Hybridizing of Multi-Objective Coronavirus Herd Immunity Optimizer with Lévy Flight for Time Scheduling of Internet of Things Appliances in Smart Homes

With the rapid deployment of Internet of Things appliances in smart homes, making efficient energy scheduling is a critical necessity to satisfy their exponentially increased residential energy demand. The problem of optimizing appliance operational times in smart homes is known as the Appliance Energy Scheduling Problem, which is a complex, NP-hard multi- objective challenge. Various metaheuristic algorithms have been utilized by researchers to address this problem; existing methods often struggle with slow convergence rates and are trapped in local optima. To overcome these limitations and produce a superior solution, this study proposes a new hybrid framework that integrates the Coronavirus Herd Immunity Optimizer (CHIO) with Lévy Flight (LF). By strategically embedding LF into the CHIO framework, the proposed method effectively balances exploration and exploitation search capabilities to achieve true global optimization. In the evaluation stage, three structural variations in hybrid CHIO models are evaluated against the standard appliance energy scheduling problem to determine the robust model and compare its performance with prominent existing methods in the literature. The experimental results demonstrate the superiority of the optimized CHIOLF-2 approach among other hybrid CHIO models. The CHIOLF-2 successfully navigates the trade-off between grid efficiency and user experience by achieving a reduction in electricity bills and the Peak-to-Average Ratio while maximizing user comfort through minimized appliance waiting times. Eventually, this research produces a highly efficient scheduling framework for modern smart homes and offers a versatile algorithmic design that can be readily adapted to address other complex real-world optimization problems.