Statistical Learning for Optimal Energy Market Participation Under Uncertainty

Institute for Design of Advanced Energy Systems (IDAES) Grid Modeling

Grid operations incorporate decision-making processes on time scales covering 12 orders of magnitude:

Powergrid Timescales

Through the IDAES project, we are developing multiscale modeling capabilities that explicity integrate individual resource operational decisions and market clearing. This enables unique analysis capabilities:

  • Elucidate complex relationships between resource dynamics and market dispatch (with uncertainty, beyond price-taker assumption)
    • Compute expected revenues
    • Understand how resource bids impact market dispatch and prices
  • ​​​​​​​Guide conceptual design/retrofit to meet current and future power grid needs
    • ​​​​​​​Balance market revenue and long-term equipment health
    • Properly size hybrid systems/storage considering both detailed dynamics and sub-hourly markets​​​​​​​

Grid Modeling Integration

Probabilistic Forecasts for Multiscale Energy Prices

GP Price Forecasts

Gaussian Process (GP) has been widely used for regression and classification. An autoregressive method with GP regression for energy prices has been tailored for Day-ahead Market (DAM). The immediate prices are used as the inputs and historical price data is used to train the model. GP regression interfaces decision-making under uncertainty and energy market bidding naturally. One of the ongoing works is to develop forecasting techniques for faster market layers (e.g. Fifteen-minute Market (FMM)) combining the information gained in slower layers (DAM).

Stochastic Economic Model Predictive Control Framework for Market Participation

Energy Market EMPC

Related Presentations

Xian Gao*, Steven Atkinson and Alexander W. Dowling. How to Make Money in Dynamic Energy Markets: Uncertainty Modeling and Optimization Frameworks. AIChE Midwest Regional Conference, University of Illinois in Chicago, Chicago, IL, March 18, 2019.

Xian Gao, Steven Atkinson, and Alexander W. Dowling*. Uncertainty Quantification and Stochastic Programming Strategies for Energy Market Participation. AIChE Annual Meeting, Pittsburgh, PA, October 30, 2018. [link]

Alexander W. Dowling*, Steven Atkinson, and Xian Gao. Optimal Energy Storage Scheduling in Electricity Markets with Multiscale Uncertainty. SIAM Conference on Uncertainty Quantification, Garden Grove, CA. April 16, 2018.

Support from Oak Ridge Institute for Science and Education (ORISE) Graduate Fellowship (X. Gao) and Faculty Fellowship (A. W. Dowling) to participate in the Institute for Advanced Design of Energy Systems (IDAES).


DOE Logo


Dr. John Siirola, Sandia National Laboratories

Dr. Bernard Knueven, Sandia National Laboratories

The IDAES Team