Wireless Resource Allocation with Collaborative Distributed and Centralized DRL under Control Channel Attacks

TL;DR

Simulation results demonstrate that the CDC-DRL algorithm significantly outperforms state-of-the-art DRL benchmarks, showcasing its ability to address resource allocation problems in large-scale CPSs under control channel attacks.

Abstract

In this paper, we consider a wireless resource allocation problem in a cyber-physical system (CPS) where the control channel, carrying resource allocation commands, is subjected to denial-of-service (DoS) attacks. We propose a novel concept of collaborative distributed and centralized (CDC) resource allocation to effectively mitigate the impact of these attacks. To optimize the CDC resource allocation policy, we develop a new CDC-deep reinforcement learning (DRL) algorithm, whereas existing DRL frameworks only formulate either centralized or distributed decision-making problems. Simulation results demonstrate that the CDC-DRL algorithm significantly outperforms state-of-the-art DRL benchmarks, showcasing its ability to address resource allocation problems in large-scale CPSs under control channel attacks.

Figures (3)

• Figure 1: Multi-sensor remote state estimation under broadcast control channel DoS attack. Actor and critic modules (in blue) will be explained in Section \ref{['sec:DRL']}.
• Figure 2: Performance comparison between CDC-DRL and the benchmarks.
• Figure 3: Convergence analysis of CDC-DRL