towards the future of the energy systems
About the Webinars
INESC TEC, through its Centre for Power and Energy Systems and the Energy cluster, has launched the Power and Energy Webinar Series initiative. In each webinar, a researcher from INESC TEC will present and discuss ideas, expected outcomes, or results regarding the energy systems of the future. In some webinars, external speakers will be invited. The expected duration of the webinar is between 45 minutes and 1 hour, depending on the format. Discussion between the speakers and the participants will be held in the last part of each webinar.
September 14, 5 PM (Portuguese time)
Carla Gonçalves & Ricardo Andrade
Data science applied to the electricity market and renewable energy forecasting
Carla Gonçalves, researcher of the Centre for Power and Energy Systems of INESC TEC
Forecasting Conditional Extreme Quantiles for Wind Energy
Probabilistic forecasting of distribution tails (i.e., quantiles below .05 and above .95) is challenging for nonparametric approaches since data for extreme events are scarce. A poor forecast of extreme quantiles can have a high impact in various power system decision-aid problems. An alternative approach more robust to data sparsity is extreme value theory (EVT), which uses parametric functions for modelling distribution’s tails. In this work, we apply conditional EVT estimators to historical data by directly combining gradient boosting trees with a truncated generalized Pareto distribution. The parametric function parameters are conditioned by covariates such as wind speed or direction from a numerical weather predictions grid. The results for a wind power plant located in Galicia, Spain, show that the proposed method outperforms state-of-the-art methods in terms of quantile score.
Ricardo Andrade, researcher of the Centre for Power and Energy Systems of INESC TEC
A Deep Learning Method for Forecasting Residual Market Curves
Forecasts of residual demand curves (RDCs) are valuable information for price-maker market agents since it enables an assessment of their bidding strategy in the market clearing price. This paper describes the application of deep learning techniques, namely long short-term memory (LSTM) network that combines past RDCs and exogenous variables (e.g., renewable energy forecasts). The main contribution is to build up on the idea of transforming the temporal sequence of RDCs into a sequence of images, avoiding any feature reduction and exploiting the capability of LSTM in handling image data. The proposed method was tested with data from the Iberian day-ahead electricity market and outperformed machine learning models with an improvement of above 35% in both root mean square error and Fréchet distance.
I want to participate
Webinar 2: Data science applied to the electricity market and renewable energy forecasting
After each webinar, the videos will be placed in this section.
"Distribution Grid Operation with Energy Storage and Smart-Transformers: Enabling Islanding" Clara Gouveia and Justino Rodrigues (July 23, 2020)
Send us an e-mail and we will contact you as soon as possible