Air-Caching: Adaptive Hybrid Data Delivery

Abstract

With the immense popularity of the Web, the world is witnessing an unprecedented demand for online data services. A growing number of applications require timely data delivery frominformation producers to thousands of information consumers. At the same time, the Internetis evolving towards an information superhighway that incorporates a wide mixture of existingand emerging communication technologies, including wireless, mobile, and hybridnetworking. For this new computing landscape, this thesis advocates creating highly scalable dataservices based on adaptive hybrid data delivery. It introduces air-caching, a technique thateffectively integrates broadcasting for massive dissemination of popular data, and unicastingfor upon-request delivery of the rest. It describes the special properties, performance goals,and challenges of air-caching. Then, it presents adaptive cache management techniques forthree different settings: servicing large numbers of data requests over heavily accessed databases, propagating data updates to mobile clients intermittently connected toinformation sources, and implementing publish/subscribe services again in the context ofmobile computing. In all cases, performance experiments demonstrate the scalability,efficiency, and versatility of this technique, even under rapidly changing data access patterns.