Collaborative caching for dissemination of videos in resource constrained environments
MetadataShow full item record
Video streaming on mobile devices such as PDA's, laptop PCs, pocket PCs and cell phones is becoming increasingly popular. Video personalization is a popular strategy to provide these resource-constrained mobile devices with video content that is most relevant to the client's request while simultaneously satisfying the client's resource constraints. However, personalization imposes significant overheads on the origin servers as well as on the network. Our system comprises of one or more video personalization servers and several geographically distributed caches. The video personalization servers use an automatic video segmentation and video indexing scheme based on semantic video content. With the objective of optimizing cache performance, we use a novel cache replacement and multi-stage client request aggregation strategies that are specifically tailored for personalized video files. Now, we incorporate a collaborative caching mechanism for further enhancing the scalability and efficiency of disseminating personalized video content. This research reports series of experiments to study the benefits and costs of Collaborative Caching for disseminating personalized video content to resource constrained clients. We also report a series of experiments pertaining to different levels of collaboration among caches and the advantages of using Multiple Servers.