Abstract
Traditionally, in cellular networks, troubleshooting experts have manually analyzed Key Performance Indicators (KPI), so that they could identify the cause of problems and fix them. With the emergence of Self-Organizing Networks, Self-Healing systems are designed to automate those troubleshooting tasks. With that aim, the behavior of the KPIs (i.e. their profile under normal and abnormal conditions) needs to be modeled. Since the behavior of the KPIs is network-dependent and it changes as the network evolves, their profile should be automatically defined and readjusted depending on the characteristics of the network. Therefore, in this letter, an automatic process to model the KPIs based on the real data taken from the network is proposed. In particular, this method is characterized by designing a pair of functions (named performance functions) from the statistical behavior of real data without requiring any information about the existence of faults (i.e. unsupervised learning). Results have shown the reliability and effectiveness of the proposed method in comparison to reference approaches.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
