P2P Caching Schemes for Jointly Minimizing Memory Cost and Transmission Delay over Information-Centric Networks

Peer-to-peer (P2P) cache techniques for information-centric networks (ICN) provide the local data resources services for mobile users by storing the popular data contents in their peer mobile users' cache stations, so that a mobile user can obtain these data contents directly from its peer mobile users instead of the remote service provider. Retrieving the requested data content from the nearby storage locations (i.e., cache stations), the P2P caching technique improves the network performance by reducing the duplicate data transmission traffic. To overcome the difficulties of minimizing the data transmission delay for the P2P caching system, we divide all mobile users in a wireless cell as several P2P caching groups, where a mobile user can obtain its requested data content from a peer mobile user in the same group, or from a peer mobile user in another group. We propose the Markov decision process (MDP) based stochastic optimization scheme in this cache system with dynamic number of peers to derive the optimal lifespan for cached data contents in cache stations. The objective of our proposed stochastic optimization framework is to efficiently minimize the cost function, which jointly measures the cache size/cost and the data content transmission delay, over all P2P caching groups in the wireless cell. To achieve this goal, we apply the finite-state Markov chain to characterize the number of mobile users in each caching group and dynamically adapt the cached data lifespan in cache stations. We also develop an efficient iteration algorithm to implement our proposed MDP scheme. Finally, we validate and evaluate the performance of our proposed schemes through the numerical analyses, which show that our proposed schemes converge to a unit optimal solution.