Smoothing-Aided Support Vector Machine Based Nonstationary Video Traffic Prediction Towards B5G Networks

Abstract

Video services have hold a surprising proportion of the whole network traffic in wireless communication networks. Accurate prediction of video traffic can endow networks with intelligence in resource management, especially for the forthcoming beyond the fifth-generation (B5G) networks. However, the existing approaches fail to accurately predict video traffic with all types of frames, due to the natures of strong long-range dependence, self-similarity and burstiness. Obviously, it is unable to meet the QoS and QoE requirements of dynamic bandwidth allocation. In this paper, we propose the feasibility of advanced machine learning methodology applied in nonstationary video traffic prediction, i.e., smoothing-aided support vector machine (SSVM) model. The model utilizes classical smoothing methods to preprocess video traffic by relieving the drastic fluctuation of video stream. It can provide an effective association for the subsequent support vector regression, as the preprocessed data becomes more smooth and continuous than the original unprocessed one. Experimental results show that our proposed model significantly outperforms the state of the art model, i.e., logistic smooth transition autoregressive, in prediction performance. The superior nonlinear approximation capacity is further demonstrated by visualized statistical analysis.

Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts

“…Figure 1 shows the proposed overall conceptual framework. The model is motivated by the promising results presented earlier [31]. The proposed ML technique is modeled as a time series batch learning process.…”

“…The local preprocessing techniques show a higher dynamic reaction to the noise level and short-term variations than the other wavelet-and Hilbert-Huang transform (HHT)-based processes. A similar approach was used earlier [31], where researchers studied the superior nonlinear approximation ability of an SVM combined with the "classical" local smoothing processes, such as Gaussian smoothing, moving average, and Savitzky-Golay filters. The study results indicated that their proposed model performed better than the state-of-the-art model, viz., logistic regression.…”

“…They determined the forecasting accuracy with the help of the RMSE and mean absolute percentage error (MAPE); the results proved the effectiveness of the proposed mechanism. The authors of [31] proposed a smooth-aided SVM-based model for video traffic forecasting; the obtained results were promising where local smoothing techniques were incorporated ahead to the SVM to normalize the fluctuations in the input traffic. The smoothed support vector machine (SSVM) has an improvement percentage of 32.35% for a one-step-ahead forecast.…”

“…Very few studies reported in the literature considered noise preprocessing, while no study presented a dynamic framework for concept changes. Previously adopted noise preprocessing methods in previous studies, such as wavelets and EMD, are less flexible than window-based noise processing [31]. The only notable study used windows-based noise processing, such as Gaussian smoothing, moving average, and Savitzky-Golay filters, and used SVMs as an ML technique.…”

PM2.5 Concentration Forecasting in Industrial Parks Based on Attention Mechanism Spatiotemporal Graph Convolutional Networks

“…Therefore, forecasting the PM2.5 concentration in industrial parks is essentially a forecast of time series data. At this stage, there are many mature time series forecasting methods, including support vector regression (SVR) [7], autoregressive moving average model (ARMA) [8], and BP neural network [9]. However, with the exponential increase in the amount of time series data and the increase in complexity, these traditional forecast methods can only extract relatively simple linear features, and it is difficult to effectively extract more complex nonlinear features and the training time is too long, and the forecast accuracy is limited and cannot meet the actual demand.…”