Deep Reinforcement Learning Based Admission Control for Throughput Maximization in Mobile Edge Computing
With the development of wireless network technologies, Mobile Cloud Computing (MCC) has been proposed as a solution for mobile devices’ high-complexity computation. Technically, with MCC, mobile devices’ high-complexity tasks are offloaded to cloud servers. However, MCC does not handle time-sensitive tasks well due to its long latency. Mobile Edge Computing (MEC), a latency-optimized MCC, deploying servers at the edge of the network. Therefore, the short transmitting distance contributes to low latency. However, edge servers are not as resource-abundant as cloud servers. Consequently, when tasks arrive at edge servers, admission control is required to increase the MEC’s performance. Therefore, we propose a Deep Reinforcement Learning (DRL) based admission control scheme, DAC, to maximize the edge server’s throughput. The performance of DAC is thoroughly investigated via extensive simulations. The simulations indicate that DAC outperforms the existing schemes in terms of system throughput and resource utilization.