Zgadzam się
Nasza strona zapisuje niewielkie pliki tekstowe, nazywane ciasteczkami (ang. cookies) na Twoim urządzeniu w celu lepszego dostosowania treści oraz dla celów statystycznych. Możesz wyłączyć możliwość ich zapisu, zmieniając ustawienia Twojej przeglądarki. Korzystanie z naszej strony bez zmiany ustawień oznacza zgodę na przechowywanie cookies w Twoim urządzeniu.
The managers of the telecommunication infrastructure face the challenge of detecting
and removing anomalies in the area of energy consumption. New technologies such as smart meters
present new possibilities for the control and optimization of energy consumption. The aim
of the article is to present the framework of a tool for the detection of anomalies related to energy consumption. The developed multi-criteria system for anomaly detection (MSFAD) consists of three methods: time series prediction with Particle Swarm Optimization (PSO), categorization based on absolute energy consumption and segmentation with the use of relative changes in energy consumption. The framework was tested on the energy consumption logs received from a telecommunications company. The analyses show that combining these methods may lead to improvedfeedback and increase the number of anomalies detected. That, in turn, would allow for a faster response, and increase the quality of the services provided
