Optimal composition of tasks in cloud manufacturing platform: a novel hybrid GWO-GA approach

Abstract

Abstract Emerging cloud manufacturing paradigm aims towards providing highly integrated solutions via enabling cooperation between distributed manufacturing resources and capabilities. Implementation of this groundbreaking idea, however, is facing serious challenges springing from the currently centralized industrial structures. In order to help it make its way out, researchers have to address a number of pivotal issues in this regard. Service composition and optimal selection (SCOS), which tackles the problem of optimally selecting and combining available resources into a composite service is one of them. To deal with this NP-hard problem, we developed a novel hybrid algorithm based on the recently-introduced grey wolf optimizer (GWO) in which evolutionary operators are also embedded into the hunting mechanism of the basic algorithm. This approach not only makes it possible to adapt an algorithm with continuous structure such as GWO to solve a combinatorial problem such as SCOS, but also empowers it with providing higher exploration through crossover and mutation operators. Experiments conducted clearly proves the superior performance of the proposed algorithm over existing discrete variations of GWO and genetic algorithm, especially in large-scale SCOS problems.