Abstract

Accurate load forecasting is critical for efficient and reliable operations of the electric power system. A large part of electricity consumption is affected by weather conditions, making weather information an important determinant of electricity usage. Personal appliances and industry equipment also contribute significantly to electricity demand with temporal patterns, making time a useful factor to consider in load forecasting. This work develops several machine learning (ML) models that take various time and weather information as part of the input features to predict the short-term system-wide total load. Ablation studies were also performed to investigate and compare the impacts of different weather factors on the prediction accuracy. Actual load and historical weather data for the same region were processed and then used to train the ML models. It is interesting to observe that using all available features, each of which may be correlated to the load, is unlikely to achieve the best forecasting performance; features with redundancy may even decrease the inference capabilities of ML models. This indicates the importance of feature selection for ML models. Overall, case studies demonstrated the effectiveness of ML models trained with different weather and time input features for ERCOT load forecasting.

Index Terms

Deep learning, Electric power system, ERCOT, Feature selection, Long-term recurrent convolutional network, Long short-term memory, Machine learning, Neural network, Short term load forecasting, Texas power grid, Weather features.

Cite this paper:

Jonathan Yang, Mingjian Tuo, Jin Lu, and Xingpeng Li, “Analysis of Weather and Time Features in Machine Learning-aided ERCOT Load Forecasting”, Texas Power and Energy Conference, College Station, TX, USA, Feb. 2024.

Contributions:

Jonathan developed the codes, trained/evaluated the ML models, and analyzed the results. Mingjian provided guidance for ML structure and helped with code debugging. Jin processed and provided the ERCOT load data and the weather data. Xingpeng supervised this work and analyzed the results. All authors contributed to the paper writing and revisions.