Multifactorial Bare Bones Sine Cosine algorithm with Chaotic-based elite learning for Multi-tasking Optimization

The problem of multi-task optimization is a new research topic in the field of evolutionary computing in recent years, and it has attracted more and more attention from the academic community. Compared with single-objective optimization and multi-objective optimization, multi-task optimization can use the similarity and complementarity between tasks to solve different optimization tasks at the same time. However, as the population evolves to the later stage, the ability of the two tasks to learn from each other gradually declines. In order to solve this problem and enhance the effectiveness of knowledge transfer between different tasks, this paper combines the bare bone sine cosine algorithm (BBSCA) and the elite learning strategy based on chaos mapping (ELM) into MFEA, and proposes the MFBBSCA-ELM algorithm. Since BBSCA and ELM have different search neighborhoods and are highly complementary to the analog binary crossover used in the classic MFEA algorithm, this article combines BBSCA and ELM, which is also the motivation of this article. In addition, the integration of BBSCA and ELM can reduce the probability of MFEA falling into a local optimum. Finally, this article verifies the effectiveness of integrating BBSCA and ELM into MFEA on the classic MTO benchmark problem. The experimental results show that compared with the classic MFEA, the performance of the MFBBSCA-ELM proposed in this paper has been significantly improved.