Search

The proposed Energy-Efficient Ethernet (EEE) standard reduces energy consumption by defining two operation modes for transmitters and receivers: active and low power. Burst transmission can provide additional energy savings when EEE is used. Collecting data frames into large-sized data bursts for back-to-back transmission maximizes the time an EEE device spends in low power, thus making its consumption nearly proportional to its traffic load. An initial evaluation shows that the additional savings in the scenarios considered range from 5 to 70 percent for conventional users and approximately 50 percent for large data centers. [ABSTRACT FROM AUTHOR]

Often, Internet measurement-based studies have followed a three-step procedure: collection of network measurements; measurementbased model inference; and generalization of the results obtained to other scenarios. Indeed, it has been a general belief that certain internetwork traffic statistics, such as the most used IP addresses and port numbers, show a similar behavior in networks with similar features, and the conclusions derived from the measurements of a given network could be extrapolated to a similar scenario. This study makes no starting assumption concerning this issue and undertakes a "spatial" analysis of network measurements. The measurement set comprises a six-month trace collected by RedIRIS (the Spanish National Research and Education Network) at different monitored points acrossthe country. Our experiment shows that, although the frequency statistics of IP addresses and port numbers follow a Zipf distribution (as expected), the distributions' characteristic parameter values vary significantly in a spatial dimension (i.e., across individual university networks), even when the profile of the networks' user bases are similar. In practical terms, this means network designers, analysts, and operators should not assume that statistics for Internet site and applications usage for one network may accurately characterize other networks, even when those networks have similar user bases and environments. Furthermore, we show that experiment durations of approximately 30 days are necessary for the traffic processes to display stationarity. Hence, in order to obtain accurate statistics on traffic characteristics of large internetworks using state-of-the-art measurement techniques, long and spatially diverse experiments may be necessary. [ABSTRACT FROM AUTHOR]

The long list of benefits (especially cost and capacity) of Ethernet LANs has made the IEEE, the ITU-T, and the Metro Ethernet Forum define the requirements for taking Ethernet beyond the local area, toward the metropolitan region. In addition, the ever-increasing traffic demands of new applications and users can only be met by the huge bandwidth capacity provided by optical fibers. This work studies how to provide metro Ethernet services over transparent tunable-transmitter fixed-receiver WDM optical ring networks. A new adaptation layer of ME to WDM is proposed, and its benefits and drawbacks are studied. It is shown that such a transparent WDM ring network can be seen as a logical full-mesh topology by the upper ME layer, thus reducing to one the number of optical-electronic-optical conversions per unicast frame. Additionally, two different approaches are proposed in the case of broadcast/multicast traffic, since this may bring scalability difficulties in ring topologies. [ABSTRACT FROM PUBLISHER]

Network operators are migrating their networks to IP over WDM architectures. In such multilayer networks, it is necessary to define mechanisms that efficiently use the resources available from both layers in a coordinated manner. Thanks to the development of the control plane (GMPLS), it is feasible to both set up and tear down lightpaths automatically. Thus the WDM layer can now adapt its configuration to both meet a set of resource constraints and fulfill some predefined quality-of-service (QoS) requirements. To this end, we define a multilayer traffic engineering algorithm that efficiently manages the resources from both layers. This algorithm, which is based on Bayesian decision theory, finds the optimal number of label-switched paths that must be switched over the optical and electronic domains. Such an optimal value is found by trading off the QoS required by the users and the limited availability of network resources. [ABSTRACT FROM PUBLISHER]