CN109214722B - Multi-agent system for processing data exception - Google Patents

Multi-agent system for processing data exception Download PDF

Info

Publication number
CN109214722B
CN109214722B CN201811325448.5A CN201811325448A CN109214722B CN 109214722 B CN109214722 B CN 109214722B CN 201811325448 A CN201811325448 A CN 201811325448A CN 109214722 B CN109214722 B CN 109214722B
Authority
CN
China
Prior art keywords
data
agent
abnormal
electric quantity
sample
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
Application number
CN201811325448.5A
Other languages
Chinese (zh)
Other versions
CN109214722A (en
Inventor
吉宇
张乐
黄霆
张敏
徐晓轶
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.)
Nantong Power Supply Co Of State Grid Jiangsu Electric Power Co
Original Assignee
Nantong Power Supply Co Of State Grid Jiangsu Electric Power Co
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 Nantong Power Supply Co Of State Grid Jiangsu Electric Power Co filed Critical Nantong Power Supply Co Of State Grid Jiangsu Electric Power Co
Priority to CN201811325448.5A priority Critical patent/CN109214722B/en
Publication of CN109214722A publication Critical patent/CN109214722A/en
Application granted granted Critical
Publication of CN109214722B publication Critical patent/CN109214722B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention provides a multi-agent system for processing data anomalies, which comprises a data monitoring agent, a data organization agent, a sample generation agent, a numerical estimation agent and a data processing agent; the data monitoring agent detects data abnormality and forms an abnormal data point number and a time mark, sends the abnormal data point number and the time mark to the data organization agent to form and maintain an abnormal data record log, sends a request for generating sample data to the sample generation agent, generates the sample data by the sample generation agent and sends the sample data to the numerical value estimation agent to obtain an electric quantity estimated value, and finally sends the electric quantity estimated value to the data processing agent to complete calculation of an electric energy meter bottom code value, and completes replacement of the table bottom code value of an abnormal data point and recalculation and reckoning of the electric quantity through interaction with the data organization agent. The invention provides a multi-agent system for processing data abnormality, which can intelligently and reliably automatically process abnormal data of an electric energy meter.

Description

Multi-agent system for processing data exception
Technical Field
The invention belongs to the technical field of electric power measurement, and particularly relates to a multi-agent system for processing data anomalies.
Background
With the rapid development of society and economy in China, power supply and distribution enterprises in China are also unprecedented. The advent and in-depth application of national power grids has greatly driven centralized power production and supply in China. The electric energy meter is mainly used for recording the electric quantity consumed by electric equipment of a user, and the electric quantity recorded by the electric energy meter is an important basis for the electric power management department to charge the electric charge to the user. In order to meet the requirements of timely collecting and accurately settling the electric energy data, a power supply company establishes an electric energy metering system covering a full gateway, achieves the functions of remote automatic collection, automatic statistical calculation, automatic formation of various time-sharing electric quantity statistical reports and the like of the electric energy data, and provides a reliable means for electric quantity settlement. Under strong electromagnetic interference environments such as transformer substations, power plants and the like, irregular distortion or missing of the bottom code of the electric energy meter can occur. Therefore, how to intelligently and reliably automatically process the abnormal data of the electric energy meter is an important factor for effectively reducing the electricity disputes between the power management department and the user.
Disclosure of Invention
The invention provides a multi-agent system for processing data abnormality, which can intelligently and reliably automatically process abnormal data of an electric energy meter.
The invention relates to a multi-agent system for processing data exception, which comprises a data monitoring agent, a data organization agent, a sample generation agent, a numerical value estimation agent and a data processing agent, wherein the data monitoring agent is connected with the data organization agent, the data organization agent is also respectively connected with the sample generation agent and the data processing agent, and the numerical value estimation agent is respectively connected with the sample generation agent and the data processing agent; the multi-agent system detects data abnormality through the data monitoring agent, forms an abnormal data point number and an abnormal time mark, sends an abnormal data request to the data organization agent, forms and maintains an abnormal data record log, sends a request for generating sample data to the sample generation agent, generates the sample data and transmits the sample data to the numerical value estimation agent to obtain an electric quantity estimated value, and then transmits the electric quantity estimated value to the data processing agent to complete calculation of an electric energy meter bottom code value, and completes table bottom code value substitution of the abnormal data point and electric quantity re-calculation and re-statistics processing through interaction with the data organization agent.
The data monitoring agent is used for monitoring the abnormity of the bottom code data of the electric energy meter, including monitoring the data distortion and monitoring the data loss, and the phenomena of the data distortion and the data loss can be effectively detected by detecting the added value of the bottom code in one integration period and judging the data quality state mark of the bottom code; the data monitoring agent can autonomously monitor all the table bottom code data, and when data distortion or data missing is monitored, the point number corresponding to the abnormal table bottom code data and the abnormal data time mark t are automatically obtained e And notifying the data organization agent of the information, and sending an abnormal data processing request to the data organization agent.
The data organization agent receives the data from the data monitoring agentAfter the exception handling request, automatically completing the determination of the corresponding telemetry point number and the electric quantity integration time range thereof according to the point number of the exception data and the time mark of the exception data, and notifying corresponding information to the sample generation agent; the data organization agent marks t with the abnormal data time scale e Integrating the integrated electric quantity data at each minute time within 15min before and after the center as a curve fitting sample, and using the abnormal data time mark t e For reference, determining the electric quantity integration time range as [ t ] e -900，t e +900]。
The sample generation agents are distributed in the whole electric energy management system, point numbers and integral time ranges of electric quantity integral measuring points obtained through the data organization agents are used for completing numerical integration of minute-level electric energy of the measuring points and forming samples for curve fitting: first, [ t ] is formed e -900，t e +900]Integrated charge per minute during the period
Figure BDA0001858619690000021
The p is k For the k-th minute, the actual active power value is the C' 0 Is a measurement multiple; next, by integrating the integrated electric power values per minute in the integration time range, an integrated electric power value corresponding to each minute from the integration start time is formed +.>
Figure BDA0001858619690000022
And form sample data (E i ，t i )。
The numerical value estimation agent adopts a least square method to perform curve fitting on sample data, and completes evaluation on fitting precision of approximation functions, an approximation function with highest fitting precision is selected as an optimal approximation function formula of the accumulated integral electric quantity E (t), and t is obtained based on the function formula e Estimation of the time-of-day accumulated integral electric quantity value
Figure BDA0001858619690000023
And the estimated value +.>
Figure BDA0001858619690000024
As parameters to the data processing agent.
After receiving the data notification, the data processing agent calculates the approximate value of the abnormal table bottom code according to a formula
Figure BDA0001858619690000025
Obtaining the approximation +.>
Figure BDA0001858619690000026
Then, the data processing agent and the data organization agent cooperate to complete the replacement operation of the abnormal table bottom code data, and trigger the recalculation and the recalculation of the electric quantity of the gateway point; the C is 0 Converting the secondary electric quantity of the gateway point into a metering multiplying power of the primary electric quantity; said->
Figure BDA0001858619690000027
At t e -900 hours of electric energy meter bottom code data of the gateway point.
Drawings
Fig. 1 is a schematic diagram of a multi-agent system for handling data anomalies according to the present invention.
Detailed Description
A detailed description of a multi-agent system for handling data anomalies according to the present invention is provided below with reference to the accompanying drawings.
As shown in fig. 1, the multi-agent system of the present invention includes a data monitoring agent, a data organization agent, a sample generation agent, a numerical estimation agent, and a data processing agent, wherein the data monitoring agent is connected with the data organization agent, the data organization agent is also connected with the sample generation agent and the data processing agent, and the numerical estimation agent is connected with the sample generation agent and the data processing agent; the multi-agent system detects data abnormality through the data monitoring agent, forms an abnormal data point number and an abnormal time mark, sends an abnormal data request to the data organization agent, forms and maintains an abnormal data record log, sends a request for generating sample data to the sample generation agent, generates the sample data and transmits the sample data to the numerical value estimation agent to obtain an electric quantity estimated value, and then transmits the electric quantity estimated value to the data processing agent to complete calculation of an electric energy meter bottom code value, and completes table bottom code value substitution of the abnormal data point and electric quantity re-calculation and re-statistics processing through interaction with the data organization agent.
The data monitoring agent is used for monitoring the abnormity of the bottom code data of the electric energy meter, including monitoring the data distortion and monitoring the data loss, and the phenomena of the data distortion and the data loss can be effectively detected by detecting the added value of the bottom code in one integration period and judging the data quality state mark of the bottom code; the data monitoring agent can autonomously monitor all the table bottom code data, and when data distortion or data missing is monitored, the point number corresponding to the abnormal table bottom code data and the abnormal data time mark t are automatically obtained e And notifying the data organization agent of the information, and sending an abnormal data processing request to the data organization agent.
After receiving the data exception handling request of the data monitoring agent, the data organization agent automatically completes the determination of the corresponding telemetry point number and the electric quantity integration time range thereof according to the point number of the exception data and the time mark of the exception data, and notifies the corresponding information to the sample generation agent; the data organization agent marks t with the abnormal data time scale e Integrating the integrated electric quantity data at each minute time within 15min before and after the center as a curve fitting sample, and using the abnormal data time mark t e For reference, determining the electric quantity integration time range as [ t ] e -900，t e +900]。
The sample generation agents are distributed in the whole electric energy management system, point numbers and integral time ranges of electric quantity integral measuring points obtained through the data organization agents are used for completing numerical integration of minute-level electric energy of the measuring points and forming samples for curve fitting: first, [ t ] is formed e -900，t e +900]Integrated charge per minute during the period
Figure BDA0001858619690000031
The p is k For the k-th minute, the actual active power value is the C' 0 Is a measurement multiple; next, by integrating the integrated electric power values per minute in the integration time range, an integrated electric power value corresponding to each minute from the integration start time is formed +.>
Figure BDA0001858619690000041
And form sample data (E i ，t i )。
The numerical value estimation agent adopts a least square method to perform curve fitting on sample data, and completes evaluation on fitting precision of approximation functions, an approximation function with highest fitting precision is selected as an optimal approximation function formula of the accumulated integral electric quantity E (t), and t is obtained based on the function formula e Estimation of the time-of-day accumulated integral electric quantity value
Figure BDA0001858619690000042
And the estimated value +.>
Figure BDA0001858619690000043
As parameters to the data processing agent.
After receiving the data notification, the data processing agent calculates the approximate value of the abnormal table bottom code according to a formula
Figure BDA0001858619690000044
Obtaining the approximation +.>
Figure BDA0001858619690000045
Then, the data processing agent and the data organization agent cooperate to complete the replacement operation of the abnormal table bottom code data, and trigger the recalculation and the recalculation of the electric quantity of the gateway point; the C is 0 Converting the secondary electric quantity of the gateway point into a metering multiplying power of the primary electric quantity; said->
Figure BDA0001858619690000046
At t e -900 hours of electric energy meter bottom code data of the gateway point.
Finally, it should be noted that the above-mentioned embodiments are merely illustrative of the technical solution of the invention and not limiting thereof. It will be understood by those skilled in the art that modifications and equivalents may be made to the particular embodiments of the invention, which are within the scope of the claims appended hereto.

Claims (5)

1. A multi-agent system for handling data anomalies, the multi-agent system comprising a data monitoring agent, a data organization agent, a sample generation agent, a numerical estimation agent, and a data processing agent, the data monitoring agent being coupled to the data organization agent, the data organization agent being further coupled to the sample generation agent, the data processing agent, respectively, the numerical estimation agent being coupled to the sample generation agent, the data processing agent, respectively; the multi-agent system detects data abnormality through the data monitoring agent, forms an abnormal data point number and an abnormal time mark, sends an abnormal data request to the data organization agent, forms and maintains an abnormal data record log, sends a request for generating sample data to the sample generation agent, generates the sample data and transmits the sample data to the numerical value estimation agent to obtain an electric quantity estimated value, and then transmits the electric quantity estimated value to the data processing agent to complete calculation of an electric energy meter bottom code value, and completes table bottom code value substitution of the abnormal data point and electric quantity re-calculation and re-statistics processing through interaction with the data organization agent;
after receiving the data exception handling request of the data monitoring agent, the data organization agent automatically completes the determination of the corresponding telemetry point number and the electric quantity integration time range thereof according to the point number of the exception data and the time mark of the exception data, and notifies the corresponding information to the sample generation agent; the data organization agent marks t with the abnormal data time scale e Integrating the integrated electric quantity data at each minute time within 15min before and after the center as a curve fitting sample, and using the abnormal data time mark t e For reference, determining the electric quantity integration time range as [ t ] e -900，t e +900]。
2. The multi-agent system for handling data anomalies according to claim 1, wherein said data monitoring agent is configured to monitor anomalies in power meter bottom code data, including monitoring for data distortions and monitoring for data deletions, by detecting an increase in the value of the bottom code in an integration period and determining a bottom code data quality status flag to effectively detect data distortions and data deletions; the data monitoring agent can autonomously monitor all the table bottom code data, and when data distortion or data missing is monitored, the point number corresponding to the abnormal table bottom code data and the abnormal data time mark t are automatically obtained e Information is notified to the data organization agent and an abnormal data processing request is sent to the data organization agent.
3. A multi-agent system for handling data anomalies according to claim 2, wherein the sample generation agents are distributed throughout the power management system, and wherein the point numbers and integration time ranges of the power integration points obtained by the data organization agents complete numerical integration of the minute-level power of the points and form samples for curve fitting: first, [ t ] is formed e -900，t e +900]Integrated charge per minute during the period
Figure FDA0004111383590000011
The p is k For the k-th minute, the actual active power value is the C' 0 Is a measurement multiple; next, by integrating the integrated electric power values per minute in the integration time range, an integrated electric power value corresponding to each minute from the integration start time is formed +.>
Figure FDA0004111383590000012
And form sample data (E i ，t i )。
4. A method for handling data differences according to claim 3The constant multi-agent system is characterized in that the numerical estimation agent adopts a least square method to perform curve fitting on sample data, completes the evaluation of fitting precision of approximation functions, selects the approximation function with the highest fitting precision as the optimal approximation function formula of the accumulated integral electric quantity E (t), and obtains t based on the function formula e Estimation of the time-of-day accumulated integral electric quantity value
Figure FDA0004111383590000021
And the estimated value +.>
Figure FDA0004111383590000022
As parameters to the data processing agent.
5. The system of claim 4, wherein the data processing agent calculates the approximation of the exception table base code according to a formula after receiving the data notification
Figure FDA0004111383590000023
Obtaining the approximation +.>
Figure FDA0004111383590000024
Then, the data processing agent and the data organization agent cooperate to complete the replacement operation of the abnormal table bottom code data, and trigger the recalculation and the recalculation of the electric quantity of the gateway point; the C is 0 Converting the secondary electric quantity of the gateway point into a metering multiplying power of the primary electric quantity; said->
Figure FDA0004111383590000025
At t e -900 hours of electric energy meter bottom code data of the gateway point. />
CN201811325448.5A 2018-11-08 2018-11-08 Multi-agent system for processing data exception Active CN109214722B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811325448.5A CN109214722B (en) 2018-11-08 2018-11-08 Multi-agent system for processing data exception

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811325448.5A CN109214722B (en) 2018-11-08 2018-11-08 Multi-agent system for processing data exception

Publications (2)

Publication Number Publication Date
CN109214722A CN109214722A (en) 2019-01-15
CN109214722B true CN109214722B (en) 2023-05-09

Family

ID=64995924

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811325448.5A Active CN109214722B (en) 2018-11-08 2018-11-08 Multi-agent system for processing data exception

Country Status (1)

Country Link
CN (1) CN109214722B (en)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104330620A (en) * 2014-10-27 2015-02-04 国家电网公司 Automatic acquisition and processing system for electric energy information
CN106053995A (en) * 2016-07-15 2016-10-26 国网山东省电力公司龙口市供电公司 Intelligent electric energy acquisition terminal
CN108362958A (en) * 2017-12-22 2018-08-03 国网冀北电力有限公司 A kind of acquisition fault point diagnosis and method for repairing and mending automatically

Also Published As

Publication number Publication date
CN109214722A (en) 2019-01-15

Similar Documents

Publication Publication Date Title
CN109298379B (en) Data monitoring-based intelligent electric meter field error abnormity identification method
CN105911499B (en) Ultrasonic wave shelf depreciation metering system and method under site environment
CN107069960B (en) Online defect diagnosis method for secondary operation and maintenance management system
CN110375787A (en) A kind of measuring instrument operating status on-line evaluation method
CN112305492B (en) Intelligent electric energy meter online error check accurate control system and method thereof
CN110928866A (en) Line topology checking method and system based on power failure information big data analysis
CN110187193B (en) Dielectric loss monitoring system and method based on total-station voltage transformer stability judgment
CN112346000B (en) Intelligent electric energy meter operation error data statistical processing system and method
CN110139235A (en) The management method and system of the wireless sensor of dynamic environment monitoring system
CN108490285B (en) Low-voltage transformer area line loss rate calculation method based on voltage drop method
CN104165660A (en) Intelligent distribution and transformation monitoring terminal capable of calculating winding temperature
CN109828229A (en) Electric energy data transmits consistency desired result method between a kind of multiservice system
CN110736957B (en) Online detection system and method for electric energy metering device based on clock synchronization
CN208127987U (en) A kind of novel intelligent distribution transformer terminals based on cloud platform
CN107453481B (en) Method for rapidly discovering power failure of low-voltage transformer area
CN110675018B (en) Line loss anomaly analysis and closed-loop management method based on expert rules
CN109214722B (en) Multi-agent system for processing data exception
CN110687494A (en) Method and system for monitoring faults of remote gateway electric energy meter
CN113034307B (en) Data acquisition method for power enterprise
CN203773039U (en) Novel insulation ohmmeter intelligent calibrating apparatus
CN110750760B (en) Abnormal theoretical line loss detection method based on situation awareness and control diagram
WO2023109882A1 (en) Smart power meter
CN115995880A (en) Comprehensive monitoring and analyzing method and system for multidimensional state of power distribution automation terminal
CN205377455U (en) Online monitored control system of wind -powered electricity generation field electric energy quality
CN210323340U (en) Remote verification system of intelligent electric energy meter

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant