A survey on resource scheduling approaches in multi-access edge computing environment: a deep reinforcement learning study

Abstract Multi-access edge computing (MEC) brings many services closer to user devices, alleviating the pressure on resource-constrained devices. It enables devices to offload compute-intensive tasks to nearby MEC servers. Hence, improving users’ quality of experience (QoS) by reducing both application execution time and energy consumption. However, to meet the huge demands, efficient resource scheduling algorithms are an essential and challenging problem. Resource scheduling involves efficiently allocating and managing MEC resources. In this paper, we survey the state-of-the-art research regarding this issue and focus on deep reinforcement learning (DRL) solutions. DRL algorithms reach optimal or near-optimal…

• CU
  Cairo University