Now or Never: Continuous Surveillance AIoT System for Ephemeral Events in Intermittent Sensor Networks

TL;DR

This paper introduces an energy-aware elastic split computing algorithm enabling continuous, reliable surveillance in resource-constrained AIoT sensor networks, effectively capturing ephemeral high-stakes events.

Contribution

It presents a novel energy-aware offloading algorithm that maintains continuous sensing in intermittent, battery-less sensor networks for critical event detection.

Findings

Stable monitoring of an additional 2,496 m² area

Capture of approximately 103 more critical events per day

Demonstrates robustness of the proposed algorithm in resource-limited settings

Abstract

Wilderness monitoring tasks, such as poaching surveillance and forest fire detection, require pervasive and high-accuracy sensing. While AIoT offers a promising path, covering vast, inaccessible regions necessitates the massive deployment of maintenance-free, battery-less nodes with limited computational resources. However, these constraints create a critical `Availability Gap.' Conventional intermittent operations prioritize computation throughput, forcing sensors to sleep during energy buffering. Consequently, systems miss ephemeral, `now-or-never' events (e.g., Vocalizations of natural monuments or Fire), which is fatal for detecting rare but high-stakes anomalies. To address this, we propose an Energy-aware Elastic Split Computing Algorithm that prioritizes continuous sensing by dynamically offloading tasks to energy-rich neighbors. Preliminary results demonstrate stable monitoring of an additional $2,496\;\text{m}^2$ and the capture of approximately 103 more critical events per day. Ultimately, this algorithm establishes a robust foundation for building resilient, fail-safe surveillance systems even on resource-constrained nodes.