Enhancing residential energy management: COA-HDNN approach for optimized demand side management

This paper presents a hybrid energy optimization technique, termed the COA-HDNN technique, which integrates the Coati Optimization Algorithm (COA) with Hamiltonian Deep Neural Networks (HDNN) to improve energy efficiency in smart homes. The proposed method's primary goal is to reduce both the cost and the peak-to-average ratio (PAR). The COA is utilized to optimize the cost of smart home equipment, while the HDNN is used to forecast load demand. By then, the performance of the proposed strategy is tested on the MATLAB platform and compared with other approaches, including Particle Swarm Optimization (PSO), Wild Horse Optimization (WHO) and Seagull Optimization Algorithm (SOA).In the proposed COA-HDNN method, the cost is 0.1 USD, and the peak-to-average ratio (PAR) is 4 %. The WHO method costs 0.29 USD with a PAR of 3.2 %. The PSO method costs 0.39 USD and has a PAR of 3.4 %. The SOA method costs 0.49 USD and has a PAR of 4.6 %. The proposed approach exhibits the lowest value when compared to other current approaches. In comparison to other existing methodologies, the proposed approach yields superior results.