Posters
Come meet the poster presenters to ask them questions and discuss their work
We would like to invite you to come and see the posters at our upcoming conference. The posters will showcase a diverse range of research topics, and will give delegates an opportunity to engage with the authors and learn more about their work. Whether you are a seasoned researcher or simply curious about the latest developments in your field, we believe that the posters will offer something of interest to everyone. So please join us at the conference and take advantage of this opportunity to learn and engage with your peers in industry and the academic community.
PO195: Neighbor-Based Estimation of Wind Turbine Power for Upgrade Performance Assessment
Qianling Wang, PhD Student, Universitat Politècnica de Catalunya (UPC)
Abstract
Quantifying marginal wind-turbine retrofit gains (typically 1%–3%) is challenging when true counterfactual measurements are unavailable, because side-by-side comparisons are inherently biased and long-horizon forecasting mod-els may drift. We propose Conv-TST, a convolution-augmented Transformer framework that reconstructs counterfactual power baselines from neighboring turbines. The model integrates a 1D CNN feature-extraction stem with a Trans- former encoder to capture local temporal patterns and long-range dependencies in SCADA and reanalysis inputs. Experiments on multi-year SCADA and ERA5 data from the Hill of Towie wind farm demonstrate improved baseline fidelity and prediction accuracy over strong benchmarks. A retrofit case study further indi-cates that most of the attributable gains concentrate in the 10–18 m/s wind-speed regime.
No recording available for this poster.
