Please cite this article as: E. Wang, Y. Yang, J. Wu, A Knapsack-based buffer management strategy for delay-tolerant networks, J. Parallel Distrib. Comput. (2015), http://dx.
Highlights(1) We propose a theoretical message scheduling and drop strategy in DTNs.(2) We improve the theoretical strategy into a practical scheduling and drop strategy.(3) We propose an efficient local parameter collection method to estimate global parameters.(4) The proposed strategy utilizes the knapsack model to deal with messages in different sizes.(5) We conduct extensive simulations on both synthetic and real mobility traces.
AbstractIn delay-tolerant networks, the dramatic change of topology and the frequent interruption of connections make it difficult to forward the message to destination. Routing protocols in DTNs seek to improve the delivery ratio through increasing the number of message copies. However, the redundant message copies easily cause the occurrence of buffer's overflowing. In this paper, in order to maximize the utilization of network resources, especially when the bandwidth is limited and the message sizes are different, we present a theoretical framework called the Knapsack-based Message Scheduling and Drop strategy in Theory (KMSDT) based on Epidemic routing protocol. KMSDT sorts the messages in the buffer according to the per-unit utility and, if buffer overflows, decides which message to drop based on the solution to the knapsack problem. Furthermore, a practical framework called the Knapsackbased Message Scheduling and Drop strategy in Practice (KMSDP) is also developed. Rather than collecting the global statistics as done in KMSDT, KMSDP estimates all the parameters through the locally-collected statistics. Simulations based on both synthetic and real mobility traces are done in ONE. Results show that, without affecting the average delay and overhead ratio, KMSDP and KMSDT achieve better delivery ratio than other congestion control strategies.