Co-evolutionary immuno-particle swarm optimization with penetrated hyper-mutation for distributed inventory replenishment

This article is betrothed to serve as a continuation of the emerging swarm techniques to solve supply chain problems. Our aim is to map some of the pressing research challenges contributed by the artificial intelligence community and to develop an improved algorithm: Co-evolutionary immuno-particle swarm optimisation with penetrated hyper-mutation (COIPSO-PHM). In this paper, we proposed a new algorithm which uses clonal selection approach in particle swarm optimisation by embedding co-evolutionary theory to solve the problem of inventory replenishment in distributed plant–warehouse–retailer system. Constraint handling is explicitly taken care by implanting augmented lagrangian concept. To demonstrate the efficiency of the algorithm, its performance are evaluated and compared on 10 benchmarked problems (made constrained problem via random initialisation in the infeasible zone) including functions with uni-modalities as well as multi-modalities. The result follows shows superior performance of the algorithm in every respect.