Vehicular fog computing (VFC) pushes the cloud computing capability to the distributed fog nodes at the edge of the Internet, enabling compute-intensive and latency-sensitive computing services for vehicles through task offloading. However, a heterogeneous mobility environment introduces uncertainties in terms of resource supply and demand, which are inevitable bottlenecks for the optimal offloading decision. Also, these uncertainties bring extra challenges to task offloading under the oblivious adversary attack and data privacy risks. In this article, we develop a new adversarial online algorithm with bandit feedback based on the adversarial multi-armed bandit theory, to enable scalable and low-complex offloading decision making on the fog node selection toward minimizing the offloading service cost in terms of delay and energy. The key is to implicitly tune exploration bonus in selection and assessment rules of the designed algorithm, taking into account volatile resource supply and demand. We theoretically prove that the input-size dependent selection rule allows to choose a suitable fog node without exploring the sub-optimal actions, and also an appropriate score patching rule allows to quickly adapt to evolving circumstances, which reduces variance and bias simultaneously, thereby achieving better exploitation exploration balance. Simulation results verify the effectiveness and robustness of the proposed algorithm.
翻译:电雾计算(VFC)将云计算能力推向互联网边缘分布的雾节点,通过任务卸载,为车辆计算密集和懒惰的计算服务,通过任务卸载;然而,不同的流动环境在资源供求方面带来不确定性,这是最佳卸载决定的不可避免的瓶颈。此外,这些不确定性给在模糊的敌人攻击和数据隐私风险下卸载任务带来了额外的挑战。在本篇文章中,我们开发了新的对抗性在线算法,根据对抗性多武装匪帮理论,提供匪帮反馈,使在雾节选择上作出可缩放和低复杂度卸载决定,以尽量减少延迟和能源方面的卸载服务成本。关键在于考虑到不稳定的资源供需,在设计算法的选择和评估规则中隐含勘探奖金。我们理论上证明,投入大小的依附选择规则允许选择适当的雾节点,而无需探索亚最佳行动,还有适当的评分补规则,可以快速适应不断变化的环境,从而降低差异和稳健的演算结果。同时,从而实现更好的开发平衡。