Energy-Aware Smart Task Scheduling in Edge Computing Networks with A3C

With the rapid development of the Internet of Things, a huge amount of data is generated from mobile users. Mobile Edge Computing (MEC) extends cloud computing capabilities to the edge of the network which enables real-time and low-latency services for mobile users. However, how to intelligently schedule tasks to save energy consumption in an edge computing environment remains a challenge. In this paper, we formulate a dynamic offloading optimization problem to find out how to minimize system energy consumption based on a two-layer heterogeneous edge cloud cellular architecture. In addition, we model the problem as a Markov Decision Process (MDP) and employ the asynchronous advantage actor-critic (A3C) algorithm to propose a suitable scheduling strategy. The simulation results verify the effectiveness of our proposed method.