Telecom service providers are faced with an overwhelming flow of alarms, which makes good alarm classification and prioritisation very important. This paper first provides statistical analysis of data collected from a real-world alarm flow and then presents a quantitative characterisation of the alarm situation. Using data from the trouble ticketing system as a reference, we examine the relationship between mechanical classification of alarms and the human perception of them. Using this knowledge of alarm flow properties and trouble ticketing information, we suggest a neural network-based approach for alarm classification. Tests using live data show that our prototype assigns the same severity as a human expert in 50% of all cases, compared to 17% for a naïve approach.Keywords: communication system operations and management; neural network applications; alarm systems.Reference to this paper should be made as follows: Wallin, S., Leijon, V. and Landén, L. (2009) 'Statistical analysis and prioritisation of alarms in mobile networks', Int.

A s with any technology, it's important to focus management solutions on the users, even when the users are those providing a service. In that broader context, network management has three types of "users": network operators, which must earn money on their services, network service users (business and consumer), who pay for using services, and network administrators, who staff the network operations center. All three user types benefit from a well-thought-out management solution: operators increase their profits, service users get better service, and administrators streamline their workload. In short, the right network management solutions empower network operators to provide new services, maintain service quality, and manage billing and usage (TeleManagement Forum enhanced Telecom Operations Map, http:// www.tmforum.org/browse.aspx?catID=1647). By its nature, network management is a hierarchical, centralized function that puts the operator in control; therefore it makes sense to provide a centralized network management solution. Operators are under pressure to reduce network operating costs and provide new services at an increasing speed. These two requirements highlight the need for an effective, automated, network-management solution. To explore such a solution, we interviewed people in charge of large telecom network management centers and identified six challenges facing big telecom operators:

Telecom operators face an increasing need for service quality management to cope with competition and complex service portfolios in the mobile sector. Improvements in this area can lead to significant market benefits for operators in highly competitive markets. We propose an architecture for a service monitoring tool, including a time aware formal language for model specification. Using these models allows for increased predictability and flexibility in a constantly changing environment.

It is desirable to be able to combine ease of implementation of a network with the ability to analyze the properties of the network. In order to address this we present a MAC protocol where the network acts as a FIFO, and examine the resulting properties of the network using both a theoretical study of the waiting times and a simulation experiment. It turns out that this type of protocol would allows us to achieve real-time guarantees for an eventtriggered system, as well as controlled jitter for message delivery. Further, temporal composability, and how to design a system using FIFO networking, is discussed.