Adaptive electricity consumption forecasting approach for universal environments

Abstract The development of an accurate electricity consumption forecast model is crucial for stable operation and intelligent management of power systems. Traditional methods often overlook user heterogeneity and lack measures to address concept drift caused by distribution changes in electricity d...

Full description

Saved in:
Bibliographic Details
Main Authors: Shiqi Zhou, Saisai Ni, Yifeng Han, Zhekang Dong, Chun Sing Lai
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10147-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343916246040576
author Shiqi Zhou
Saisai Ni
Yifeng Han
Zhekang Dong
Chun Sing Lai
author_facet Shiqi Zhou
Saisai Ni
Yifeng Han
Zhekang Dong
Chun Sing Lai
author_sort Shiqi Zhou
collection DOAJ
description Abstract The development of an accurate electricity consumption forecast model is crucial for stable operation and intelligent management of power systems. Traditional methods often overlook user heterogeneity and lack measures to address concept drift caused by distribution changes in electricity data over time. We propose an adaptive electricity consumption probability forecasting method tailored to universal environments. The method includes a nonmonotonic correlation elimination-based recursive feature selection that adaptively determines the optimal feature combination. Our model incorporates a joint loss function combining point and probability forecasting evaluations to accurately quantify online batch errors. It also features a buffer to store batch data showing pattern changes and dynamically adjusts weights to counteract concept drift. We validated our method, adaptive electricity consumption forecast for universal environments (AECF-UC), against some mainstream methods using a multi-environment dataset. Comparative and ablation experiments show that AECF-UC outperforms others, achieving average RMSE, pinball loss and CRPS of 0.3041, 0.0567 and 0.1683 respectively, with the joint loss method improving prediction accuracy by about 6% over the single-loss method. These results indicate that the proposed method exhibits certain advantages in universality and adaptability.
format Article
id doaj-art-de05e8d27ecd451b9dd8bd939836cdbc
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-de05e8d27ecd451b9dd8bd939836cdbc2025-08-20T03:42:49ZengNature PortfolioScientific Reports2045-23222025-07-0115111610.1038/s41598-025-10147-2Adaptive electricity consumption forecasting approach for universal environmentsShiqi Zhou0Saisai Ni1Yifeng Han2Zhekang Dong3Chun Sing Lai4College of Electronic Information, Hangzhou Dianzi UniversityCollege of Electronic Information, Hangzhou Dianzi UniversityCollege of Electronic Information, Hangzhou Dianzi UniversityCollege of Electronic Information, Hangzhou Dianzi UniversityDepartment of Electronic and Computer Engineering, Brunel UniversityAbstract The development of an accurate electricity consumption forecast model is crucial for stable operation and intelligent management of power systems. Traditional methods often overlook user heterogeneity and lack measures to address concept drift caused by distribution changes in electricity data over time. We propose an adaptive electricity consumption probability forecasting method tailored to universal environments. The method includes a nonmonotonic correlation elimination-based recursive feature selection that adaptively determines the optimal feature combination. Our model incorporates a joint loss function combining point and probability forecasting evaluations to accurately quantify online batch errors. It also features a buffer to store batch data showing pattern changes and dynamically adjusts weights to counteract concept drift. We validated our method, adaptive electricity consumption forecast for universal environments (AECF-UC), against some mainstream methods using a multi-environment dataset. Comparative and ablation experiments show that AECF-UC outperforms others, achieving average RMSE, pinball loss and CRPS of 0.3041, 0.0567 and 0.1683 respectively, with the joint loss method improving prediction accuracy by about 6% over the single-loss method. These results indicate that the proposed method exhibits certain advantages in universality and adaptability.https://doi.org/10.1038/s41598-025-10147-2Electricity consumption forecastingConcept driftProbability forecastingHidden Markov model
spellingShingle Shiqi Zhou
Saisai Ni
Yifeng Han
Zhekang Dong
Chun Sing Lai
Adaptive electricity consumption forecasting approach for universal environments
Scientific Reports
Electricity consumption forecasting
Concept drift
Probability forecasting
Hidden Markov model
title Adaptive electricity consumption forecasting approach for universal environments
title_full Adaptive electricity consumption forecasting approach for universal environments
title_fullStr Adaptive electricity consumption forecasting approach for universal environments
title_full_unstemmed Adaptive electricity consumption forecasting approach for universal environments
title_short Adaptive electricity consumption forecasting approach for universal environments
title_sort adaptive electricity consumption forecasting approach for universal environments
topic Electricity consumption forecasting
Concept drift
Probability forecasting
Hidden Markov model
url https://doi.org/10.1038/s41598-025-10147-2
work_keys_str_mv AT shiqizhou adaptiveelectricityconsumptionforecastingapproachforuniversalenvironments
AT saisaini adaptiveelectricityconsumptionforecastingapproachforuniversalenvironments
AT yifenghan adaptiveelectricityconsumptionforecastingapproachforuniversalenvironments
AT zhekangdong adaptiveelectricityconsumptionforecastingapproachforuniversalenvironments
AT chunsinglai adaptiveelectricityconsumptionforecastingapproachforuniversalenvironments