Quantifying and Predicting Residential Building Flexibility Using Machine Learning Methods
This addresses the need for grid operators to manage residential building flexibility, but it is incremental as it extends existing methods from commercial to residential buildings.
The paper tackled the problem of quantifying and predicting flexibility in residential buildings for grid support by proposing power and energy flexibility metrics and testing machine learning models, with LSTM achieving the best performance, predicting power flexibility up to 24 hours ahead with an average error of about 0.7 kW.
Residential buildings account for a significant portion (35\%) of the total electricity consumption in the U.S. as of 2022. As more distributed energy resources are installed in buildings, their potential to provide flexibility to the grid increases. To tap into that flexibility provided by buildings, aggregators or system operators need to quantify and forecast flexibility. Previous works in this area primarily focused on commercial buildings, with little work on residential buildings. To address the gap, this paper first proposes two complementary flexibility metrics (i.e., power and energy flexibility) and then investigates several mainstream machine learning-based models for predicting the time-variant and sporadic flexibility of residential buildings at four-hour and 24-hour forecast horizons. The long-short-term-memory (LSTM) model achieves the best performance and can predict power flexibility for up to 24 hours ahead with the average error around 0.7 kW. However, for energy flexibility, the LSTM model is only successful for loads with consistent operational patterns throughout the year and faces challenges when predicting energy flexibility associated with HVAC systems.