R&D NESTER PRESENTED SHORT TERM NET LOAD FORECASTING TOOL AT RENEWABLE ENERGY GRID INTEGRATION WEEK
R&D Nester was present in the 7th E-Mobility Power System Integration Symposium held in Copenhagen, Denmark, on 25 September 2023.
The Renewable Energy Grid Integration Week, organized by the German energy consulting company Energynautics GmbH, provides an international forum to discuss project experiences, innovative ideas, and present results from ongoing research. It aims to stimulate interdisciplinary thinking between wind/solar/hydrogen/e-mobility energy and power transmission industries as well as universities and to identify subjects requiring more research efforts.
Benefits include the high technical level in considering challenges, solutions and trends and combining international project experience with networking between industry and academia. Presentations are held by invited speakers from companies and leading research institutes as well as by workshop participants selected through a call for papers.
In this 7th edition, R&D Nester presented a paper titled "Short Term Net Load Forecasting Using Computational Intelligence Techniques".
The content of the paper presented was produced as part of R&D Nester's participation in the I-NERGY project founded by the European programme H2020. This initiative gathers 17 partners with the aim of supporting and developing new AI-based energy services and enhancing the service layer of the European AI on-demand platform (ai4europe.eu) in the energy sector.
The paper evaluates several forecasting methods, including an adaptive random forest method based on incremental learning incorporating a drift detector, a method based on a recurrent neural network using long short-term memory (LSTM), and a method based on an ensemble of models including decision trees (DT), support vector machines (SVM), extreme gradient boosting algorithms (XGBoost), and Lasso regressions.
The experiment was conducted using the net load data collected at the TSO-DSO interface in Portugal, where concept drift can be observed, possibly due to increasing integration of distributed energy resources behind the meter.
A series of experiments were conducted, exploring various scenarios, and an in-depth comparative analysis was then carried out.
For more information: