Abstract
Software Defined Networking has become an efficient and promising means for overcoming the limitations of traditional networks, e.g., by guaranteeing the corresponding Quality of Service (QoS) of various applications. Compared with the inherent distributed characteristics of the traditional network, SDN is logically centralized and can utilize machine learning techniques to keep track of transmission requirements of each application. In this research, we first develop an efficient data dimension reduction approach by considering the correlation coefficients between data items. We classify the traffic data into distinguished categories based on the QoS requirements by a supervised machine learning method. Then, we propose a QoS Aware Routing (QAR) algorithm according to the QoS requirements of each application that finds a path with either the minimum average link occupied times or the maximum average path residual capacity. The accuracy of machine learning model shows that our proposed dimension reduction approach is more effective than other data preprocessing methods, and the results of blocking probability indicate that our QAR algorithm outperforms significantly previous algorithms.
Similar content being viewed by others
References
Optimization G (2016) Gurobi optimizer[J]. https://www.gurobi.com
Rojas JS (2017) Ip network traffic flows labeled with 75 apps. Kaggle. Retrieved from https://www.kaggle.com/jsrojas/ip-network-traffic-flows-labeled-with-87-apps
Akin E, Korkmaz T (2019) Comparison of routing algorithms with static and dynamic link cost in SDN. In 16th IEEE Annual Consumer Communications & Networking Conference (CCNC) pp. 1–8
Alam F, Katib I, Alzahrani AS (2013) New networking era: Software defined networking. Int J Adv Res Comput Sci Softw 3(11):349–353
AlGhadhban A, Shihada B (2018) Flight: A fast and lightweight elephant-flow detection mechanism. In 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS) pp. 1537–1538
Amaral P, Dinis J, Pinto P, Bernardo L, Tavares J, Mamede HS (2016) Machine learning in software defined networks: data collection and traffic classification. In Proc 24th Int Conf Network Protocols (ICNP) pp. 1–5
Astuto B, Mendonca M, Nguyen Z, Obraczka K, Turletti T (2014) A survey of software-defined networking: Past, present, and future of programmable networks. IEEE Commun Surv Tutorials 16(3):1617–1634
Becker N, Werft W, Toedt G, Lichter P, Benner A (2009) Penalizedsvm: A r-package for feature selection svm classification. Bioinformatics 25(13):1711–1712
Biau G, Scornet E (2016) A random forest guided tour. Test 25(2):197–227
Callado AC, Kamienski CA, Szabó G, Gero BP, Kelner J, Fernandes SF, Sadok DFH (2009) A survey on Internet traffic identification. IEEE Commun Surv Tutorials 11(3):37–52
Caruana R, Niculescu-Mizil A (2006) An empirical comparison of supervised learning algorithms. In Proceedings of the 23rd International Conference on Machine learning ACM pp. 161–168
Chen Y, Farley T, Ye N (2004) QoS requirements of network applications on the internet. Inf Knowl Syst Manag 4(1):55–76
Chhabra A, Kiran M (2017) Classifying elephant and mice flows in high-speed scientific networks
Christiansen B (2005) The shortcomings of nonlinear principal component analysis in identifying circulation regimes. J Clim 18:4814–4823
Conti M, Gregori E, Panzieri F (2000) Load distribution among replicated web servers: A qos-based approach. ACM SIGMETRICS Performance Evaluation Review 27(4):12–19
Da Silva AS, Machado CC, Bisol RV, Granville LZ, Schaeffer-Filho A (2015) Identification and selection of flow features for accurate traffic classification in SDN. In Proc IEEE 14th Int Symp Network Computing and Applications (NCA) IEEE pp. 134–141
Erman J, Arlitt M, Mahanti A (2006) Traffic classification using clustering algorithms. In Proceedings of the 2006 SIGCOMM workshop on Mining network data pp. 281–286
Erman J, Mahanti A, Arlitt M, Cohen I, Williamson C (2007) Semi-supervised network traffic classification. In Proceedings of the 2007 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer ystems pp. 369–370
Ersoz D, Yousif MS, Das CR (2007) Characterizing network traffic in a cluster-based, multi-tier data center. In 27th International Conference on Distributed Computing Systems (ICDCS’07) IEEE pp. 59
Fonti V, Belitser E (2017) Feature selection using lasso. VU Amsterdam Research Paper in Business Analytics 30:1–25
Jarschel M, Zinner T, Höhn T, Tran-Gia P (2013) On the accuracy of leveraging sdn for passive network measurements. In 2013 Australasian Telecommunication Networks and Applications Conference (ATNAC) IEEE pp. 41–46
Jolliffe I (2002) Principal Component Analysis, 2nd ed. Springer
Karakus M, Durresi A (2017) Quality of service (QoS) in software defined networking (SDN): A survey. J Netw Comput Appl 80:200–218
Kotsiantis SB, Zaharakis I, Pintelas P (2007) Supervised machine learning: A review of classification techniques. Emerg Artif Intell Appl Comput Eng 160:3–24
Layeghy S, Pakzad F, Portmann M (2016) Scor: Software-defined constrained optimal routing platform for sdn. arXiv preprint arXiv:1607.03243
Li C-Y, Li G, Wai P-KA, Li VO (2004) A wavelength-switched time-slot routing scheme for wavelength-routed networks. In 2004 IEEE International Conference on Communications (IEEE Cat. No. 04CH37577) 3:1689–1693
Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE (2017) A survey of deep neural network architectures and their applications. Neurocomputing 234:11–26
McKeown N, Anderson T, Balakrishnan H, Parulkar G, Peterson L, Rexford J, Shenker S, Turner J (2008) Openflow: enabling innovation in campus networks. ACM SIGCOMM Computer Communication Review 38(2):69–74
Menze BH, Kelm BM, Masuch R, Himmelreich U, Bachert P, Petrich W, Hamprecht FA (2009) A comparison of random forest and its gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics 10(1):1–16
Mwangi B, Tian TS, Soares JC (2014) A review of feature reduction techniques in neuroimaging. Neuroinformatics 12(2):229–244
Neums L, Meier R, Koestler DC, Thompson JA (2019) Improving survival prediction using a novel feature selection and feature reduction framework based on the integration of clinical and molecular data. In PACIFIC SYMPOSIUM ON BIOCOMPUTING 2020. World Scientific, pp. 415–426
Patle A, Chouhan DS (2013) Svm kernel functions for classification. In 2013 International Conference on Advances in Technology and Engineering (ICATE) IEEE pp. 1–9
Pua Y-H, Kang H, Thumboo J, Clark RA, Chew ES-X, Poon CL-L, Chong H-C, Yeo S-J (2019) Machine learning methods are comparable to logistic regression techniques in predicting severe walking limitation following total knee arthroplasty. Knee Surgery, Sports Traumatology, Arthroscopy pp. 1–10
Ripley BD (2007) Pattern recognition and neural networks. Cambridge University Press
Rish I et al (2001) An empirical study of the naive bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence 3:41–46
Shlens J (2014) A tutorial on principal component analysis. arXiv preprint arXiv:1404.1100
Sylvester EV, Bentzen P, Bradbury IR, Clément M, Pearce J, Horne J, Beiko RG (2018) Applications of random forest feature selection for fine-scale genetic population assignment. Evol Appl 11(2):153–165
Tibshirani RJ et al (2013) The lasso problem and uniqueness. Electron J Stat 7:1456–1490
Velasco L, Jirattigalachote A, Ruiz M, Monti P, Wosinska L, Junyent G (2012) Statistical approach for fast impairment-aware provisioning in dynamic all-optical networks. J Opt Commun Networking 4(2):130–141
Vu HD, But J (2015) How rtt between the control and data plane on a sdn network impacts on the perceived performance. In 2015 International Telecommunication Networks and Applications Conference (ITNAC) IEEE pp. 179–184
Wang Z, Crowcroft J (1996) Quality-of-service routing for supporting multimedia applications. IEEE J Sel Areas Commun 14(7):1228–1234
Wei JY, McFarland RI (2000) Just-in-time signaling for wdm optical burst switching networks. J Lightwave Technol 18(12):2019–2037
Xiao P, Liu N, Li Y, Lu Y, Tang X-J, Wang H-W, Li M-X (2016) A traffic classification method with spectral clustering in SDN. In Proc 17th Int Conf Parallel and Distributed Computing, Applications and Technologies (PDCAT) IEEE pp. 391–394
Xie J, Yu FR, Huang T, Xie R, Liu J, Liu Y (2018) A survey of machine learning techniques applied to software defined networking (SDN): Research issues and challenges. IEEE Commun Surv Tutorials 21(1):393–430
Yamansavascilar B, Guvensan MA, Yavuz AG, Karsligil ME (2017) Application identification via network traffic classification. In 2017 International Conference on Computing, Networking and Communications (ICNC) IEEE pp. 843–848
Yang M, Wu Q, Guo K, Zhang Y (2019) Evaluation of device cost, power consumption, and network performance in spatially and spectrally flexible sdm optical networks. J Lightwave Technol 37(20):5259–5272
Ye Q, Li J, Qu K, Zhuang W, Shen X, Li X (2018) A network slicing framework for end-to-end QoS provisioning in 5G networks. IEEE Veh Technol Mag 13(2):65–74
Yen JY (1971) Finding the k shortest loopless paths in a network. Manag Sci 17(11):712–716
Zhang J, Chen X, Xiang Y, Zhou W, Wu J (2014) Robust network traffic classification. IEEE/ACM Trans Networking 23(4):1257–1270
Zhang J, Xiang Y, Wang Y, Zhou W, Xiang Y, Guan Y (2012) Network traffic classification using correlation information. IEEE Trans Parallel Distrib Syst 24(1):104–117
Acknowledgements
We would like to thank Prof. Neil Millar and anonymous reviewers, whose insightful comments and modification suggestions are valuable for the improvement and completion of this paper. This work has been partially supported by JSPS Grant-in-Aid for Scientific Research (C) 21K04544.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zheng, W., Yang, M., Zhang, C. et al. Application-aware QoS routing in SDNs using machine learning techniques. Peer-to-Peer Netw. Appl. 15, 529–548 (2022). https://doi.org/10.1007/s12083-021-01262-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12083-021-01262-8