AAA: Priority-Aware and Latency-Optimized Task Scheduling in Fog Computing
Vemula Satish, Ashwini Reddy Kandi, Mattepalli Praneeth Kumar, K Anusha, C N Veena, Santhosh Kumar Medishetti
Abstract
Fog computing has emerged as a crucial paradigm to support latency-sensitive and heterogeneous Internet of Things (IoT) applications by extending computational resources closer to end-users. However, efficient task scheduling remains a significant challenge due to varying task priorities, resource heterogeneity, and stringent latency requirements. To address these issues, this paper introduces a novel task scheduling framework based on the Artificial Afterimage Algorithm (AAA), which leverages adaptive exploration and exploitation mechanisms to optimize task allocation in fog environments. The proposed approach was implemented and evaluated using the El Capitan workload on the iFogSim simulator, considering task priority, heterogeneity, and latency as performance parameters. Comparative analysis against established metaheuristic algorithms Genetic Algorithm (GA), Ant Colony Optimization (ACO), and Particle Swarm Optimization (PSO) demonstrates that AAA achieves superior performance, with 17.6% improvement in priority-aware scheduling, 14.3% enhancement in handling heterogeneous tasks, and 21.8% reduction in latency. These results underline the robustness and adaptability of AAA in dynamic fog infrastructures, offering a scalable and energy-efficient solution for real-time and mission-critical applications in next-generation computing ecosystems.