ABSTRACT
Network slicing will allow 5G network operators to offer a diverse set of services over a shared physical infrastructure. We focus on supporting the operation of the Radio Access Network (RAN) slice broker, which maps slice requirements into allocation of Physical Resource Blocks (PRBs). We first develop a new metric, REVA, based on the number of PRBs available to a single Very Active bearer. REVA is independent of channel conditions and allows easy derivation of an individual wireless link's throughput. In order for the slice broker to efficiently utilize the RAN, there is a need for reliable and short term prediction of resource usage by a slice. To support such prediction, we construct an LTE testbed and develop custom additions to the scheduler. Using data collected from the testbed, we compute REVA and develop a realistic time series prediction model for REVA. Specifically, we present the X-LSTM prediction model, based upon Long Short-Term Memory (LSTM) neural networks. Evaluated with data collected in the testbed, X-LSTM outperforms Autoregressive Integrated Moving Average Model (ARIMA) and LSTM neural networks by up to 31%. X-LSTM also achieves over 91% accuracy in predicting REVA. By using X-LSTM to predict future usage, a slice broker is more adept to provision a slice and reduce over-provisioning and SLA violation costs by more than 10% in comparison to LSTM and ARIMA.
- 2016. Description of network slicing concept. Technical Report 1. NGMN 5G Alliance.Google Scholar
- 3GPP. 2011. Evolved Universal Terrestrial Radio Access Physical channels and modulation. TS 36.211. 3rd Generation Partnership Project (3GPP).Google Scholar
- 3GPP. 2018. Policy and charging control architecture (Release 15). TS 23.203. 3rd Generation Partnership Project (3GPP).Google Scholar
- 5G Infrastructure Association and others. 2017. Deliverable D3.2 5G NORMA network architecture Intermediate report. January (2017).Google Scholar
- Haitham Abu-Ghazaleh and Attahiru Sule Alfa. 2010. Application of mobility prediction in wireless networks using markov renewal theory. IEEE Transactions on Vehicular Technology 59, 2 (2010), 788--802.Google ScholarCross Ref
- George EP Box, Gwilym M Jenkins, Gregory C Reinsel, and Greta M Ljung. 2015. Time Series analysis: forecasting and control. John Wiley & Sons.Google Scholar
- Chia-Yu Chang, Navid Nikaein, and Thrasyvoulos Spyropoulos. 2018. Radio access network resource slicing for flexible service execution. In Proc. of IEEE INFOCOM Workshop on RS-FCN.Google ScholarCross Ref
- Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014).Google Scholar
- Xenofon Foukas, Mahesh K Marina, and Kimon Kontovasilis. 2017. Orion: RAN Slicing for a Flexible and Cost-Effective Multi-Service Mobile Network Architecture. In Proc. of ACM MobiCom. Google ScholarDigital Library
- Felix A Gers, Nicol N Schraudolph, and Jürgen Schmidhuber. 2002. Learning precise timing with LSTM recurrent networks. Journal of Machine Learning Research 3, 8 (2002), 115--143. Google ScholarDigital Library
- Balázs Héder, Péter Szilágyi, and Csaba Vulkán. 2016. Dynamic and adaptive QoE management for OTT application sessions in LTE. In Proc. of IEEE PIMRC.Google ScholarCross Ref
- Sepp Hochreiter, Yoshua Bengio, Paolo Frasconi, and Jürgen Schmidhuber. 2001. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. (2001).Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780. Google ScholarDigital Library
- Ekram Hossain and Monowar Hasan. 2015. 5G cellular: key enabling technologies and research challenges. IEEE Instrumentation & Measurement Magazine 18, 3 (2015), 11--21.Google ScholarCross Ref
- Andrej Karpathy, Justin Johnson, and Li Fei-Fei. 2015. Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078 (2015).Google Scholar
- Gwanmo Ku and John MacLaren Walsh. 2015. Resource allocation and link adaptation in LTE and LTE advanced: A tutorial. IEEE Communications Surveys & Tutorials 17, 3 (2015), 1605--1633.Google ScholarCross Ref
- Raymond Kwan, Rob Arnott, Riccardo Trivisonno, and Mitsuhiro Kubota. 2010. On pre-emption and congestion control for LTE systems. In Proc. of IEEE VTC 2010-Fall.Google ScholarCross Ref
- Mathieu Leconte, Georgios Paschos, Panayotis Mertikopoulos, and Ulas Kozat. 2017. A resource allocation framework for network slicing. In Proc. of IEEE INFOCOM.Google Scholar
- Cristina Marquez, Marco Gramaglia, Marco Fiore, Albert Banchs, and Xavier Costa-Perez. 2018. How Should I Slice My Network?: A Multi-Service Empirical Evaluation of Resource Sharing Efficiency. In Proc. of ACM Mobicom. Google ScholarDigital Library
- Daniel Neil, Michael Pfeiffer, and Shih-Chii Liu. 2016. Phased LSTM: Accelerating recurrent network training for long or event-based sequences. In Advances in Neural Information Processing Systems. 3882--3890. Google ScholarDigital Library
- Peter Rost, Christian Mannweiler, Diomidis S Michalopoulos, Cinzia Sartori, Vincenzo Sciancalepore, Nishanth Sastry, Oliver Holland, Shreya Tayade, Bin Han, Dario Bega, et al. 2017. Network Slicing to Enable Scalability and Flexibility in 5G Mobile Networks. IEEE Communications Magazine 55, 5 (2017), 72--79. Google ScholarDigital Library
- Josep Xavier Salvat, Lanfranco Zanzi, Andres Garcia-Saavedra, Vincenzo Sciancalepore, and Xavier Costa-Perez. 2018. Overbooking network slices through yield-driven end-to-end orchestration. In Proc. of ACM CoNext. Google ScholarDigital Library
- Konstantinos Samdanis, Xavier Costa-Perez, and Vincenzo Sciancalepore. 2016. From network sharing to multi-tenancy: The 5G network slice broker. IEEE Commun. Mag. 54, 7 (2016), 32--39. Google ScholarDigital Library
- Zulfiquar Sayeed, Qi Liao, Dave Faucher, Ed Grinshpun, and Sameer Sharma. 2015. Cloud analytics for wireless metric prediction-framework and performance. In in Proc. of IEEE CLOUD. Google ScholarDigital Library
- Vincenzo Sciancalepore, Konstantinos Samdanis, Xavier Costa-Perez, Dario Bega, Marco Gramaglia, and Albert Banchs. 2017. Mobile traffic forecasting for maximizing 5G network slicing resource utilization. In Proc. of IEEE INFOCOM.Google ScholarCross Ref
- Julius Shiskin. 1965. The X-11 variant of the census method II seasonal adjustment program. Number 15. US Government Printing Office.Google Scholar
- R Sivakumar, E Ashok Kumar, and G Sivaradje. 2011. Prediction of traffic load in wireless network using time series model. In Proc. of IEEE PACC.Google ScholarCross Ref
- Péter Szilágyi and Csaba Vulkán. 2015. LTE user plane congestion detection and analysis. In Proc. of IEEE PIMRC.Google ScholarCross Ref
- Huandong Wang, Fengli Xu, Yong Li, Pengyu Zhang, and Depeng Jin. 2015. Understanding mobile traffic patterns of large scale cellular towers in urban environment. In Proc. of ACM IMC. Google ScholarDigital Library
- Jing Wang, Jian Tang, Zhiyuan Xu, Yanzhi Wang, Guoliang Xue, Xing Zhang, and Dejun Yang. 2017. Spatiotemporal modeling and prediction in cellular networks: A big data enabled deep learning approach. In Proc. of IEEE INFOCOM.Google ScholarCross Ref
- Xiaoli Wang, Edward Grinshpun, David Faucher, and Sameer Sharma. 2017. On Medium and Long Term Channel Conditions Prediction for Mobile Devices. In Proc. of IEEE WCNC.Google ScholarCross Ref
- Xu Wang, Zimu Zhou, Zheng Yang, Yunhao Liu, and Chunyi Peng. 2017. Spatiotemporal analysis and prediction of cellular traffic in metropolis. In Proc. of IEEE ICNP.Google Scholar
- Xiufeng Xie, Xinyu Zhang, Swarun Kumar, and Li Erran Li. 2015. piStream: Physical layer informed adaptive video streaming over LTE. In Proc. of ACM MobiCom. Google ScholarDigital Library
- Qiang Xu, Sanjeev Mehrotra, Zhuoqing Mao, and Jin Li. 2013. PROTEUS: network performance forecast for real-time, interactive mobile applications. In Proc. of ACM MobiSys. Google ScholarDigital Library
- Chaoyun Zhang, Xi Ouyang, and Paul Patras. 2017. ZipNet-GAN: Inferring Fine-grained Mobile Traffic Patterns via a Generative Adversarial Neural Network. In Proc. of ACM CoNEXT. Google ScholarDigital Library
- Chaoyun Zhang and Paul Patras. 2018. Long-term mobile traffic forecasting using deep spatio-temporal neural networks. In Proc. of ACM Mobihoc. Google ScholarDigital Library
- Xuan Kelvin Zou, Jeffrey Erman, Vijay Gopalakrishnan, Emir Halepovic, Rittwik Jana, Xin Jin, Jennifer Rexford, and Rakesh K Sinha. 2015. Can accurate predictions improve video streaming in cellular networks?. In Proc. of ACM HotMobile. Google ScholarDigital Library
Index Terms
- RAN Resource Usage Prediction for a 5G Slice Broker
Recommendations
Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks
Mobihoc '18: Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and ComputingForecasting with high accuracy the volume of data traffic that mobile users will consume is becoming increasingly important for precision traffic engineering, demand-aware network resource allocation, as well as public transportation. Measurements ...
Demo: Efficient Multi-Service RAN Slice Management and Orchestration
NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management SymposiumThe 5G mobile network is supposed to handle a variety of services with different requirements. By means of virtualization, network slices form customized virtual networks transporting services with associated service guarantees. Especially the radio ...
Resource utilization prediction: long term network web service traffic
RIIT '13: Proceedings of the 2nd annual conference on Research in information technologyShort-term prediction has been established in computing as a mechanism for improving services. Long-term prediction has not been pursued because attempts to use multiple steps to extend short-term predictions have been shown to become less accurate the ...
Comments