Energy Services Demand Forecasting Combined with Feature Preferences and Bidirectional Long- and Short-Term Memory Networks

Accurate and efficient demand forecasting of customer energy services is crucial for quality and risk management in grid customer service. Therefore, this paper proposes a user energy service demand prediction model based on feature selection. The methodology includes introducing a sampling algorith...

Full description

Saved in:
Bibliographic Details
Main Author: KANG Feng, TAN Huochao, SU Liwei, JIAN Donglin, WANG Shuai, QIN Hao, ZHANG Yongjun
Format: Article
Language:zho
Published: Editorial Office of Journal of Shanghai Jiao Tong University 2025-07-01
Series:Shanghai Jiaotong Daxue xuebao
Subjects:
Online Access:https://xuebao.sjtu.edu.cn/article/2025/1006-2467/1006-2467-59-7-1007.shtml
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061542575308800
author KANG Feng, TAN Huochao, SU Liwei, JIAN Donglin, WANG Shuai, QIN Hao, ZHANG Yongjun
author_facet KANG Feng, TAN Huochao, SU Liwei, JIAN Donglin, WANG Shuai, QIN Hao, ZHANG Yongjun
author_sort KANG Feng, TAN Huochao, SU Liwei, JIAN Donglin, WANG Shuai, QIN Hao, ZHANG Yongjun
collection DOAJ
description Accurate and efficient demand forecasting of customer energy services is crucial for quality and risk management in grid customer service. Therefore, this paper proposes a user energy service demand prediction model based on feature selection. The methodology includes introducing a sampling algorithm to solve the class imbalance problem in the data on the basis of analysing the user energy service data, reducing the dimensionality of the data based on an autoencoder to ensure efficient clustering of the K-mean algorithm, constructing a feature selection algorithm based on a lightweight gradient lifting machine to filter the effective features and improve the training efficiency of the prediction model, and establishing a bidirectional long- and short-term memory neural network multi-label predicting model based on an attentional mechanism to refine the user’s energy service demand. Through the analysis of 720 000 work order data from Guangdong Power Grid over three years, showing that the model proposed can effectively improve the prediction accuracy and speed.
format Article
id doaj-art-0c5b908c6c57425db669d02686bb49b6
institution DOAJ
issn 1006-2467
language zho
publishDate 2025-07-01
publisher Editorial Office of Journal of Shanghai Jiao Tong University
record_format Article
series Shanghai Jiaotong Daxue xuebao
spelling doaj-art-0c5b908c6c57425db669d02686bb49b62025-08-20T02:50:12ZzhoEditorial Office of Journal of Shanghai Jiao Tong UniversityShanghai Jiaotong Daxue xuebao1006-24672025-07-015971007101810.16183/j.cnki.jsjtu.2023.458Energy Services Demand Forecasting Combined with Feature Preferences and Bidirectional Long- and Short-Term Memory NetworksKANG Feng, TAN Huochao, SU Liwei, JIAN Donglin, WANG Shuai, QIN Hao, ZHANG Yongjun01. Customer Service Center of Guangdong Power Grid Co., Ltd., Foshan 528000, Guangdong, China;2. School of Electric Power Engineering, South China University of Technology, Guangzhou 510000, ChinaAccurate and efficient demand forecasting of customer energy services is crucial for quality and risk management in grid customer service. Therefore, this paper proposes a user energy service demand prediction model based on feature selection. The methodology includes introducing a sampling algorithm to solve the class imbalance problem in the data on the basis of analysing the user energy service data, reducing the dimensionality of the data based on an autoencoder to ensure efficient clustering of the K-mean algorithm, constructing a feature selection algorithm based on a lightweight gradient lifting machine to filter the effective features and improve the training efficiency of the prediction model, and establishing a bidirectional long- and short-term memory neural network multi-label predicting model based on an attentional mechanism to refine the user’s energy service demand. Through the analysis of 720 000 work order data from Guangdong Power Grid over three years, showing that the model proposed can effectively improve the prediction accuracy and speed.https://xuebao.sjtu.edu.cn/article/2025/1006-2467/1006-2467-59-7-1007.shtmlenergy servicesdemand forecastingclass imbalanceautomatic encoderfeature optimizationmulti label classification
spellingShingle KANG Feng, TAN Huochao, SU Liwei, JIAN Donglin, WANG Shuai, QIN Hao, ZHANG Yongjun
Energy Services Demand Forecasting Combined with Feature Preferences and Bidirectional Long- and Short-Term Memory Networks
Shanghai Jiaotong Daxue xuebao
energy services
demand forecasting
class imbalance
automatic encoder
feature optimization
multi label classification
title Energy Services Demand Forecasting Combined with Feature Preferences and Bidirectional Long- and Short-Term Memory Networks
title_full Energy Services Demand Forecasting Combined with Feature Preferences and Bidirectional Long- and Short-Term Memory Networks
title_fullStr Energy Services Demand Forecasting Combined with Feature Preferences and Bidirectional Long- and Short-Term Memory Networks
title_full_unstemmed Energy Services Demand Forecasting Combined with Feature Preferences and Bidirectional Long- and Short-Term Memory Networks
title_short Energy Services Demand Forecasting Combined with Feature Preferences and Bidirectional Long- and Short-Term Memory Networks
title_sort energy services demand forecasting combined with feature preferences and bidirectional long and short term memory networks
topic energy services
demand forecasting
class imbalance
automatic encoder
feature optimization
multi label classification
url https://xuebao.sjtu.edu.cn/article/2025/1006-2467/1006-2467-59-7-1007.shtml
work_keys_str_mv AT kangfengtanhuochaosuliweijiandonglinwangshuaiqinhaozhangyongjun energyservicesdemandforecastingcombinedwithfeaturepreferencesandbidirectionallongandshorttermmemorynetworks