# Sustainable Edge Intelligence Through Energy-Aware Early Exiting

arXiv: https://arxiv.org/abs/2305.14094 · HTML: https://mlsanity.com/paper/2305.14094/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices](https://mlsanity.com/paper/2108.09457/) (2021)
- [A Reinforcement-Learning Approach to Proactive Caching in Wireless Networks](https://mlsanity.com/paper/1712.07084/) (2017)

## Built on by (most cited first, 2 of 2)

- [Energy-Aware Dynamic Neural Inference](https://mlsanity.com/paper/2411.02471/) (2024)
- [Goal-oriented Communications based on Recursive Early Exit Neural Networks](https://mlsanity.com/paper/2412.19587/) (2024)

## Abstract (arXiv)

Deep learning (DL) models have emerged as a promising solution for the Internet of Things (IoT). However, due to their computational complexity, DL models consume significant amounts of energy, which can rapidly drain the battery and compromise the performance of IoT devices. For sustainable operation, we consider an edge device with a rechargeable battery and energy harvesting (EH) capabilities. In addition to the stochastic nature of the ambient energy source, the harvesting rate is often insufficient to meet the inference energy requirements, leading to drastic performance degradation in energy-agnostic devices. To mitigate this problem, we propose energy-adaptive dynamic early exiting (EE) to enable efficient and accurate inference in an EH edge intelligence system. Our approach derives an energy-aware EE policy that determines the optimal amount of computational processing on a per-sample basis. The proposed policy balances the energy consumption to match the limited incoming energy and achieves continuous availability. Numerical results show that accuracy and service rate are improved up to 25% and 35%, respectively, in comparison with an energy-agnostic policy.