Deep Reinforcement Learning Based Admission Control for Throughput Maximization in Mobile Edge Computing

With the development of wireless network technologies, such as LTE/5G, Mobile Cloud Computing (MCC) has been proposed as a solution for mobile devices that need to carry out high-complexity computation with limited resources. Technically, with MCC, high-complexity computation tasks are offloaded from mobile devices to cloud servers. However, MCC does not work well for time-sensitive mobile applications due to the relatively long latency between mobile devices and cloud servers. Mobile Edge Computing (MEC), is expected to solve the problem with MCC. With MEC, edge servers, instead of cloud servers, are deployed at the edge of the network to provide offloading services to mobile devices. Since edge servers are much closer to mobile devices, the resulting latency is significantly lower. Despite the advantages of MEC over MCC, edge servers are not as resource-abundant as cloud servers. Consequently, when many offloaded tasks arrive at an edge server, admission control needs to be in place to arrive at the best performance. In this paper, we propose a Deep Reinforcement Learning (DRL) based admission control scheme, DAC, to maximize the system throughput of an edge server. Our experimental results indicate that DAC outperforms the existing admission control schemes for MEC in terms of system throughput.

I. Introduction

With the wide deployment of mobile devices, e.g. smart-phones, the quantity and type of mobile applications have grown rapidly over the past years. Nowadays, many mobile applications, such as online games and virtual reality, involve high-complexity computation that requires a large amount of hardware resources, which often exceeds the processing capacity of mobile devices [1]–[4]. Even if mobile devices have sufficient resources to execute these applications, the high-complexity nature of these applications typically leads to lengthy execution time, which is not energy-friendly to battery-powered mobile devices. To meet the computation requirements of these mobile applications or reduce the energy consumption of mobile devices, Mobile Cloud Computing (MCC) was proposed as a solution to this computation problem. With MCC, high-complexity computation tasks are offloaded from mobile devices to cloud servers. Once cloud servers complete the offloaded tasks, the computation results are returned to mobile devices.