No abstract

No abstract

No abstract

This work considers the problem of control and resource scheduling in networked systems. We present DIRA, a Deep reinforcement learning based Iterative Resource Allocation algorithm, which is scalable and control-aware. Our algorithm is tailored towards large-scale problems where control and scheduling need to act jointly to optimize performance. DIRA can be used to schedule general time-domain optimization based controllers. In the present work, we focus on control designs based on suitably adapted linear quadratic regulators. We apply our algorithm to networked systems with correlated fading communication channels. Our simulations show that DIRA scales well to large scheduling problems.

The problem of remote state estimation in the presence of eavesdroppers has recently been investigated in the literature. For unstable systems it has been shown that one can keep the expected estimation error covariance bounded, while the expected eavesdropper error covariance becomes unbounded in the infinite horizon, using schemes based on transmission scheduling. In this paper we consider an alternative approach to achieve security, namely injecting noise into sensor transmissions, similar to the artificial noise technique used in physical layer security for wireless communications. Numerical results demonstrate significant performance improvements using this approach, with respect to the trade-off between the expected estimation error covariance and expected eavesdropper covariance.