Forecast Load Demand in Thermal Power Plant with Machine Learning Algorithm: A Review

Abstract

A thermal power plant is valuable in the current energy infrastructure because it provides power and heat to their respective consumers. The electrical industry must operate properly. Several machine learning methods have been developed to reduce the complexity of electric load. This paper reviews various electricity load forecasting models with machine learning methods. The researcher used ML techniques to predict the load demand and outcome before it happened. ML is a branch of artificial intelligence (AI) focused on studying and developing mathematical algorithms for data understanding. It discusses various applications and the most popular techniques for enhancing the performance and accuracy of the models. This review paper will provide an effective solution for load forecasting in thermal power plants by hybrid machine learning methods. For this review, reference papers are selected from 2020 to 2023. This research identifies gaps in current ML applications and predicts future scope and development methods.

Keywords:

• Load forecasting
• neural networks
• midterm
• long-term and short-term forecasting
• machine learning

Disclosure Statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Preeti Manke

Preeti Manke is pursuing Ph.d at Rungta College of Engineering & Technology, Bhilai, Chhattisgarh, 490024, India. Also, he is working as an Associate Professor Computer Science & Engineering, Institute of Technology, Korba, Chhattisgarh, India.

Sourabh Rungta

Sourabh Rungta is working as a professor in the Department of Computer Science & Engineering, Rungta College of Engineering & Technology, Bhilai, Chhattisgarh, India.

Satydharma Bharti

Satydharma Bharti is working as a professor in the Department of Electrical Engineering, Rungta College of Engineering & Technology, Bhilai, Chhattisgarh, India.