CAREER: Reassessing the Foundations of Internet Transport
Principal Investigator: Jasleen Sahni
Funding Agency: National Science Foundation
Agency Number: CNS-0347814
Abstract
Research Goals: The Internet has grown rapidly along several dimensions over the past decade and a half. Yet, the core transport mechanisms used in its operation have not changed much. It is difficult to blindly believe that the assumptions on which network designs were based a decade ago are valid even today. Unfortunately, due to the in-feasibility of collecting sufficient statistics in the past, answers to several questions related to the transport performance in today's Internet are unknown: Is there any congestion in today's Internet? Are the basic assumptions used in the design of legacy transport mechanisms, valid any more? Are transport mechanisms of the past working well for current applications? If not, how can they be redesigned? It is the goal of my research to address these concerns by: 1. Pursuing extensive measurements and analysis to develop a fundamental understanding of transport performance of networks and validate legacy assumptions. 2. Studying the impact of invalid assumptions on the design, analysis, and evaluation of existing transport mechanisms. 3. Developing new mechanisms and analysis techniques based on the findings.
Education Goals: Computer scientists are currently strongly focused on using sophisticated measurement and analysis techniques for a variety of purposes. Unfortunately, current Computer Science (CS) courses rarely go into depths of rigorous measurement methodologies or scientific analysis. Thus, they do not equip students well with the set of skills needed to meet tomorrow's challenges. Furthermore, networking education is based mostly on classroom teaching and simplified course projects. These pedagogical techniques are not adequate to understand and appreciate the intricacies of the Internet. I plan to use my research interests to advance the current state of CS education in three main ways: 1. Introduce the treatment of scientific measurements and analysis into CS curricula. 2. Use the measurement tools and techniques developed in my research to improve the efficacy of networking education. 3. Encourage participation of undergraduates in research through substantial, yet accessible, measurement projects.
Intellectual Merits: The research proposed in this project will help answer several fundamental questions related to the transport performance of the Internet. Our analysis and design efforts will lay a sound foundation for designing transport mechanisms that serve the needs of tomorrow's Internet. In addition, we will make freely available to the research community: (i) the source code of all the measurement and analysis tools developed in this project, and (ii) the data we collect through our passive and active measurement efforts, to facilitate other research projects. Broader Impacts: 1. Experience in measurements and analysis is invaluable to federal, commercial, and academic institutions that are involved in mining for information in large data-sets. I believe that the proposed research project will be an excellent source of undergraduate and graduate students trained in these aspects. 2. The proposed efforts in employing measurement tools to improve the effectiveness of CS education will help develop new pedagogical techniques. 3. The proposed efforts in designing transport protocols that scale with technological advancement will have an impact on the use of the Internet for scientific research and distributed analysis by the High Energy Physics, Bio-informatics. and Radioastronomy.