Trading routing diversity for better network performance

摘要

Most sensor networks employ distributed and dynamic routing protocols. The flexibility that each node can choose the best forwarder from a diverse candidate set could offer excellent routing performance when the network is highly dynamic. However, it sacrifices routing predictability since it is possible that routing loops are frequently formed. Can we increase the network predictability by controlling the network? As a step towards solving this problem, we introduce FlexCut, a flexible approach for cutting off wireless links, which essentially limits the candidate forwarder set of each node. Unlike existing SDN solutions, FlexCut introduces flexible control over existing distributed and dynamic routing protocols. FlexCut can trade arbitrary amounts of routing diversity for better network performance by exposing to network operators a parameter which quantifies the aggressiveness. We propose novel algorithms, both centralized and distributed, to cut off user-defined number of links so that loops can be alleviated while routing flexibility can be preserved to the largest extent. We evaluate FlexCut extensively by both testbed experiments and simulations. Results show that FlexCut improves the performance by 40% ~ 90% compared with a baseline algorithm in terms of our optimization goal. Results also show that FlexCut can improve the network performance of a sensor network by 20% ~ 35%, 30% ~ 50%, 25% respectively, in terms of packet delivery ratio, transmission delay and radio duty cycle.