A Computational Offloading Strategy Based on Deep Reinforcement Learning in Small cell networks

With the rapid development of communication technology in recent years, computing-intensive services such as virtual reality and face recognition are rapidly popularized. These services not only bring challenges to resource-constrained networks, but also cause a large amount of energy consumption and high delay on mobile devices with limited computing power and battery capacity. Mobile edge computing technology and small cell networks are the research hotspots in 5G era. Combining these two technologies can enable the network to have stronger coverage to provide users with more powerful computing power. In this paper, we propose a computing offloading algorithm model based on deep reinforcement learning in small cell networks. Considering the battery power of mobile devices and dynamic network bandwidth, the proposed algorithm aims to complete computing offload with a smaller overall overhead. The simulation shows that the performance of the proposed computational offloading algorithm is better than the comparative algorithm.