Risk prediction method for power Internet of Things operation based on ensemble learning

INTRODUCTION: The power Internet of Things is an important strategic support for the State Grid Corporation of China to build an international leading energy internet enterprise. However, the operating environment of the power Internet of Things is complex and varied, which has serious implications...

Full description

Saved in:
Bibliographic Details
Main Authors: Chao Hong, Xiaoyun Kuang, Yiwei Yang, Yixin Jiang, Yunan Zhang
Format: Article
Language:English
Published: European Alliance for Innovation (EAI) 2025-02-01
Series:EAI Endorsed Transactions on Energy Web
Subjects:
Online Access:https://publications.eai.eu/index.php/ew/article/view/6045
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078554554892288
author Chao Hong
Xiaoyun Kuang
Yiwei Yang
Yixin Jiang
Yunan Zhang
author_facet Chao Hong
Xiaoyun Kuang
Yiwei Yang
Yixin Jiang
Yunan Zhang
author_sort Chao Hong
collection DOAJ
description INTRODUCTION: The power Internet of Things is an important strategic support for the State Grid Corporation of China to build an international leading energy internet enterprise. However, the operating environment of the power Internet of Things is complex and varied, which has serious implications for the safe operation of the power Internet of Things. OBJECTIVES: To timely predict the various risk. METHODS: A data set is fused based on time series. The training set is over-sampled using an adaptive synthetic oversampling method. Then, by jointly considering the contribution of features to classification and the correlation between features, a risk prediction method ground on ensemble learning is established. RESULTS: From the results, the accuracy of predicting 5 risk categories increased by 7.00%, 1.10%, 2.20%, 2.30%, and 0.60%, respectively, reducing the features from the original 118 columns to 60 columns and reducing the data dimension by 49.00%. Compared with traditional models, the accuracy was 98.61%, and the overall accuracy was improved by 0.60%. CONCLUSION: This risk prediction scheme can quickly and accurately predict the risk categories that affect its operation. It has high prediction accuracy and fast speed than other algorithms. This research can provide strong assistance for security decision-making in the power Internet of Things.
format Article
id doaj-art-05aa860b2f784ff290f00651b7ca977a
institution DOAJ
issn 2032-944X
language English
publishDate 2025-02-01
publisher European Alliance for Innovation (EAI)
record_format Article
series EAI Endorsed Transactions on Energy Web
spelling doaj-art-05aa860b2f784ff290f00651b7ca977a2025-08-20T02:45:31ZengEuropean Alliance for Innovation (EAI)EAI Endorsed Transactions on Energy Web2032-944X2025-02-011210.4108/ew.6045Risk prediction method for power Internet of Things operation based on ensemble learningChao Hong0Xiaoyun Kuang1Yiwei YangYixin Jiang2Yunan Zhang3CSG Electric Power Research Institute Co.CSG Electric Power Research Institute Co.CSG Electric Power Research Institute Co.CSG Electric Power Research Institute Co. INTRODUCTION: The power Internet of Things is an important strategic support for the State Grid Corporation of China to build an international leading energy internet enterprise. However, the operating environment of the power Internet of Things is complex and varied, which has serious implications for the safe operation of the power Internet of Things. OBJECTIVES: To timely predict the various risk. METHODS: A data set is fused based on time series. The training set is over-sampled using an adaptive synthetic oversampling method. Then, by jointly considering the contribution of features to classification and the correlation between features, a risk prediction method ground on ensemble learning is established. RESULTS: From the results, the accuracy of predicting 5 risk categories increased by 7.00%, 1.10%, 2.20%, 2.30%, and 0.60%, respectively, reducing the features from the original 118 columns to 60 columns and reducing the data dimension by 49.00%. Compared with traditional models, the accuracy was 98.61%, and the overall accuracy was improved by 0.60%. CONCLUSION: This risk prediction scheme can quickly and accurately predict the risk categories that affect its operation. It has high prediction accuracy and fast speed than other algorithms. This research can provide strong assistance for security decision-making in the power Internet of Things. https://publications.eai.eu/index.php/ew/article/view/6045adaptive synthetic oversamplingensemble learningpower internet of thingspredictionrisk
spellingShingle Chao Hong
Xiaoyun Kuang
Yiwei Yang
Yixin Jiang
Yunan Zhang
Risk prediction method for power Internet of Things operation based on ensemble learning
EAI Endorsed Transactions on Energy Web
adaptive synthetic oversampling
ensemble learning
power internet of things
prediction
risk
title Risk prediction method for power Internet of Things operation based on ensemble learning
title_full Risk prediction method for power Internet of Things operation based on ensemble learning
title_fullStr Risk prediction method for power Internet of Things operation based on ensemble learning
title_full_unstemmed Risk prediction method for power Internet of Things operation based on ensemble learning
title_short Risk prediction method for power Internet of Things operation based on ensemble learning
title_sort risk prediction method for power internet of things operation based on ensemble learning
topic adaptive synthetic oversampling
ensemble learning
power internet of things
prediction
risk
url https://publications.eai.eu/index.php/ew/article/view/6045
work_keys_str_mv AT chaohong riskpredictionmethodforpowerinternetofthingsoperationbasedonensemblelearning
AT xiaoyunkuang riskpredictionmethodforpowerinternetofthingsoperationbasedonensemblelearning
AT yiweiyang riskpredictionmethodforpowerinternetofthingsoperationbasedonensemblelearning
AT yixinjiang riskpredictionmethodforpowerinternetofthingsoperationbasedonensemblelearning
AT yunanzhang riskpredictionmethodforpowerinternetofthingsoperationbasedonensemblelearning