# Energy Consumption of Neural Networks on NVIDIA Edge Boards: an Empirical Model

arXiv: https://arxiv.org/abs/2210.01625 · HTML: https://mlsanity.com/paper/2210.01625/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## Builds on (most cited first, 3 of 3)

- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [Discontinuous Computation Offloading for Energy-Efficient Mobile Edge Computing](https://mlsanity.com/paper/2008.03508/) (2020)

## Built on by (most cited first, 7 of 7)

- [Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows](https://mlsanity.com/paper/2604.09611/) (2026)
- [A Comparative Study of Machine Learning Algorithms for Anomaly Detection in Industrial Environments: Performance and Environmental Impact](https://mlsanity.com/paper/2307.00361/) (2023)
- [Kernel-Level Energy-Efficient Neural Architecture Search for Tabular Dataset](https://mlsanity.com/paper/2504.08359/) (2025)
- [QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference](https://mlsanity.com/paper/2506.23934/) (2025)
- [Energy Efficiency in AI for 5G and Beyond: A DeepRx Case Study](https://mlsanity.com/paper/2507.10409/) (2025)
- [Physics-Informed Spiking Neural Networks via Conservative Flux Quantization](https://mlsanity.com/paper/2511.21784/) (2025)
- [Design-Time Optimization of Deep Neural Networks for Intermittent Learning on Microcontrollers](https://mlsanity.com/paper/2608.03589/) (2026)

## Abstract (arXiv)

Recently, there has been a trend of shifting the execution of deep learning inference tasks toward the edge of the network, closer to the user, to reduce latency and preserve data privacy. At the same time, growing interest is being devoted to the energetic sustainability of machine learning. At the intersection of these trends, we hence find the energetic characterization of machine learning at the edge, which is attracting increasing attention. Unfortunately, calculating the energy consumption of a given neural network during inference is complicated by the heterogeneity of the possible underlying hardware implementation. In this work, we hence aim at profiling the energetic consumption of inference tasks for some modern edge nodes and deriving simple but realistic models. To this end, we performed a large number of experiments to collect the energy consumption of convolutional and fully connected layers on two well-known edge boards by NVIDIA, namely Jetson TX2 and Xavier. From the measurements, we have then distilled a simple, practical model that can provide an estimate of the energy consumption of a certain inference task on the considered boards. We believe that this model can be used in many contexts as, for instance, to guide the search for efficient architectures in Neural Architecture Search, as a heuristic in Neural Network pruning, or to find energy-efficient offloading strategies in a Split computing context, or simply to evaluate the energetic performance of Deep Neural Network architectures.