QOS Monitoring and Fault Detection Using Call Detail Records - A Different Approach that has Come to Add Value

The purpose of this paper is to demonstrate an algorithm to monitor the QoS and, while monitoring, detect the occurrence of failures in wireless and wireline communication systems. It’s a new approach based on the analysis of data stored in Call Detail Records (CDR). Each time a call is made in a voice system, VoIP or PSTN, a detailed record is generated. Detail Records are tickets whose data provide information related to the system elements involved, such as time and duration of the call, phone types and numbers, SS7 signaling, etc. The tickets are generated and stored either in PSTN switches or in VoIP gateways. For VoIP systems the detail records are usually called IPDR (Internet Protocol Detail Record). As we have already mentioned, the algorithm works on the information stored in Detail Records. So, our main goal here is to show, analyze and classify this algorithm according to its performance and use.

[1]  Umeshwar Dayal,et al.  A data-warehouse/OLAP framework for scalable telecommunication tandem traffic analysis , 2000, Proceedings of 16th International Conference on Data Engineering (Cat. No.00CB37073).

[2]  Anne Rogers,et al.  Hancock: A language for analyzing transactional data streams , 2004, TOPL.

[3]  A. R. Kaye,et al.  Traffic monitoring in a network of PBXs , 1990, [Proceedings] GLOBECOM '90: IEEE Global Telecommunications Conference and Exhibition.

[4]  Wang Dong,et al.  A feature extraction method for fraud detection in mobile communication networks , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[5]  Maurizio Lenzerini,et al.  Data integration and warehousing in Telecom Italia , 1999, SIGMOD '99.

[6]  Lian Yan,et al.  Predicting customer behavior via calling links , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[7]  Eric Johnson,et al.  Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry , 2000, IEEE Trans. Neural Networks Learn. Syst..

[8]  Yizhak Idan,et al.  Discovery of fraud rules for telecommunications—challenges and solutions , 1999, KDD '99.

[9]  Philip Ginzboorg.  Seven comments on charging and billing , 2000, CACM.