Optimizing Computational Offloading in Mobile Edge Computing Using Reinforcement Learning: A System Cost Minimization Approach

Abstract

The advancement of science and technology has led to the widespread adoption of intelligent mobile devices, resulting in a rapid increase in mobile device traffic. However, these devices often face limitations in resources and computing performance, making it challenging to handle computation-intensive applications. Mobile edge computing technology offers a high-performance, low-latency, and high-bandwidth carrier-class service environment, effectively addressing these issues. To minimize the total weighted cost of the system, this paper proposes a computational offloading and resource allocation scheme based on reinforcement learning. Simulation results demonstrate that the proposed algorithm significantly reduces the total weighted cost of the system compared to several benchmark methods.