A restless bandit approach for capacitated condition based maintenance scheduling

This paper considers the problem of optimally maintaining multiple non-identical machines deteriorating over time. The number of maintenance activities that can be carried out simultaneously is restricted by the number of maintenance workers. The main goal is to propose a heuristic with low complexity that consistently produces solutions close to the optimal strategy for problems of real size. We cast the problem as a restless bandit problem and propose an index based heuristic (Whittle's index policy) which can be computed efficiently. Another goal is to empirically compare the performance of the index heuristic with alternative policies. In addition to achieving superior performance over failure-based and threshold policies, Whittle's policy converges to the optimal solution when the number of machines is moderately high and/or maintenance workload is high.