Predictive networking and optimization for flow-based networks

School of Graduate Studies The University of Alabama in Huntsville Degree Masters of Science College/Dept. College of Science/Computer Science in Computer Science Name of Candidate Michael Arnold Title Predictive Networking and Optimization For Flow Based Networks 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. Abstract Approval: Committee Chair Dr. Daniel RochowiakApproval: Committee Chair Dr. Daniel Rochowiak Department Chair Dr. Heggere Ranganath Graduate Dean Dr. David Berkowitz