Coding-based cooperative caching in data broadcast environments

Abstract

Data broadcasting has been commonly deployed in many emerging mobile applications such as intelligent transportation systems and location-based services because it is a scalable approach to disseminating information from the mobile support station (MSS) to a large population of mobile hosts (MHs). To provide timely data access and better data availability, MHs can store data items broadcast by the MSS in their local caches and share cached data items cooperatively among neighboring peers via peer-to-peer (P2P) communication. However, MHs which are not neighbors cannot cooperate even if they have each other’s requested data item in their own caches. Network coding is a technique, by exploiting which multiple MHs can retrieve different requested data items from an encoded packet which encodes a number of data items broadcast by the MSS in a broadcast time unit. In this research work, we propose to apply network coding to enabling MHs which are not neighbors to cooperate indirectly. We devise two algorithms running at the MSS and MHs, respectively, for making encoding decisions and decoding requested data from encoded packets. We build the simulation model for performance evaluation and the simulation results demonstrate that the proposed solution not only increases the bandwidth efficiency of the limited downlink communication channel from the MSS to MHs but also enhances the system performance by reducing the latency in satisfying requests.