A Model for Job-Shop Scheduling Based on NN-PSO Technique
Job-shop scheduling problem (JSP) has been one of the NP-Hard problems. Now, the most advanced algorithm is only limited to solve small scale problems effectively. For large-scale and super large scale job-shop scheduling problem, there is still no effective way to find its optimal solution quickly. In recent years, it is the main trend to solve the problem of job-shop scheduling with the combination of neural network and generic algorithms (GA). However, there will be complex operations such as crossover and mutation, and slow convergence or even stop convergence when approaching the optimal solution with GA. As an alternative, in this paper, we proposed a model for job-shop scheduling based on NN-PSO technique-neural network trained by the particle swarm optimization algorithm, which is simple, less parameter and easy to implement, greatly accelerates the convergence speed. Experiments show that job-shop scheduling based on NN-PSO technique is superior to most traditional scheduling rules.
KeywordsJob-shop scheduling NN-PSO
This work was supported by Key Research and Development Plan Project of Shandong Province, China (No. 2017GGX201001).
- 2.Simon, Y.P., Takefuji, Y.: Stochastic neural networks for solving job-shop scheduling. I. Problem representation. In: IEEE International Conference on Neural Networks, vol. 2, pp. 275–282. IEEE (1988)Google Scholar
- 3.Simon, Y.P., Takefuji, Y.: Stochastic neural networks for solving job-shop scheduling. II. Architecture and simulations. In: IEEE International Conference on Neural Networks, vol. 2, pp. 283–290. IEEE (1988)Google Scholar
- 5.Shen, X., Chen, C., He, T., Yang, J.: Postgraduate entrant and employment forecasting using modified BP neural network with PSO. In: International Conference on Computer Science & Education, pp. 1699–1703. IEEE (2009)Google Scholar
- 6.Sallehudin, R., Shamuddin, S.M.H.: Grey relational with BP_PSO for time series foreasting. In: IEEE International Conference on Systems, Man and Cybernetics, pp. 4895–4900. IEEE (2009)Google Scholar
- 7.Hajizadeh, E., Mahootchi, M., Esfahanipour, A., Kh, M.M.: A new NN-PSO hybrid model for forecasting Euro/Dollar exchange rate volatility. Neural Comput. Appl. 1–9 (2015)Google Scholar
- 10.Dang, T.L., Hoshino, Y.: Hardware/software co-design for a neural network trained by particle swarm optimization algorithm. Neural Process. Lett. 1–25 (2018)Google Scholar
- 12.Lawrence, S.: Resource constrained project scheduling: an experimental investigation of heuristic scheduling techniques (supplement). Graduate School of Industrial Administration, Carnegie-Mellon University, Pittsburgh, PA (1984)Google Scholar