Unit Commitment Problem Solved by the Hybrid Particle Swarm-Whale Optimization Method Using Algorithm for Medical Internet of Things MIoT

Nowadays the Whale Optimization Algorithm (WOA) technique has gained significant attention from researchers for different applications; especially in medical image processing for tasks such as image segmentation. For accurate diagnosis and treatment, automated information is required from different medical images (MRI and CT) modalities through image segmentation. Accurate segmentation leads to an accurate diagnosis. Segmentation accuracy has recently been achieved by WOA; however, there have yet to be refinements by the WOA, which are indeed required to address the complete objectives of medical image segmentation. In this paper, we focused on using a novel hybrid optimization technique based on WOA and Particle Swarm Optimization (PSO) called HPSO_WOA to solve the unit commitment problem with reference to medical image segmentation. We presented the evaluation of HPSO_WOA with PSO and WOA in order to solve this unit commitment problem. For the most part, there are two steps to manage this issue. The initial step discovers which units will be worked on, which tends to be comprehended by utilizing numerous techniques, for example, the priority list strategy. The second step determines the distribution of the load demand among the units, which are committed from the first step to minimize cost and achieve the load demand and constraints, which were solved in this study by using the three previously stated methods. By using the HPSO_WOA method, in all iterations of simulation, the best particle in the WOA population is inserted into the PSO population and manipulated, and then returned to the WOA population. There are four testing cases used: 4, 10, 20, and 40 generators. It combines both exploration and exploitation characteristics, so the reliability, speed of convergence, and accuracy are increased.