Tor Kvernvik

Subscriber classification within telecom networks utilizing big data technologies and machine learning

This paper describes a scalable solution for identifying influential subscribers in for example telecom networks. The solution estimates one weighted value of influence out of several Social Network Analysis(SNA) metrics. The novel method for aggregation of several metrics utilizes machine learning to train models. A prototype solution has been implemented on a Hadoop platform to support scalability and to reduce hard ware cost by enabling the usage of commodity computers. The SNA algorithms have been adapted to efficiently execute on the MapReduce distributed platform. The prototype solution has been tested on a Hadoop cluster. The tests have verified that the solution can scale to support networks with millions of subscribers. Both real data from a telecom network operator with 2.4 million subscribers and synthetic data for networks up to 100 million subscribers have been used to verify the scalability and accuracy of the solution. The correlation between metrics have been analyzed to identify the information gain from each metric.

Using the Policy Control system as an auxiliary tool to improve the Service Assurance Process in Telecommunication Networks

Telecommunication networks are shifting their role from networks optimized for circuit switched voice into IP-based multi service networks. Doing so enables the delivery of more feature-rich services, such as voice over IP (VoIP), streaming, push to talk (PoC) and mobile TV. Along with this change in network utilization, the infrastructure is also changing, to be able to deliver new and emerging services, as well as existing services, over different access technologies. These access technologies and services will require new tools and methods that are capable of monitoring operation in an efficient and automated manner. Service Assurance is especially important in this context and can be defined as a guarantee that services will be provided according to the expectations of the end-user. This paper shows how the policy control system can be used to enhance and automate the service assurance process without any major impacts on existing network architectures or functionalities. Information dynamically created in the policy control system is used to derive Key Performance Indicators for each media component in a service which are used to monitor and ensure the quality of the service. The benefits of using the policy control system compared to other methods (briefly described) are also explained. The process described in this paper follows the enhanced Telecom operations map (eTom) [1] guidelines for providing service assurance.