T-LGBKS: An Interpretable Machine Learning Framework for Electricity Consumption Forecasting
Electricity is an essential resource that plays a vital role in modern society, and its demand has increased rapidly alongside industrialization. The accurate forecasting of a country’s electricity demand is crucial for economic development. A high-precision electricity forecasting framework can ass...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/16/11/4294 |
_version_ | 1797597689461866496 |
---|---|
author | Mengkun Liang Renjing Guo Hongyu Li Jiaqi Wu Xiangdong Sun |
author_facet | Mengkun Liang Renjing Guo Hongyu Li Jiaqi Wu Xiangdong Sun |
author_sort | Mengkun Liang |
collection | DOAJ |
description | Electricity is an essential resource that plays a vital role in modern society, and its demand has increased rapidly alongside industrialization. The accurate forecasting of a country’s electricity demand is crucial for economic development. A high-precision electricity forecasting framework can assist electricity system managers in predicting future demand and production more accurately, thereby effectively planning and scheduling electricity resources and improving the operational efficiency and reliability of the electricity system. To address this issue, this study proposed a hybrid forecasting framework called T-LGBKS, which incorporates TPE-LightGBM, k-nearest neighbor (KNN), and the Shapley additive explanation (SHAP) methods. The T-LGBKS framework was tested using Chinese provincial panel data from 2005 to 2021 and compared with seven other mainstream machine learning models. Our testing demonstrated that the proposed framework outperforms other models, with the highest accuracy (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>=</mo><mn>0.9732</mn></mrow></semantics></math></inline-formula>). This study also analyzed the interpretability of this framework by introducing the SHAP method to reveal the relationship between municipal electricity consumption and socioeconomic characteristics (such as how changes in economic strength, traffic levels, and energy structure affect urban electricity demand). The findings of this study provide guidance for policymakers and assist decision makers in designing and implementing electricity management systems in China. |
first_indexed | 2024-03-11T03:09:07Z |
format | Article |
id | doaj.art-fbf6dfc6694a4f9e8d78ec37c15775da |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-11T03:09:07Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-fbf6dfc6694a4f9e8d78ec37c15775da2023-11-18T07:46:57ZengMDPI AGEnergies1996-10732023-05-011611429410.3390/en16114294T-LGBKS: An Interpretable Machine Learning Framework for Electricity Consumption ForecastingMengkun Liang0Renjing Guo1Hongyu Li2Jiaqi Wu3Xiangdong Sun4College of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, ChinaCollege of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, ChinaCollege of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, ChinaCollege of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, ChinaCollege of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, ChinaElectricity is an essential resource that plays a vital role in modern society, and its demand has increased rapidly alongside industrialization. The accurate forecasting of a country’s electricity demand is crucial for economic development. A high-precision electricity forecasting framework can assist electricity system managers in predicting future demand and production more accurately, thereby effectively planning and scheduling electricity resources and improving the operational efficiency and reliability of the electricity system. To address this issue, this study proposed a hybrid forecasting framework called T-LGBKS, which incorporates TPE-LightGBM, k-nearest neighbor (KNN), and the Shapley additive explanation (SHAP) methods. The T-LGBKS framework was tested using Chinese provincial panel data from 2005 to 2021 and compared with seven other mainstream machine learning models. Our testing demonstrated that the proposed framework outperforms other models, with the highest accuracy (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>=</mo><mn>0.9732</mn></mrow></semantics></math></inline-formula>). This study also analyzed the interpretability of this framework by introducing the SHAP method to reveal the relationship between municipal electricity consumption and socioeconomic characteristics (such as how changes in economic strength, traffic levels, and energy structure affect urban electricity demand). The findings of this study provide guidance for policymakers and assist decision makers in designing and implementing electricity management systems in China.https://www.mdpi.com/1996-1073/16/11/4294electricity consumptionforecastingmachine learninginterpretabilitydata-driven |
spellingShingle | Mengkun Liang Renjing Guo Hongyu Li Jiaqi Wu Xiangdong Sun T-LGBKS: An Interpretable Machine Learning Framework for Electricity Consumption Forecasting Energies electricity consumption forecasting machine learning interpretability data-driven |
title | T-LGBKS: An Interpretable Machine Learning Framework for Electricity Consumption Forecasting |
title_full | T-LGBKS: An Interpretable Machine Learning Framework for Electricity Consumption Forecasting |
title_fullStr | T-LGBKS: An Interpretable Machine Learning Framework for Electricity Consumption Forecasting |
title_full_unstemmed | T-LGBKS: An Interpretable Machine Learning Framework for Electricity Consumption Forecasting |
title_short | T-LGBKS: An Interpretable Machine Learning Framework for Electricity Consumption Forecasting |
title_sort | t lgbks an interpretable machine learning framework for electricity consumption forecasting |
topic | electricity consumption forecasting machine learning interpretability data-driven |
url | https://www.mdpi.com/1996-1073/16/11/4294 |
work_keys_str_mv | AT mengkunliang tlgbksaninterpretablemachinelearningframeworkforelectricityconsumptionforecasting AT renjingguo tlgbksaninterpretablemachinelearningframeworkforelectricityconsumptionforecasting AT hongyuli tlgbksaninterpretablemachinelearningframeworkforelectricityconsumptionforecasting AT jiaqiwu tlgbksaninterpretablemachinelearningframeworkforelectricityconsumptionforecasting AT xiangdongsun tlgbksaninterpretablemachinelearningframeworkforelectricityconsumptionforecasting |