Hybrid multi-verse optimizer with grey wolf optimizer for power scheduling problem in smart home using IoT

The power scheduling problem in smart home (PSPSH) is one of the complex NP-hard scheduling problems, where it has a deep and rugged search space due to the high number of constraints and objectives. PSPSH is an optimization problem of finding the best schedule for operation times of smart appliances using a dynamic pricing scheme(s) according to several constraints. The primary purpose of addressing PSPSH is to optimize electricity bills, power consumed at peak periods, and users’ comfort levels. Smart appliances must be interconnected for data exchange and control. Different approaches have been proposed to interconnect appliances, where the Internet of Things (IoT) approach is the most useful for data transferring and exchanging. PSPSH has been addressed by different optimization methods, where the metaheuristics are the most popular. However, metaheuristics show low performance in investigating very large-scale search spaces, like PSPSH; therefore, the hybridization approach is utilized to improve metaheuristics’ performance by combining their searching behaviour with other methods. In this paper, a new hybrid method (MVOG) is proposed by combining two of the most well-known optimization methods, called multi-verse optimizer (MVO) and grey wolf optimizer (GWO), to address PSPSH efficiently. The purpose of the MVOG is to improve the MVO performance by updating the worst solutions and finding better schedules using the GWO. PSPSH is modelled as a multi-objective problem to include all objectives in the optimization processes. Furthermore, the communication between the smart home components is designed utilizing IoT technologies to improve exchanging data. In the experimental results, the MVOG is examined using seven consumption scenarios. The proposed hybridization is utilized on other four optimization methods to investigate its performance for different methods. The performance of the proposed method is evaluated using three different comparisons, including original methods, hybrid methods, and state-of-the-art hybrid methods. The MVOG shows high performance in addressing PSPSH compared with other methods.