Advertisement

Journal of Network and Systems Management

, Volume 22, Issue 2, pp 174–207 | Cite as

Application of Bayesian Networks for Autonomic Network Management

  • Abul BasharEmail author
  • Gerard Parr
  • Sally McClean
  • Bryan Scotney
  • Detlef Nauck
Article

Abstract

The ever evolving telecommunication networks in terms of their technology, infrastructure, and supported services have always posed challenges to the network managers to come up with an efficient Network Management System (NMS) for effective network management. The need for automated and efficient management of the current networks, more specifically the Next Generation Network (NGN), is the subject addressed in this research. A detailed description of the management challenges in the context of current networks is presented and then this work enlists the desired features and characteristics of an efficient NMS. It then proposes that there is a need to apply Artificial Intelligence (AI) and Machine Learning (ML) approaches for enhancing and automating the functions of NMS. The first contribution of this work is a comprehensive survey of the AI and ML approaches applied to the domain of NM. The second contribution of this work is that it presents the reasoning and evidence to support the choice of Bayesian Networks (BN) as a viable solution for ML-based NMS. The final contribution of this work is that it proposes and implements three novel NM solutions based on the BN approach, namely BN-based Admission Control (BNAC), BN-based Distributed Admission Control (BNDAC) and BN-based Intelligent Traffic Engineering (BNITE), along with the description of algorithms underpinning the proposed framework.

Keywords

Network Management Data Mining Machine Learning Artificial Intelligence Call Admission Control Intelligent Traffic Engineering Next Generation Networks Bayesian Networks 

Notes

Acknowledgements

The authors would like to acknowledge the support of Prince Mohammad Bin Fahd University, Saudi Arabia, for providing the facilities to perform this research work. The Vice Chancellors Research Scholarship support provided by the University of Ulster, UK during the first author's PhD research is highly appreciated. A special thanks to British Telecom, British Council UKIERI and IU-ATC (http://www.iu-atc.com) for funding the research internships at IIT Madras, India and BT Adastral Park, UK during this joint research work.

References

  1. 1.
    Ali, E.S., Darwish, M.G.: Diagnosing network faults using bayesian and case-based reasoning techniques. In: International Conference on Computer Engineering & Systems, pp. 145–150. (2007)Google Scholar
  2. 2.
    Alpaydin, E.: Introduction to Machine Learning. MIT Press, Cambridge (2004)Google Scholar
  3. 3.
    Assaf, T., Dugan, J.B.: Decision automation for predictive analysis models. In: Symposium on Reliability and Maintainability, pp. 335–340. (2007)Google Scholar
  4. 4.
    Auld, T., Moore, A.W., Gull, S.F.: Bayesian Neural Networks for Internet Traffic Classification. IEEE. Trans. Neural. Netw. 18(1), 223–239 (2007)CrossRefGoogle Scholar
  5. 5.
    Baldi, M., Baralis, E., Risso, F.: Data mining techniques for effective and scalable traffic analysis. In: IEEE Conference on Integrated Network Management, pp. 105–118. (2005)Google Scholar
  6. 6.
    Bashar, A., Parr, G.P., McClean, S.I., Scotney, B.W., Subramanian, M., Chaudhari, S.K., Gonsalves, T.A.: Employing Bayesian belief networks for energy efficient network management. In: 16th IEEE National Conference on Communications (NCC 2010), pp. 1–5. (2010)Google Scholar
  7. 7.
    Bashar, A., Parr, G.P., McClean, S.I., Scotney, B.W., Nauck, D.: Machine learning based call admission control approaches: A comparative study. In: 6th IEEE/IFIP International Conference on Network and Service Management (CNSM 2010), pp. 431–434. (2010)Google Scholar
  8. 8.
    Bashar, A., Parr, G.P., McClean, S.I., Scotney, B.W., Nauck, D.: Performance analysis of bayesian networks-based distributed call admission control for NGN. In: 5th IEEE/IFIP Workshop on Distributed Autonomous Network Management System (DANMS 2012), pp. 1214–1220. (2012)Google Scholar
  9. 9.
    Bisio, R., Gemello, R., Montariolo, E.: Using a machine learning tool in diagnosis of network overload. In: IEEE International Conference on Communications (ICC), pp. 1563–1567. (1992)Google Scholar
  10. 10.
    Bouckaert, R. R. et al.: Weka manual (3.7.1). http://prdownloads.sourceforge.net/weka/WekaManual-3-7-1.pdf?download (2009). (Last accessed : Nov 2012)
  11. 11.
    Burn-Thornton, K.E., Garibaldi, J., Mahdi, A.E.: Pro-active network management using data mining. In: IEEE Conference on Global Telecommunications (GLOBECOM 98), pp. 1208–1211. (1998)Google Scholar
  12. 12.
    Calvert, K.L., Griffioen, J., Wen, S.: Scalable network management using lightweight programmable network services. J. Netw. Syst. Manage. 14(1), 15–47 (2006)CrossRefGoogle Scholar
  13. 13.
    Case, J., Fedor, M., Schoffstall, M., Davin, J.: Simple network management protocol. In: RFC 1157, IETF (1990)Google Scholar
  14. 14.
    Cebulka, K.D., Muller, M.J., Riley, C.A.: Applications of AI for meeting network management challenges in the 1990s. In: IEEE GLOBECOM 1989, pp. 501–506. (1989)Google Scholar
  15. 15.
    Chadha, R.: Applications of policy-based network management. In: Network Operations and Management Symposium (NOMS) 2004, pp. 907–908. (2004)Google Scholar
  16. 16.
    Cheng, Y., Leon-Garcia, A., Foster, I.: Toward an Autonomic Service Management Framework: A Holistic Vision of SOA, AON, and Autonomic Computing. IEEE Commun. Mag. 46(5), 138–146 (2008)CrossRefGoogle Scholar
  17. 17.
    Choi, M., Hong, J.W.: Towards management of next generation networks. IEICE Transactions on Communications E90B, 3004–3014 (2007)Google Scholar
  18. 18.
    Claise, B.: Cisco Systems NetFlow Services Export Version 9. In: RFC 3954, IETF (2004)Google Scholar
  19. 19.
    Claise, B.: IPFIX Protocol Specification. In: RFC 5101, IETF (2008)Google Scholar
  20. 20.
    Clemm, A.: Network Management Fundamentals. 1st edn. Cisco Press, USA (2006)Google Scholar
  21. 21.
    Covo, A.A., Moruzzi, T.M., Peterson, E.D.: AI-assisted telecommunications network management. In: IEEE GLOBECOM 1989, pp. 487–491. (1989)Google Scholar
  22. 22.
    De Paola A., et al.: Rule based reasoning for network management. In: International Workshop on Computer Architecture for Machine Perception, pp. 25–30. (2005)Google Scholar
  23. 23.
    Deng, R.H., Lazar, A.A., Wang, W.: A probabilistic approach to fault diagnosis in linear lightwave networks. IEEE J. Select. Areas Commun. 11(9), 1438–1448 (1993)CrossRefGoogle Scholar
  24. 24.
    Ding, J.G., Kramer, B., Xu, S.H., Chen, H.S., Bai, Y.C.: Predictive fault management in the dynamic environment of IP networks. In: IEEE Workshop on IP Operations and Management Proceedings (IPOM 2004), pp. 233–239. (2004)Google Scholar
  25. 25.
    Dini, P., Hasan, M.Z., Morrow, M., Parr, G., Rolin, P.: IP/MPLS OAM: challenges and directions. In: IEEE Workshop on IP Operations and Management, pp. 1–8. (2004)Google Scholar
  26. 26.
    Ekaette, E.U., Far, B.H.: A framework for distributed fault management using intelligent software agents. In: IEEE Canadian Conference on Electrical and Computer Engineering 2003, vol. 2, pp. 797–800. (2003)Google Scholar
  27. 27.
    Enns, R.: Netconf Configuration Protocol. In: RFC 4741, IETF (2006)Google Scholar
  28. 28.
    Ezawa, K.J., Norton, S.W.: Constructing Bayesian networks to predict uncollectible telecommunications accounts. IEEE Exp. 11(5), 45–51 (1996)CrossRefGoogle Scholar
  29. 29.
    Fan, C.F., Yu, Y.C.: BBN-based software project risk management. J. Syst. Softw. 73(2), 193–203 (2004)CrossRefGoogle Scholar
  30. 30.
    Guo, D., Wang, X.: Bayesian network loss inference. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 33–36. (2003)Google Scholar
  31. 31.
    Harrington, D., Presuhn, R., Wijnen, B.: An architecture for describing SNMP management frameworks. In: RFC 3411, IETF (2002)Google Scholar
  32. 32.
    Heckerman, D.: A tutorial on learning with Bayesian networks. 1st edn. MIT Press, Cambridge (1999)Google Scholar
  33. 33.
    Hood, C.S., Ji, C.: Proactive network fault detection. In: IEEE INFOCOM 1997, pp. 1147–1155. (1997)Google Scholar
  34. 34.
    Hugin Expert A/S: Hugin Researcher 7.3. http://www.hugin.com. (Accessed : Nov 2012)
  35. 35.
    IBM: SPSS Modeler 13.0. http://www.spss.com. (Last accessed : Nov 2012)
  36. 36.
    Jensen, F.: Bayesian Networks and Decision Graphs. 2nd edn. Springer Co., USA (2007)CrossRefzbMATHGoogle Scholar
  37. 37.
    Jensen, F.V., Lauritzen, S.L., Olesen, K.G.: Bayesian updating in causal probabilistic networks by local computations. Comput. Stat. Quat. 4(1), 269–282 (1990)MathSciNetGoogle Scholar
  38. 38.
    Jeon, G., Falcon, R., Kim, D., Lee, R., Jeong, J.: Application of Bayesian Belief Network in Reliable Analysis for Video Deinterlacing. IEEE Trans. Consum. Electron. 54(1), 123–130 (2008)CrossRefGoogle Scholar
  39. 39.
    Jia, L., Zhu, W., Zhai, C., Du, Y.: Research on an Integrated Network Management System. In: International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007), pp. 311–316. (2007)Google Scholar
  40. 40.
    Jun, L., Shunyi, Z., Yanqing, L., Zailong, Z.: Internet traffic classification using machine learning. In: International Conference on Communications and Networking, pp. 239–243. (2007)Google Scholar
  41. 41.
    Kataria, D., Logothetis, D.: Fixed mobile convergence: network architecture, services, terminals, and traffic management. In: 16th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC 2005), pp. 2289–2300. (2005)Google Scholar
  42. 42.
    Khan, M.J., Shamail, S., Awais, M.M., Hussain, T.: Comparative study of various artificial intelligence techniques to predict software quality. In: IEEE Multitopic Conference, INMIC 2006, pp. 173–177. (2006)Google Scholar
  43. 43.
    Khanafer, R.M., Solana, B., Triola, J., Barco, R., Moltsen, L., Altman, Z., Lazaro, P.: Automated Diagnosis for UMTS Networks Using Bayesian Network Approach. IEEE Trans. Veh. Technol. 57(4), 2451–2461 (2008)CrossRefGoogle Scholar
  44. 44.
    Lauritzen, S.L.: The EM algorithm for graphical association models with missing data. Comput. Stat. Data Anal. 19(2), 191–201 (1995)CrossRefzbMATHGoogle Scholar
  45. 45.
    Lee, C., Knight, D.: Realization of the next-generation network. IEEE Commun. Mag. 43(10), 34–41 (2005)CrossRefGoogle Scholar
  46. 46.
    Li, M., Sandrasegaran, K.: Network management challenges for next generation networks. In: 30th IEEE Conference on Local Computer Networks, pp. 1–6 (2005)Google Scholar
  47. 47.
    Liu, G., Ji, C.: Resilience of all-optical network architectures under in-band crosstalk attacks: a probabilistic graphical model approach. IEEE J. Select. Areas Commun. 25(3), 2–17 (2007)CrossRefGoogle Scholar
  48. 48.
    Livadas, C., Walsh, R., Lapsley, D., Strayer, W.T.: Using ML techniques to identify botnet traffic. In: IEEE Conference on Local Computer Networks, pp. 967–974. (2006)Google Scholar
  49. 49.
    Luo, J.Z., Gu, G.Q., Fei, X.: An architectural model for intelligent network management. J. Comput. Sci. Technol. 15(2), 136–143 (2000)CrossRefGoogle Scholar
  50. 50.
    McClean, S.I.: Data mining and knowledge discovery. Encyclopaedia of Physical Science and Technology 4(1), 229–246 (2002)Google Scholar
  51. 51.
    Modarressi, A.R., Mohan, S.: Control and management in next-generation networks: challenges and opportunities. IEEE Commun. Mag. 38(10), 94–102 (2000)CrossRefGoogle Scholar
  52. 52.
    Muller, C., Magill, E.H., Prosser, P., Smith, D.G.: Artificial intelligence in telecommunications. In: IEEE GLOBECOM 1993, pp. 883–887. (1993)Google Scholar
  53. 53.
    Nguyen, T.T.T., Armitage, G.: A survey of techniques for internet traffic classification using machine learning. IEEE Commun. Surveys Tutorials 10(4), 56–76 (2008)CrossRefGoogle Scholar
  54. 54.
    Open systems interconnection (OSI) Common Management Information Protocol: specification. ITU-T Recommendation X.711 (1997)Google Scholar
  55. 55.
    Parakhine, A., O’Neill, T., Leaney, J.: Application of Bayesian Networks to Architectural Optimisation. In: IEEE International Conference on Engineering of Computer-Based Systems, pp. 37–44 (2007)Google Scholar
  56. 56.
    Phillips, I., Parish, D., Sandford, M., Bashir, O., Pagonis, A.: Architecture for the management and presentation of communication network performance data. IEEE Trans. Instrum. Meas. 55(3), 931–938 (2006)CrossRefGoogle Scholar
  57. 57.
    Pras, A., Schoenwaelder, J., Burgess, M., Festor, O., Perez, G.M., Stadler, R., Stiller, B.: Key research challenges in network management. IEEE Commun. Mag. 45(10), 104–110 (2007)CrossRefGoogle Scholar
  58. 58.
    Prieto, A.G., Stadler, R.: Adaptive Distributed Monitoring with Accuracy Objectives. In: ACM SIGCOMM Workshop on Internet Network Management (INM 06), pp. 65–70. (2006)Google Scholar
  59. 59.
    Qi, J., Wu, F., Li, L., Shu, H.: Artificial intelligence applications in the telecommunications industry. Expert Syst. 24(4), 271–291 (2007)CrossRefGoogle Scholar
  60. 60.
    Samaan, N., Karmouch, A.: Towards Autonomic Network Management: an Analysis of Current and Future Research Directions. IEEE Commun. Surveys Tutorials 11(3), 22–36 (2009)CrossRefGoogle Scholar
  61. 61.
    Sasisekharan, R., Seshadri, V., Weiss, S.M.: Data mining and forecasting in large-scale telecommunication networks. IEEE Expert 11(1), 37–43 (1996)CrossRefGoogle Scholar
  62. 62.
    Sohail, S., Khanum, A.: Simplifying network management with fuzzy logic. In: IEEE International Conference on Communications (ICC 2008), pp. 195–201 (2008)Google Scholar
  63. 63.
    Spiegelhalter, D.J., Lauritzen, S.L.: Sequential updating of conditional probabilities on directed graphical structures. Networks, Special Issue on Influence Diagrams 20(5), 579–605 (1990)zbMATHMathSciNetGoogle Scholar
  64. 64.
    Spirtes, P., Glymour, C., Scheines, R.: Causation, Prediction, and Search. 2nd edn. MIT Press, (2001)zbMATHGoogle Scholar
  65. 65.
    Steck, H.: Constrained-based structural learning in Bayesian networks using finite data sets. Ph.D. thesis, Department of Informatics, Technical University Munich (2001)Google Scholar
  66. 66.
    Strassner, J., Menich, B.J.: Philosophy and methodology for knowledge discovery in autonomic computing systems. In: International Workshop Database and Expert Systems Applications, pp. 738–743 (2005)Google Scholar
  67. 67.
    Sun, S., Zhang, C., Yu, G.: A bayesian network approach to traffic flow forecasting. IEEE Transactions on Intelligent Transportation Systems 7(1), 124–132 (2007)Google Scholar
  68. 68.
    Sun, Y.T., Tsang, K.F., Tung, H.Y., Lam, K.L., Ko, K.T.: QoS prediction for High Speed Packet Access Networks. In: IEEE Consumer Communications and Networking Conference, pp. 788–789 (2008)Google Scholar
  69. 69.
    Tele Management Forum : NGOSS and eTOM overview. http://www.itarchitects.ca/whitepaper/TeleManagementForum/NGOSSandeTOM.pdf (2008). (Last accessed : May 2012)
  70. 70.
    TMN Management Functions. ITU-T Recommendation M.3400 (2000)Google Scholar
  71. 71.
    Tong, H., Brown, T.X.: Reinforcement Learning for Call Admission Control and Routing under Quality of Service. Mach. Learn. 49(2-3), 111–139 (2002)CrossRefzbMATHGoogle Scholar
  72. 72.
    Waldbusser, S., Cole, R., Kalbfleisch, C., Romascanu, D.: Introduction to the Remote Monitoring (RMON) Family of MIB Modules. In: RFC 3577, IETF (2003)Google Scholar
  73. 73.
    Williams, N., Zander, S., Armitage, G.: A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification. SIGCOMM Comput. Commun. Rev. 36(5), 5–16 (2006)CrossRefGoogle Scholar
  74. 74.
    Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques. 2nd edn. Morgan Kaufmann Series, CA, USA (2005)Google Scholar
  75. 75.
    Wu, J., Zhou, J., Yan, P., Wu, M.: A study on network fault knowledge acquisition based on support vector machine. In: International Conference on Machine Learning and Cybernetics, pp. 3893–3898 (2005)Google Scholar
  76. 76.
    Yang, Y., Webb, G., Wu, X.: Discretization methods. In: Maimon, O., Rokach, L. (eds) Data Mining and Knowledge Discovery Handbook., pp. 113–130. Springer, Berlin (2005)CrossRefGoogle Scholar
  77. 77.
    Zander, S., Nguyen, T., Armitage, G.: Automated traffic classification and application identification using machine learning. In: IEEE Conference on Local Computer Networks, pp. 250–257 (2005)Google Scholar
  78. 78.
    Zhang, R., Bivens, A.: Comparing the use of Bayesian networks and neural networks in response time modeling for service-oriented systems. In: ACM Workshop on Service-Oriented Computing Performance, SOCP 2007, pp. 67–74 (2007)Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Abul Bashar
    • 1
    Email author
  • Gerard Parr
    • 2
  • Sally McClean
    • 2
  • Bryan Scotney
    • 2
  • Detlef Nauck
    • 3
  1. 1.College of Computer Engineering and SciencesPrince Mohammad Bin Fahd UniversityAl-KhobarSaudi Arabia
  2. 2.School of Computing and Information EngineeringUniversity of UlsterColeraineUK
  3. 3.Service and OperationsBT TechnologyIpswichUK

Personalised recommendations