The CICQ switches have inherent advantages in supporting multicast traffic, and scheduling policies can be simplified to a great extent when distributed scheduling is applied. However, simulation results indicate that...
详细信息
The CICQ switches have inherent advantages in supporting multicast traffic, and scheduling policies can be simplified to a great extent when distributed scheduling is applied. However, simulation results indicate that the increment of multicast will block unicast, and finally reduce the performance of the entire switch. To overcome this deficiency, the paper proposes a new switch called MCICQ (multicast supporting CICQ) which supports the uni- and multicast hybrid scheduling, and scheduling policies MFdr and MFS which support the parallel distributed uni- and multicast are also proposed. With the fanout splitting mechanism, both MFdr and MFS can achieve good performance without speedup, and their complexities are only O(1). MFS scheduling policy can also provide different bandwidth guarantees for uni- and multicast traffic. Simulation results under SPES show that both MFdr and MFS can achieve good performance.
The focus of this paper is on access security aspects of 3G-WLAN interworking. Firstly, the authentication entities which do not rely on the concrete heterogeneous network are abstracted by analyzing 3G-WLAN multi-kin...
详细信息
In this paper, the security of userdomain including mobile terminal (MT) and user in heterogeneous wireless networks (HWN) are paid more attention. We introduce the Trusted Platform Module (TPM) to ensure the termina...
详细信息
Identity Authentication and key agreement are two critical security issues for the heterogeneous networks (HWN). It is likely that public key based authentication will be useddue to their intrinsic advantages over sy...
详细信息
Congestion is a natural phenomenon in any network queuing system, and is unavoidable if the queuing system is operated near capacity. In this paper, we study how to set rules of a satellite queuing system so that all ...
详细信息
Congestion is a natural phenomenon in any network queuing system, and is unavoidable if the queuing system is operated near capacity. In this paper, we study how to set rules of a satellite queuing system so that all the users have self-interest in controlling congestion when it happens. Most of the mechanisms proposed to accomplish this in terrestrial Internet involve complicated packet scheduling algorithms. These algorithms may not be implemented in satellite routerdue to satellite hardware constraints or performance differences;thus, finding more easily implemental variants of such algorithms may be of significant practical value. After investigating characteristics of satellite traffic traces, we propose PA (Penalize heavy volume unresponsive flows and Avoid unnecessary bandwidth waste) to allocate bandwidth fairly and eliminate unnecessary bandwidth waste. PA is a simple packet dropping scheme anddiscriminates against the flows which submit more packets/sec than is allowed by their fair share. Game-theoretic analysis shows that PA could impose Nash equilibrium on selfish agents. Simulation results suggest that the design provides a good tradeoff between efficiency and fairness in a wide variety of operating conditions.
In this paper,a brief introduction to SCH of CdMA system is *** the paper account for Soft Handoff of High Speed Packet data and the *** the base of above account,this paper give the flow of High Speed Packet data'...
详细信息
In this paper,a brief introduction to SCH of CdMA system is *** the paper account for Soft Handoff of High Speed Packet data and the *** the base of above account,this paper give the flow of High Speed Packet data's Soft Handoff.
The differentiated services (diffServ) model relies on the Per Hop Behavior (PHB) in each network device to treat packets differently based on packet headers™ dSCP (diffServ Code Point). For each diffServ compliant ro...
ISBN:
(纸本)9789639799264
The differentiated services (diffServ) model relies on the Per Hop Behavior (PHB) in each network device to treat packets differently based on packet headers™ dSCP (diffServ Code Point). For each diffServ compliant router, the scheduling algorithm is critical in implementing PHBs, according to which packets are forwarded. In this paper, we propose the parallel maximum urgency first (PMUF) scheduling algorithm for combined input-crosspoint queued (CICQ) switches to support diffServ classes. The proposed PMUF algorithm features in a distributed scheduling scheme which can be implemented on each input and each output independently and in parallel. It adopts a two-stage flow control mechanism based on periodic statistic to provide minimum bandwidth guarantees for EF and AF traffic, and uses a priority scheduling mechanism to provide lowerdelay for EF traffic. The time complexity of PMUF is only O(log N), hence is practical and scalable for high speed application. Simulation results show that PMUF provides minimum bandwidth guarantees for EF and AF traffic and fair bandwidth allocation for BE traffic. Moreover, PMUF exhibits betterdelay performance than existing maximal matching baseddiffServ scheduling schemes especially under non-uniform traffic.
All internet routers contain buffers to store packets. Selecting appropriate buffer size can not only ensure router performance, but can also contribute to reducing uncertainty in the internet. This paper aims to size...
详细信息
All internet routers contain buffers to store packets. Selecting appropriate buffer size can not only ensure router performance, but can also contribute to reducing uncertainty in the internet. This paper aims to size buffers for forwarding engines known as the main part of a router. First, a high-speed pipeline which is designed for forwarding engines is presented, and its memory analysis model is also given, then, the memory demand of forwarding engines is analyzed under two situations: the forwarding capability being not less than and less than the input rate. Our analysis results and experiments both show that, when the forwarding capability is not less than the input rate, a forwarding engine only need to buffer a several packets of maximum length, when the forwarding capability is less than the input rate, a forwarding engine only needs to buffer about ten packets in the view of buffer use efficiency, and further increasing the buffer size will have little effect.
In the current Internet, hosts are identified using IP addresses that depend on the topological location of the hosts. In other words, the IP addresses are semantically overloaded since they identify both hosts and to...
详细信息
In the current Internet, hosts are identified using IP addresses that depend on the topological location of the hosts. In other words, the IP addresses are semantically overloaded since they identify both hosts and topological locations. The host identity protocol (HIP) introduces a way of separating the location and host identity information. It introduces a new namespace, cryptographic in nature, for host identities. The IP addresses continue to be used for packet routing. In this paper we present the current status and make a comparison with HIP-like technologies. After the discussion, future work will be recommended.
暂无评论