Analyzing Energy and Performance Trade-offs for Network Anomaly Detection based on Deep Learning
Open Access
- 19 May 2025
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 224-237
Abstract
Network anomaly detection based on Deep Learning has already achieved outstanding performance results. However, the performance obtained by deep learning solutions is partially explained by the large scale of such underlying models. This paper studies the energy and performance trade-offs for deep learning models and their hyperparameter configurations when applied to network anomaly detection. The paper proposes an energy and performance profiling mechanism to observe the results obtained from different configurations of a given model, using a combination of statistical and instrumented profiling.Keywords
This publication has 23 references indexed in Scilit:
- Machine Learning in Network Anomaly Detection: A SurveyIEEE Access, 2021
- Green machine learning via augmented Gaussian processes and multi-information source optimizationSoft Computing, 2021
- Neural architecture search for image saliency fusionInformation Fusion, 2020
- Enhanced Network Anomaly Detection Based on Deep Neural NetworksIEEE Access, 2018
- A lightweight anomaly detection technique for low-resource IoT devices: A game-theoretic methodology2016
- Deep learningNature, 2015
- Traffic anomaly diagnosis in Internet backbone networks: A surveyComputer Networks, 2014
- Techniques to Measure, Model, and Manage Power2012
- A detailed analysis of the KDD CUP 99 data set2009
- Learning long-term dependencies with gradient descent is difficultIEEE Transactions on Neural Networks, 1994