Harmony search augmented with optimal computing budget allocation capabilities for noisy optimization

In this work we introduce the combinatory use of Harmony Search (HS) with Optimal Computing Budget Allocation (OCBA) as a means to tackle noisy optimization situations as those that occur during the execution of Discrete Event Systems (DES) for modeling complex systems. The OCBA procedure is employed for the exclusion of the worst harmony during the memory updating process in order to minimize the computational cost and at the same time retain a pool of promising solutions. The proposed hybrid approach is tested on real valued test functions as a proof of concept and the results are promising in case of small computational budgets.