Faculty Involved:  Mike Wittie

Increasingly, full participation in modern society depends on communication services like Twitter, Skype, and even online games, such as World of Warcraft. Future versions of such services will rely heavily on interactive communication streams, including voice, video, and control traffic, as part of their functionality. Unfortunately, the existing designs of application infrastructure struggle to deliver low-latency services users enjoy, gradually isolating rural communities from the modern society.

While the reach of the Internet has grown dramatically in recent decades, the delivered quality of online services has significant geographic variation. To benefit from the economies of scale, services are instantiated on large datacenters often quite distant from rural users. Physical separation introduces significant delays to rural users’ packets that impairs application usability. Unless the problem of latency disparity is addressed, the future will see innovation and expansion of interactive communications become available only to a dwindling percentage of well-connected urban users.

The key to assuring equal access is to recognize that interactive communications are social by nature, in that they exhibit a strong locality of interest among nearby users. Our previous work shows how locality of interest can be leveraged to design a finely distributed infrastructure for more responsive online social networks. Similarly, other interactive applications could connect users through increasingly distributed cloud datacenters, thereby eliminating the disconnect between local communication patterns and centralized infrastructure design. The challenge is to design methods for distributed cloud resource allocation and application implementation to make services based on such widely distributed infrastructure viable.

Support:

This research is supported by Mike's startup funds and covers to Ph.D. students. Additional funds pending from NSF and HP proposals.

Opportunities:

The broad nature of this work provides multiple opportunities in:

  • Network and cloud infrastructure performance measurement
  • Network optimization techniques with emphasis on distributed optimization methods
  • Cloud based interactive application development, including provider agnostic middleware