学研究院有限公司 An electricity stealing identification system based on data analysis of typical electricity stealing industry and historical electricity stealing sample library
CN112150209A (en) * 2020-06-19 2020-12-29 南京理工大学 Construction method of CNN-LSTM time sequence prediction model based on clustering center

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070265713A1 (en) * 2006-02-03 2007-11-15 Michel Veillette Intelligent Monitoring System and Method for Building Predictive Models and Detecting Anomalies
US20080294558A1 (en) * 2007-05-23 2008-11-27 Masahiro Shimanuki Portable electronic appliance, data processor, data communication system, computer program, data processing method
CN107766979A (en) * 2017-10-23 2018-03-06 国网湖南省电力公司 Methods of electric load forecasting based on cloud model
US20200074325A1 (en) * 2018-08-29 2020-03-05 National Chiao Tung University Systems and Methods for Creating an Optimal Prediction Model and Obtaining Optimal Prediction Results Based on Machine Learning
CN109583680A (en) * 2018-09-30 2019-04-05 国网浙江长兴县供电有限公司 A kind of stealing discrimination method based on support vector machines
CN109740784A (en) * 2018-10-11 2019-05-10 云南电网有限责任公司 A kind of construction method of area power quantity predicting model
CN110137959A (en) * 2019-05-23 2019-08-16 国网湖北省电力有限公司黄冈供电公司 A kind of administering method of Rural Power Distribution Network voltage out-of-limit
CN111191909A (en) * 2019-12-26 2020-05-22 中国电力科学研究院有限公司 An electricity stealing identification system based on data analysis of typical electricity stealing industry and historical electricity stealing sample library
CN112150209A (en) * 2020-06-19 2020-12-29 南京理工大学 Construction method of CNN-LSTM time sequence prediction model based on clustering center

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
M. ANAS ET AL: "Minimizing electricity theft using smart meters in AMI", 2012 SEVENTH INTERNATIONAL CONFERENCE ON P2P, pages 176 - 182 *
杨波: "用电信息采集系统在反窃电中的实践运用", 电力讯息, pages 96 - 97 *
金保华 等: "一种基于电力大数据的反窃电预测方法", 轻工学报, vol. 35, no. 4, pages 81 - 87 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115759430A (en) * 2022-11-23 2023-03-07 国网商用大数据有限公司 Method and device for predicting population mobility based on power data and government affair data

Similar Documents

Publication Publication Date Title
CN107169628B (en) A distribution network reliability assessment method based on big data mutual information attribute reduction
CN110336289A (en) A method, device, equipment, and storage medium for monitoring and identifying electricity loads
CN113077020B (en) Transformer cluster management method and system
CN110636066A (en) Network Security Threat Situation Assessment Method Based on Unsupervised Generative Reasoning
CN108154256A (en) The determining method and device of forecasting risk value, storage medium
CN112149873A (en) Low-voltage transformer area line loss reasonable interval prediction method based on deep learning
CN114580829A (en) Power utilization safety sensing method, equipment and medium based on random forest algorithm
CN114997321A (en) A method, device, electronic device and storage medium for identifying a household change relationship in a station area
Tian et al. A network traffic prediction method based on IFS algorithm optimised LSSVM
CN108960488A (en) A kind of accurate prediction technique of saturation loading spatial distribution based on deep learning and Multi-source Information Fusion
CN120074026B (en) Full-dimensional real-time monitoring stable operation linkage system of power system
CN116148753A (en) Intelligent electric energy meter operation error monitoring system
CN117435937A (en) A smart meter abnormal data identification method, device, equipment and storage medium
CN119583182A (en) A power grid network attack detection method and system based on deep learning
CN119398787B (en) Transaction card swiping early warning method and device based on AI identification
CN116840689A (en) A battery capacity prediction method, device and computer-readable storage medium
CN119577556B (en) Power grid fault online identification system and method based on big data
CN112884307A (en) Power consumption data-based standing population prediction model construction method
CN115166625A (en) Smart meter error estimation method and device
CN118095643B (en) Fire safety situation low-sensitivity optimization method based on multi-mode sensing
CN107274025B (en) System and method for realizing intelligent identification and management of power consumption mode
CN109871998B (en) Power distribution network line loss rate prediction method and device based on expert sample library
CN118017500A (en) Short-term wind power cluster power prediction method based on global information self-adaptive sensing
CN117332280A (en) A low-voltage user-side power consumption behavior clustering method, device, equipment and medium
CN117171548A (en) Intelligent network security situation prediction method based on power grid big data

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210601