Abstract
This paper proposes a method for the job shop scheduling problem (JSSP) based on the hybrid metaheuristic method. This method makes use of the merits of an improved particle swarm optimization (PSO) and a tabu search (TS) algorithm. In this work, based on scanning a valuable region thoroughly, a balance strategy is introduced into the PSO for enhancing its exploration ability. Then, the improved PSO could provide diverse and elite initial solutions to the TS for making a better search in the global space. We also present a new local search strategy for obtaining better results in JSSP. A real-integer encode and decode scheme for associating a solution in continuous space to a discrete schedule solution is designed for the improved PSO and the tabu algorithm to directly apply their solutions for intensifying the search of better solutions. Experimental comparisons with several traditional metaheuristic methods demonstrate the effectiveness of the proposed PSO-TS algorithm.
| Original language | English |
|---|---|
| Pages (from-to) | 2044-2054 |
| Journal | IEEE Transactions on Industrial Informatics |
| Volume | 10 |
| Issue number | 4 |
| Early online date | 23 Jul 2014 |
| DOIs | |
| Publication status | Published - Nov 2014 |
| Externally published | Yes |
Funding
This work was supported in part by the Introduction Foundation for the Talent of Nanjing University of Posts and Telecommunications under Grant NY212025, in part by the National Natural Science Foundation of China under Grant 61203270, and in part by the China Postdoctoral Science Foundation under Grant SBH14015. Paper no. TII-14-0331.
Keywords
- Global search
- job shop scheduling
- particle swarm optimization (PSO)
- tabu search (TS)