The Electricity Load Prediction Model for Residential Buildings: A Critical Review of Output Types, Prediction Methods and Driving Factors
An electrification revolution in the Chinese building energy field has been promoted by China’s carbon peak and carbon neutrality goals. An accurate electricity load prediction was essential to resolve the conflict between substations which was caused by the current increase in energy demand, on bot...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/15/6/925 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850089463109124096 |
|---|---|
| author | Zhenjing Wu Min Qi Weiling Zhang Xudong Zhang Qiang Yang Wenyuan Zhao Bin Yang Zhihan Lyu Faming Wang Zhichao Wang |
| author_facet | Zhenjing Wu Min Qi Weiling Zhang Xudong Zhang Qiang Yang Wenyuan Zhao Bin Yang Zhihan Lyu Faming Wang Zhichao Wang |
| author_sort | Zhenjing Wu |
| collection | DOAJ |
| description | An electrification revolution in the Chinese building energy field has been promoted by China’s carbon peak and carbon neutrality goals. An accurate electricity load prediction was essential to resolve the conflict between substations which was caused by the current increase in energy demand, on both the generation and consumption sides. This review provided an in-depth study of prediction models for residential building electricity load and inspected various output types, prediction methods and driving factors. The prediction types were divided into three categories: (i) time scale, (ii) geographical scale and (iii) regional scale. Predictive model building methods were classified as classical, algorithms based on Machine Learning (ML) or Deep Learning (DL) and hybrid methods. Driving factors included single and multiple features. By summarizing the driving factors, the influence of improving the prediction accuracy according to the characteristics of output types on selecting the driving factors correctly was discussed. The review provided a key perspective for future studies in electricity load prediction by analyzing the regional variations in electricity load characteristics. It suggested that the regional electricity load prediction model for residential buildings based on diverse driving factors in each region was established to offer valuable solutions for future residential planning and energy distribution. |
| format | Article |
| id | doaj-art-72fe7f62ec8b4cd791c7bd6c0732e280 |
| institution | DOAJ |
| issn | 2075-5309 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj-art-72fe7f62ec8b4cd791c7bd6c0732e2802025-08-20T02:42:46ZengMDPI AGBuildings2075-53092025-03-0115692510.3390/buildings15060925The Electricity Load Prediction Model for Residential Buildings: A Critical Review of Output Types, Prediction Methods and Driving FactorsZhenjing Wu0Min Qi1Weiling Zhang2Xudong Zhang3Qiang Yang4Wenyuan Zhao5Bin Yang6Zhihan Lyu7Faming Wang8Zhichao Wang9School of Energy and Safety Engineering, Tianjin Chengjian University, Tianjin 300401, ChinaSchool of Energy and Safety Engineering, Tianjin Chengjian University, Tianjin 300401, ChinaSchool of Energy and Safety Engineering, Tianjin Chengjian University, Tianjin 300401, ChinaSchool of Energy and Safety Engineering, Tianjin Chengjian University, Tianjin 300401, ChinaState Key Laboratory of Building Safety and Built Environment, Beijing 100013, ChinaState Key Laboratory of Building Safety and Built Environment, Beijing 100013, ChinaSchool of Energy and Safety Engineering, Tianjin Chengjian University, Tianjin 300401, ChinaDepartment of Game Design, Faculty of Arts, Uppsala University, SE-62167 Uppsala, SwedenCentre for Molecular Biosciences and Non-Communicable Diseases, Xi’an University of Science and Technology, Xi’an 710054, ChinaState Key Laboratory of Building Safety and Built Environment, Beijing 100013, ChinaAn electrification revolution in the Chinese building energy field has been promoted by China’s carbon peak and carbon neutrality goals. An accurate electricity load prediction was essential to resolve the conflict between substations which was caused by the current increase in energy demand, on both the generation and consumption sides. This review provided an in-depth study of prediction models for residential building electricity load and inspected various output types, prediction methods and driving factors. The prediction types were divided into three categories: (i) time scale, (ii) geographical scale and (iii) regional scale. Predictive model building methods were classified as classical, algorithms based on Machine Learning (ML) or Deep Learning (DL) and hybrid methods. Driving factors included single and multiple features. By summarizing the driving factors, the influence of improving the prediction accuracy according to the characteristics of output types on selecting the driving factors correctly was discussed. The review provided a key perspective for future studies in electricity load prediction by analyzing the regional variations in electricity load characteristics. It suggested that the regional electricity load prediction model for residential buildings based on diverse driving factors in each region was established to offer valuable solutions for future residential planning and energy distribution.https://www.mdpi.com/2075-5309/15/6/925load predictionresidential buildingsmodel methodspatiotemporal characteristicselectricity grid planningcritical review |
| spellingShingle | Zhenjing Wu Min Qi Weiling Zhang Xudong Zhang Qiang Yang Wenyuan Zhao Bin Yang Zhihan Lyu Faming Wang Zhichao Wang The Electricity Load Prediction Model for Residential Buildings: A Critical Review of Output Types, Prediction Methods and Driving Factors Buildings load prediction residential buildings model method spatiotemporal characteristics electricity grid planning critical review |
| title | The Electricity Load Prediction Model for Residential Buildings: A Critical Review of Output Types, Prediction Methods and Driving Factors |
| title_full | The Electricity Load Prediction Model for Residential Buildings: A Critical Review of Output Types, Prediction Methods and Driving Factors |
| title_fullStr | The Electricity Load Prediction Model for Residential Buildings: A Critical Review of Output Types, Prediction Methods and Driving Factors |
| title_full_unstemmed | The Electricity Load Prediction Model for Residential Buildings: A Critical Review of Output Types, Prediction Methods and Driving Factors |
| title_short | The Electricity Load Prediction Model for Residential Buildings: A Critical Review of Output Types, Prediction Methods and Driving Factors |
| title_sort | electricity load prediction model for residential buildings a critical review of output types prediction methods and driving factors |
| topic | load prediction residential buildings model method spatiotemporal characteristics electricity grid planning critical review |
| url | https://www.mdpi.com/2075-5309/15/6/925 |
| work_keys_str_mv | AT zhenjingwu theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT minqi theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT weilingzhang theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT xudongzhang theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT qiangyang theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT wenyuanzhao theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT binyang theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT zhihanlyu theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT famingwang theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT zhichaowang theelectricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT zhenjingwu electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT minqi electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT weilingzhang electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT xudongzhang electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT qiangyang electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT wenyuanzhao electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT binyang electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT zhihanlyu electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT famingwang electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors AT zhichaowang electricityloadpredictionmodelforresidentialbuildingsacriticalreviewofoutputtypespredictionmethodsanddrivingfactors |