Multi Population's Killer Whales Optimizer: A New Optimization Approach Based On Fixed Primary Objective

Abstract This paper has presented a new algorithm called Multi Population's Killer Whales Optimizer (MPKWO). This algorithm is inspired by hunting of a group of Southern Hemisphere Killer Whales. In MPKWO algorithm, a fixed primary objective is used for optimization and search of the main target. In MPKWO algorithm, two populations of the Killer Whales, those waves-generating and the spy Killer Whales, have been used to simulate the hunting process. The spy Killer Whales have a fixed position (fixed primary objective) and wave-generating Killer Whales move closer to the target by moving in each iteration of the algorithm. In fact, in MPKWO algorithm, initially, an initial value is considered as the target, and the position of the main objective is searched for around that point. The proposed algorithm has been evaluated by 18 functions of the standard test. The results obtained from the proposed algorithm are compared with several known and new algorithms. In other words, compared to other algorithms, the proposed algorithm has successfully obtained the optimal values in 71.4% of the cases for Unimodal functions, 66.64% for Multi-modal functions and 80% for fixed-dimension multimodal functions. In addition, three classic engineering problems are solved by MPKWO algorithm. For a more accurate evaluation, the MPKWO algorithm was ultimately used to estimate the software effort and optimize the ABE method. Simulation results show that the proposed algorithm has been more effective than the compared algorithms.