Realtime mobile bandwidth prediction using LSTM neural network and Bayesian fusion

Abstract With the increasing popularity of mobile Internet and the higher bandwidth requirement of mobile applications, user Quality of Experience (QoE) is particularly important. For applications requiring high bandwidth and low delay, such as video streaming, video conferencing, and online gaming, etc., if the future bandwidth can be estimated in advance, applications can leverage the estimation to adjust their data transmission strategies and significantly improve the user QoE. In this paper, we focus on accurate bandwidth prediction to improve user QoE. Specifically, We study realtime mobile bandwidth prediction in various mobile networking scenarios, such as subway and bus rides along different routes. The primary method used is Long Short Term Memory (LSTM) recurrent neural network. In individual scenarios, LSTM significantly improves the prediction accuracy of state-of-the-art prediction algorithms, such as Recursive Least Squares (RLS) by 12% in Root Mean Square Error (RMSE) and by 17% in Mean Average Error (MAE). We further developed Multi-Scale Entropy (MSE) to analyze the bandwidth patterns in different mobility scenarios and discuss its connection to the achieved accuracy. For practical applications, we developed Model Switching and Bayes Model Fusion to use pre-trained LSTM models for online realtime bandwidth prediction.

[1]  Hongzi Mao,et al.  Neural Adaptive Video Streaming with Pensieve , 2017, SIGCOMM.

[2]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[3]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[4]  Robert W. Heath,et al.  Using random shape theory to model blockage in random cellular networks , 2012, 2012 International Conference on Signal Processing and Communications (SPCOM).

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Bing Wang,et al.  LinkForecast: Cellular Link Bandwidth Prediction in LTE Networks , 2018, IEEE Transactions on Mobile Computing.

[7]  Thar Baker,et al.  Big Data Environment for Smart Healthcare Applications Over 5G Mobile Network , 2018, Applications of Big Data Analytics.

[8]  Yi Sun,et al.  CS2P: Improving Video Bitrate Selection and Adaptation with Data-Driven Throughput Prediction , 2016, SIGCOMM.

[9]  Yong Liu,et al.  Towards agile and smooth video adaptation in dynamic HTTP streaming , 2012, CoNEXT '12.

[10]  Thar Baker,et al.  A Deep Learning Approach for Energy Efficient Computational Offloading in Mobile Edge Computing , 2019, IEEE Access.

[11]  Richard A. Brown,et al.  Introduction to random signals and applied kalman filtering (3rd ed , 2012 .

[12]  Andra Lutu,et al.  MONROE-Nettest: A configurable tool for dissecting speed measurements in mobile broadband networks , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[13]  Robert W. Heath,et al.  Analysis of Blockage Effects on Urban Cellular Networks , 2013, IEEE Transactions on Wireless Communications.

[14]  Qi He,et al.  On the predictability of large transfer TCP throughput , 2007, Comput. Networks.

[15]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[16]  Paul Barford,et al.  A Machine Learning Approach to TCP Throughput Prediction , 2007, IEEE/ACM Transactions on Networking.

[17]  Thar Baker,et al.  Comparison Data Traffic Scheduling Techniques for Classifying QoS over 5G Mobile Networks , 2017, 2017 31st International Conference on Advanced Information Networking and Applications Workshops (WAINA).

[18]  Madalena Costa,et al.  Multiscale entropy analysis of complex physiologic time series. , 2002, Physical review letters.

[19]  Guy Pujolle,et al.  NeuTM: A neural network-based framework for traffic matrix prediction in SDN , 2017, NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium.

[20]  Bruno Sinopoli,et al.  A Control-Theoretic Approach for Dynamic Adaptive Video Streaming over HTTP , 2015, Comput. Commun. Rev..

[21]  Yong Liu,et al.  Real-time bandwidth prediction and rate adaptation for video calls over cellular networks , 2016, MMSys.

[22]  Andra Lutu,et al.  The good, the bad and the implications of profiling mobile broadband coverage , 2016, Comput. Networks.

[23]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .