MFWOA: Multifactorial Whale Optimization Algorithm

Abstract

Multi-task optimization is an emerging research topic in the field of evolutionary computation, which can exploit the synergy between tasks to solve multiple optimization problems simultaneously and efficiently. However, the correlation and negative transfer problems between tasks are the main challenges faced by multi-task optimization. To this end, this paper proposes a new multi-task optimization algorithm, named Multifactorial Whale Optimization Algorithm (MFWOA). MFWOA uses the Whale Optimization Algorithm (WOA) as a search mechanism and designs an adaptive knowledge transfer strategy to effectively exploit the correlation between tasks. This strategy includes two ways: one is to exchange search experience by adding distance terms from other tasks; the other is to generate new random individuals or optimal individuals through crossover and mutation operations and use them to guide position updates. By combining these two methods, MFWOA can explore a wider area. In addition, in order to better balance the useful information transfer between and within tasks, MFWOA also designs a random mating probability parameter adaptive strategy. Experimental results show that MFWOA can achieve effective and efficient knowledge transfer, and outperforms other multi-task optimization algorithms in terms of convergence speed and accuracy. It is a promising multi-task optimization algorithm.