Energy-Aware Multi-Exit TinyML for Smart Zero-Energy Devices

TL;DR

This paper introduces an energy-aware multi-exit TinyML framework for zero-energy devices, enabling adaptive, energy-efficient person detection with reduced power consumption and maintained accuracy.

Contribution

It presents a novel multi-exit TinyML architecture combined with energy-aware circuits to optimize energy use on zero-energy edge devices.

Findings

Achieves approximately 29.6% reduction in energy consumption.

Maintains detection accuracy while reducing energy use.

Enables autonomous operation of zero-energy devices.

Abstract

The proliferation of smart and autonomous systems has motivated a shift toward executing intelligence directly on edge devices. This shift becomes particularly challenging for zero-energy devices (ZEDs), where severe constraints on memory, energy availability, and inference accuracy must be addressed simultaneously. In this paper, we present a unified approach to managing these constraints for smart ZEDs. Specifically, we design, train, and deploy a tiny machine learning (TinyML) model for person detection on a ZED. The proposed architecture stores a single model in memory while enabling adaptive inference through multiple exit points, allowing computational effort to scale with input difficulty. As a result, low-energy inference is performed for easy instances, while higher-precision inference is selectively employed for harder cases. This strategy significantly reduces energy consumption without sacrificing detection accuracy. Furthermore, to enhance device autonomy and prevent power failures, we introduce auxiliary energy-aware circuits that dynamically regulate system operation based on available energy. Compared with a state-of-the-art energy-aware single-exit TinyML approach, the proposed method achieves an energy consumption reduction of approximately $29.6\%$. Overall, the proposed framework is appealing for enabling accurate and energy-efficient intelligence on ZED platforms.