Hybrid Deep Learning and Machine Learning Approaches for Industrial Power Load Forecasting: A Review

Abstract

Industrial Power Load in the United States is rising gradually due to rapid manufacturing facilities enhancement in the recent year. Due to this expansion, accurate forecasting of industrial electricity load plays a vital role for power generation, transmission, and distribution planning for a specified manufacturing zone. The statistical model of forecasting faces a significant challenge due to the nonlinearity and multi scale nature of industrial load data. But recent application of Hybrid Deep Learning and Machine Learning models has demonstrated superior performance in industrial power load forecasting over statistical forecasting model. This paper presents a structured and comparative review of the recent Hybrid Deep Learning and Machine Learning based Data driven approaches for Industrial power load forecasting. The findings of our study highlight the effectiveness of the hybrid approach for reliable and high precision industrial power load forecasting which enhances the intelligent energy management in modern industrial systems.