Intelligent performance management in the world of 5G

  • Date: –15:15
  • Location: Polacksbacken ITC 1111
  • Lecturer: Andreas Johnsson
  • Organiser: The Department of Information Technology
  • Contact person: Andreas Johnsson
  • Phone: 0737-600004
  • Docentföreläsning

The Department of Information Technology hereby invite all interested to a docent (associate professorship) lecture in subject Computer Science with specialisation in Computer Communication.

5G and networked systems beyond, including cloud infrastructures and Internet of Things, will support new applications and services in areas such as entertainment, transportation, industry, mining, and healthcare. Many existing and future services will be delivered over the network under strict service-level agreements, which translates into high requirements on management of networks and other infrastructure. Performance management and service assurance are especially challenging areas due to system complexity in terms of observability, scale, heterogeneity, and dynamicity.

This presentation will discuss fundamentals of performance management of distributed services with strict quality requirements. Focus will be on service assurance, which can be described as a continuous cycle, where the first step is to observe the environment and thereby produce accurate and timely measurement data from the network. In the second step the vast amount of data is analysed, using statistical methods such as machine learning, to produce insights and knowledge. Finally, in the third step an action is taken to ensure high-quality service delivery. The presentation ends with research challenges for performance management, with focus on machine learning as an approach for making management and network infrastructure more intelligent.

The lecture is an obligatory teaching test for those applying for admittance as docent (associate professor) and it should be possible for students and others with basic academic education in the relevant field to follow it. The lecture will last for 45 minutes and afterwards the audience may ask questions. The lecture will be given in English.