Research Project Title:
Understanding the Fundamentals of Reconfigurable Data Center Networks
abstract:Traditional data center networks design has a fundamental shortcoming: network operators must decide in advance the capacity to provision between switches. Then, the interconnect is either expensive or it limits application performance when demand between two nodes exceeds capacity. In response, researchers have proposed reconfigurable interconnects. However, they can be complex and have hidden assumptions of the scheduling algorithm to establish on-demand links. This project explores the design space of reconfigurable data centers by first developing a simulation to experiment with various data center architectures and scheduling algorithms. Next, we propose a new scheduling algorithm based on application characteristics and compare its performance with state-of-the-art architectures.
"Taking 6.033 (Computer Systems Engineering), I became fascinated with systems in general but with the internet in particular. Our project aims to explore new designs of data centers, a backbone of scalable modern internet technologies. Through this, I hope to learn about different architectures and schools of thought, while also learning to propose, communicate, explore, and validate ideas. I am most excited about working within a team."