Deluge Harmony Search Algorithm For Nurse Rostering Problems

Abstract

Harmony search algorithm (HSA) is one of the relatively new metaheuristic algorithms that classified under population-based search algorithms. Based on literature, hybridizing local-based searching algorithms with population-based algorithms can improve the performance of hybridized algorithms. This research is an extension to our previous work that focus on solving Nurse Rostering Problems (NRP) using hybrid metaheuristic algorithms. One of the improved version of HSA is enhanced harmony search algorithm (EHSA) where it overcomes some of the weaknesses of basic HSA. Slow convergence is noticed in EHSA which encourage us to hybridize it with other metaheuristic algorithms to improve its performance. In this research, EHSA is hybridized with great deluge algorithm (GD) and called Deluged harmony search algorithm (DHSA). DHSA then compared to CHSA (the hybridization of EHSA with Hill climbing (HC)) which developed earlier. To strike the balance between exploration and exploitation, the exploration stage run using EHSA and the exploitation stage used GD. DHSA is tested to solve a real world NRP problem at National University Malaysia Medical Center (UKMMC). The results show that, DHSA performed much better than CHSA in all instances in terms of solution quality with slightly higher execution time.