CAJ | 학술논문

现有机会路由选择未考虑数据流的分布，可能使候选节点空闲或过载，导致网络吞吐量提升有限．本文将多并发流的机会路由描述成一个凸优化问题，基于对偶和子梯度方法，提出分布式联合候选节点选择和速率分配的多流机会路由算法（Opportunistic Routing for Multi-Flow ，ORMF）．该算法迭代进行流速率分配，并在速率分配过程中完成候选节点选择．实验结果表明，与基于期望传输次数和期望任意传输次数指标的机会路由相比，ORMF平均可提高33．4％和27．9％的汇聚吞吐量．
현유궤회로유선택미고필수거류적분포，가능사후선절점공한혹과재，도치망락탄토량제승유한．본문장다병발류적궤회로유묘술성일개철우화문제，기우대우화자제도방법，제출분포식연합후선절점선택화속솔분배적다류궤회로유산법（Opportunistic Routing for Multi-Flow ，ORMF）．해산법질대진행류속솔분배，병재속솔분배과정중완성후선절점선택．실험결과표명，여기우기망전수차수화기망임의전수차수지표적궤회로유상비，ORMF평균가제고33．4％화27．9％적회취탄토량．
Opportunistic routing (OR) does not take account of the traffic load ,therefore ,some nodes may be overloaded while the others may be idle ,leading to network performance decline .The OR for multi-flow is described as a convex optimization problem .By primal-dual and sub-gradient methods ,a distributed joint candidate nodes selection and rate allocation opportunistic routing for multi-flow algorithm (ORMF) is proposed .ORMF allocates the flow rate iteratively which decides the candidate node . The simulation results show that the throughputs of ORMF are 33 .4% and 27 .9% ,higher than those of OR with expected transmis-sion number and expected anycast transmission metrics ,respectively .