OIDM: An Observability-based Intelligent Distributed Edge Sensing Method for Industrial Cyber-Physical Systems

TL;DR

This work tackles stochastic sensor scheduling in edge-enabled ICPS where guaranteeing observability under wireless losses is challenging. It introduces OIDM, an observability-based intelligent distributed edge sensing method that uses deep reinforcement learning (DDPG) to balance sensing accuracy and power by tying transmission success to observability. Key contributions include new linear approximations of observability criteria, probabilistic bounds on observability to guide action space design, and an MDP formulation that integrates observability constraints into the scheduling objective. Applied to slab temperature estimation in hot rolling, OIDM demonstrates improved performance over baseline stochastic and deterministic schemes, showing practical potential for reliable, energy-efficient sensing in industrial edge networks.

Abstract

Industrial cyber-physical systems (ICPS) integrate physical processes with computational and communication technologies in industrial settings. With the support of edge computing technology, it is feasible to schedule large-scale sensors for efficient distributed sensing. In the sensing process, observability is the key to obtaining complete system states, and stochastic scheduling is more suitable considering uncertain factors in wireless communication. However, existing works have limited research on observability in stochastic scheduling. Targeting this issue, we propose an observability-based intelligent distributed edge sensing method (OIDM). Deep reinforcement learning (DRL) methods are adopted to optimize sensing accuracy and power efficiency. Based on the system's ability to achieve observability, we establish a bridge between observability and the number of successful sensor transmissions. Novel linear approximations of observability criteria are provided, and probabilistic bounds on observability are derived. Furthermore, these bounds guide the design of action space to achieve a probabilistic observability guarantee in stochastic scheduling. Finally, our proposed method is applied to the estimation of slab temperature in industrial hot rolling process, and simulation results validate its effectiveness.

Figures (6)

• Figure 1: The architecture of edge computing supported ICPS.
• Figure 2: Basic logic flow of proposed OIDM.
• Figure 3: An example of the topology of $(J,\tilde{G})$.
• Figure 4: One typical scenario of ICPS: temperature estimation in industrial hot rolling process.
• Figure 5: Comparisons of average cost with different $\beta$.