A QoS-aware input-queued scheduling algorithm, called Smallest Timestamp First (STF), is proposed, which is improved upon iSLIP and can allocate bandwidth among inputs sharing a common output based on their reservatio...A QoS-aware input-queued scheduling algorithm, called Smallest Timestamp First (STF), is proposed, which is improved upon iSLIP and can allocate bandwidth among inputs sharing a common output based on their reservation by assigning suitable finishing tiniest-amps to contending cells. STF can also provide isolation between flows that share a common output, link. Misbehaving flows will be restricted to guarantee the behaving flows' bandwidth. Simulations prove the feasibility of our algorithm.展开更多
A new approximation of fair queuing called Compensating Hound Robin (CRR) is presented in this paper. The algorithm uses packet-by-packet scheduler with a compensating measure. It achieves good fairness in terms of th...A new approximation of fair queuing called Compensating Hound Robin (CRR) is presented in this paper. The algorithm uses packet-by-packet scheduler with a compensating measure. It achieves good fairness in terms of throughput, requires only O( I) time complexity to process a packet, and is simple enough to be implemented in hardware. After the performances are analyzed, the fairness and packet loss rate of the algorithm are simulated. Simulation results show that the CRR can effectively isolate the effects of contending .sources.展开更多
Cloud computing provides the essential infrastructure for multi-tier Ambient Assisted Living(AAL) applications that facilitate people's lives. Resource provisioning is a critically important problem for AAL applic...Cloud computing provides the essential infrastructure for multi-tier Ambient Assisted Living(AAL) applications that facilitate people's lives. Resource provisioning is a critically important problem for AAL applications in cloud data centers(CDCs). This paper focuses on modeling and analysis of multi-tier AAL applications, and aims to optimize resource provisioning while meeting requests' response time constraint. This paper models a multi-tier AAL application as a hybrid multi-tier queueing model consisting of an M/M/c queueing model and multiple M/M/1 queueing models. Then, virtual machine(VM) allocation is formulated as a constrained optimization problem in a CDC, and is further solved with the proposed heuristic VM allocation algorithm(HVMA). The results demonstrate that the proposed model and algorithm can effectively achieve dynamic resource provisioning while meeting the performance constraint.展开更多
基金Supported by National Natural Science Foundation of China under Grant No.69896246
文摘A QoS-aware input-queued scheduling algorithm, called Smallest Timestamp First (STF), is proposed, which is improved upon iSLIP and can allocate bandwidth among inputs sharing a common output based on their reservation by assigning suitable finishing tiniest-amps to contending cells. STF can also provide isolation between flows that share a common output, link. Misbehaving flows will be restricted to guarantee the behaving flows' bandwidth. Simulations prove the feasibility of our algorithm.
文摘A new approximation of fair queuing called Compensating Hound Robin (CRR) is presented in this paper. The algorithm uses packet-by-packet scheduler with a compensating measure. It achieves good fairness in terms of throughput, requires only O( I) time complexity to process a packet, and is simple enough to be implemented in hardware. After the performances are analyzed, the fairness and packet loss rate of the algorithm are simulated. Simulation results show that the CRR can effectively isolate the effects of contending .sources.
文摘Cloud computing provides the essential infrastructure for multi-tier Ambient Assisted Living(AAL) applications that facilitate people's lives. Resource provisioning is a critically important problem for AAL applications in cloud data centers(CDCs). This paper focuses on modeling and analysis of multi-tier AAL applications, and aims to optimize resource provisioning while meeting requests' response time constraint. This paper models a multi-tier AAL application as a hybrid multi-tier queueing model consisting of an M/M/c queueing model and multiple M/M/1 queueing models. Then, virtual machine(VM) allocation is formulated as a constrained optimization problem in a CDC, and is further solved with the proposed heuristic VM allocation algorithm(HVMA). The results demonstrate that the proposed model and algorithm can effectively achieve dynamic resource provisioning while meeting the performance constraint.
