Research on anomaly detection and correction of power metering data based on machine learning algorithm

Electric energy measurement is the basis of marketization of electric energy. If the power metering device is abnormal, it will directly affect the economic interests of both sides. At present, the electric energy measurement data of power grid enterprises has generally adopted the mode of remote ce...

Full description

Saved in:
Bibliographic Details
Main Authors: Sida Zheng, Meiying Zhu, Ying Liu
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:Science and Technology for Energy Transition
Subjects:
Online Access:https://www.stet-review.org/articles/stet/full_html/2025/01/stet20240325/stet20240325.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841554630532661248
author Sida Zheng
Meiying Zhu
Ying Liu
author_facet Sida Zheng
Meiying Zhu
Ying Liu
author_sort Sida Zheng
collection DOAJ
description Electric energy measurement is the basis of marketization of electric energy. If the power metering device is abnormal, it will directly affect the economic interests of both sides. At present, the electric energy measurement data of power grid enterprises has generally adopted the mode of remote centralized collection. The existing methods of abnormal detection and location of electric energy metering are mainly through the analysis of the abnormal data alarm issued by the electric energy acquisition system and the on-site inspection of the metering device. With the continuous expansion of the scale of electric power data, the existing methods highlight the shortcomings of low accuracy and low efficiency. In order to explore the optimal solution to the above problems, this paper constructs a multi-model fusion anomaly detection method of electric energy measurement data based on machine learning, and gives the anomaly correction scheme of electric energy measurement data. The results show that the fusion model has the best performance in the actual situation, with Area Under Curve (AUC) reaching 0.9653 and True Positive Rate (TPR) exceeding 0.64 under the condition of zero False Positive Threshold (FPT). The comprehensive performance is better than that of other single models.
format Article
id doaj-art-5ad79f0f4bbf4692a4c5f7a1be9c7c18
institution Kabale University
issn 2804-7699
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series Science and Technology for Energy Transition
spelling doaj-art-5ad79f0f4bbf4692a4c5f7a1be9c7c182025-01-08T11:24:01ZengEDP SciencesScience and Technology for Energy Transition2804-76992025-01-0180610.2516/stet/2024106stet20240325Research on anomaly detection and correction of power metering data based on machine learning algorithmSida Zheng0Meiying Zhu1Ying Liu2State Grid Jibei Electric Power Company Limited Center of MetrologyState Grid Jibei Electric Power Company Limited Center of MetrologyState Grid Jibei Electric Power Company Limited Center of MetrologyElectric energy measurement is the basis of marketization of electric energy. If the power metering device is abnormal, it will directly affect the economic interests of both sides. At present, the electric energy measurement data of power grid enterprises has generally adopted the mode of remote centralized collection. The existing methods of abnormal detection and location of electric energy metering are mainly through the analysis of the abnormal data alarm issued by the electric energy acquisition system and the on-site inspection of the metering device. With the continuous expansion of the scale of electric power data, the existing methods highlight the shortcomings of low accuracy and low efficiency. In order to explore the optimal solution to the above problems, this paper constructs a multi-model fusion anomaly detection method of electric energy measurement data based on machine learning, and gives the anomaly correction scheme of electric energy measurement data. The results show that the fusion model has the best performance in the actual situation, with Area Under Curve (AUC) reaching 0.9653 and True Positive Rate (TPR) exceeding 0.64 under the condition of zero False Positive Threshold (FPT). The comprehensive performance is better than that of other single models.https://www.stet-review.org/articles/stet/full_html/2025/01/stet20240325/stet20240325.htmlmachine learningelectric energy measurement dataanomaly detectioncorrectionmulti-model fusion
spellingShingle Sida Zheng
Meiying Zhu
Ying Liu
Research on anomaly detection and correction of power metering data based on machine learning algorithm
Science and Technology for Energy Transition
machine learning
electric energy measurement data
anomaly detection
correction
multi-model fusion
title Research on anomaly detection and correction of power metering data based on machine learning algorithm
title_full Research on anomaly detection and correction of power metering data based on machine learning algorithm
title_fullStr Research on anomaly detection and correction of power metering data based on machine learning algorithm
title_full_unstemmed Research on anomaly detection and correction of power metering data based on machine learning algorithm
title_short Research on anomaly detection and correction of power metering data based on machine learning algorithm
title_sort research on anomaly detection and correction of power metering data based on machine learning algorithm
topic machine learning
electric energy measurement data
anomaly detection
correction
multi-model fusion
url https://www.stet-review.org/articles/stet/full_html/2025/01/stet20240325/stet20240325.html
work_keys_str_mv AT sidazheng researchonanomalydetectionandcorrectionofpowermeteringdatabasedonmachinelearningalgorithm
AT meiyingzhu researchonanomalydetectionandcorrectionofpowermeteringdatabasedonmachinelearningalgorithm
AT yingliu researchonanomalydetectionandcorrectionofpowermeteringdatabasedonmachinelearningalgorithm