Electricity smart metering systems generate volumes of data, which potentially may be exploited much beyond the consumed energy and its profiles provision to consumers. In addition to active energy, smart meters measure and deliver voltage, current, active/reactive power, and reactive energy readings. Seeking to utilize this data, the last five years in many scientific publications anomaly detection techniques dedicated to thefts, meter failures, grid status changes monitoring were studied intensively. This information is important both for energy providers and energy consumers, because it could lead to fast issues discovery and consequently their removal. For example, an increase of smart meter error may cause either consumer or provider financial losses due to incorrect metering. According to the metrological supervision regulations, the reverification period of smart meters is quite long (in Lithuania 12 years). Therefore, a non-compliant meter may stay in service for a long period. By continuous meter status monitoring using the offered methods, the anomalous situation could be discovered much faster. However, the most of the published techniques are based on assumptions that are difficult to meet in real life. To name a few the mandatory sum meter, its readings accumulation alongside with consumers’ meter readings, demand of smart meters establishment for all considered grid consumers, knowledge of grid topology and distribution line parameters can be mentioned. The project team brings together specialists in measurement, electrical power systems, electronic instrumentation and machine learning.
Project funding:
Projects funded by the Research Council of Lithuania (RCL), Projects carried out by researchers’ teams
Project results:
We plan to develop methods for anomaly detection using smart meter readings when distribution line parameters information is lacking, smart meter deployment is partial, some renewable energy sources are operated in the grid, and sum meter may be absent.
Period of project implementation: 2024-09-02 - 2027-08-31
Project coordinator: Kaunas University of Technology
