Monday, October 20, 2014

ChoiceNet at Global Environment for Network Innovations (GENI) Engineering Conference (GEC21)

Today,  the GENI Engineering Conference 21  (GEC21) begins at Indiana University and, tomorrow afternoon, there will be a two part tutorial on our National Science Foundation (NSF) project ChoiceNet.    

More details on the tutorial can be found here and here. My UMass ciolleague, Professor Tilman Wolf,  and University of Kentucky colleague, Professor Jim Griffioen,  will be conducting the tutorial along with two doctoral students.

The full schedule can be accessed here.

GENI, also known as the Global Environment for Network Innovations, provides a virtual laboratory for networking and distributed systems research and education. It is well suited for exploring networks at scale, thereby promoting innovations in network science, security, services and applications.
ChoiceNet is our project, funded by NSF under the grant: Network Innovation Through Choice. UMass Amherst is the lead on this multiunveisrity project with Professor Tilman Wolf of the Department of Computer and Electrical Engineering as the PI and me as the Co-PI, along with colleagues from the University of Kentucky, North Carolina State University, and the University of North Carolina. ChoiceNet is one of five NSF Future Internet Architecture projects.

Professor Wolf prepared this page on our ChoiceNet project, which will continue to be updated.

Specifically, we seek to introduce an Economy plane into the Internet.


The goal of ChoiceNet is to enable choices and the associated economic relationships between entities in the network. ChoiceNet makes it possible for network service providers to compete for customers and be rewarded for quality and innovation. In today’s network, money enters the network ecosystem only around the edges: consumers (individuals or enterprises) pay access providers for Internet service. Most access providers, in turn, pay other ISPs to carry their traffic to/from the rest of the Internet. Indeed, most end-to-end traffic in the Internet traverses at least three distinct service

Thus, in today’s Internet (i) no single provider controls all end-to-end paths; (ii) money flow between providers is outside the architecture and by necessity changes slowly; and (iii) traffic flow is constrained at the granularity of providers to follow the money flow. The result is that transit providers have neither means nor incentive to compete via new service offerings, and consumers have essentially no control over the service they receive or its quality. A central thesis of ChoiceNet is that enabling money flow to follow traffic flow (instead of vice versa), coupled with greater support for choice among end-users, should lead to increased provider competition and more innovation.

ChoiceNet’s economy plane aims to give assurances to providers that they can compete for customers and be compensated for the services they render. At the same time, ChoiceNet provides users with the ability to select from a set of offerings and combine them to form complex services, thereby separating services that are currently entangled in the current Internet. Key to such an architecture is the ability to market services and then form or dissolve business relationships on (potentially small) time scales. Moreover, ChoiceNet must enable providers (and consumers) to prove (or verify) that the contracted service was rendered as promised.

I have two doctoral students at the Isenberg School of Management conducting research on ChoiceNet: Sara Saberi and Dong "Michelle" Li. We are specifically working on the game theory and network economics aspects and have already published a series of papers, including:
  • Anna Nagurney, Dong Li, Tilman Wolf, and Sara Saberi. A network economic game theory model of a service-oriented internet with choices and quality competition. NETNOMICS: Economic Research and Electronic Networking, 14(1–2):1–25, November 2013. (Notable Article in Computing in 2013 by ACM Computing Reviews) DOI
  • Anna Nagurney and Tilman Wolf. A Cournot-Nash-Bertrand game theory model of a service-oriented internet with price and quality competition among network transport providers. Computational Management Science, 11(4), pages 475-502. DOI
  • Sara Saberi, Anna Nagurney, Tilman Wolf, A network economic game theory model of s service-oriented Internet with price and quality competition in both content and network provision. Service Science, 6(4), December 2014, pages 1-24.
I hope that everyone at GEC21 has a rewarding conference!