A novel adaptive whale optimization algorithm for global optimization

Abstract

Background/Objectives: In the meta-heuristic algorithms, randomization plays a very crucial role in both exploration and exploitation. So meta-heuristic algorithms are proposed to avoid these problems. Methods/Statistical Analysis: A novel bio-inspired optimization algorithm based on the special bubble-net hunting strategy used by humpback whales called the Whale Optimization Algorithm (WOA). In contrast to meta-heuristic, main feature is randomization having a relevant role in both exploration and exploitation in optimization problem. A novel randomization technique termed adaptive technique is integrated with WOA and exercised on ten unconstraint test benchmark function. Findings: WOA algorithm has quality feature that it uses logarithmic spiral function so it covers a broader area in exploration phase then addition with powerful randomization adaptive technique potent the adaptive whale optimization Algorithm (AWOA) to attain global optimal solution and faster convergence with less parameter dependency. Application/Improvements: Adaptive WOA (AWOA) solutions are evaluated and results shows its competitively better performance over standard WOA optimization algorithm.