Integrating Multi-access Edge Computing(MEC) in Low Earth Orbit(LEO) network is an important way to provide globally seamless low-delay service. In this paper, we consider the scenario that MEC platforms with computat...Integrating Multi-access Edge Computing(MEC) in Low Earth Orbit(LEO) network is an important way to provide globally seamless low-delay service. In this paper, we consider the scenario that MEC platforms with computation and storage resource are deployed on LEO satellites, which is called "LEO-MEC". Service request dispatching decision is very important for resource utilization of the whole LEO-MEC system and Qo E of MEC users. Another important problem is service placement that is closely coupled with request dispatching. This paper models the joint service request dispatching and service placement problem as an optimization problem, which is a Mixed Integer Linear Programming(MILP). Our proposed mechanism solves this problem and uses the solved decision variables to dispatch requests and place services. Simulation results show that our proposed mechanism can achieve better performance in terms of ratio of served users and average hop count compared with baseline mechanism.展开更多
Web serverclusters has become a popular solutionto achieve high performance duetotheirlow price, highreliability,and good scalability. One ofthe key technologiesis “request dispatching”, which is to centrallyaccept...Web serverclusters has become a popular solutionto achieve high performance duetotheirlow price, highreliability,and good scalability. One ofthe key technologiesis “request dispatching”, which is to centrallyacceptallthe incoming HTTPrequests and dispatchthem to the serversinthe clusterto achieve parallelism .The research showsthatthe efficiency ofrequest dispatching is determined by whetherthe serverloads are balanced duringthe dispatching.This paper studies the characteristics ofthe load generated by HTTPrequests,gives anefficient method ofloadsampling,and presentsa novelrequestdispatching algorithm which can predicttheload andbalanceit.The method can be usedto build Web serverclusters ofheterogeneous machines.展开更多
The problem of state space explosion is still ran outstanding challenge in Markovian performance analysis for multiserver multiqueue (MSMQ) systems. The system behavior of a MSMQ system is described using stochastic h...The problem of state space explosion is still ran outstanding challenge in Markovian performance analysis for multiserver multiqueue (MSMQ) systems. The system behavior of a MSMQ system is described using stochastic high-level Petri net (SHLPN) models, and an approximate performance analysis technique is proposed based on decomposition and refinement methods as well as iteration technique. A real MSMQ system, Web-server cluster, is investigated. The performance of an integrated scheme of request dispatching and scheduling is analyzed with both Poisson and self-similar request arrivals. The study shows that the approximate analysis technique significantly reduces the complexity of the model solution and is also efficient for accuracy of numerical results.展开更多
基金funded by the Excellent Postdoctoral Study Project Funding of Hebei Province,grant number B2019005006。
文摘Integrating Multi-access Edge Computing(MEC) in Low Earth Orbit(LEO) network is an important way to provide globally seamless low-delay service. In this paper, we consider the scenario that MEC platforms with computation and storage resource are deployed on LEO satellites, which is called "LEO-MEC". Service request dispatching decision is very important for resource utilization of the whole LEO-MEC system and Qo E of MEC users. Another important problem is service placement that is closely coupled with request dispatching. This paper models the joint service request dispatching and service placement problem as an optimization problem, which is a Mixed Integer Linear Programming(MILP). Our proposed mechanism solves this problem and uses the solved decision variables to dispatch requests and place services. Simulation results show that our proposed mechanism can achieve better performance in terms of ratio of served users and average hop count compared with baseline mechanism.
文摘Web serverclusters has become a popular solutionto achieve high performance duetotheirlow price, highreliability,and good scalability. One ofthe key technologiesis “request dispatching”, which is to centrallyacceptallthe incoming HTTPrequests and dispatchthem to the serversinthe clusterto achieve parallelism .The research showsthatthe efficiency ofrequest dispatching is determined by whetherthe serverloads are balanced duringthe dispatching.This paper studies the characteristics ofthe load generated by HTTPrequests,gives anefficient method ofloadsampling,and presentsa novelrequestdispatching algorithm which can predicttheload andbalanceit.The method can be usedto build Web serverclusters ofheterogeneous machines.
文摘The problem of state space explosion is still ran outstanding challenge in Markovian performance analysis for multiserver multiqueue (MSMQ) systems. The system behavior of a MSMQ system is described using stochastic high-level Petri net (SHLPN) models, and an approximate performance analysis technique is proposed based on decomposition and refinement methods as well as iteration technique. A real MSMQ system, Web-server cluster, is investigated. The performance of an integrated scheme of request dispatching and scheduling is analyzed with both Poisson and self-similar request arrivals. The study shows that the approximate analysis technique significantly reduces the complexity of the model solution and is also efficient for accuracy of numerical results.
