Energy efficient for UAV-enabled mobile edge computing networks: Intelligent task prediction and offloading

Abstract

Mobile edge computing (MEC) network provides near-users computing and communication functions and has become a potential 5G evolutionary architecture. In order to overcome the shortcomings of the existing MEC network in fixed base stations and limited computing resources, unmanned arial vehicle (UAV) is introduced as a relay edge computing node and UAV-enabled MEC networks are proposed. However, UAVs have limited energy. Thus, energy consumption would be an optimal target during the information interaction. Therefore, an energy efficiency optimization algorithm based on a three-layer computation offloading strategy is proposed in this paper by combining the UAV position optimization algorithm and the LSTM-based task prediction algorithm. The experiments show that the computation offloading strategy of the UAV-enabled MEC network can be dynamically programmed with the proposed algorithm and architecture, according to the required delay, UAV height, and data size in order to effectively reduce the energy consumption of the UAV.