A Reinforcement Learning Approach for Ensemble Machine Learning Models in Peak Electricity Forecasting

Warut Pannakkong, Vu Thanh Vinh, Nguyen Ngoc Minh Tuyen and Jirachai Buddhakulsomsiri ()
Additional contact information
Warut Pannakkong: School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Pathum Thani 12120, Thailand
Vu Thanh Vinh: School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Pathum Thani 12120, Thailand
Nguyen Ngoc Minh Tuyen: School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Pathum Thani 12120, Thailand
Jirachai Buddhakulsomsiri: School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Pathum Thani 12120, Thailand

Energies, 2023, vol. 16, issue 13, 1-20

Abstract: Electricity peak load forecasting plays an important role in electricity generation capacity planning to ensure reliable power supplies. To achieve high forecast accuracy, multiple machine learning models have been implemented to forecast the monthly peak load in Thailand over the past few years, yielding promising results. One approach to further improve forecast accuracy is to effectively select the most accurate forecast value for each period from among the forecast values generated by these models. This article presents a novel reinforcement learning approach using the double deep Q-network (Double DQN), which acts as a model selector from a pool of available models. The monthly electricity peak load data of Thailand from 2004 to 2017 are used to demonstrate the effectiveness of the proposed method. A hyperparameter tuning methodology using a fractional factorial design is implemented to significantly reduce the number of required experimental runs. The results indicate that the proposed selection model using Double DQN outperforms all tested individual machine learning models in terms of mean square error.

Keywords: double deep Q-network; electricity peak load; forecasting; machine learning; reinforcement learning; time series; artificial neural network; support vector regression; deep belief network (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1996-1073/16/13/5099/pdf (application/pdf)
https://www.mdpi.com/1996-1073/16/13/5099/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:16:y:2023:i:13:p:5099-:d:1184903

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().