The NRG-Pro engine is based on patented Big Data Machine Learning methods.

The NRG-Pro model monitors every meter separately, learns its underlying correlations, then uses unique information-theory based algorithms in order to decompose each meter's behavior into sub-series, which are then automatically modeled. 

The exclusive ‘problem decomposition’ feature visually presents the meters 'behavior rules' in a way that can be easily understood by decision makers. These rules enable to perform various types of 'what if' analysis, in a manner that is intuitive and comprehensible to engineers. 

After the modeling phase, the NRG-Pro engine monitors each meter, using distinctive anomaly detection algorithms, in order to detect early warnings of changes in the meters' patterns and behavior. Whenever such a deviation is detected, the NRG-Pro solution automatically identifies the irregularities' signature, and determines whether irregularities are caused due to tampering, meter malfunctioning or change in consumption patterns. If changes in consumption behavior are identified, the NRG-Pro engine remodels the meter, and a full self-learning automated mechanism is achieved, in order to provide an ongoing modeling process and guarantee the accuracy of forecasts, as well as the detection of anomalies at an early stage.