Energy traders make profits (or incur losses) by buying and selling energy. To guide their trading, they use software models and weather forecasting to make predictions about the future prices of all forms of energy. Public utilities generate or buy electricity to distribute to their customers and, to keep costs low, they forecast the cost of power from multiple sources to adjust their portfolio accordingly.
In the Pacific Northwest, hydroelectric power represents 50-60% of generated electricity, making water supply forecasts more important there than other regions in the U.S. Most organizations that trade power in the Pacific Northwest use the U.S. government’s deterministic forecast called the Single Trace Procedure (STP) to inform trade decisions related to hydropower production.
Researchers in RTI’s Center for Water Resources have developed a “forecast of the forecast” of the STP. While the current STP is released only once a week, RTI’s STPredict offers daily forecasts that give traders the ability to anticipate changes to the STP before the official forecast is available. We have also developed our own forecast for the Columbia Basin, the RTI-Forecast. This is a forecast of reservoir inflows with improved accuracy, which can be distributed to customers at timely intervals, offering strategic value for improved financial decisions.
Both forecasts are developed from a combination of classic hydrological forecast models and techniques in combination with a Recurrent Neural Network (RNN) to refine forecast outputs. The RNN component improves the fit of the forecast based on user-defined statistical metrics and “learning” from a historical training data set. During development, a validation period was run to assess the performance of a forecast based on a data set that the model did not train from to mimic a real-time system.
The STPredict is trained to forecast the changes in the NWRFC STP, while the RTI-Forecast is trained to forecast actual observed inflows, both over an approximate 10-year training period. These forecast models are continuously retrained and improved over time with the addition of new data.
- Two daily forecasts (STPredict and RTI’s CBF) for four locations – Grand Coulee, The Dalles, Lower Granite and Chief Joseph
- Forecasts based on historical simulated accuracy and comparisons to forecast and observed inflows
- Continuously improved accuracy through the integration of machine learning