An Adaptive Cooperative Frequency Strategy in Distributed Cooperative Co-evolution

Cooperative co-evolution (CC) is an effective tech-nique for optimizing high dimensional problems. The scalability and efficiency of CC can be further improved by combing with distributed computing, resulting in distributed CC (dCC). How to balance the cooperation and communication among sub-problems is an important issue in dCC. Through preliminary research on three types of benchmark functions, we found that the optimal value of collaboration frequency is problem-dependent and needs to be tuned to balance performance and resource consumption. To solve this problem, we design an adaptive cooperative frequency (ACF) strategy to change the cooperative interval dynamically without any prior knowledge of the relationship among variables. Experimental results show that the proposed ACF strategy achieves better performance on most functions compared with the ones with fixed communication intervals.