Mid-Term Load Forecasting in a Data Center-Dense Region: A Case Study of Texas

In this study, we consider mid-term load forecasting which is essential for energy infrastructure planning and investment. This study focuses on the Texas power grid, where electricity consumption has surged due to rising industrial activity and rapid data center expansion. Based on an extensive exploratory data analysis, we identify key characteristics of monthly electricity demand in Texas, including an accelerating upward trend, strong seasonality, and temperature sensitivity. In response, we propose a regression-based forecasting model that incorporates a carefully designed set of input features, including a nonlinear trend, lagged demand variables, a seasonality-adjusted month variable, average temperature of a representative area, and calendar-based proxies for industrial activity. The model is trained on monthly data from 2013 to 2023 and tested in 2024. Comparative experiments against benchmarks including Holt-Winters, SARIMA, Prophet, RNN, LSTM, Random Forest, LightGBM, and XGBoost, show that the proposed model achieves superior performance with a mean absolute percentage error of approximately 2%. The results indicate that a well-structured regression approach can effectively outperform several advanced machine learning methods in mid-term load forecasting.