CAJ | 학술논문

负载调度是云计算得以大规模应用及提高服务性能的关键技术，对提高云供应商服务质量、用户满意度以及数据中心集群资源利用率等有极其重要的意义。云计算环境中，由于用户任务类型的不同，对带宽的需求也不尽相同，若不区分不同任务对不同带宽的要求，可能会造成资源的浪费，增长用户等待时间。本文对经典M in-M in算法进行改进，提出了BCLL-Min-Min算法，该算法满足带宽需求约束，并且实现相对负载均衡调度。仿真实验表明，BCLL-Min-Min算法能够适应云计算环境下任务多样性和不确定性的情况，使用该调度算法可以提高集群的吞吐率、较大改善数据中心的负载均衡性。
부재조도시운계산득이대규모응용급제고복무성능적관건기술，대제고운공응상복무질량、용호만의도이급수거중심집군자원이용솔등유겁기중요적의의。운계산배경중，유우용호임무류형적불동，대대관적수구야불진상동，약불구분불동임무대불동대관적요구，가능회조성자원적낭비，증장용호등대시간。본문대경전M in-M in산법진행개진，제출료BCLL-Min-Min산법，해산법만족대관수구약속，병차실현상대부재균형조도。방진실험표명，BCLL-Min-Min산법능구괄응운계산배경하임무다양성화불학정성적정황，사용해조도산법가이제고집군적탄토솔、교대개선수거중심적부재균형성。
T he scheduling strategy on load balancing ,w hich is one of key techniques in cloud computing , plays an important role inimproving high service performance ,customer satisfaction and utilization of clus-terresource in data center .In cloud computing ,allocating the same bandwidth to different tasks indiscrimi-nately may cause the computing resources to be wasted and users'waiting time to be lengthened since dif-ferent tasks require different bandwidth .In this paper ,we have improvedMin-Min algorithm which is one of classical load balancing algorithms and present a new improved algorithm named BCLL-Min-Min .It can satisfy the bandwidth constraint and implement the relative load balancing scheduling .The simulated ex-periments show that our proposed algorithm is more available for the diverse and uncertain tasks in cloud computing .It improves the load balance in data center and enhances the throughput in the cluster .