IWO with Increased Deviation and Stochastic Selection (IWO-ID-SS) for global optimization of noisy fitness functions

Invasive weed optimization (IWO) has been found to be a simple but powerful algorithm for function optimization over continuous spaces. It has reportedly outperformed many types of evolutionary algorithms and other search heuristics when tested over both benchmark and real-world problems. However the performance of most search heuristics deteriorates severely when applied to the task of optimization of noisy landscapes. This paper presents an improved IWO algorithm to effectively find the global optima of noisy functions. This is achieved by using an increased value of standard deviation, changing the manner of its reduction to linear and by employing a novel selection strategy which varies from the one use in the standard IWO. An extensive performance comparison of the newly proposed scheme, the original DE (DE/Rand/1/Exp), the canonical PSO, standard real-coded EA, and DE-RSF-TS has been presented using well-known benchmarks corrupted by zero-mean Gaussian noise. It has been found that the proposed method outperforms the others in a statistically significant way.