A DRL-Based Task Offloading Scheme for Server Decision-Making in Multi-Access Edge Computing

Multi-access edge computing (MEC), based on hierarchical cloud computing, offers abundant resources to support the next-generation Internet of Things network. However, several critical challenges, including offloading methods, network dynamics, resource diversity, and server decision-making, remain open. Regarding offloading, most conventional approaches have neglected or oversimplified multi-MEC scenarios, fixating single-MEC instances. This myopic focus fails adapt computational during MEC overload, rendering such methods sub-optimal for real-world deployments. To address this deficiency, we propose a solution that employs deep reinforcement learning-based soft actor-critic (SAC) approach compute facilitate decision-making in multi-user, environments. Numerical experiments were conducted evaluate performance our proposed solution. The results demonstrate significantly reduces latency, enhances energy efficiency, achieves rapid stable convergence, thereby highlighting algorithm’s superior over existing methods.