Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning for Wireless Networked Systems: a joint Estimation-Control-Scheduling Approach

Zihuai Zhao, Wanchun Liu, Daniel E. Quevedo, Yonghui Li, Branka Vucetic

TL;DR

Deep-learning-based estimator-control-scheduler co-design for a model-unknown nonlinear WNCS over wireless fading channels is systematically investigated and a novel deep reinforcement learning (DRL)-based algorithm for controller and scheduler optimization utilizing both model-free and model-based data is proposed.

Abstract

Wireless networked control system (WNCS) connecting sensors, controllers, and actuators via wireless communications is a key enabling technology for highly scalable and low-cost deployment of control systems in the Industry 4.0 era. Despite the tight interaction of control and communications in WNCSs, most existing works adopt separative design approaches. This is mainly because the co-design of control-communication policies requires large and hybrid state and action spaces, making the optimal problem mathematically intractable and difficult to be solved effectively by classic algorithms. In this paper, we systematically investigate deep learning (DL)-based estimator-control-scheduler co-design for a model-unknown nonlinear WNCS over wireless fading channels. In particular, we propose a co-design framework with the awareness of the sensor's age-of-information (AoI) states and dynamic channel states. We propose a novel deep reinforcement learning (DRL)-based algorithm for controller and scheduler optimization utilizing both model-free and model-based data. An AoI-based importance sampling algorithm that takes into account the data accuracy is proposed for enhancing learning efficiency. We also develop novel schemes for enhancing the stability of joint training. Extensive experiments demonstrate that the proposed joint training algorithm can effectively solve the estimation-control-scheduling co-design problem in various scenarios and provide significant performance gain compared to separative design and some benchmark policies.

Deep Learning for Wireless Networked Systems: a joint Estimation-Control-Scheduling Approach

TL;DR

Deep-learning-based estimator-control-scheduler co-design for a model-unknown nonlinear WNCS over wireless fading channels is systematically investigated and a novel deep reinforcement learning (DRL)-based algorithm for controller and scheduler optimization utilizing both model-free and model-based data is proposed.

Abstract

Wireless networked control system (WNCS) connecting sensors, controllers, and actuators via wireless communications is a key enabling technology for highly scalable and low-cost deployment of control systems in the Industry 4.0 era. Despite the tight interaction of control and communications in WNCSs, most existing works adopt separative design approaches. This is mainly because the co-design of control-communication policies requires large and hybrid state and action spaces, making the optimal problem mathematically intractable and difficult to be solved effectively by classic algorithms. In this paper, we systematically investigate deep learning (DL)-based estimator-control-scheduler co-design for a model-unknown nonlinear WNCS over wireless fading channels. In particular, we propose a co-design framework with the awareness of the sensor's age-of-information (AoI) states and dynamic channel states. We propose a novel deep reinforcement learning (DRL)-based algorithm for controller and scheduler optimization utilizing both model-free and model-based data. An AoI-based importance sampling algorithm that takes into account the data accuracy is proposed for enhancing learning efficiency. We also develop novel schemes for enhancing the stability of joint training. Extensive experiments demonstrate that the proposed joint training algorithm can effectively solve the estimation-control-scheduling co-design problem in various scenarios and provide significant performance gain compared to separative design and some benchmark policies.
Paper Structure (22 sections, 41 equations, 11 figures, 8 tables, 2 algorithms)

This paper contains 22 sections, 41 equations, 11 figures, 8 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model
  3. WNCS Model
  4. Control and transmission schedule
  5. Design Objectives and Challenges
  6. Estimation and Control Co-Design over Static Channels
  7. DL-based Remote State Estimator
  8. DRL-based Controller with Hybrid Model-based and Model-free (MB-MF) Data
  9. Network Structure of the DRL-based Controller
  10. Training of Intelligent Controller
  11. Estimation-Control-Scheduling Co-Design over Dynamic Fading Channels
  12. DRL-based Controller and Scheduler over Fading Channels
  13. Joint Training of Controller and Scheduler
  14. Numerical Experiments
  15. Experiment Setups
  16. ...and 7 more sections

Figures (11)

  • Figure 1: A wireless networked control system (WNCS).
  • Figure 2: Estimator-controller co-design of the low-mobility WNCS.
  • Figure 3: Network structure of the estimator.
  • Figure 4: Network structure of the actor (and also the critic).
  • Figure 5: Estimator-controller-scheduler co-design of the high-mobility WNCS.
  • ...and 6 more figures