International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)
A Quantum Annealing-Based Approach for Solving Talent Scheduling
Kundjanasith Thonglek, Pongsakorn Sihapitak, Chonho Lee
Abstract
Talent scheduling is a complicated task that arises from the intricate interplay of human resources, project dynamics, and organizational goals. The inherent complexities are magnified when managing tasks that involve a diverse array of factors, including skills, project timelines, and resource limitations. This paper introduces a novel approach employing quantum annealing to address the complex challenge of talent scheduling. Quantum annealing, an emerging field known for its innate optimization capabilities, offers a compelling framework for addressing this multifaceted challenge. We present a comprehensive exploration of our proposed quantum annealing-based method, comparing its efficacy against the traditional dynamic programming approach and various meta-heuristic algorithms. Our experimental results reveal that the proposed quantum annealing-based approach achieves optimality equivalent to the dynamic programming approach but with significantly reduced runtime. Additionally, we examine the outcomes when compared to other meta-heuristic approaches, shedding light on the comparative strengths and limitations. Furthermore, we investigate the impact of varying the number of samples and sweeps within our quantum annealing-based approach, providing insights into the sensitivity of our method to these parameters.