Enhancing Nurse Scheduling with User Preferences: Hybrid Genetic Algorithm and Variable Neighbourhood Search Approach

Abstract

The Nurse Scheduling Problem (NSP) assigns nurses to shifts while meeting constraints, making it an NP-hard problem. This study proposes GAV_NS<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, a hybrid Genetic Algorithm (GA) and Variable Neighbourhood Search (VNS) model, to optimize scheduling while considering nurse preferences. Implemented in Java, GAV_NS<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> was evaluated using simulations and a dataset of 151 nurses from a Federal Medical Centre in Nigeria. Results showed allocation, duplication, clash, and multiple shift rates of 98.6%, 0.11%, 0.39%, and 0.2%, respectively. Simulations achieved 99.02%, 0%, 1.15%, and 0%, with computation times of 50.13ms−85.91ms. GAV_NS<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> outperforms manual and traditional GA-based scheduling. While it optimally distributes obligatory shifts, non-obligatory preferences like 3-day weekends were not fully met. The adoption of this system will enhance hospital efficiency, and nurse satisfaction, and provide historical data for future decision-making.