Cooperative Coevolution as an Alternative Effective Approach to Planning Sustainable Multi-Agent Cyber–Physical Production Systems

Although the Cyber–Physical Production Systems (CPPSs) paradigm offers significant potential for enhancing the economic and environmental performance of production systems and contributing to the achievement of the Sustainable Development Goals (SDGs) in the manufacturing sector, it also presents challenges for developing sustainable CPPSs. Sustainable CPPSs consist of collaborative networked entities in cyber space and physical space through ICT. Optimizing sustainable CPPSs is a challenging task due to the discrete and nonconvex solution space involved, making the development of effective problem solvers essential for improving their performance. Metaheuristic algorithms provide an approach to addressing the challenges of optimizing sustainable Cyber–Physical Production Systems (CPPSs). Cooperative Coevolution (CC) provides a divide-and-conquer approach to improving the performance. However, studies on the applying CC to sustainable CPPSs planning problems remain limited. To bridge this gap, we combine CC with a single Differential Evolution (DE) strategy to develop several solution algorithms for planning sustainable CPPSs. The results show that the proposed CC-based DE algorithms outperform most single strategy metaheuristic algorithms and are comparable to the self-adaptive algorithms with two DE strategies in terms of performance and robustness. The results indicate that the proposed CC-based algorithms provide an effective alternative approach to the optimization of sustainable CPPSs.