Stefan Wallin

Magneto approach to QoS monitoring

Quality of Service (QoS) monitoring of end-user services is an integral and indispensable part of service management. However in large, heterogeneous and complex networks where there are many services, many types of end-user devices, and huge numbers of subscribers, it is not trivial to monitor QoS and estimate the status of Service Level Agreements (SLAs). Furthermore, the overwhelming majority of end-terminals do not provide precise information about QoS which aggravates the difficulty of keeping track of SLAs. In this paper, we describe a solution that combines a number of techniques in a novel and unique way to overcome the complexity and difficulty of QoS monitoring. Our solution uses a model driven approach to service modeling, data mining techniques on small sample sets of terminal QoS reports (from “smarter” end-user devices), and network level key performance indicators (N-KPIs) from probes to address this problem. Service modeling techniques empowered with a modeling engine and a purpose-built language hide the complexity of SLA status monitoring. The data mining technique uses its own engine and learnt data models to estimate QoS values based on N-KPIs, and feeds the estimated values to the modeling engine to calculate SLAs. We describe our solution, the prototype and experimental results in the paper.

Telecom Network and Service Management: An Operator Survey

It is hard to know which research problems in network management we should focus our attention on. To remedy this situation we have surveyed fifteen different telecom operators on four continents to gather some feedback on what they desire and expect from the network management research community. Their input forms a foundation for future directions in network management research, and provides us with valuable insight into what the most urgent problems are in industry.

Statistical analysis and prioritisation of alarms in mobile networks

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 naive approach.

Rethinking Network Management Solutions

Telecommunication network management solutions need to shift perspective from one of network element management to service management. Operators need a service view of their network, with automatic service-impact correlation. This requires some major changes in the underlying solutions: equipment vendors must improve the supplied management interfaces and network management solutions must implement a higher degree of automation and correlation with a service focus. One obstacle is the lack of models and formalism to describe topology and service structures

SALmon A Service Modeling Language and Monitoring Engine

To be able to monitor complex services and examine their properties we need a modeling language that can express them in an efficient manner. As telecom operators deploy and sell increasingly complex services the need to monitor these services increases. We propose a novel domain specific language called SALmon, which allows for efficient representation of service models, together with a computational engine for evaluation of service models. This working prototype allows us to perform experiments with full scale service models, and proves to be a good trade-off between simplicity and expressive power.

Chasing a Definition of Alarm

Alarm management has been around for decades in telecom solutions. We have seen various efforts to define standardised alarm interfaces. The research community has focused on various alarms correlation strategies. Still, after years of effort in industry and research alike, network administrators are flooded with alarms; alarms are suffering from poor information quality; and the costs of alarm integration have not decreased. In this paper, we explore the concept of ‘alarm’. We define ‘alarm’ and alarm-type concepts by investigating the different definitions currently in use in standards and research efforts. Based on statistical alarm data from a mobile operator we argue that operational and capital expenditures would decrease if alarm sources would apply to our alarm model.

Multi-Purpose Models for QoS Monitoring

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.

Rethinking network management: Models, data-mining and self-learning

Network Service Providers are struggling to reduce cost and still improve customer satisfaction. We have looked at three underlying challenges to achieve these goals; an overwhelming flow of low-quality alarms, understanding the structure and quality of the delivered services, and automation of service configuration. This thesis proposes solutions in these areas based on domain-specific languages, data-mining and self-learning. Most of the solutions have been validated based on data from a large service provider. We look at how domain-models can be used to capture explicit knowledge for alarms and services. In addition, we apply data-mining and self-learning techniques to capture tacit knowledge. The validation shows that models improve the quality of alarm and service models, and enables automatic rendering of functions like root cause correlation, service and SLA status, as well as service configuration. The data-mining and self-learning solutions show that we can learn from available decisions made by experts and automatically assign alarm priorities.

IPTV service modeling in Magneto networks

One of the main steps of service assurance is service monitoring using Key Performance Indicators (KPIs) and Service Level Agreements (SLAs). We show an approach for service modeling, first starting with an abstract service model that depends on the network. And then, we show how a corresponding model can be realized using a domain specific language. This solution is able to condense various sources of service model requirements into a condense formal and executable model including service decomposition and KPI aggregation. We have described this solution in the context of Magneto project and uses IPTV as a service in our description.

Telecom Alarm Prioritization Using Neural Networks

Telecom Service Providers are faced with an overwhelming flow of alarms. Network administrators need to judge which alarms to resolve in order to maintain the service quality. The problem is that it is hard to pick the most important alarms. Which alarms have the highest priority? A solution that automatically assigns priorities to alarms would increase the efficiency of Network Management Centers. We have prototyped a solution that uses neural networks to assign alarm priority. The neural network learns from network administrators by using the manually assigned priorities in trouble-tickets. Our tests are based on live-data from a large mobile service provider and we show that neural networks can learn to assign relevant priorities to 75% of the alarms.