Automated Generation of Knowledge Plane Components for Multimedia Access Networks Steven Latr´ e 1 , Pieter Simoens 1 , Wim Van de Meerssche 1 , Bart De Vleeschauwer 1 , Filip De Turck 1 , Bart Dhoedt 1 , Piet Demeester 1 , Steven Van den Berghe 2 , and Edith Gilon-de Lumley 2 1 IBBT - IBCN, Department of Information Technology, Ghent University, Belgium Gaston Crommenlaan 8/201, 9050 Gent, Belgium Tel.: +32 9 33 14 981; Fax: +32 9 33 14 899 Steven.Latre@intec.ugent.be 2 Alcatel-Lucent Bell Labs, Copernicuslaan 50, B-2018 Antwerpen, Belgium Abstract. The management of Quality of Experience (QoE) in the ac- cess network is largely complicated by the wide range of offered services, the myriad of possible QoE restoring actions and the increasing hetero- geneity of home network configurations. The Knowledge Plane is an au- tonomic framework for QoE management in the access network, aiming to provide QoE management on a per user and per service basis. The Knowledge Plane contains multiple problem solving components that determine the appropriate restoring actions. Due to the wide range of possible problems and the requirement of being adaptive to new services or restoring actions, it must be possible to easily add or adapt problem solving components. Currently, generating such a problem solving com- ponent takes a lot of time and needs manual tweaking. To enable an automated generation, we present the Knowledge Plane Compiler which takes a service management objective as input, stating available moni- tor inputs and relevant output actions and determines a suitable neural network based Knowledge Plane incorporating this objective. The archi- tecture of the compiler is detailed and performance results are presented. 1 Introduction In today’s broadband access networks, new added value services such as Broad- cast TV, Video on Demand (VoD) and mobile thin clients are introduced. Each of these services has large service demands: they often require a considerable amount of bandwidth and only tolerate a minimum amount of packet loss, delay and jitter. In order to meet these demands, current access networks are ad- vancing from a best-effort packet delivery to a triple-play service delivery, where the Quality of Experience (QoE: the quality as perceived by the end user) is of prime importance. Several factors are complicating the QoE management. First, the type of degradation due to network anomalies is highly dependent on the service type and the current network status. Furthermore, a myriad of tech- niques has been deployed in the access network, such as VLANs with bandwidth S. van der Meer, M. Burgess, and S. Denazis (Eds.): MACE 2008, LNCS 5276, pp. 50–61, 2008. c  Springer-Verlag Berlin Heidelberg 2008