Destination LAN Research Articles

Dynamic resource-allocation for congestion-control in high-speed LAN Interconnection

When an ATM network is used as a backbone interconnection medium for a set of legacy low-speed LANs, a congestion control scheme is required to protect destination LANs from the risk of congestion that might be created when multiple users attempt to simultaneously communicate with the same LAN. In this paper, we present a novel congestion-control scheme in which the rate-based and bandwidth advertisement approaches inter-operate to efficiently manage and protect destination resources. In this scheme, each destination LAN is connected to source LANs through a tree-based virtual path (VP) layout that is rooted at the destination and has the source LANs as leaves. Under the rate-based framework, fractions (quotas) of the destination bandwidth are periodically computed on a hop-by-hop basis for each VP. Quotas are based on the estimated average load on each VP link. At source LANs, these quotas are used to regulate the instantaneous transmission rate into the ATM network. The bandwidth advertisement framework on the other hand works end-to-end. It uses the destination LAN buffer to regulate quota migration from low activity LANs to the high activity ones depending on the total buffer occupancy, as well as the individual buffer occupancy per source LAN at the destination. The scheme uses simple calculations, which makes it suitable for real time implementation. The performance of the scheme is evaluated through computer simulation under several network parameters and traffic patterns. Results show that a near zero packet loss probability at the destination is achieved while attaining high resource utilization. The results also demonstrate the fairness of the proposed scheme.

An integrated call admission and buffer management scheme for LAN interconnection over a shared-memory ATM switch

We consider the problem of interconnecting low speed LANs over a high-speed shared-memory ATM switch. A bottleneck is formed when more than one source originate traffic to the same destination LAN. In this case, a congestion may be created at the output gateway (destination LAN interface) and the required services are interrupted. In this paper we propose a new integrated scheme for call admission (CAC) and buffer management. The objective of the scheme is to prevent the congestion at the destination LANs, as well as within the ATM switch, while minimizing connection rejection rates (maximizing the utilization of the ATM switch). The scheme uses two types of parameters: first, the connection parameters which are estimated at the network interface unit and specified during connection set-up, and second, the actual traffic characteristics and buffer requirements. Therefore, the proposed scheme combines both parameter-based and measurement-based approaches to the problems of call admission and congestion control. The proposed scheme is shown not to require intensive computations and can be implemented in real time in a high-speed ATM switch. A simulation model for the system is developed from which the performance of our integrated CAC and buffer management scheme is evaluated. It is shown that the application of our CAC criteria maintains cell/packet dropping to within the same order of magnitude. It is also shown that using virtual buffer allocation, in conjunction with our CAC criteria, results in almost no cell/packet dropping.

Delay performance of VSAT‐based satellite wide area networks

AbstractThis paper studies the performance of VSAT‐based satellite wide area networks. Very small aperture terminals are used as transport gateways to interconnect local area networks through satellites to form a wide area network. This paper concentrates on analysing the delay of the network, which is the time needed to send a packet from a station in the source LAN to a station in the destination LAN. Several access techniques are considered for comparison. It is observed through numerical examples that TDMA on the up‐link and TDM on the down‐link offers the best delay performance.