Configuring Transmission Thresholds in IIoT Alarm Scenarios for Energy-Efficient Event Reporting

TL;DR

This work tackles energy-efficient event reporting in IIoT alarm scenarios by optimizing per-device transmission thresholds that trigger data reporting. It develops a convex-approximation framework (P2) and applies multiple solution paradigms, including SCA, BCD, Voronoi-based partitioning, Bayesian KNN, GA, PSO, and RL (Q-learning), to manage collisions and miss-detections while meeting a target error limit. Empirical results show RL achieving the largest energy reductions (up to 94% in low density, 60% in high density) and consistently meeting the error constraint, with convex methods offering valuable trade-offs in complexity. The findings highlight the practicality of threshold-based policies and data-driven RL for scalable, energy-efficient IIoT alarm reporting in diverse deployment densities.

Abstract

Industrial Internet of Things (IIoT) applications involve real-time monitoring, detection, and data analysis. This is challenged by the intermittent activity of IIoT devices (IIoTDs) and their limited battery capacity. Indeed, the former issue makes resource scheduling and random access difficult, while the latter constrains IIoTDs' lifetime and efficient operation. In this paper, we address interconnected aspects of these issues. Specifically, we focus on extending the battery life of IIoTDs sensing events/alarms by minimizing the number of unnecessary transmissions. Note that when multiple devices access the channel simultaneously, there are collisions, potentially leading to retransmissions, thus reducing energy efficiency. We propose a threshold-based transmission-decision policy based on the sensing quality and the network spatial deployment. We optimize the transmission thresholds using several approaches such as successive convex approximation, block coordinate descent methods, Voronoi diagrams, explainable machine learning, and algorithms based on natural selection and social behavior. Besides, we propose a new approach that reformulates the optimization problem as a $Q$-learning solution to promote adaptability to system dynamics. Through numerical evaluation, we demonstrate significant performance enhancements in complex IIoT environments, thus validating the practicality and effectiveness of the proposed solutions. We show that Q-learning performs the best, while the block coordinate descending method incurs the worst performance. Additionally, we compare the proposed methods with a benchmark assigning the same threshold to all the devices for transmission decision. Compared to the benchmark, up to 94\% and 60\% reduction in power consumption are achieved in low-density and high-density scenarios, respectively.

Figures (10)

• Figure 1: Illustration of an IIoT network where a coordinator controls and collects information from $N=55$ IIoTDs. The influence of an event on the surrounding IIoTDs is modeled by a probability activation function that decays with the distance from the event epicenter to the IIoTDs.
• Figure 2: The coverage regions of an illustrative network deployment for a) (top left) $\eta = 1$ and 25 IIoTDs, b) (top right) $\eta = 1$ and 100 IIoTDs, c) (bottom left) $\eta = 0.1$ and 25 IIoTDs, and d) (bottom right) $\eta = 0.1$ and 100 IIoTDs. The activation probability shows the event detection coverage.
• Figure 3: Approximation to \ref{['cdf']} fo different $u,v$ and $\eta$ values, (left) $u,v = 25$ and (rigth) $u,v = 50$.
• Figure 4: Illustration of a Voronoi diagram for a grid IIoT deployment with 5 devices (represented as red dots). The black lines represent the Voronoi polygon corresponding to each IIoTD, while the blue lines represent the sensing area border. (left) Voronoi-(i), (center) Voronoi-(ii), and (right) Voronoi-(iii).
• Figure 5: The trade-off between model interpretability and performance.

Theorems & Definitions (2)

• Theorem 1
• Theorem 2