Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNetwork-wide Statistical Modeling and Prediction of Computer Traffic
496
0
0.0
(
0
)
Added by
Stilian Stoev
Publication date
2010
fields
Mathematical Statistics
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
In order to maintain consistent quality of service, computer network engineers face the task of monitoring the traffic fluctuations on the individual links making up the network. However, due to resource constraints and limited access, it is not possible to directly measure all the links. Starting with a physically interpretable probabilistic model of network-wide traffic, we demonstrate how an expensively obtained set of measurements may be used to develop a network-specific model of the traffic across the network. This model may then be used in conjunction with easily obtainable measurements to provide more accurate prediction than is possible with only the inexpensive measurements. We show that the model, once learned may be used for the same network for many different periods of traffic. Finally, we show an application of the prediction technique to create relevant control charts for detection and isolation of shifts in network traffic.
rate research
Read More
We develop a probabilistic framework for global modeling of the traffic over a computer network. This model integrates existing single-link (-flow) traffic models with the routing over the network to capture the global traffic behavior. It arises from a limit approximation of the traffic fluctuations as the time--scale and the number of users sharing the network grow. The resulting probability model is comprised of a Gaussian and/or a stable, infinite variance components. They can be succinctly described and handled by certain space-time random fields. The model is validated against simulated and real data. It is then applied to predict traffic fluctuations over unobserved links from a limited set of observed links. Further, applications to anomaly detection and network management are briefly discussed.
This paper introduces a statistical model for the arrival times of connection events in a computer network. Edges between nodes in a network can be interpreted and modelled as point processes where events in the process indicate information being sent along that edge. A model of normal behaviour can be constructed for each edge in the network by identifying key network user features such as seasonality and self-exciting behaviour, where events typically arise in bursts at particular times of day. When monitoring the network in real time, unusual patterns of activity could indicate the presence of a malicious actor. Four different models for self-exciting behaviour are introduced and compared using data collected from the Imperial College and Los Alamos National Laboratory computer networks.
Accurate forecasting of traffic conditions is critical for improving safety, stability, and efficiency of a city transportation system. In reality, it is challenging to produce accurate traffic forecasts due to the complex and dynamic spatiotemporal correlations. Most existing works only consider partial characteristics and features of traffic data, and result in unsatisfactory performances on modeling and forecasting. In this paper, we propose a periodic spatial-temporal deep neural network (PSTN) with three pivotal modules to improve the forecasting performance of traffic conditions through a novel integration of three types of information. First, the historical traffic information is folded and fed into a module consisting of a graph convolutional network and a temporal convolutional network. Second, the recent traffic information together with the historical output passes through the second module consisting of a graph convolutional network and a gated recurrent unit framework. Finally, a multi-layer perceptron is applied to process the auxiliary road attributes and output the final predictions. Experimental results on two publicly accessible real-world urban traffic data sets show that the proposed PSTN outperforms the state-of-the-art benchmarks by significant margins for short-term traffic conditions forecasting
Short-term traffic forecasting based on deep learning methods, especially long short-term memory (LSTM) neural networks, has received much attention in recent years. However, the potential of deep learning methods in traffic forecasting has not yet fully been exploited in terms of the depth of the model architecture, the spatial scale of the prediction area, and the predictive power of spatial-temporal data. In this paper, a deep stacked bidirectional and unidirectional LSTM (SBU- LSTM) neural network architecture is proposed, which considers both forward and backward dependencies in time series data, to predict network-wide traffic speed. A bidirectional LSTM (BDLSM) layer is exploited to capture spatial features and bidirectional temporal dependencies from historical data. To the best of our knowledge, this is the first time that BDLSTMs have been applied as building blocks for a deep architecture model to measure the backward dependency of traffic data for prediction. The proposed model can handle missing values in input data by using a masking mechanism. Further, this scalable model can predict traffic speed for both freeway and complex urban traffic networks. Comparisons with other classical and state-of-the-art models indicate that the proposed SBU-LSTM neural network achieves superior prediction performance for the whole traffic network in both accuracy and robustness.
Link dimensioning is used by ISPs to properly provision the capacity of their network links. Operators have to make provisions for sudden traffic bursts and network failures to assure uninterrupted operations. In practice, traffic averages are used to roughly estimate required capacity. More accurate solutions often require traffic statistics easily obtained from packet captures, e.g. variance. Our investigations on real Internet traffic have emphasized that the traffic shows high variations at small aggregation times, which indicates that the traffic is self-similar and has a heavy-tailed characteristics. Self-similarity and heavy-tailedness are of great importance for network capacity planning purposes. Traffic modeling process should consider all Internet traffic characteristics. Thereby, the quality of service (QoS) of the network would not affected by any mismatching between the real traffic properties and the reference statistical model. This paper proposes a new class of traffic profiles that is better suited for metering bursty Internet traffic streams. We employ bandwidth provisioning to determine the lowest required bandwidth capacity level for a network link, such that for a given traffic load, a desired performance target is met. We validate our approach using packet captures from real IP-based networks. The proposed link dimensioning approach starts by measuring the statistical parameters of the available traces, and then the degree of fluctuations in the traffic has been measured. This is followed by choosing a proper model to fit the traffic such as lognormal and generalized extreme value distributions. Finally, the optimal capacity for the link can be estimated by deploying the bandwidth provisioning approach. It has been shown that the heavy tailed distributions give more precise values for the link capacity than the Gaussian model.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
