Random restart local search optimization technique for sustainable energy-generating induction machine

The goal focused upon is efficiency optimization of an induction machine, using a Random Restart Local Search Optimization technique. Recently, many studies have been designed to boost the operation efficiency of induction machines using optimization techniques, but the existing techniques have failed in the efficiency enhancement of induction machine design. To resolve this efficiency problem, a Hill Climbing Based Local Search Optimization technique was designed. Initially, IM data are collected, and the random restart local search optimization is implemented to formulate four objective functions. After the objective function calculation, the value obtained is compared to a threshold value using the continuous hill climbing algorithm. Finally, the optimal induction machine data set with the highest efficiency is selected for designing the induction machine. The proposed method is compared to state-of-the-art methods.