DRL driven energy-efficient resource allocation for multimedia broadband services in mobile edge network

Traffic-intensive Multimedia Broadband Services (MBS) lead to the explosive mobile traffic growth in 5G network, and Mobile Edge Network(MEN) is a potential solution for it. Mobile edge computing network mainly provides users with ubiquitous computing support to meet the needs of delay-sensitive and computation-reinforcement services. Although mobile edge networks can provide advantages such as low latency, moving storage and computing resources down also leads to more complex resource management for mobile edge networks. Therefore, how to allocate resources such as bandwidth and power more efficiently and efficiently while meeting the needs of users has become an urgent problem to be solved. Though Deep Reinforcement Learning (DRL) has been used to a lot of aspects of studies related to edge networks, there lacks the applications for energy-efficient resource allocation. A Deep Reinforcement Learning (DRL) based energy-efficient resource allocation mechanism is proposed in this paper with the goal of efficiently allocating the resources while meeting the demands of each mobile user. The energy efficiency value could be obtained when the algorithm reaches convergence based on the analysis of the simulation results. The efficiency of the DRL-based mechanism and its effectiveness in meeting user requirements and implementing energy-efficient resource allocation are verified.