A Whittle Index Policy for the Remote Estimation of Multiple Continuous Gauss-Markov Processes over Parallel Channels

In this paper, we study a sampling and transmission scheduling problem for multi-source remote estimation, where a scheduler determines when to take samples from multiple continuous-time Gauss-Markov processes and send the samples over multiple channels to remote estimators. The sample transmission times are i.i.d. across samples and channels. The objective of the scheduler is to minimize the weighted sum of the time-average expected estimation errors of these Gauss-Markov sources. This problem is a continuous-time Restless Multi-arm Bandit (RMAB) problem with a continuous state space. We prove that the arms are indexable and derive an exact expression of the Whittle index. To the extent of our knowledge, this is the first Whittle index policy for multi-source signal-aware remote estimation. This result has two degenerated cases of interest: (i) In the single-source case, the Whittle index policy reproduces earlier threshold-based sampling policies for the remote estimation of Wiener and Ornstein-Uhlenbeck processes. When the instantaneous estimation error of the Gauss-Markov process crosses the optimal threshold, the Whittle index is precisely equal to 0. In addition, a new optimal sampling policy for the remote estimation of the unstable Ornstein-Uhlenbeck process is obtained. (ii) In the signal-agnostic case, we find an exact expression of the Whittle index for Age of Information (AoI)-based remote estimation, which complements earlier results by allowing for random transmission times. Our numerical results show that the proposed policy performs better than the signal-agnostic AoI-based Whittle index policy and the Maximum-Age-First, Zero-Wait (MAF-ZW) policy. The performance gain of the proposed policy is high when some of the Gauss-Markov processes are highly unstable or when the sample transmission times follow a heavy-tail distribution.