2020 · 10 citations · 15 references
ComputingCloud ComputingComputer SystemsEdge ComputingMobile ComputingUnmanned Aircraft SystemsEdge-cloud ArchitectureEnergy-efficient Mobile ComputingMobile Cloud ComputingMobile Edge ComputingMobile NetworksTask OffloadingChannel AssignmentCloud OffloadingMixed-integer OptimizationMixed-integer ProgrammingOptimization-based OffloadingPower ConsumptionPower Consumption OptimizationWorkload Offloading
Multiple unmanned aerial vehicles (UAVs) can act as intermediate relay for their flexible mobility. In mobile cloud computing (MCC) and mobile edge computing (MEC), UAVs assist ground user equipments (UEs) to offload traffic to cloudlet or cloud. In this scenario, different UEs may have different quality of experience (QoE) requirement. Moreover, the endurance flying as well as battery limitation of UAVs and UEs make this offloading architecture power sensitive. Thus, UEs' QoE, as well as overall system power consumption should be well-balanced by the MIMO channel assignment and UAVs' trajectory plan. This paper formulates such issue as a non-convex and mixed-integer optimization problem, and further proposes a heuristic joint power and QoE (HJPQ) algorithm to solve it. The numeral simulations reveal the algorithm has great QoE performance with high energy efficiency in different conditions.
15
Deep Reinforcement Learning with Double Q-Learning
Hado van Hasselt, Arthur Guez, David Silver · 2016 · 6K citations · Full text