Predictive networking and optimization for flow-based networks
Networking and Internet Architecture
2017-07-24 v1 Neural and Evolutionary Computing
Abstract
Artificial Neural Networks (ANNs) were used to classify neural network flows by flow size. After training the neural network was able to predict the size of a flows with 87% accuracy with a Feed Forward Neural Network. This demonstrates that flow based routers can prioritize candidate flows with a predicted large number of packets for priority insertion into hardware content-addressable memory.
Keywords
Cite
@article{arxiv.1707.06729,
title = {Predictive networking and optimization for flow-based networks},
author = {Michael Arnold},
journal= {arXiv preprint arXiv:1707.06729},
year = {2017}
}
Comments
A thesis submitted for the Master of Science Degree at The University of Alabama in Huntsville