IEEE Transactions on Intelligent Transportation Systems · 2020 · 126 citations · 27 references
ComputingComputer ScienceComputer SystemsEdge ComputingMachine LearningMobile ComputingEdge Computing InfrastructureEdge InfrastructureEnergy-efficient Mobile ComputingMobile Edge ComputingReinforcement LearningTask OffloadingDeep Reinforcement LearningEdge Task OffloadingEnergy ConsumptionEnergy-aware Task OffloadingExperience ReplayPolicy GradientsReinforcement Learning For OffloadingVehicular Task Offloading
In the transportation industry, task offloading services of edge-enabled Internet of Vehicles (IoV) are expected to provide vehicles with the better Quality of Experience (QoE). However, the various status of diverse edge servers and vehicles, as well as varying vehicular offloading modes, make a challenge of task offloading service. Therefore, to enhance the satisfaction of QoE, we first introduce a novel QoE model. Specifically, the emerging QoE model restricted by the energy consumption: 1) intelligent vehicles equipped with caching spaces and computing units may work as carriers; 2) various computational and caching capacities of edge servers can empower the offloading; and 3) unpredictable routings of the vehicles and edge servers can lead to diverse information transmission. We then propose an improved deep reinforcement learning (DRL) algorithm named PS-DDPG with the prioritized experience replay (PER) and the stochastic weight averaging (SWA) mechanisms based on deep deterministic policy gradients (DDPG) to seek an optimal offloading mode, saving energy consumption. Specifically, the PER scheme is proposed to enhance the availability of the experience replay buffer, thus accelerating the training. Moreover, reducing the noise in the training process and thus stabilizing the rewards, the SWA scheme is introduced to average weights. Extensive experiments certify the better performance, i.e., stability and convergence, of our PS-DDPG algorithm compared to existing work. Moreover, the experiments indicate that the QoE value can be improved by the proposed algorithm.
27
Averaging Weights Leads to Wider Optima and Better Generalization
Pavel Izmailov, D. A. Podoprikhin, Timur Garipov et al. · 2018 · 617 citations