Multi-scale electricity consumption prediction model based on land use and interpretable machine learning: A case study of China

The prediction of electricity consumption plays a vital role in promoting sustainable development, ensuring energy security and resilience, facilitating regional planning, and integrating renewable energy sources. A novel electricity consumption characterization and prediction model based on land us...

Full description

Saved in:
Bibliographic Details
Main Authors: Haizhi Luo, Yiwen Zhang, Xinyu Gao, Zhengguang Liu, Xiangzhao Meng, Xiaohu Yang
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Advances in Applied Energy
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666792424000350
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061152949633024
author Haizhi Luo
Yiwen Zhang
Xinyu Gao
Zhengguang Liu
Xiangzhao Meng
Xiaohu Yang
author_facet Haizhi Luo
Yiwen Zhang
Xinyu Gao
Zhengguang Liu
Xiangzhao Meng
Xiaohu Yang
author_sort Haizhi Luo
collection DOAJ
description The prediction of electricity consumption plays a vital role in promoting sustainable development, ensuring energy security and resilience, facilitating regional planning, and integrating renewable energy sources. A novel electricity consumption characterization and prediction model based on land use was proposed. This model achieves land-use subdivision to provide highly correlated variables; exhibits strong interpretability, thereby revealing even marginal effects of land use on electricity consumption; and demonstrates high performance, thereby enabling large-scale simulations and predictions. Using 297 cities and 2,505 counties as case studies, the key findings are as follows: (1) The model demonstrates strong generalization ability (R2 = 0.91), high precision (Kappa = 0.77), and robustness, with an overall prediction accuracy exceeding 80 %; (2) The marginal impact of industrial land on electricity consumption is more complex, with more efficiency achieved by limiting its area to either 104.3 km2 or between 288.2 and 657.3 km2; (3) The marginal impact of commercial and residential land on electricity consumption exhibits a strong linear relationship (R2 > 0.80). Restricting the scale to 11.3 km2 could effectively mitigate this impact. Mixed commercial and residential land is advantageous for overall electricity consumption control, but after exceeding 43.5 km2, separate layout considerations for urban residential land are necessary; (4) In 2030, Shanghai's electricity consumption is projected to reach 155,143 million kW·h, making it the highest among the 297 cities. Meanwhile, Suzhou Industrial Park leads among the 2,505 districts with a consumption of 30,996 million kW·h; (5) Identify future electricity consumption hotspots and clustering characteristics, evaluate the renewable energy potential in these hotspot areas, and propose targeted strategies accordingly.
format Article
id doaj-art-ecc0570ab6144c1fab2edd756b01bdcc
institution DOAJ
issn 2666-7924
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Advances in Applied Energy
spelling doaj-art-ecc0570ab6144c1fab2edd756b01bdcc2025-08-20T02:50:20ZengElsevierAdvances in Applied Energy2666-79242024-12-011610019710.1016/j.adapen.2024.100197Multi-scale electricity consumption prediction model based on land use and interpretable machine learning: A case study of ChinaHaizhi Luo0Yiwen Zhang1Xinyu Gao2Zhengguang Liu3Xiangzhao Meng4Xiaohu Yang5Institute of the Building Environment & Sustainability Technology, School of Human Settlements and Civil Engineering, Xi'an Jiaotong University, Xi'an 710049, ChinaSchool of Architecture and Civil Engineering, Xiamen University, Xiamen 361005, ChinaInstitute of the Building Environment & Sustainability Technology, School of Human Settlements and Civil Engineering, Xi'an Jiaotong University, Xi'an 710049, ChinaDepartment of Chemical Engineering, School of Engineering, The University of Manchester, Manchester, M13 9PL, UKInstitute of the Building Environment & Sustainability Technology, School of Human Settlements and Civil Engineering, Xi'an Jiaotong University, Xi'an 710049, China; Corresponding authors.Institute of the Building Environment & Sustainability Technology, School of Human Settlements and Civil Engineering, Xi'an Jiaotong University, Xi'an 710049, China; School of Sustainable Development of Society and Technology, Mälardalen University, 721 23 Västerås, Sweden; Corresponding authors.The prediction of electricity consumption plays a vital role in promoting sustainable development, ensuring energy security and resilience, facilitating regional planning, and integrating renewable energy sources. A novel electricity consumption characterization and prediction model based on land use was proposed. This model achieves land-use subdivision to provide highly correlated variables; exhibits strong interpretability, thereby revealing even marginal effects of land use on electricity consumption; and demonstrates high performance, thereby enabling large-scale simulations and predictions. Using 297 cities and 2,505 counties as case studies, the key findings are as follows: (1) The model demonstrates strong generalization ability (R2 = 0.91), high precision (Kappa = 0.77), and robustness, with an overall prediction accuracy exceeding 80 %; (2) The marginal impact of industrial land on electricity consumption is more complex, with more efficiency achieved by limiting its area to either 104.3 km2 or between 288.2 and 657.3 km2; (3) The marginal impact of commercial and residential land on electricity consumption exhibits a strong linear relationship (R2 > 0.80). Restricting the scale to 11.3 km2 could effectively mitigate this impact. Mixed commercial and residential land is advantageous for overall electricity consumption control, but after exceeding 43.5 km2, separate layout considerations for urban residential land are necessary; (4) In 2030, Shanghai's electricity consumption is projected to reach 155,143 million kW·h, making it the highest among the 297 cities. Meanwhile, Suzhou Industrial Park leads among the 2,505 districts with a consumption of 30,996 million kW·h; (5) Identify future electricity consumption hotspots and clustering characteristics, evaluate the renewable energy potential in these hotspot areas, and propose targeted strategies accordingly.http://www.sciencedirect.com/science/article/pii/S2666792424000350Electricity consumptionLand useHigh-performance prediction modelInterpretable machine learningMulti scale spatial characterization
spellingShingle Haizhi Luo
Yiwen Zhang
Xinyu Gao
Zhengguang Liu
Xiangzhao Meng
Xiaohu Yang
Multi-scale electricity consumption prediction model based on land use and interpretable machine learning: A case study of China
Advances in Applied Energy
Electricity consumption
Land use
High-performance prediction model
Interpretable machine learning
Multi scale spatial characterization
title Multi-scale electricity consumption prediction model based on land use and interpretable machine learning: A case study of China
title_full Multi-scale electricity consumption prediction model based on land use and interpretable machine learning: A case study of China
title_fullStr Multi-scale electricity consumption prediction model based on land use and interpretable machine learning: A case study of China
title_full_unstemmed Multi-scale electricity consumption prediction model based on land use and interpretable machine learning: A case study of China
title_short Multi-scale electricity consumption prediction model based on land use and interpretable machine learning: A case study of China
title_sort multi scale electricity consumption prediction model based on land use and interpretable machine learning a case study of china
topic Electricity consumption
Land use
High-performance prediction model
Interpretable machine learning
Multi scale spatial characterization
url http://www.sciencedirect.com/science/article/pii/S2666792424000350
work_keys_str_mv AT haizhiluo multiscaleelectricityconsumptionpredictionmodelbasedonlanduseandinterpretablemachinelearningacasestudyofchina
AT yiwenzhang multiscaleelectricityconsumptionpredictionmodelbasedonlanduseandinterpretablemachinelearningacasestudyofchina
AT xinyugao multiscaleelectricityconsumptionpredictionmodelbasedonlanduseandinterpretablemachinelearningacasestudyofchina
AT zhengguangliu multiscaleelectricityconsumptionpredictionmodelbasedonlanduseandinterpretablemachinelearningacasestudyofchina
AT xiangzhaomeng multiscaleelectricityconsumptionpredictionmodelbasedonlanduseandinterpretablemachinelearningacasestudyofchina
AT xiaohuyang multiscaleelectricityconsumptionpredictionmodelbasedonlanduseandinterpretablemachinelearningacasestudyofchina