Machine learning of electrical system behavior, and related systems, apparatuses, and methods

A controller of an electrical power system, the controller comprising:

• a data storage device configured to store model data indicating, for time points of a time period of operation of the electrical power system, a model load power for one or more loads of the electrical power system;
• and
• a processor operably coupled to the data storage device, the processor to:
• receive current data from one or more sensors of the electrical power system, the current data including a current load power for the one or more loads during a current time period corresponding to the time period of the model data stored by the data storage device;
• transform, during the current time period, the model data to fit an early portion of the model data to an early portion of the current data and generate predicted data for a later portion of the current time period based on how the early portion of the model data is fitted to the current data;
• control operation of one or more electrical components of the electrical power system based, at least in part, on the predicted data;
• and
• update, for use during future time periods, the model data by combining the model data with the current data.