DTBO: Optimizing Resource Usage in Fog-Edge Environment using Meta-Heuristic Scheduling Algorithm
Santhosh Kumar Medishetti, K Anusha, Srinivasa Babu Kasturi, S. Radhika, Aravind Reddy Bommineni, Mada Eswara Rao
Abstract
Task Scheduling (TS) in Fog-Edge Computing (FEC) environments is crucial for optimizing resource allocation, reducing latency, and ensuring efficient service delivery for Internet of Things (IoT) applications. In this study, we propose a novel Driving Training-Based Optimization (DTBO) algorithm for effective task scheduling in fog-edge computing. The DTBO algorithm leverages the principles of driving training, such as gradual learning and adaptive decision-making, to balance the workload between fog and edge nodes. By dynamically adjusting the scheduling strategy based on real-time system conditions, DTBO minimizes latency, energy consumption, and network congestion, while maximizing resource utilization. The proposed DTBO algorithm shows significant improvements in performance metrics, including task completion time by 18%, resource efficiency by 19.6%, and response time by 16.4%, compared to existing scheduling algorithms. Simulation results demonstrate that DTBO is capable of effectively managing heterogeneous workloads, providing timely responses for delay-sensitive tasks, and optimizing overall system efficiency in fog-edge environments. The findings highlight the potential of DTBO to enhance the quality of service in fog-edge computing, especially for time-sensitive IoT applications.