SMU Data Science Review
Abstract
Due to the recent power events in Texas, power forecasting has been brought national attention. Accurate demand forecasting is necessary to be sure that there is adequate power supply to meet consumer's needs. While Texas has a forecasting model created by the Electricity Reliability Council of Texas (ERCOT), constant efforts are required to ensure that the model stays at the state-of-the-art and is producing the most reliable forecasts possible. This research seeks to provide improved short- and medium-term forecasting models, bringing in state-of-the-art deep learning models to compare to ERCOT’s forecasts. A model that is more accurate than ERCOT’s own models during certain time periods was found. To have the most accurate energy forecasts in Texas, it is recommended that ERCOT investigate using different models in their Coast, Far West, North, North Central and West zones specifically. No models produced in this analysis accurately predicted the actual load that the state experienced during Winter Storm Uri due to the predicted load exceeding the practical grid capacity given the extreme weather. Synthetic data that simulates these types of extreme weather events could aid in training models for prediction in the future.
Recommended Citation
Eysenbach, Joshua; Franklin, Bodie; Larsen, Andrew J.; and Lindsey, Joel
(2021)
"Predicting Power Using Time Series Analysis of Power Generation and Consumption in Texas,"
SMU Data Science Review: Vol. 5:
No.
3, Article 5.
Available at:
https://scholar.smu.edu/datasciencereview/vol5/iss3/5
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Included in
Data Science Commons, Longitudinal Data Analysis and Time Series Commons, Oil, Gas, and Energy Commons
