Machine Learning in Event-Triggered Control: Recent Advances and Open Issues

Abstract

Network control systems have gained considerable attention over the last decade as a result of the trend towards decentralised control applications and the emergence of cyber-physical system applications. However, real-world network control systems suffer from limited communication bandwidths, reliability issues, and a lack of awareness of network dynamics due to the complex nature of wireless networks. Combining machine learning and event-triggered control has the potential to alleviate some of these issues. For example, machine learning can be used to overcome the problem of a lack of network models by learning system behavior or adapting to dynamically changing models by continuously learning model dynamics. Event-triggered control can help to conserve communication bandwidth by transmitting control information only when necessary or when resources are available. The purpose of this article is to conduct a review of the literature on the use of machine learning in combination with event-triggered control. Machine learning techniques such as statistical learning, neural networks, and reinforcement learning-based approaches such as deep reinforcement learning are being investigated in combination with event-triggered control. We discuss how these learning algorithms can be used for different applications depending on the purpose of the machine learning use. Following the review and discussion of the literature, we highlight open research questions and challenges associated with machine learning-based event-triggered control and suggest potential solutions.

Event-triggered semi-active TLCD for ground motion-induced vibration control

“…In event-triggered control, the concept revolves around triggering the controller to modify control inputs only when specific conditions are met [34,35]. Event-triggered control typically comprises two main components: the feedback controller and the trigger condition which determines when the control input should be updated [36][37][38]. In the proposed event-triggered TLCD system, as an example, the control input remains at 0 (indicating that the two baffles are fixed) if the measured sensor signals do not satisfy the predefined conditions.…”

Robust Bellman State Prediction with Learning and Model Preferences

“…ETC reactively decides policy updates after unforeseen disturbances violate continually monitored thresholds. Sedghi et al (2022) review machine learning approaches to ETC where thresholds are static, state or time dependent, or Lyapunov stability-based. State-deviation thresholds were extended to learning new models under communication gaps, forming event-triggered learning (ETL) (e.g.…”