English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Wind energy resource assessment typically requires numerical models, but suchmodels are too computationally intensive to consider multi-year timescales.Increasingly, unsupervised machine learning techniques are used to identify asmall number of representative weather patterns to simulate long-termbehaviour. Here we develop a novel wind energy workflow that for the first timecombines weather patterns derived from unsupervised clustering techniques withnumerical weather prediction models (here WRF) to obtain efficient and accuratelong-term predictions of power and downstream wakes from an entire wind farm.We use ERA5 reanalysis data clustering not only on low altitude pressure butalso, for the first time, on the more relevant variable of wind velocity. Wealso compare the use of large-scale and local-scale domains for clustering. AWRF simulation is run at each of the cluster centres and the results areaggregated using a novel post-processing technique. By applying our workflow totwo different regions, we show that our long-term predictions agree with thosefrom a year of WRF simulations but require less than 2% of the computationaltime. The most accurate results are obtained when clustering on wind velocity.Moreover, clustering over the Europe-wide domain is sufficient for predictingwind farm power output, but downstream wake predictions benefit from the use ofsmaller domains. Finally, we show that these downstream wakes can affect thelocal weather patterns.  Our approach facilitates multi-year predictions of power output anddownstream farm wakes, by providing a fast, accurate and flexible methodologythat is applicable to any global region. Moreover, these accurate long-termpredictions of downstream wakes provide the first tool to help mitigate theeffects of wind energy loss downstream of wind farms, since they can be used todetermine optimum wind farm locations.

An unsupervised learning approach for predicting wind farm power and downstream wakes using weather patterns