Network Traffic Prediction Using PSO-LightGBM- TM

Network traffic prediction performs a main function in characterizing network community performance. An approach which could appropriately seize the salient characteristics of the network visitors could be very useful for network analysis and simulation. Network traffic prediction methods could be divided into two classes: one is the single models and the opposite is the hybrid fashions. The hybrid models integrate the merits of several single models and consequently can enhance the network traffic prediction accuracy. In this paper, a new hybrid network traffic prediction method (EPSVM) primarily based on Empirical Mode Decomposition (EMD), Particle Swarm Optimization (PSO), and Support Vector Machines (SVM) is presented. The EPSVM first utilizes EMD to eliminate the impact of noise signals. Then, SVM is applied to model training and fitting, and the parameters of SVM are optimized by PSO. The effectiveness of the presented method is examined by evaluating it with different methods, including basic SVM (BSVM), Empirical Mode Decomposition processed by SVM (ESVM), and SVM optimized by Particle Swarm Optimization (PSVM). Case studies have demonstrated that EPSVM performed better than the other three network traffic prediction models.

Internet of Things (IoT) is a network of interconnected devices, such as sensors and smart devices that have processing, sensing, and communication capabilities, as well as can transmit information to each other and a supreme console through the Internet. Network traffic prediction is an important operational and management function for any data network. It has a significant role in today's increasingly complex and diverse networks. Network traffic prediction is also more important for IoT networks to provide reliable communication. The artificial neural network (ANN) has been successfully applied to traffic prediction. In this paper, we perform the IoT traffic time series prediction using a multistep ahead prediction with Time Series NARX Feedback Neural Networks. The estimation error of a prediction approach has been evaluated using the performance functions MSE, SSE, and MAE, besides, another measure of prediction accuracy the mean absolute percent of error (MAPE).

With the increasing complexity of the network, the current network traffic has strong nonlinearity and burstiness. Therefore, the traditional traffic prediction model is no longer applicable. The neural network model, especially the LSTM, can well fit the nonlinearity of time-series data and preserve the information memory of the past. However, as for the periodicity of long-term span network traffic data, the neural network model does not perform well. Based on this, this paper proposes LTS-TP (Long-Term Span Traffic Prediction model), a network traffic prediction model, to solve the problem. First, the model decomposes the collected network traffic data using the improved STL decomposition algorithm to preserve the seasonal component. Then, the trend component and the remainder component are input into the Seq2Seq model based on the LSTM added with the improved attention mechanism for prediction. Finally, the predicted value of the output is added to the seasonal component, and the final network traffic prediction value is obtained. In the simulation part, this paper uses the MAWI public data set to test the proposed network traffic prediction model and compared performance with other models. The results show that the network traffic prediction model proposed in this paper has a good predictive effect on long-term span network traffic data.

A traffic matrix (TM) is a source of critical traffic throughput information for traffic engineering activities and network management tasks such as traffic prediction, capacity planning, network provisioning, and anomaly detection. However, estimating TM poses several challenges for network engineers. One of the challenges is that traffic data statistics are constantly changing, and their aggregation for real-time monitoring becomes a difficult task. This paper presents a near real-time TM estimation approach for OpenFlow (OF) networks. It makes use of Big Data techniques based on MapReduce operations to tackle the aggregation problem. The proposed method uses traffic data statistics collected from OF switches through an SDN controller as input and aggregates these data in a Big Data streaming processing environment. This paper explores the benefits of the distributed MapReduce computing model to provide an estimate of the TM for all origin-destination (OD) pairs of hosts in the network in two ways: 1) the accumulated throughput and 2) the throughput between two sequential TM estimates. This procedure enables network engineers to monitor the behavior and evolution of the throughput on each OD pair in the network and on each link in the path between each OD pair. The generated TM is persisted in a NoSQL database and can be made available for a variety of network traffic monitoring applications. The results of the simulations show the potential of the proposed MapReduce approach for TM estimation.

In conventional cellular networks, base stations (B-Ss) usually suffer from severe power consumption since they are working to guarantee the coverage and QoS (quality-of-service) requirement according to the peak traffic load generated by the mobile cellular users Accordingly, how to precisely forecast the future traffic load to promote network cooperation and adaptive energy resource allocation in complying with the variation of spatial-temporal traffic load has been an emerged issue due to the significant energy exhaustion of BSs. In this paper, we propose a spatial-temporal compressed sensing based network traffic prediction method to solve this problem. We first construct a traffic matrix (TM) by using previously measured data and setting the data to be predicted as zeros, corresponding to the volume of traffic load. Then, compressed sensing approach with large scale and small scale temporal constraints as well as spatial constraints is employed to factorize the traffic matrix. By reuniting the results of traffic matrix factorization, we obtain the estimation of predicted traffic data. Numerical results have showed that this method can restrict the prediction error under 10% when dealing with real traffic load data.

Traffic prediction is of significant importance for telecommunication network planning and network optimization. In this paper, the traffic series from a certain mobile network in Heilongjiang province in China is studied. The characteristics in respect of both trend and periodicity are explored with autocorrelation function. Based on the characteristics exhibited in the traffic series, multiplicative seasonal autoregressive integrated moving average model (ARIMA) is employed to make traffic series prediction. Average daily traffic per month for the province as well as its every sub-region from July to December in 2009 is forecasted and compared with the actual operation data. The mean absolute percentage error (MAPE) for one-step ahead prediction is 1.382%, and MAPE for the 6 steps is within 6%. The prediction result is of high precision. Furthermore, the cause for the big prediction error in 2 regions is analyzed, and the appropriateness of the model is testified on the opposite aspect. This paper also provides an effective method by using correlation coefficients to analyze the cause for significant prediction errors which do not happen in time series prediction applications rarely.

Aiming at the key problems of traffic flow prediction and road condition recognition in Intelligent Transportation System (ITS), this paper puts forward an optimized framework of pattern recognition algorithm which integrates multi-source data and dynamic weight adjustment. Firstly, a spatio-temporal semantic model integrating sensor, traffic flow and event information is constructed, and graph neural network (GNN) is used to capture the link association. Then, an adaptive weighting mechanism based on attention and reinforcement learning (RL) is designed to improve the prediction robustness in complex scenes. Combined with Transformer-LSTM and Particle Swarm Optimization (PSO), the computational overhead is reduced and edge deployment is supported. Experiments are carried out based on PeMSD4 data and real-time data of an industrial park. The results show that the proposed method is superior to traditional and deep learning models in traffic flow forecasting performance. The root mean square error (RMSE) of 15-minute forecasting task is 23.4, the mean absolute percentage error (MAPE) is 8.7%, and the sudden congestion error is 28.9%. In the aspect of road condition recognition, the accuracy rate is 94.7% in normal weather, F1-score is 0.93, 88.4% in heavy rain, F1-score 0.85, 85.2% in sensor failure, and F1-score 0.82, which shows high robustness and reliability. At the same time, the parameters of the model are reduced from 43.2MB to 9.8MB, the reasoning delay is reduced from 121ms to 36ms, and the energy consumption is reduced from 293mJ to 87mJ, which has obvious lightweight characteristics and provides an efficient, accurate and adaptable solution for traffic flow prediction and road condition identification in ITS.

Network traffic prediction is hot spot in recent years' research, which is of great significance in area such as congestion control, network management and diagnostic. Network traffic is non-linear, non-stationary, and uncertain, and its uncertainty increases rapidly when making short-term traffic flow prediction. After reviewing current network traffic prediction algorithms' merits and drawbacks based on Time-Series analysis, Artificial Neural Network here, a new network traffic prediction algorithms in short-term is proposed. The time interval when detecting that network data packet pass on certain section is treated as a stochastic process. In the ARCH (autoregressive conditional heteroskedasticity) framework, stochastic process is described by a marked point process that different point processes may generate different ACD (autoregressive conditional duration) model, then ACD model can be used to complete the description of time interval when network data packet passing. Based on this model, a particle filter is applied to non-stationary motion system for short-term network traffic prediction. At last, this algorithm is applied to real data for real-evidence analysis.

Traffic flow prediction using spatial-temporal network data remains one of the most important problems in intelligent transportation systems. Timely and accurate traffic prediction is necessary to provide valuable information for different urban planning, traffic control, and guidance tasks. The complexity of the problem is explained by the fact that traffic flows have high nonlinearity and complex spatial-temporal correlations. The development of mathematical models, and, in particular, the deep learning models, allows to use convolutional neural networks to solve traffic prediction problems. In this article, we analyze the architecture of the graph convolution network for traffic flow prediction. The considered graph convolution network takes into account daily and weekly patterns of traffic flow distributions. Experimental studies of the graph neural network model were carried out on the transportation network of Samara city. Experiments show that the considered model outperforms other baseline forecasting algorithms.

In connexion with the effect of the self-similar characteristic of satellite network service traffic on queueing performance, a prediction model with optimised triple exponential smoothing is first established in this paper. This model performs network traffic prediction based on the dynamic triple exponential smoothing model and optimises the smoothing coefficient of the model through the differential evolution algorithm; a cubic function based on traffic prediction is further proposed to improve the adaptive random early detection (ARED) queue management algorithm. Based on the network traffic prediction results and the ARED, this algorithm uses the cubic function to perform nonlinear processing on the packet drop probability function. The simulation results show that the prediction model with optimised triple exponential smoothing has a high prediction accuracy, and the improved ARED algorithm based on the cubic function of traffic prediction in the presence of data bursts in self-similar traffic. It can effectively reduce the packet loss rate and improve the throughput, so as to better control the network congestion caused by self-similar traffic in satellite network.

In this paper, a comparison of two network traffic activities prediction models will be presented, namely a backpropagation neural network (BPNN) and a genetic algorithm based backpropagation neural network (GABPNN). A backpropagation neural network (BPNN) prediction model can be used to learn a time-series dataset. However, the performance of the BPNN can be improved by optimizing the BPNN using a genetic algorithm. This paper outlines a network traffic prediction model that is developed using a typical backpropagation neural network (BPNN) coupled with a genetic algorithm (GA). The performance of the GABPNN is measured by using a statistical analysis, namely Mean of Square Error (MSE). The results show that the MSE value of GABPNN obtained was lower with the population size of 400, crossover probability was 0.01, uniform mutation probability was 0.8, and 50 iterations. Therefore, the obtained results of the GABPNN model illustrates that the proposed model GABPNN has improved the prediction accuracy compared to the traditional BPNN model.

Accurate prediction of network traffic is crucial to network resource management, whether it's network resource provisioning or malicious attack detection, reliable network traffic prediction mechanisms are needed for advance warning existing network traffic prediction methods still have some obvious limitations, existing network traffic prediction methods still have some obvious limitations, such as high computational complexity, VMD decomposition parameter optimization problem, premature convergence into local optimum solutions, and integrated prediction model prediction accuracy is not high many problems. In response to the above, this paper presents a model that combines Variation Mode Decomposition (VMD) and Extreme Learning Machine (ELM) for predicting network traffic based on Genetic Algorithm (GA).

As an important part of data management, network traffic evaluation and prediction can not only find network anomalies but also judge the future trends of the network. To predict network traffic more accurately, a novel hybrid model, integrating Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) with long short-term memory neural network (LSTM) optimized by the improved particle swarm optimization (IPSO) algorithm, is established for network traffic prediction. Firstly, an LSTM prediction model for the real-time mutation and dependence of network traffic is constructed, and the IPSO is applied to optimize the hyperparameters. Then, CEEMDAN is introduced to decompose sequences of raw network traffic data into several different modal components containing different information to reduce the complexity of the network traffic sequence. Finally, the evaluation of the experiments shows the feasibility and effectiveness of the proposed method by comparing it with other deep neural architectures and regression models. The results show that the proposed model CEEMDAN-IPSO-LSTM produced a significantly superior performance with a reduction of the prediction error.

An essential step in surface wave exploration is the inversion of dispersion curves. By inverting dispersion curves, we can effectively establish the shear-wave velocity model and obtain reliable subsurface stratigraphic information. The inversion of dispersion curves is an inversion problem with multiple parameters and multiple poles, and obtaining a high precision solution is difficult. Among the methods of inversion of dispersion curves, local search methods are prone to fall into local extremes, and global search methods such as particle swarm optimization (PSO) and genetic algorithm (GA) present the disadvantages of slow convergence speed and low precision. Deep learning models with strong nonlinear mapping capability can effectively solve nonlinear problems. Therefore, we propose a method called PSO-optimized long short-term memory (LSTM) network (PSO-LSTM) to invert the dispersion curves in order to improve the effect of inversion of dispersion curves. The method is based on the LSTM network, and PSO is used to optimize the LSTM network structure and other parameters that need to be given manually to improve the prediction of the network. Two theoretical geological models are used in the paper: Model A and Model B to test the PSO-LSTM. The tests include the noisy data test and noise-free data test. Model A was tested without noise, and Model B was tested with noise. In addition, PSO and LSTM were tested on model A to compare the performance of PSO-LSTM. In Model A, the maximum relative errors of PSO and LSTM are 20.76% and 5.85%, respectively, and the maximum standard deviations of PSO and LSTM are 57.37 and 1.97, respectively. For PSO-LSTM, the maximum relative errors of Model A and Model B in the inverse results are 2.05% and 2.09%, and the maximum standard deviations of Model A and Model B in the inverse results are 1.23 and 3.87, respectively. The test results of Model A show that the inversion performance of PSO-LSTM is better than those of LSTM and PSO, and the performance of the network can be improved after PSO is used to optimize the network parameters. The inverse results from Model B show that the PSO-LSTM is robust and can invert the dispersion curves well even after adding noise to the model. Finally, the PSO-LSTM is used to invert the actual data from Wyoming, USA, which demonstrates that the PSO-LSTM can be used for the quantitative interpretation of Rayleigh wave dispersion curves.

The features of dynamic, noise and instability, make the network traffic eruptive and unstable, and this obstructs the network traffic prediction. In order to figure out its characteristics and developing tendency accurately, the paper proposes a wavelet-transform-based prediction algorithm: Firstly, with the multi-resolution analysis of wavelet transform, the network traffic, which is difficult to be analyzed or modeled in the time domain, is divided into different bands of frequency by wavelet decomposition. Later, simplify and stabilize the divided traffic by denoising with different thresholds on the detail components of different sub-bands of frequency. At last, synthesizes the traffic prediction with the predictions of the denoised sub-traffic by Auto Regressive Moving Average Model. The algorithm improves the prediction accuracy significantly in practical modeling, especially in short-range traffic prediction.