A neural network to enhance local search in the permutation flowshop

This paper considers the n-job, m-machine permutation flowshop with the objective of minimizing the mean flowtime. Initial sequences that are structured to enhance the performance of local search techniques are constructed from job rankings delivered by a trained neural network. The network's training is done by using data collected from optimal sequences obtained from solved examples of flowshop problems. Once trained, the neural network provides rankable measures that can be used to construct a sequence in which jobs are located as close as possible to the positions they would occupy in an optimal sequence. The contribution of these 'neural' sequences in improving the performance of some common local search techniques, such as adjacent pairwise interchange and tabu search, is examined. Tests using initial sequences generated by different heuristics show that the sequences suggested by the neural networks are more effective in directing neighborhood search methods to lower local optima.