Minimizing power consumption in the area of ICT (Information and Communication Technologies) is becoming a hot topic. In computer networks, traffic measurements have indicated that the network utilization may become very low (less than 10%) during non-peak hours, which provides the opportunity to power off some routers and links in a network to conserve energy consumption without causing network performance deterioration. This paper formulates an optimization problem for power saving in backbone networks during non-peak hours and proposes a heuristic algorithm for the optimization problem. The performance investigation shows that the proposed heuristic can save up to 50% more power than a popular power saving algorithm for backbone networks.

A service scheduling scheme is to control the order of servicing cells within an ATM node and maintain their quality of service (QoS). Recent researchers have focused on the efficient ways of isolation among different incoming traffic, or the different approach to improve the overall QoS. However they seldom try to achieve both objectives simultaneously. In this paper, we propose a new service scheduling scheme with fuzzy logic design to achieve these two goals. We use a fuzzy controller to choose an appropriate service scheduling scheme from the two traditional methods for the current input traffic environment. Numerical results show that this approach not only can achieve both objectives, but also show better performance as compared with traditional methods.

We investigate a state dependent multicast routing algorithm called least load multicast routing (LLMR), for single rate loss networks. The algorithm is based on least load routing (LLR) concept and the approach is to select the least load links for establishing connections. The networks considered are assumed fully connected. In addition, connection requests are Poisson arrival and the holding times of accepted calls are exponentially distributed. The analytical model that we developed for calculating the blocking probabilities is based on the link independence assumption and the reduced load approximation (RLA). Analytical results are compared with simulation results and the agreement is surprisingly good. We find that the effect of link independence assumption is insignificant for the analytical model.

We study the problem of dynamic bandwidth allocation for an ATM multiplexer loaded with real-rime VBR video traffic. The proposed mechanism adjusts the allocated bandwidth at regular intervals based on measured QoS. Instead of actual measurement of small cell loss ratios, we combine a virtual output buffer method with a regression method to shorten the time interval required for estimating the required bandwidth to support the specified QoS by prediction. Using numerical examples, we show that our proposed dynamic bandwidth allocation scheme is more efficient than the optimum static bandwidth allocation scheme. Our measurement-based scheme offers several advantages: (1) it removes the dependence on accurate traffic parameters to be declared by users; (2) it can be applied to a wide variety of traffic sources; (3) it adapts quickly to the variations of traffic with small measurement intervals, and (4) the complexity of the algorithm is small.

An important parameter in asynchronous transfer model (ATM)-based network design and management is the cell loss ratio (CLR) in ATM multiplexers. It is a key parameter to many vital functions in the network such as call admission control (CAC), bandwidth allocation, etc. However, the CLR depends usually on many unknown and unpredictable traffic parameters such as input traffic correlations. In this paper, we propose a simple and robust fuzzy-based algorithm to predict the CLR in large-sized systems based on both a small amount of information from small-sized systems, and the asymptotic behavior for very large systems. Unlike the model-based approaches, our approximation avoids the problem of assuming any traffic parameters or arrival process. This algorithm is used with real-time traffic measurement to propose an effective measurement-based call admission control framework for ATM networks.

In this paper, we study the bandwidth allocation problem for an ATM multiplexer loaded with compressed VBR video sources. To estimate the bandwidth required by a VBR video source, we characterize its traffic by five parameters: peak rate, bottom rate, mean rate, standard deviation, and the coefficient of the autocorrelation function. The aggregate traffic of a number of VBR video sources is modelled by a discrete-time Markov modulated deterministic process (D-MMDP) which is approximately equal to the superposition of a number of identical and independent two-active-state mini-sources. Based on the effective bandwidth approach and the Gaussian approximation, we derive simple formulas for estimating the required bandwidth.