Advertisement

Classification of Network Game Traffic Using Machine Learning

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 848)

Abstract

With the rapid development of the Internet, different kinds of network games are emerging. The classification of network game flow is important to improve the quality of service. In this paper, we propose an approach to identify network game traffic. It firstly filters the game traffic data based on protocol filtering and IP filtering to reduce background noise as much as possible. Then, to remove irrelevant and redundant features, Pearson correlation coefficient and information gain ratio are used as the criteria to choose features. By analyzing various statistical features of game traffic, it is found that employing the three features, ratio of inbound to outbound data packets, downlink packet size information entropy and downlink Packets per second, is able to yield better classification performance. The experimental results show that the proposed method is feasible and can achieve higher accuracy than an existing method.

Keywords

Classification of network game traffic Statistical features IP filtering SVM 

Notes

Acknowledgments

The authors would like to thank National Natural Science Foundation of China (No. 61271233) and the HIRP program of Huawei Technology Co. Ltd to sponsor this work in part.

References

  1. 1.
    Dainotti, A., Pescape, A., Claffy, K.: Issues and future directions in traffic classification. IEEE Netw. 26, 35–40 (2012)CrossRefGoogle Scholar
  2. 2.
    Deebalakshmi, R., Jyothi, V.L.: A survey of classification algorithms for network traffic. In: Second International Conference on Science Technology Engineering and Management (ICONSTEM) IEEE, pp. 151–156 (2016)Google Scholar
  3. 3.
    Nair, L.M., Sajeev, G.P.: Internet traffic classification by aggregating correlated decision tree classifier. In: 7th International Conference on Computational Intelligence, Modelling and Simulation (CIMSim 2015), pp. 135–140 (2015)Google Scholar
  4. 4.
    Jiang, D., Long, L.: P2P traffic identification research based on the SVM. In: Wireless and Optical Communication Conference (WOCC), IEEE, pp. 683–686 (2013)Google Scholar
  5. 5.
    Han, Y.T., Park, H.S.: Game traffic classification using statistical characteristics at the transport layer. ETRI J. 32, 22–32 (2010)CrossRefGoogle Scholar
  6. 6.
    Han, Y.T., Park, H.S.:UDP based P2P Game Traffic Classification with Transport Layer Behaviors. In: 14th Asia-Pacific Conference on Communications, pp. 1–5 (2008)Google Scholar
  7. 7.
    Mu, X., Wu, W.: A parallelized network traffic classification based on hidden markov model. In: International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery IEEE Computer Society, pp. 107–112 (2011)Google Scholar
  8. 8.
    Maia, J.E.B., Filho, R.H.: Internet traffic classification using a hidden markov model. In: 10th International Conference on Hybrid Intelligent Systems, pp. 37–42 (2010)Google Scholar
  9. 9.
    Claypool, M., Finkel, D., Grant, A., Solano, M.: Thin to win? network performance analysis of the OnLive thin client game system. In: 11th Annual Workshop on Network and Systems Support for Games, pp. 1–6 (2012)Google Scholar
  10. 10.
    Cheand, X., Ip, B.: Packet-level traffic analysis of online games from the genre characteristics perspective. J. Netw. Comput. Appl. 35, 240–252 (2012)CrossRefGoogle Scholar
  11. 11.
    Eggert, C., Herrlich, M., Smeddinck, J., Malaka, R.: Classification of player roles in the team-based multi-player game Dota 2. In: Chorianopoulos, K., Divitini, M., Hauge, J.B., Jaccheri, L., Malaka, R. (eds.) ICEC 2015. LNCS, vol. 9353, pp. 112–125. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24589-8_9CrossRefGoogle Scholar
  12. 12.
    Middleton, S.E., Modafferi, S.: Scalable classification of QoS for real-time interactive applications from IP traffic measurements. Comput. Netw. 107, 121–132 (2016)CrossRefGoogle Scholar
  13. 13.
    Neto, A.M., et al.: Pearson’s correlation coefficient for discarding redundant information in real time autonomous navigation system. In: IEEE International Conference on Control Applications IEEE, pp. 426–431 (2007)Google Scholar
  14. 14.
    Chen, Z., Peng, L., Zhao, S., Zhang, L., Jing, S.: Feature selection toward optimizing internet traffic behavior identification. In: Sun, X.-h., Qu, W., Stojmenovic, I., Zhou, W., Li, Z., Guo, H., Min, G., Yang, T., Wu, Y., Liu, L. (eds.) ICA3PP 2014. LNCS, vol. 8631, pp. 631–644. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-11194-0_56CrossRefGoogle Scholar
  15. 15.
    Yuan, J., et al.: T-drive: driving directions based on taxi trajectories. In: Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 99–108 (2010)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.College of Telecommunications and Information EngineeringNanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations