A dynamic Markov chain prediction model for delay-tolerant networks

In this study, prediction routing algorithms are proposed to select efficient relay nodes. While most prediction algorithms assume that nodes need additional information such as node’s schedule and connectivity between nodes, the network reliability is lowered when additional information is unknown. To solve this problem, this study proposes a context-aware Markov chain prediction based on the Markov chain that uses the node’s movement history information without requiring additional information. The evaluation results show that the proposed scheme has competitive delivery ratio but with less average latency.