We consider a variant of M/M/1 where customers arrive singly or in pairs. Each single and one member of each pair is called primary;the other member of each pair is called secondary. Each primary joins the queue upon ...We consider a variant of M/M/1 where customers arrive singly or in pairs. Each single and one member of each pair is called primary;the other member of each pair is called secondary. Each primary joins the queue upon arrival. Each secondary is delayed in a separate area, and joins the queue when “pushed” by the next arriving primary. Thus each secondary joins the queue followed immediately by the next primary. This arrival/delay mechanism appears to be new in queueing theory. Our goal is to obtain the steady-state probability density function (pdf) of the workload, and related quantities of interest. We utilize a typical sample path of the workload process as a physical guide, and simple level crossing theorems, to derive model equations for the steady-state pdf. A potential application is to the processing of electronic signals with error free components and components that require later confirmation before joining the queue. The confirmation is the arrival of the next signal.展开更多
Sector capacity estimation plays an important role in applied research of airspace management.Previous researches manifest that sector capacity should be influenced by its standard flow,or routes in that sector.Howeve...Sector capacity estimation plays an important role in applied research of airspace management.Previous researches manifest that sector capacity should be influenced by its standard flow,or routes in that sector.However,if air traffic controller(ATCO)workload busy levels(level of proactivity of an ATCO)are ignored,the estimated sector capacity may not be accurate.There is a need to compare the estimated sector capacity with and without busy levels consideration,both with differentiated routes consideration.This paper proposes a method for sector capacity estimation based on ATCO workload considering differentiated routes and busy levels.Firstly,the main routes in the sector are identified,and for each route,the ATCO workload per flight is determined.Secondly,the workload for each route at three busy levels is determined.Regression analysis is then applied to determine the relationship between workload and the number of flights(with and without considering busy levels)in 15 min and 1h time slices.Sector capacity is then determined on the basis of a specified workload threshold,for the two cases with and without considering busy levels.Comparing the two scenarios and following validation by ATCO survey,it is found that capacity estimation considering busy levels is a more realistic and accurate approach.The validated capacity values for the Zhengzhou approach(ZHCC AP)airspace sector accounting for the busy levels were determined accurately as 10 and 33 flights for the 15 min and 1h slices,respectively.The corresponding results without considering busy levels were 12 and 41 flights for the 15 min and 1h time slices,respectively.展开更多
基础设施即服务(Iaa S,Infrastructure as a Service)平台提供商为用户提供高性能服务的同时,必须考虑如何在不违反服务级别协议(SLA,Service Level Agreement)的前提下,节约云平台的能耗成本.采用基于负载特征聚类的方法,提出一种Iaa ...基础设施即服务(Iaa S,Infrastructure as a Service)平台提供商为用户提供高性能服务的同时,必须考虑如何在不违反服务级别协议(SLA,Service Level Agreement)的前提下,节约云平台的能耗成本.采用基于负载特征聚类的方法,提出一种Iaa S云平台上保证SLA的资源调度算法,最终实现降低SLA违反率和节约能耗的目标.具体采用能耗相关的负载特征提取和改进K-means聚类分析的研究方法,进行资源调度算法研究,对物理资源进行有效分配,以保证Iaa S平台节约能耗的要求.实验验证方面,通过扩展Cloud Sim模拟实验平台,对本研究算法与改进BFD(Best Fit Decreasing)算法进行比较,得出本研究算法在SLA违反率和节能方面更优.展开更多
文摘We consider a variant of M/M/1 where customers arrive singly or in pairs. Each single and one member of each pair is called primary;the other member of each pair is called secondary. Each primary joins the queue upon arrival. Each secondary is delayed in a separate area, and joins the queue when “pushed” by the next arriving primary. Thus each secondary joins the queue followed immediately by the next primary. This arrival/delay mechanism appears to be new in queueing theory. Our goal is to obtain the steady-state probability density function (pdf) of the workload, and related quantities of interest. We utilize a typical sample path of the workload process as a physical guide, and simple level crossing theorems, to derive model equations for the steady-state pdf. A potential application is to the processing of electronic signals with error free components and components that require later confirmation before joining the queue. The confirmation is the arrival of the next signal.
基金partially supported by the National Natural Science Foundation of China(No.61304190)the Fundamental Research Funds for the Central Universities(No.NJ20140018)
文摘Sector capacity estimation plays an important role in applied research of airspace management.Previous researches manifest that sector capacity should be influenced by its standard flow,or routes in that sector.However,if air traffic controller(ATCO)workload busy levels(level of proactivity of an ATCO)are ignored,the estimated sector capacity may not be accurate.There is a need to compare the estimated sector capacity with and without busy levels consideration,both with differentiated routes consideration.This paper proposes a method for sector capacity estimation based on ATCO workload considering differentiated routes and busy levels.Firstly,the main routes in the sector are identified,and for each route,the ATCO workload per flight is determined.Secondly,the workload for each route at three busy levels is determined.Regression analysis is then applied to determine the relationship between workload and the number of flights(with and without considering busy levels)in 15 min and 1h time slices.Sector capacity is then determined on the basis of a specified workload threshold,for the two cases with and without considering busy levels.Comparing the two scenarios and following validation by ATCO survey,it is found that capacity estimation considering busy levels is a more realistic and accurate approach.The validated capacity values for the Zhengzhou approach(ZHCC AP)airspace sector accounting for the busy levels were determined accurately as 10 and 33 flights for the 15 min and 1h slices,respectively.The corresponding results without considering busy levels were 12 and 41 flights for the 15 min and 1h time slices,respectively.
文摘基础设施即服务(Iaa S,Infrastructure as a Service)平台提供商为用户提供高性能服务的同时,必须考虑如何在不违反服务级别协议(SLA,Service Level Agreement)的前提下,节约云平台的能耗成本.采用基于负载特征聚类的方法,提出一种Iaa S云平台上保证SLA的资源调度算法,最终实现降低SLA违反率和节约能耗的目标.具体采用能耗相关的负载特征提取和改进K-means聚类分析的研究方法,进行资源调度算法研究,对物理资源进行有效分配,以保证Iaa S平台节约能耗的要求.实验验证方面,通过扩展Cloud Sim模拟实验平台,对本研究算法与改进BFD(Best Fit Decreasing)算法进行比较,得出本研究算法在SLA违反率和节能方面更优.
