Multi-Interface Channel Allocation in Fog Computing Systems using Thompson Sampling

Abstract

In fog computing systems, each fog node often maintains multiple interfaces to achieve simultaneous communication with end devices. To maximize the utilization of network capacities and avoid interference, a critical mission for each fog node is to allocate distinct channels to its interfaces, a.k.a. multi-interface channel allocation, to maximize the total throughput by successful transmissions over time. However, the effective allocation scheme design is challenging because the full knowledge of channel state dynamics is often hard to attain in practice. Faced with such uncertainties, online learning is needed to cooperate with online decision making. In this paper, we devise an integrated design to conduct such multi-interface channel allocation in fog computing systems. Specifically, by formulating the channel allocation problem in the settings of multi-armed bandit with multiple plays and leveraging Thompson sampling techniques, we propose a Multi-Interface Channel Allocation with Binary feedback (MICAB) scheme, which makes online channel allocation decisions through effective learning from binary transmission feedback. Our theoretical analysis shows that MICA-B achieves a sublinear $O(\log T)$ regret bound over the performance loss (a.k.a regret) over a finite time horizon T. Further, we propose MICA-M which extends MICA to handle more general multi-level feedback information. Our simulation results verify the effectiveness and robustness of both MICA-B and MICA-M in terms of regret reduction.