Internet Traffic Prediction Research Articles

Internet traffic prediction analog to solitons propagation in optical fibers via the concatenation model and stability analysis

Internet traffic (IT) is a measure of data transfer across devices. In this paper, an analogy is made between data transfer and soliton propagation in optical fibers. This is achieved by employing the concatenation model (CM) that describes soliton propagation in optical fibers, which is presented recently in the literature. The CM contains nonlinear space-time dispersion effect, that may lead to bottleneck soliton shape (BNSS). Thus, in view of this model, BNSS effect of soliton propagation may occur, which is analogous to a possible BN in IT. So, the prediction of the characteristics of internet traffic can be depicted via the CM, which is studied here with Caputo-q time derivative. Also, a variety of exact solutions of the CM are derived. These solutions are represented graphically and they show multiple shapes of concatenated solitons. Among them, bottleneck, M-shaped, hybrid M shaped, chirped solitons and vector of dromian patterns. On the other side, the speed of IT and chips heating are estimated. It is found that the speed of IT is constant with time and the effects of distributed time delay (recent memory (RM)) is to slow the traffic speed. This is done via varying the fractional order. Also, it is observed, when accounting for RM, that the chip heating is too small. We think that the results for the speed of IT and chip heat are, qualitatively, realistic. The stability of a steady state solution is analyzed and the controlled parameters for stability is determined.

Analyzing the Impact of Outlier Data Points on Multi-Step Internet Traffic Prediction Using Deep Sequence Models

The task of predicting internet traffic is challenging, particularly in multi-step forecasting due to the volatile and random nature of data. In addition, real-world traffic may contain outlier data points, so developing a prediction model that integrates anomaly detection and mitigation is necessary. This paper compares several deep sequence models, such as Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), LSTM Encoder-Decoder (LSTM En De), LSTM Encoder-Decoder with attention layer (LSTM En De Atn), and Gated Recurrent Unit (GRU), with our proposed methodology for single-step prediction. Our proposed LSTM En De model, integrated with outlier detection, outperforms traditional deep sequence models in single-step prediction, reducing the deviation between actual and predicted traffic by over 11%. We also apply our methodology to multi-step forecast analysis, using multiple output strategies for forecast horizons of 3, 6, 9, and 12 steps ahead. Experimental results demonstrate the effectiveness of our proposed methodology in improving the accuracy of singlestep prediction and multi-step forecasting tasks, especially when dealing with outlier data points that adversely affect model accuracy. In summary, this paper investigates the challenges of real-world internet traffic prediction, proposes a novel prediction model integrated with anomaly detection and mitigation, and compares different deep sequence models for single-step and multi-step forecasting tasks.

Advanced Ensemble Machine Learning Models to Predict SDN Traffic

Internet traffic prediction plays a significant role in network management, network planning, utilization of the network resources, and quality of service. Internet future traffic can be predicted based on past traffic characteristics, it is possible only when we have accurate statistics of the network parameters. Prediction of the network traffic can be for the dynamic allocation and deallocation of the network resoureces as well as the congestion avoidance. We aim to predict the Software defined network(SDN) traffic. SDN is the enhanced architecture of the traditional network which separates the control plane with the data plane. In SDN the control plane has centralized control over the network. In this paper we applied Random Forest(RF), eXtreme Gradient Boosting(XGBoost), Light Gradient Boosting Model(LightGBM) as three base ensemble machine learning models, and proposed an advanced ensemble machine learning model which is a combination of these three models on the real world data with different sampling intervals and showed that the proposed model outperforms the other base models.

Internet Traffic Prediction with Distributed Multi-Agent Learning

Internet traffic prediction has been considered a research topic and the basis for intelligent network management and planning, e.g., elastic network service provision and content delivery optimization. Various methods have been proposed in the literature for Internet traffic prediction, including statistical, machine learning and deep learning methods. However, most of the existing approaches are trained and deployed in a centralized approach, without considering the realistic scenario in which multiple parties are concerned about the prediction process and the prediction model can be trained in a distributed approach. In this study, a distributed multi-agent learning framework is proposed to fill the research gap and predict Internet traffic in a distributed approach, in which each agent trains a base prediction model and the individual models are further aggregated with the cooperative interaction process. In the numerical experiments, two sophisticated deep learning models are chosen as the base prediction model, namely, long short-term memory (LSTM) and gated recurrent unit (GRU). The numerical experiments demonstrate that the GRU model trained with five agents achieves state-of-the-art performance on a real-world Internet traffic dataset collected in a campus backbone network in terms of root mean square error (RMSE) and mean absolute error (MAE).

Internet traffic matrix prediction with convolutional LSTM neural network

With the rapid growing trend of Internet, prediction‐based network operation optimization and management has drawn the attention from both the academia and the industry. For predicting Internet traffic, deep learning models have been proven more effective than linear and statistical models. However, some of the previous studies model the Internet traffic prediction as a multivariate time series prediction problem simply, without using the Internet traffic matrix structure. In this letter, the Internet traffic matrix prediction problem is firstly modeled as a video prediction task. Then a ConvLSTM‐based Seq2Seq model named ConvLSTM‐TM is proposed for predicting the traffic matrix in the next time slot. Based on three real‐world traffic matrix datasets, ConvLSTM‐TM outperforms five deep learning baselines with a lower prediction error. For replication, the dataset, code, and results are publicly available in a Github repository.

Internet traffic prediction with deep neural networks

With the evolution of Internet, traffic prediction has been more important than ever, because better resource allocation and network management schemes are based on the precise prediction of future demands. Formulated as a time series prediction problem, different solutions have been proposed, including linear statistical models and non‐linear machine learning models. However, there lacks of a comprehensive evaluation of the recently developed deep neural networks for this important problem, which we aim to fill in this letter. Based on an open Internet bandwidth usage dataset collected for 6 months, 13 deep neural networks are evaluated and compared with five baseline models. The experiments demonstrate that all deep neural networks outperform baseline models, in particular among them InceptionTime achieves the lowest prediction error, in terms of RMSE and MAE. As a benchmark for future studies, the dataset, code, and results are publicly available in a Github repository.

Traffic self-similarity analysis and application of industrial internet

Industrial internet traffic prediction is not only an academic problem, but also a concern of industry and network performance department. Efficient prediction of industrial internet traffic is helpful for protocol design, traffic scheduling, detection of network attacks, etc. This paper proposes an industrial internet traffic prediction method based on the Echo State Network. In the first place this paper proves that the industrial internet traffic data are self-similar by means of the calculation of Hurst exponent of each traffic time series. It indicates that industrial internet traffic can be predicted utilizing nonlinear time series models. Then Echo State Network is applied for industrial internet traffic forecasting. Furthermore, to avoid the weak-conditioned problem, grid search algorithm is used to optimize the reservoir parameters and coefficients. The dataset this paper perform experiments on are large-scale industrial internet traffic data at different time scale. They come from Industrial Internet in three regions and are provided by ZTE Corporation. The result shows that our approach can predict industrial internet traffic efficiently, which is also a verification of the self-similarity analysis.

Tensor mutual information and its applications

SummaryCorrelation analysis has long been a question of great interest in measuring the relationship among different variables and has been applied in many fields, such as dimension reduction, classification, and so on. However, current methods of correlation analysis take into account the linear relationship between multiple variables and only few works on nonlinear interaction of two variables have been considered. In this article, we first present a nonlinear analysis method of multiple (two or more) variables based on mutual information for tensor analysis (MITA). In addition, we extend the mutual‐information matrix analysis directly to MITA and show the multivariable mutual information formula based on Venn diagram. Experiments on multiview dimension reduction, including attacking internet traffic prediction, advertisement classification, and biometric structure prediction illustrate the effectiveness of the proposed method, especially in the case of low‐dimensional subspace.

Forecasting Website Traffic Using Prophet Time Series Model

Web traffic is the amount of data sent and received by visitors to a website and it has been the largest portion of Internet traffic. Internet traffic flow prediction heavily depends on historical and real-time traffic data collected from various internet flow monitoring sources. With the widespread traditional traffic sensors and new emerging traffic sensor technologies, traffic data are exploding, and we have entered the era of big data internet traffic. Internet traffic management and control driven by big data is becoming a new trend. Although there have been already many internet traffic flow prediction systems and models, most of which use shallow traffic models and are still somewhat unsatisfying. This inspires us to reconsider the internet traffic flow prediction model based on deep architecture models with such rich amount of internet traffic data. ARIMA is a existing forecasting technique that predicts the future values of a series based entirely on its own inertia. Existing traffic flow prediction methods mainly use simple traffic prediction models and are still unsatisfying for many real-world applications. Now we proposed the prophet time series model to forecasting website traffic.

Kernel least mean square with adaptive kernel size

Kernel adaptive filters (KAF) are a class of powerful nonlinear filters developed in Reproducing Kernel Hilbert Space (RKHS). The Gaussian kernel is usually the default kernel in KAF algorithms, but selecting the proper kernel size (bandwidth) is still an open important issue especially for learning with small sample sizes. In previous research, the kernel size was set manually or estimated in advance by Silverman׳s rule based on the sample distribution. This study aims to develop an online technique for optimizing the kernel size of the kernel least mean square (KLMS) algorithm. A sequential optimization strategy is proposed, and a new algorithm is developed, in which the filter weights and the kernel size are both sequentially updated by stochastic gradient algorithms that minimize the mean square error (MSE). Theoretical results on convergence are also presented. The excellent performance of the new algorithm is confirmed by simulations on static function estimation, short term chaotic time series prediction and real world Internet traffic prediction.

Computer network traffic prediction: a comparison between traditional and deep learning neural networks

This paper compares four different artificial neural network approaches for computer network traffic forecast, such as: 1) multilayer perceptron (MLP) using the backpropagation as training algorithm; 2) MLP with resilient backpropagation (Rprop); (3) recurrent neural network (RNN); 4) deep learning stacked autoencoder (SAE). The computer network traffic is sampled from the traffic of the network devices that are connected to the internet. It is shown herein how a simpler neural network model, such as the RNN and MLP, can work even better than a more complex model, such as the SAE. Internet traffic prediction is an important task for many applications, such as adaptive applications, congestion control, admission control, anomaly detection and bandwidth allocation. In addition, efficient methods of resource management, such as the bandwidth, can be used to gain performance and reduce costs, improving the quality of service (QoS). The popularity of the newest deep learning methods have been increasing in several areas, but there is a lack of studies concerning time series prediction, such as internet traffic.

Forecasting internet traffic by using seasonal GARCH models

With the rapid growth of Internet traffic, accurate and reliable prediction of Internet traffic has been a key issue in network management and planning. This paper proposes an autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH) error model for forecasting Internet traffic and evaluates its performance by comparing it with seasonal autoregressive integrated moving average (ARIMA) models in terms of root mean square error (RMSE) criterion. The results indicated that the seasonal AR-GARCH models outperformed the seasonal ARIMA models in terms of forecasting accuracy with respect to the RMSE criterion.

An Improved LS-SVR Ensemble Learning in Internet Traffic Prediction

In this paper, we present a new method for internet traffic forecasting based on a boosting LS-SVR algorithm. AdaBoost has been proved to be an effective method for improving the performance of weak learning algorithms and widely applied to classification problems. Inspired by it, we use LS-SVR to complete the initial training; and pay more attention on the “high error areas” in the time series; then, we use an ensemble learning algorithm to learn these areas.