A TABU SEARCH FOR MULTIPLE MULTI-LEVEL REDUNDANCY ALLOCATION PROBLEM IN SERIES-PARALLEL SYSTEMS

The traditional RAP (Redundancy Allocation Problem) is to consider only the component redundancy at the lowest-level. A system can be functionally decomposed into system, module, and component levels. Modular redundancy can be more effective than component redundancy at the lowest-level. We consider a MMRAP (Multiple Multi-level Redundancy Allocation Problem) in which all available items for redundancy (system , module, and component) can be simultaneously chosen. A tabu search of memory-based mechanisms that balances intensification with diversification via the short-term and long-term memory is proposed for its solution. To the best of our knowledge, this is the first attempt to use a TS for MMRAP. Our algorithm is compared with the previous genetic algorithm for MMRAP on the new composed test problems as well as the benchmark problems from the literature. Computational results show that the tabu search outstandingly outperforms the genetic algorithm for all test problems.