In this paper a fuzzy autoregressive (AR) model described in [1] is used to model and predict highspeed network traffic. This model approximates a complex nonlinear time-variant process by combining linear local autoregressive processes using a fuzzy clustering algorithm. We propose a method to estimate the traffic effective bandwidth at regular intervals, assuming the network traffic can be de...

In this study a framework for developing an object-oriented tool –DRONE (areawide Dynamic ROad traffic NoisE simulator) to generate areawide noise contour maps for a road network is demonstrated. This provides faster access to information for abatement of noise policies. The approach for integrating the dynamic output from traffic simulator to noise model, which predicts traffic noise based on ...

In this paper, we show that prediction algorithms in the least mean square error sense prove better in a burst rather than in a packet switching network. For the latter, further information about the packet arrival distribution within the prediction interval is required. Regarding burst switching, we compare Optical Burst Switching networks with and without linear prediction to conclude that li...

Prediction of future time series values is area of statistics and computer science research related to pattern recognition. Especially possibility of prediction of the future computer network traffic may be usable in detection of abnormal situations like DoS attacks or occurrence of problems with network infrastructure. The article is devoted to usage artificial neural networks, with radial bas...

A novel prediction scheme is proposed for real-time MPEG video to predict the burst and long-range dependent traffic. The trend and periodic characteristics of MPEG video traffic are fully captured by a proposed stochastic state-space dynamic model. Then a recursive filtering algorithm is proposed to estimate traffic for long-range prediction. Simulation results based on real MPEG traffic data ...

-Network traffic forecasting has many important role to play in the domain of network traffic congestion control, its management and network traffic engineering. Characterizing the traffic and modeling are necessary for efficient functioning of the network. It is very vital for any model to depict self similarity, heavy tailed distribution and long range dependence (LRD). Thus modeling of time ...

 FARIMA(p,d,q) model is a good traffic model capable of capturing both the long-range and short-range behavior of a network traffic stream in time. In this paper, we propose a prediction-based admission control algorithm for integrated service packet network. We suggest a method to simplify the FARIMA model fitting procedure and hence to reduce the time of traffic modeling and prediction. Our ...

Abstract: Short-term prediction of traffic flow is central to alleviating congestion and controlling the negative impacts of environmental pollution resulting from vehicle emissions on both interand intra-urban highways. The strong need to monitor and control congestion time and costs for metropolis in developing countries has therefore motivated the current study. This paper establishes the ap...

Using machine learning for predicting traffic is described in the context of a competition organized using the TunedIT platform. A heuristic is proposed for reconstructing the route of a car in a street graph from a temporal stream of its coordinates. A resilient propagation neural network for approximating the average velocity on a given street from irregular time series of instantaneous veloc...

ions to meet these challenges. Data Intensive Network Organization Traffic prediction networks require a combination of big data and large number of devices to combine semi-global historic traffic information and on-line vehicle updates. This requires the convergence of approaches used by the datacenter community and real-time community. Such dynamical systems with real-time constraints require...