Conformal Prediction for Enhanced Decision-Making of PV Power in Electricity Markets

We are happy to invite you to our next EI-ERIM-OR seminar. It will take place on campus, on Friday, April 19, 12:00-13:00 in room Langeveld 1.18. You can find the information about the talk below. Please let one of us (Ece, Olga, or Ruben) know if you would like to have a meeting with the speaker after the seminar or if you would like to attend the seminar online. 

Abstract

The increasing integration of solar photovoltaic (PV) power poses challenges for power system operation. Accurate forecasts of PV power are both financially beneficial for electricity suppliers and necessary for grid operators to optimize operation and avoid grid imbalances. This seminar will explore a framework utilizing conformal prediction (CP), an emerging probabilistic forecasting methodology, to assist decision-making for PV power market participants on the day-ahead market (DAM). It will begin by demonstrating how machine learning models can be employed to construct the point predictions based on weather forecasts. Subsequently, various variants of conformal prediction are introduced to quantify the uncertainty of these predictions. The seminar will then explore the application of several market bidding strategies, including Trust-the-forecast, worst-case, Newsvendor and expected utility maximization (EUM), to facilitate decision-making for market participants on the DAM using CP methods. Through a case study in the Netherlands, it will highlight how CP when combined with certain bidding strategies can lead to increased profit with minimal energy imbalance, outperforming classical probabilistic forecasting methods, such as linear quantile regression. The seminar will conclude by emphasizing the need to expand the framework to cover other short-term markets, namely intra-day markets.

About

Dr. ir. Tarek Alskaif is an assistant professor of energy informatics at the Information Technology group, Wageningen University. His primary research interests lie in energy forecasting, electricity markets and smart integration of distributed energy resources, using modelling, optimization, and artificial intelligence.