Effective deep Q-networks (EDQN) strategy for resource allocation based on optimized reinforcement learning algorithm

Abstract The healthcare industry has always been an early adopter of new technology and a big benefactor it. use reinforcement learning in the system repeatedly resulted improved outcomes.. Many challenges exist concerning architecture RL method, measurement metrics, model choice. More significantly, validation authentic clinical settings needs further work. This paper presents Effective Resource Allocation Strategy (ERAS) for Fog environment, which is suitable Healthcare applications. ERAS tries to achieve effective resource management environment via real-time allocating as well prediction algorithms. Comparing with state-of-the-art algorithms, achieved minimum Makespan compared previous allocation while maximizing Average Utilization (ARU) Load Balancing Level (LBL). For each application, we contrasted models assessment metrics. In critical care, tremendous potential enhance decision-making. two main contributions, (i) Optimization hyperparameters using PSO, (ii) Using optimized load balancing fog environment. Because its exploitation, exploration, capacity get rid local minima, PSO significant significance when other optimization methodologies.