Optimal load demand forecasting in air conditioning using deep belief networks optimized by an improved version of snake optimization algorithm

Abstract

Air conditioning systems play a vital role in maintaining comfortable indoor environments, particularly in hot and humid climates. However, these systems consume a significant amount of energy, making load demand forecasting an important aspect of energy management. In this study, the authors propose a novel approach for load demand forecasting in air conditioning systems using a hybrid deep belief network (HDBN) and an improved snake optimization algorithm (ISOA). The HDBN is a machine learning technique that combines deep learning and probabilistic graphical models to capture complex patterns in the input data. The ISOA is a nature‐inspired optimization algorithm that mimics the movement of a snake to search for optimal solutions. The proposed approach is evaluated using real‐world data from a commercial building in a hot and humid region. The results show that the proposed HDBN/ISOA approach outperforms other commonly used techniques in terms of accuracy. The proposed approach can be used to optimize energy consumption and reduce costs in air conditioning systems.