# Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems

arXiv: https://arxiv.org/abs/1810.07751 · HTML: https://mlsanity.com/paper/1810.07751/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2018.

## Built on by (most cited first, 25 of 25)

- [Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edge](https://mlsanity.com/paper/2101.07511/) (2021)
- [Machine Learning for Microcontroller-Class Hardware: A Review](https://mlsanity.com/paper/2205.14550/) (2022)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [A Survey on Collaborative DNN Inference for Edge Intelligence](https://mlsanity.com/paper/2207.07812/) (2022)
- [Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI](https://mlsanity.com/paper/2312.14229/) (2023)
- [Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning](https://mlsanity.com/paper/2301.00130/) (2022)
- [Towards Battery-Free Machine Learning and Inference in Underwater Environments](https://mlsanity.com/paper/2202.08174/) (2022)
- [Update Compression for Deep Neural Networks on the Edge](https://mlsanity.com/paper/2203.04516/) (2022)
- [Is TinyML Sustainable? Assessing the Environmental Impacts of Machine Learning on Microcontrollers](https://mlsanity.com/paper/2301.11899/) (2023)
- [DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning](https://mlsanity.com/paper/2401.09068/) (2024)
- [Enabling Fast Deep Learning on Tiny Energy-Harvesting IoT Devices](https://mlsanity.com/paper/2111.14051/) (2021)
- [MATADOR: Automated System-on-Chip Tsetlin Machine Design Generation for Edge Applications](https://mlsanity.com/paper/2403.10538/) (2024)
- [Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence](https://mlsanity.com/paper/2407.15320/) (2024)
- [Energy-Aware Deep Learning on Resource-Constrained Hardware](https://mlsanity.com/paper/2505.12523/) (2025)
- [EVE: Environmental Adaptive Neural Network Models for Low-power Energy Harvesting System](https://mlsanity.com/paper/2207.09258/) (2022)
- [Send Less, Save More: Energy-Efficiency Benchmark of Embedded CNN Inference vs. Data Transmission in IoT](https://mlsanity.com/paper/2510.24829/) (2025)
- [A Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge](https://mlsanity.com/paper/2403.07036/) (2024)
- [Energy-Aware Dynamic Neural Inference](https://mlsanity.com/paper/2411.02471/) (2024)
- [Register Your Forests: Decision Tree Ensemble Optimization by Explicit CPU Register Allocation](https://mlsanity.com/paper/2404.06846/) (2024)
- [Memory-efficient Energy-adaptive Inference of Pre-Trained Models on Batteryless Embedded Systems](https://mlsanity.com/paper/2405.10426/) (2024)
- [Revisiting DNN Training for Intermittently-Powered Energy-Harvesting Micro-Computers](https://mlsanity.com/paper/2408.13696/) (2024)
- [E-QUARTIC: Energy Efficient Edge Ensemble of Convolutional Neural Networks for Resource-Optimized Learning](https://mlsanity.com/paper/2409.08369/) (2024)
- [Offload Rethinking by Cloud Assistance for Efficient Environmental Sound Recognition on LPWANs](https://mlsanity.com/paper/2502.15285/) (2025)
- [UnIT: Scalable Unstructured Inference-Time Pruning for MAC-efficient Neural Inference on MCUs](https://mlsanity.com/paper/2507.07885/) (2025)
- [AutoTailor: Automatic and Efficient Adaptive Model Deployment for Diverse Edge Devices](https://mlsanity.com/paper/2511.22355/) (2025)

## Abstract (arXiv)

Energy-harvesting technology provides a promising platform for future IoT applications. However, since communication is very expensive in these devices, applications will require inference "beyond the edge" to avoid wasting precious energy on pointless communication. We show that application performance is highly sensitive to inference accuracy. Unfortunately, accurate inference requires large amounts of computation and memory, and energy-harvesting systems are severely resource-constrained. Moreover, energy-harvesting systems operate intermittently, suffering frequent power failures that corrupt results and impede forward progress. This paper overcomes these challenges to present the first full-scale demonstration of DNN inference on an energy-harvesting system. We design and implement SONIC, an intermittence-aware software system with specialized support for DNN inference. SONIC introduces loop continuation, a new technique that dramatically reduces the cost of guaranteeing correct intermittent execution for loop-heavy code like DNN inference. To build a complete system, we further present GENESIS, a tool that automatically compresses networks to optimally balance inference accuracy and energy, and TAILS, which exploits SIMD hardware available in some microcontrollers to improve energy efficiency. Both SONIC & TAILS guarantee correct intermittent execution without any hand-tuning or performance loss across different power systems. Across three neural networks on a commercially available microcontroller, SONIC & TAILS reduce inference energy by 6.9x and 12.2x, respectively, over the state-of-the-art.