Enhanced exchange heuristic based resource constrained scheduler using ARTMAP

The Exchange Heuristic (EH) has demonstrated superior results compared with other RCS methods in solving Resource Constrained Scheduling (RCS) problems. Selecting the most promising target constitutes the success of EH. The current version of EH highly depends on expertsʹ intuition in selecting a target. Expert systems and Fuzzy rulebase as well as Neural Network (NN) have been considered as alternatives for human experts. Expert systems are brittle in its nature, and Fuzzy rulebase needs membership functions defined for each linguistic variable. However, these membership function can not be justified and can be very subjective. Therefore, Neural Network is employed because of its capability of learning as well as dealing with fuzzy data. Known examples are used to train the NN. Back propagation algorithm is used first, then Adaptive Resonance Theory (ART) network is employed to reduce training time since new rules come up often. Even at the end of the training the NN, we may end up with local optima or the NN which is too general to specific problems. Utilizing Genetic Algorithm (GA) will help to further refine or adapt the weights of the NN which optimizes target selection strategy for a specific problem.