A cooperative distributed Hyper-Heuristic framework for scheduling

Abstract

In recent years, hyper-heuristics have emerged as a new search methodology that is motivated by the goal of increasing the level of generality of meta-heuristics. In this paper, we aim at investigating the role of cooperative decision making in the selection process of low level heuristics. We propose a novel cooperative distributed hyper-heuristic framework. The cooperative distributed hyper-heuristic framework is an agent-based system composed of a Hyper-Heuristic Agent (HHA) and a number of Low Level Heuristic Agents (LLHA). The HHA is in charge of the selection of the low level heuristic to apply at a decision point in the search process. The LLHAs search synchronously through the same solution space, starting from the same solution and using different low level heuristics. We conducted several experiments, using the permutation flow shop benchmark instances, to investigate the performance of the developed cooperative distributed hyper-heuristic approaches.