Predictive networking and optimization for flow-based networks
This work addresses network optimization for flow-based systems, but it is incremental as it applies an existing method to a specific domain without broad advancements.
The researchers tackled the problem of classifying neural network flows by size using Artificial Neural Networks, achieving 87% prediction accuracy with a Feed Forward Neural Network, which enables flow-based routers to prioritize large flows for hardware content-addressable memory insertion.
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.