CAJ | 학술논문

针对目前已有的拥塞控制算法普遍存在资源利用率低下、RTT不公平和多瓶颈链路不公平等问题，分析了网络拥塞控制中的博弈现象，考虑网络局域信息在拥塞控制过程中的影响，建立了一种基于局域信息少数者博弈的拥塞控制模型，提出并实现了一种基于局域信息少数者博弈的拥塞控制算法。仿真实验表明，该算法在保证瓶颈链路资源利用率的同时，有效地解决了异构RTT流的不公平性问题，实现了多瓶颈链路下的最大最小公平性。
침대목전이유적옹새공제산법보편존재자원이용솔저하、RTT불공평화다병경련로불공평등문제，분석료망락옹새공제중적박혁현상，고필망락국역신식재옹새공제과정중적영향，건립료일충기우국역신식소수자박혁적옹새공제모형，제출병실현료일충기우국역신식소수자박혁적옹새공제산법。방진실험표명，해산법재보증병경련로자원이용솔적동시，유효지해결료이구RTT류적불공평성문제，실현료다병경련로하적최대최소공평성。
Low link utility, RTT unfairness and unfairness of Multi-Bottleneck network are the existing problems in the present network congestion control algorithms at large. Considering the local information of network, a congestion con-trol model based on minority game (MG) with local information was proposed to solve these problems. Based on the model, a congestion control algorithm was designed. The result of simulation indicates that the proposed algorithm has good performance on link utilization and fairness of RTT flow in multi-bottleneck network.