Abstract
The accurate estimation of future network traffic is a key enabler for early warning of network degradation and automated orchestration of network resources. The long short-term memory neural network (LSTM) is a popular architecture for network traffic forecasting, and has been successfully used in many applications. However, it has been observed that LSTMs suffer from limited memory capacity problems when the sequence is long. In this paper, we propose a gated dilated causal convolution based encoder-decoder (GDCC-ED) model for network traffic forecasting. The GDCC-ED learns a vector representation in the encoder from historical network traffic series, in which gated dilated causal convolutions are adopted to expand the long-range memory capacity. Moreover, different types of features in various perspectives, including temporal-independent and temporal-related features, are incorporated. In the decoder, the GDCC-ED exploits an RNN with LSTM units to map the vector representation back to a variable-length target sequence. Besides, a sequence data augmentation technique is designed to solve the problem of data scarcity. Experimental results demonstrate that our model achieves superior performance than state-of-the-art algorithms by 11.6%.
Highlights
With the popularity of smart devices and diverse applications, the demand of network traffic has grown rapidly around the world
To address the above-mentioned challenges, in this paper, we propose a gated dilated causal convolution based encoderdecoder (GDCC-ED) model for network traffic forecasting
Many studies have been done on network traffic forecasting with traditional linear models, such as the autoregressive moving average model (ARMA) and the autoregressive integrated moving average model (ARIMA)
Summary
With the popularity of smart devices and diverse applications, the demand of network traffic has grown rapidly around the world. As a kind of specially designed neural network, the recurrent neural network (RNN) has been widely used to model complicated nonlinear sequence patterns, which provides promising results in many fields. Other works [13]–[18] utilize both the spatio and temporal dependencies of network traffic between different services or adjacent base stations These studies require raw data with spatio-temporal properties, otherwise these models become invalid. To address the above-mentioned challenges, in this paper, we propose a gated dilated causal convolution based encoderdecoder (GDCC-ED) model for network traffic forecasting. GDCC-ED enhances the long-range memory capacity by gated dilated causal convolutions without increasing the number of model parameters, in order to learn a vector representation of the input sequence. Proposing a gated dilated causal convolution based encoder-decoder (GDCC-ED) model for network traffic forecasting.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
