Abstract
Telecommunication networks are developed over many years (over 100 in the case of the UK) and buried underground. Creating and maintaining accurate inventories of the materials used in their construction is challenging, when these systems were implemented electronic records did not exist and large scale surveys are uneconomic and unreliable. A Bayesian model of the network structure is developed and it is shown how this can be used in combination with the telemetry derived from a DSL network to create estimates that repair the inventory records. This approach was evaluated using a physical investigation of a sample of network elements and these results are presented along with a discussion of the limitations of the approach that have been identified. This result was derived vs an inventory system of approximately 7 million entries and required data processed from approximately 130 Tb of telemetry an applied to over 2 million cable records. This technique is now used to deliver broadband services in the UK.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
POSTnote 494: UK Broadband Infrastructure, The Parliamentary Office of Science and Technology, May 2015. http://researchbriefings.files.parliament.uk/documents/POST-PN-0494/POST-PN-0494.pdf. Accessed July 2017
Bishop, C.M.: A new framework for machine learning. In: Zurada, J.M., Yen, G.G., Wang, J. (eds.) WCCI 2008. LNCS, vol. 5050, pp. 1–24. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-68860-0_1
Cyr, D., Gauthier, S., Etheridge, D.A., Kayahara, G.J., Bergeron, Y.: A simple Bayesian Belief Network for estimating the proportion of old-forest stands in the Clay Belt of Ontario using the provincial forest inventory. Can. J. For. Res. 40(3), 573–584 (2010)
Heckerman, D., Wellman, M.P.: Bayesian networks. Commun. ACM 38(3), 27–31 (1995)
Herbrich, R., Minka, T., Graepel, T.: TrueSkill™: a Bayesian skill rating system. In: Advances in Neural Information Processing Systems, pp. 569–576 (2007)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Representation and Reasoning Series. Morgan Kaufmann, San Mateo (1988). ISBN 0-934613-73-7
Steinder, M., Sethi, A.S.: Probabilistic fault localization in communication systems using belief networks. IEEE/ACM Trans. Netw. 12(5), 809–822 (2004)
Zhao, T., Nehorai, A.: Distributed sequential Bayesian estimation of a diffusive source in wireless sensor networks. IEEE Trans. Signal Process. 55(4), 1511–1524 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Ferguson, A., Thompson, S. (2017). Cable Belief Networks (Best Application Paper). In: Bramer, M., Petridis, M. (eds) Artificial Intelligence XXXIV. SGAI 2017. Lecture Notes in Computer Science(), vol 10630. Springer, Cham. https://doi.org/10.1007/978-3-319-71078-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-71078-5_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-71077-8
Online ISBN: 978-3-319-71078-5
eBook Packages: Computer ScienceComputer Science (R0)