Showing papers by "Kenneth L. Calvert published in 2013"
Proceedings Article•
16 Apr 2013
TL;DR: This work discusses how to design a network architecture where choices at different layers of the protocol stack are explicitly exposed to users, and develops a comprehensive system where these solutions can be incorporated and compete to allow the network to adapt to current and future challenges.
Abstract: Computer networks, in particular the Internet, represent essential infrastructure for business, government, military, and personal communication. Several recent trends in technology and network use have pushed the capabilities required of the Internet beyond what can be provided by the currently deployed infrastructure. To address these limitations, the network community has developed a variety of technologies to adapt the functionality of network protocols and services. A critical question that remains unanswered is how to integrate these technologies into an ecosystem that involves users, service providers, and developers in such a way that new ideas can be deployed and used in practice. In this work, we discuss how to design a network architecture where choices at different layers of the protocol stack are explicitly exposed to users. Our ChoiceNet system is based on three tightly coupled principles in that it aims to (1) encourage alternatives to allow users to choose among a range of services, (2) let users vote with their wallets to reward superior and innovative services, and (3) provide the mechanisms to stay informed on available alternatives and their performance. This approach ensures that innovative technical solutions can be deployed and rewarded, which is essential to encourage wide deployment of this architecture. Overall, our work does not aim at reinventing technical solutions to networking problems, but at developing a comprehensive system where these solutions can be incorporated and compete to allow the network to adapt to current and future challenges.
27 citations
20 Mar 2013
TL;DR: A new service is described designed to simplify the process of setting up and runningGENI experiments while at the same time adding support for real-world users to join GENI experiments, based on a network hypervisor service used to deploy "HyperNets": pre-defined experimental environments that can be quickly and easily created by experimenters.
Abstract: Although the underlying network resources needed to support virtualized networks are rapidly becoming available, the tools and abstractions needed to effectively make use of these virtual networks is severely lacking. Although networks like GENI are now available to experimenters, creating an experimental network can still be a daunting and error-prone task. While virtual networks enable experimenters to build tailored networks from the "ground up", starting from scratch is rarely what an experimenter wants to do. Moreover, the challenges of incorporating real-world users into GENI experiments make it difficult to benefit real users or obtain realistic traffic. In this paper we describe a new service designed to simplify the process of setting up and running GENI experiments while at the same time adding support for real-world users to join GENI experiments. Our approach is based on a network hypervisor service used to deploy "HyperNets": pre-defined experimental environments that can be quickly and easily created by experimenters. To illustrate the utility and simplicity of our approach, we describe two example HyperNets, and show how our network hypervisor service is able to automatically deploy them on GENI. We then present some initial performance results from our implentation on GENI. Because our network hypervisor is itself a client of GENI (i.e., it calls the GENI AM APIs to create HyperNets), we briefly discuss our experience using GENI and the challenges we encountered mapping HyperNets onto the GENI framework.
5 citations