This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).
Even in the US, many regions suffer poor Internet connectivity, due to high prices, capacity limitations, poor infrastructure, or low population density. Rural communities may be underserved because of DSL distance limits and the high cost of bringing fiber optic cable to low-density regions. Even when businesses or schools can be connected by DSL, its capacity limits may still provide poor end-user experience when many people share the connection. This research is addressing these problems by using intelligent software to enhance network connectivity. By aggressive data caching and off-peak prefetching, data can be stored on disk and retrieved locally instead of always being fetched from the Internet. For environments with many users, this system can reduce bandwidth consumption by an order of magnitude, providing higher effective end-user bandwidth, or allow cost reductions by purchasing less wide-area bandwidth. The expected outcome of this research is an open-source system that can be deployed at Internet gateways, which will transparently improve network performance. Possible locations include schools, small businesses, and Internet Service Providers (ISPs). In schools, when a classroom full of students accesses a topic, only one copy is downloaded, and the rest get it from the cache. For news sites that update during the day, only the changed portions get downloaded, instead of whole articles. Prefetching will also reduce latency, by determining user patterns and preloading content before it is needed.
