Advanced Fault Detection analytics is used to detect anomalies in complex and repetitive systems. For instance, it could be used to anticipate failures in pump motors, drives or robotic arms. It leverages unsupervised machine learning techniques to model the expected normal behavior of a system. Then, it uses this model to detect anomalous behavior in order to anticipate a failure of the system. Advanced Fault Detection should be used when the system is supposed to be repetitive. It does not require the user to provide a dataset with past failures.

Building Energy Modeling analytics provides the ability to automatically identify the energy consumption model (a.k.a. 'Thermal signature’) of a Building. It can consider several drivers (e.g. the production for a plant, the number of people among others) that also influence the energy consumption.

Forecasting analytics makes future prediction based on past and present trends. It uses supervised machine learning techniques to learn the relationship between variables (input) at hand and the variable (the target) we want to forecast. For instance, this could be the forecast of a production line or the prediction of a daily building energy consumption. Forecasting should be used when the target variable is supposed to have an underlying pattern and when historical measurements are available.

The Virtual Sensor Analytics Component is a software sensor used to serve in place of a physical sensor for variables (called targets) that are too costly or impractical to measure. It leverages supervised machine learning techniques to learn the relationship between the target variable and a set of heterogeneous available variables (inputs). This component should be used when the target variable is supposed to have an underlying pattern and when historical measurements are available. These measurements could be data collected manually (sample) or data collected by a temporary sensor. 

The Virtual Sensor Fault Detection is used to detect faults in a variable of importance. This could be for instance to detect overheating in electrical assets or to detect thermal anomalies in HVAC process. It leverages supervised machine learning techniques to learn the relationship between the target variable, a set of heterogenous available variables (inputs), and to identify drift between the predicted value of the target and its actual variable. This component should be used when the target variable is supposed to have an underlying pattern and when measurements of the target variable are available.

Instant KWH, Historical KWH, Historical Water & Gas (by hour, day, month) and Temperature for all sites or individual sites in segments such as Eco District, Multifamily Residential, Social Landlords, and Small Business. 

Please note that you need to be pre-authorized by Schneider-Electric to use this API. Contact your Schneider Electric account manager for more information.