An Enhanced Water Flow Optimizer Incorporating Adaptive Weights and Search Step Sizes

Meta-heuristic algorithms are highly regarded for their exceptional global search capability. In recent years, a novel natural inspired algorithm known as the Water Flow Optimizer (WFO) has emerged. This algorithm mimics the laminar and turbulent flow phenomena observed in natural water systems and showcases remarkable optimization performance. However, similar to other meta-heuristic algorithms, WFO still suffers from the drawback of getting trapped in local optima. In this paper, we propose an enhanced water flow optimizer (AWS-WFO) based on adaptive weights and search step sizes to prevent the algorithm from getting stuck in local optima. AWS-WFO considers the weights and adaptive exploration performance mechanism, draws inspiration from the advantageous features of LDIWPSO (Linearly Decreasing Inertia Weight Particle Swarm Optimization) and effectively enhances the optimization performance of WFO. In order to evaluate the performance of the proposed AWS-WFO algorithm, comparative experiments were conducted using seven widely recognized test functions as benchmarks. The experimental results indicate that the proposed algorithm exhibits a certain level of competitiveness.