A dynamic call admission scheme for VBR traffic in ATM networks

The role of call admission control (CAC) in high-speed networks is to maintain the network utilization at a high level, while ensuring that the quality of service (QoS) requirements of the individual calls are met. We use the term static CAC to describe schemes that always allocate the same bandwidth to a specific group of multiplexed calls, independent of the other traffic sharing the link. Dynamic CAC, on the other hand, denotes a scheme in which the bandwidth allocation to a group of calls sharing a queue is influenced by the traffic in other queues destined for the same outgoing link. We propose a generic dynamic call admission scheme for VBR and ABR traffic whose aim is to reduce the blocking rate for VBR calls at the expense of a higher blocking rate for ABR calls. Our scheme is generic because it builds up on a pre-existing static scheme, e.g., one based on a simple notion of effective bandwidth. Our simple approach results in a significant reduction of the blocking rate for VBR traffic (several orders of magnitude), if the bandwidth requirements of a single call are a reasonably small fraction of the link capacity. At the same time, the deterioration of service for ABR traffic can be contained. This revised version was published online in August 2006 with corrections to the Cover Date.     

Traffic locality characteristics in a parallel forwarding system

Due to the widening gap between the performance of microprocessors and that of memory, using caches in a system to take advantage of locality in its workload has become a standard approach to improve overall system performance. At the same time, many performance problems finally reduce to cache performance issues. Locality in system workload is the fact that makes caching possible. In this paper, we first use the reuse distance model to characterize temporal locality in Internet traffic. We develop a model that closely matches the empirical data. We then extend the work to investigate temporal locality in the workload of multi‐processor forwarding systems by comparing locality under different packet scheduling schemes. Our simulations show that for systems with hash‐based schedulers, caching can be an effective way to improve forwarding performance. Based on flow‐level traffic characteristics, we further discuss the relationship between load‐balancing and hash‐scheduling, which yields insights into system design. Copyright © 2003 John Wiley & Sons, Ltd.     

MAC‐assisted topology control for ad hoc wireless networks

We consider ad hoc wireless networks and the topology control problem defined as minimizing the amount of power needed to maintain connectivity. The issue boils down to selecting the optimum transmission power level at each node based on the position information of reachable nodes. Local decisions regarding the transmission power level induce a subgraph of the maximum powered graph G_max in which edges represent direct reachability at maximum power. We propose a new algorithm for constructing minimum‐energy path‐preserving subgraphs of G_max, i.e. ones minimizing the energy consumption between node pairs. Our algorithm involves a modification to the medium access control (MAC) layer. Its superiority over previous solutions, up to 60% improvement in sparse networks, demonstrates once again that strict protocol layering in wireless networks tends to be detrimental to performance. Copyright © 2005 John Wiley & Sons, Ltd.     

Routing in multihop packet switching networks: Gb/s challenge

The authors survey networking solutions that have been proposed for high-speed packet-switched applications. Using these solutions as examples, they identify the specific problems resulting from very high transmission rates and explain how these problems influence the design of high-speed networks and protocols. They conclude that the solutions based on deflection routing are the most promising ones and suggest a number of directions for their evolution. By a packet-switching protocol we mean the network-specific portion of the third OSI layer (i.e., the network layer) of the protocol stack. One part of a packet-switching protocol (according to our definition) is the routing scheme, i.e., the set of rules that assign incoming packets to output links. In general, we can talk about the following three components of the communication subnetwork which are relevant from our point of view: the routing protocol; the congestion-control mechanisms that can be effectively incorporated into the routing protocol; and the network topology. These components are closely related to each other and together offer a single functionality. We discuss routing protocols and congestion-control mechanisms employed in contemporary packet-switched networks, not necessarily in networks operating at very high transmission rates. Then, following some basic definitions related to the topology component, we investigate the challenges posed by the Gb/s transmission rates     

A Variable Slot Length TDMA Protocol for Personal Communication Systems

We present a new TDMA-based scheme intended for carrying traffic withdiverse QoS requirements in mobile environments, e.g.,Personal Communication Systems (PCS).In contrast to mostother TDMA protocols for mobile applications, instead oftrying to fit the offered traffic to the slot size, our solution adaptsthe slot size to the offered traffic.This feature is combined with a dynamic and responsive bandwidth scheduler.As demonstrated by our performance studies, the proposedscheme is more flexible and incurs lower bandwidth overhead than otherTDMA-based solutions.     

On the effectiveness of alternative paths in QoS routing

We propose a routing strategy in which connection requests with specific bandwidth demands can be assigned to one of several alternative paths connecting the source to the destination. The primary goal of this multiple‐path approach is to compensate for the inaccuracy of the knowledge available to routing nodes, caused by the limited frequency of link state (LS) information exchanges. We introduce a collection of K‐shortest path routing schemes and investigate their performance under a variety of traffic conditions and network configurations. We subsequently demonstrate that K‐shortest path routing offers a lower blocking probability in all scenarios and more balanced link utilization than other routing methods discussed in the literature. With our approach, it is possible to reduce the frequency of link state exchanges, and the incurred bandwidth overhead, without compromising the overall performance of the network. Based on the proposed routing scheme, we investigate different link state dissemination algorithms, which are aimed at reducing the communication overhead by prioritizing the scope and differentiating the qualitative content of LS update messages. Copyright © 2004 John Wiley & Sons, Ltd.     

CBRMA++/SR: on the design of a MAN/WAN MAC protocol for high-speednetworks

A new MAN/WAN medium-access control (MAC) protocol called CBRMA++/SR is introduced. It is suitable for a folded bus topology with optical fiber used as the transmission medium. The eminent features of CBRMA++/SR are total fairness and full bandwidth utilization. The preemptive approach employed in bandwidth allocation enables CBRMA+++/SR not to suffer from the deficiencies of DQDB, which stem mostly from the inconsistency of the distributed queue at a given instant. The protocol is based on the concept of fair share, which also provides a solid ground to support connection-oriented services. A powerful slot-reuse scheme complements the protocol     

A slotted multicode CDMA protocol for efficient integration of voice and data in cellular networks

This paper presents a novel radio channel structure based on slotted CDMA technology intended for carrying traffic with diverse bandwidth/QoS requirements in mobile environments, e.g. personal communication systems (PCS). The essence of our approach is a combination of flexible slotting with allocation of multiple codes to high‐bandwidth mobiles. As demonstrated by our performance studies, the proposed scheme efficiently integrates multiple traffic classes into a unified CDMA system. It is highly flexible and incurs low overheads for a wide range of realistic traffic conditions. Copyright © 2002 John Wiley & Sons, Ltd.     

A note on the performance of ENET II

The performance of the ENET II protocol is discussed and compared to the performance of the commercial Ethernet. Linear network topologies with various number of stations uniformly distributed along the bus are considered. The comparison is based on extensive simulation studies and a recently published performance analysis of ENET II by Y.-C. Liu and G.L. Wise (1987). The experimental results agree with the analysis by Liu and Wise, but they do not confirm the results of M.K. Molloy (1985)