Learning for serving deadline-constrained traffic in multi-channel wireless networks

We study the problem of serving randomly arriving and delay-sensitive traffic over a multi-channel communication system with time-varying channel states and unknown statistics. This problem deviates from the classical exploration-exploitation setting in that the design and analysis must accommodate the dynamics of packet availability and urgency as well as the cost of each channel use at the time of decision. To that end, we have developed and investigated two policies, one index-based (UCB-Deadline) and the other Bayesian (TS-Deadline), both of which perform dynamic channel allocation decisions that incorporate these traffic requirements and costs. Under symmetric channel conditions, we have proved that the UCB-Deadline policy can achieve bounded regret in the likely case where the cost of using a channel is not too high to prevent all transmissions, and logarithmic regret otherwise. In our numerical studies, we also show that TS-Deadline achieves superior performance over its UCB counterpart, making it a potentially useful alternative when fast convergence to optimal is important.