Real-Time Task Scheduling using Bio-Inspired Algorithms: A Comparative Study of ACO, PSO, and GWO

This work investigates the use of bio-inspired algorithms in real-time task scheduling, whereby their capabilities are explored in intelligent computing to enhance performance optimization. Three influential bio-inspired algorithms, including Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO), are employed in the real-time task scheduling process. The dataset utilized includes $\mathbf{6, 8 0 0}$ periodic task sets, with each set including 9 tasks. The evaluation of the proposed algorithms is based on two primary metrics: success ratio, which quantifies the proportion of activities finished within their established time limits, and CPU utilization factor, which evaluates the effectiveness of processor utilization. The success ratio and CPU utilization were evaluated based on low, high and very high CPU load on ACO, PSO and GWO. Based on the observations, it is observed that GWO performed significantly better than ACO and PSO. The empirical findings illustrate the efficacy of bioinspired algorithms in augmenting job scheduling for real-time systems, therefore providing significant insights into their suitability for optimizing system performance.