Method and system for unsupervised identification of behind-the-meter battery energy storage systems

A system for identifying behind-the-meter battery energy storage systems in a distribution system comprising distributed generators installed at a number of locations in the distribution system, the system comprising:

• one or more processors, and
• a non-transitory memory in communication with the one or more processors, the non-transitory memory including algorithmic modules executable by the one or more processors, the algorithmic modules comprising:
• a BESS location detection module configured to:
• obtain time series data of measured net power over a number of days via a respective meter at each location, and
• for each meter, process the time series data to detect a behind-the-meter battery energy storage system (BESS) at the corresponding location based on detection of flat intervals in which the measured net power is constant within a defined tolerance band for a minimum continuous period, the flat intervals indicative of BESS charge/discharge activity,
• a BESS sessions detection module executable if a BESS is detected, the BESS sessions detection module configured to use the time series data of the measured net power to detect a first state defined by intervals of net power consumption from a grid, a second state defined by intervals of net power fed into the grid, and a third state defined by flat intervals corresponding to BESS charge/discharge activity, and therefrom determining one or more eligible days that include a state change from the third state to the first state and a state change from the third state to the second state, and
• a BESS size evaluation module configured to evaluate a size of the detected BESS based on extracted intervals of BESS charge/discharge activity in the one or more eligible days.