10.5281/zenodo.6959993
https://zenodo.org/records/6959993
oai:zenodo.org:6959993
Lahmer, Seyyidahmed
Seyyidahmed
Lahmer
University of Padova
Khoshsirat, Aria
Aria
Khoshsirat
University of Padova
Rossi, Michele
Michele
Rossi
University of Padova
Zanella, Andrea
Andrea
Zanella
University of Padova
Energy Consumption of Neural Networks on NVIDIA Edge Boards: an Empirical Model
Zenodo
2022
Energy consumption
Deep Neural Networks
Edge Computing
Inference
2022-08-04
eng
10.5281/zenodo.6959992
https://zenodo.org/communities/greenedge-itn
https://zenodo.org/communities/eu
Creative Commons Attribution 4.0 International
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.
European Commission
10.13039/501100000780
953775
Taming the environmental impact of mobile networks through GREEN EDGE computing platforms