Data-Driven Modeling of Auxiliary Consumption in Utility-Scale BESS

Accurately modeling the auxiliary power consumption of Battery Energy Storage Systems (BESSs) is increasingly important as grid-scale storage assets are becoming involved in electricity markets. In this paper, we develop a data-driven framework to characterize and forecast auxiliary consumption using operational data from a utility-scale BESS deployed in Italy. To capture the short-term thermal inertia of the system and the delayed response of the cooling systems, a set of predictors based on moving averages of power and ambient temperature is constructed. Two novel modeling approaches are proposed: a three-dimensional look-up table (LUT) representation that provides an interpretable characterization of system behavior, as well as a Random Forest (RF) regression model capable of capturing complex non-linear relationships between parameters. These are evaluated in comparison with a two-dimensional LUT from the literature. The analysis showed a superior performance of the RF model that comes at the cost of reduced interpretability and computational efficiency, while both proposed models outperform the literature-based LUT. Moreover, the impact of the number and type of predictors on model performance is systematically assessed, to shed light on what constitutes the requirements for a reasonably accurate estimation of the auxiliary systems. Finally, the concept of forecasting uncertainty for the temperature and day-ahead forecasting applicability for the auxiliary systems is investigated by introducing a persistence-based logic and an evaluation of the impact on the results. Overall, the study highlights the importance of explicitly modeling auxiliary consumption in grid-scale BESSs, proposes well-performing models for its estimation, and provides practical guidelines for their implementation in energy management and forecasting applications.