.png){kind=icon}
.png){kind=icon}
Return
Communication-Control Codesign for Large-Scale Wireless Networked Control Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/JSAC.2025.3574602.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Wireless networked control systems (WNCSs) are critical to Industry 4.0, enabling applications like drone swarms and autonomous robots. The tight interdependence between communication and control demands integrated design, yet traditional approaches treat them separately, leading to inefficiencies. Existing codesign methods often rely on simplified models for single-loop or independent multi-loop systems, overlooking the complexities of large-scale WNCSs. These include coupled control loops, time-correlated wireless channels, sensing-control trade-offs, and computational challenges. To address these challenges, we propose a practical WNCS model that captures correlated dynamics among spatially distributed sensors and actuators sharing limited wireless resources over multi-state Markov block-fading channels. To solve the resulting high-dimensional codesign problem, we develop a deep reinforcement learning (DRL) algorithm that scales efficiently by managing hybrid action spaces, capturing communication-control dependencies, and maintaining robust performance under time-correlated dynamics and resource constraints. Simulations demonstrate that our DRL approach outperforms benchmarks, providing a scalable and effective solution for large-scale industrial WNCSs.
Keywords:
Wireless networked control
Industry 4.0
transmission scheduling
deep reinforcement learning
Journal
IF:
17.2
Papers:
6.4K
Citations:
3.1W