Comparative Analysis of Particle Swarm Optimization and Genetic Algorithm Approaches for Electricity Cost Optimization in Residential Energy Management System

In order to meet the growing demand for energy and support sustainable development worldwide, renewable and resource distribution have recently emerged. Cost-effective integration of these resources is accomplished through the deployment of an energy management system (EMS). The stability and energy security of power networks may be impacted by the intermittent nature of solar energy. This research presents an optimization-based home energy management system that focuses on the efficient sizing of PV panels and battery storage to minimize electricity bill using Particle Swarm Optimization (PSO). Optimizing load schedules with the GA algorithm aims to reduce electric bills by efficiently managing and shifting energy consumption to off-peak hours when tariff rates are lower. The simulation results from the two approaches are then compared. Block rate tariffs in the PSO algorithm and time-of-use (ToU) tariffs in the Genetic algorithm (GA) technique utilized to estimate the cost of electricity. Finally, the simulation results from the two approaches are then compared. The PSO based EMS was found effective to minimize the residential electricity bill consequently. As the electricity price rate significantly changes, the optimization based PSO technique was found effective and can minimize the residential electricity bill up to 64.72% consequently.