Wireless Computing Architecture
Abstract
Work of the project has led to a number of findings and conclusions. These results have been published or will be published in the near future: -Localization with Snap-Inducing Shaped Residuals (SIRS): Coping with Errors in Measurement, 15th Annual International Conference on Mobile Computing and Networking (MobiCom 2009), September 2009. -A Computational Wireless Network Backplane: Performance in a Distributed Speaker Identification Application, Military Communications Conference (MILCOM 2008), November 2008. -Rainbow: A Wireless Medium Access Control Using Network Coding for Mulit-hop Content Distribution, Military Communications Conference (MILCOM 2008), November 2008. Our work has mainly been motivated by the need of providing on-demand local computing resources over a wireless computing and communication infrastructure. In the next decade we will begin to face very large sensor-generated datasets on the order of zettabytes or even yottabytes. While centralized control and applications may still be needed, the bulk of the processing and storage must be distributed near the sensors. Moreover, for flexibility in resource deployment, communications over wireless networks will be essential. Technologies need to be developed which can cope with modest bandwidths of wireless communications while being able to take advantage of their broadcast capabilities. We have obtained new results capable of addressing these challenges. In the rest of this document, we highlight our accomplishments in three related areas.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 2009
- Accession Number
- ADA503260
Entities
People
- H.t. Kung
- William H. Gates
Organizations
- Harvard University