Neural Modelling of Ethernet Traffic over Atm Networks
نویسندگان
چکیده
The purpose of this paper is to present a method of modeling a superposition of individual Ethernet sources over an Asynchronous Transfer Mode (ATM) network through neural networks. It is proposed the two-state MMPP model (Markov Modulated Poisson Process) to approximate the aggregated ATM traffic because of its simplicity and analytical tractability. The neural network is able to calculate the MMPP model of real Ethernet traffic over a 155 Mbps ATM network, avoiding, through this adaptive and real-time technique, complex analytic solutions. Besides, to match long-time dependence, it is studied the two-level MMPP model, that considers several time scales.
منابع مشابه
Carrying ATM Cells over Ethernet
This paper describes the research carried out to obtain the advantages of ATM technology over legacy Ethernet networks. A protocol called “Cells In Frame” (CIF) allows to encapsulate ATM cells in Ethernet frames. We have implemented the CIF protocol in the kernel of the Linux operating system. Measures of speed, delay and delay variation have been carried out in order to check that the develope...
متن کاملPerformance Analysis of Metro Ethernet Network (MEN) Services over Asynchronous Transfer Mode (ATM) Services for Enterprise
Metro Ethernet networks (MENs) technology has provided economic sustainability to small and big enterprises. Today, individual and organizations rely on ICT to perform daily operations. The costs of using these services determine the accessibility of the users. MEN is flexible to use compare with other switch network like ATM. In this paper, features of MEN technology are explored to determine ...
متن کاملVoice and Video over Gigabit Ethernet and ATM Backbone Networks: A Simulation Study
This chapter aims to report on the performance of voice and video traffic over two popular backbone network technologies, namely Gigabit Ethernet (GbE) and Asynchronous Transfer Mode (ATM). ATM networks are being used by many universities and organizations for their unique characteristics such as scalability and guaranteed Quality of Service (QoS), especially for voice and video applications. G...
متن کاملMonthly runoff forecasting by means of artificial neural networks (ANNs)
Over the last decade or so, artificial neural networks (ANNs) have become one of the most promising tools formodelling hydrological processes such as rainfall runoff processes. However, the employment of a single model doesnot seem to be an appropriate approach for modelling such a complex, nonlinear, and discontinuous process thatvaries in space and time. For this reason, this study aims at de...
متن کاملA Performance Evaluation of Emerging Ethernet Technologies: Switched/high-speed/full-duplex Ethernet and Ethernet Lan Emulation over Atm
| The advent of switched LAN and ATM technology is dramatically altering today's networking environment. Given the preponderance of existing Ethernet networks today, high-speed, switched and/or full-duplex Ethernet and Ethernet LAN Em-ulation over ATM are extremely important, as is bridging between Ethernet and ATM. In this paper , we evaluate the performance of these newly emerging technologie...
متن کامل