Mayfly Taylor Optimisation-Based Scheduling Algorithm with Deep Reinforcement Learning for Dynamic Scheduling in Fog-Cloud Computing

Fog computing domain plays a prominent role in supporting time-delicate applications, which are associated with smart Internet of Things (IoT) services, like healthcare and city. However, cloud is capable standard for IoT data processing owing to the high latency restriction cloud, it incapable satisfying needs time-sensitive applications. The resource provisioning allocation process fog-cloud structure considers dynamic alternations user necessities, also restricted access resources fog devices more challenging. global adoption IoT-driven applications has led rise structure, permits perfect connection mobile edge resources. effectual scheduling application tasks environments challenging task because heterogeneity, stochastic behaviours, network hierarchy, controlled abilities, mobility elements IoT. deadline most significant challenge due variations requirement parameters. In this paper, Mayfly Taylor Optimisation Algorithm (MTOA) developed model. MTOA-based Deep Q-Network (DQN) showed better performance energy consumption, service level agreement (SLA), computation cost 0.0162, 0.0114, 0.0855, respectively.