A Meta-Learning Scheme for Adaptive Short-Term Network Traffic Prediction

Abstract

Network traffic prediction is a fundamental prerequisite for dynamic resource provisioning in wireline and wireless networks, but is known to be challenging due to non-stationarity and due to its burstiness and self-similar nature. The prediction of network traffic at the user level is particularly challenging, because the traffic characteristics emerge from a complex interaction of user level and application protocol behavior. In this work we address the problem of predicting the network traffic at the user level over a short horizon, motivated by its applications in cellular scheduling. Motivated by recent works on robust adversarial learning, we treat the prediction problem for non-stationary traffic in an adversarial context, and propose a meta-learning scheme that consists of a set of predictors, each optimized to predict a particular kind of traffic, and of a master policy that is trained for choosing the best fit predictor dynamically based on recent prediction performance, using deep reinforcement learning. We evaluate the proposed meta-learning scheme on a variety of traffic traces consisting of video and nonvideo traffic. Our results show that it consistently outperforms state-of-the-art predictors, and can adapt to before unseen traffic without the need for retraining the individual predictors.

Prediction of Network Traffic in Wireless Mesh Networks Using Hybrid Deep Learning Model

“…Recently, researchers have also seen the rise of attention mechanism [29] and deep learning in interdisciplinary ways [30]. This trend is slowly reflected in traffic prediction.He et al [31] applied a meta-learning scheme for faster traffic prediction in smaller networks. Li et al [32] combined wavelet analysis with backpropagation neural networks for traffic flow analysis in wireless networks.…”

Traffic Prediction-Enabled Energy-Efficient Dynamic Computing Resource Allocation in CRAN Based on Deep Learning

“…Moreover, transfer learning strategy is also utilized for exploiting the similarities among different types of cellular traffic as well as capturing the pattern similarity of cellular traffic among different areas. A meta-learning scheme is proposed in [28], aiming at addressing the problem of shortterm user-level network traffic prediction. The proposed metalearning scheme is an ensemble of different predictors for predicting different types of traffic.…”

Machine Learning for Multimedia Communications

“…The second challenge is mainly focused on the non-stationarity of the data traffic, which makes it difficult and computationally expensive to train a one-size-fits-all predictor/controller. For this reason, in [ 97 ] a meta-learning scheme has been proposed consisting in a set of predictors, each optimized to predict a particular kind of traffic, which provide a prior for the adaptive streaming strategy. In [ 98 , 99 ], the critical aspect of an accurate prediction in low-latency streaming systems is discussed.…”