As the world becomes more inter-connected and dependent on the Internet, networks become ever more pervasive, and the stresses placed upon them more demanding. Similarly, the expectations of networks to maintain a high level of performance have also increased. Network performance is highly important to any business that operates online, depends on web traffic, runs any part of their infrastructure in a cloud environment, or even hosts their own network infrastructure. Depending upon the exact nature of a network, whether it be local or wide-area, 10 or 100 Gigabit, it will have distinct performance characteristics and it is important for a business or individual operating on the network to understand those performance characteristics and how they affect operations.

To better understand our networks, it is necessary that we test them to measure their performance capabilities and track these metrics over time. In our work, we provide an in-depth analysis of how best to run cloud benchmarks to increase our network intelligence and how we can use the results of those benchmarks to predict future performance and identify performance anomalies. To achieve this, we explain how to effectively run cloud benchmarks and propose a scheduling algorithm for running large numbers of cloud benchmarks daily. We then use the performance data gathered from this method to conduct a thorough analysis of the performance characteristics of a cloud network, train neural networks to forecast future throughput based on historical results and detect performance anomalies as they occur.

Degree Date

Fall 2022

Document Type


Degree Name



Computer Science and Engineering


Dr. Suku Nair

Second Advisor

Dr. Jennifer Dworak

Third Advisor

Dr. Nageswara Rao

Fourth Advisor

Dr. Michael Hahsler

Fifth Advisor

Dr. Jeff Tian

Subject Area

Computer Science

Number of Pages




Creative Commons License

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License