Age of Information Optimization in Multi-Channel Network With Sided Information

We consider a discrete-time multi-channel network where the destination collects time-sensitive packets from multiple sources with sided channel information. The popular metric, Age of Information (AoI), is applied to measure data freshness at destination. Due interference constraint, only disjoint source-channel pairs can be chosen for transmission in each time slot, and decision maker should choose optimal scheduling minimize average AoI To learn selection, we apply linear contextual bandit (LCB) framework by utilizing information provided pilots. Concretely, establish relationship between regret sub-optimal selection times propose both age-independent age-dependent algorithms. former method proven achieve sub-linear but outperformed latter algorithm non-linear model simulation.