College of Information System and Management, National University of Defense Technology, Changsha 410073, P. R. China

---

Abstract—Since the multistage production planning problem possesses high-dimensional variables and largescale solution space, it is hard to be solved in an acceptable time. To deal with this challenge, we propose a parallel evolution based intelligent optimization algorithm. The proposed algorithm employs the differential evolution as the algorithm framework to implement the primary mutation and crossover operations, then the entire variables are clustered into several sub-populations according to the problem structure, finally a parallel evolution strategy is proposed to speed up the convergence and progress the search precision of the sub-population. A case of weapons production planning is studied to validate the proposed algorithm. The results show that this algorithm has the fastest convergence and the best global searching capability, compared with classical differential evolution algorithm, genetic algorithm and particle swarm optimization algorithm.

Index Terms—Production planning; multistage stochastic programming; differential evolution; parallel evolution; variables clustering

[PDF]

Cite: Yu Zhou, Jiang Jiang, "A Parallel Evolution based Intelligent Optimization Algorithm to Solve Large-scale Production Planning Problem in Defense Industry," Journal of Software vol. 8, no. 10, pp. 2474-2481, 2013.