Optimized Resource Management and Security Enhancement in Fog Computing using Advanced Q-Learning Approaches
Kusuma G. S., Manju Devi · Engineering Technology & Applied Science Research · 2025
Fog computing enhances cloud computing functionalities at the network edge, providing diminished latency and improved data processing. Optimizing resource allocation and energy consumption in this dispersed infrastructure is essential for fulfilling the requirement for efficient operations. This research presents a novel energy-efficient resource optimization algorithm designed for data centers in fog computing settings. The suggested methodology utilizes the Enhanced Q-Learning (EQL) and Secure Q-Learning (SQL) algorithms to achieve dynamic resource allocation and ensure operational efficacy. The proposed technique addresses energy consumption issues and guarantees optimal resource utilization by integrating adaptive incentive functions and safe state-action mechanisms, while ensuring robust security. The simulation outcomes with CloudSim exhibit substantial enhancements in energy efficiency, system throughput, and resource optimization relative to conventional approaches.