This research is carried out in collaboration with Vattenfall, to investigate the performance of a 76-turbine onshore wind farm. Since the start of operation, the wind farm has not been reaching P50 production estimates. Over the first five years of operation, there has been a big average gap between Annual Energy Production (AEP) and long-term AEP P50 estimates. This thesis gives insights into the physical causes of this apparent underperformance. Conventional 10 minutes averaged data as well as data with a higher resolution, named high-frequency data, has been available for this purpose. Therefore, the research question to be answered is: “Can the underlying physical causes for the underperformance of the Pen y Cymoedd wind farm be found by the use of 10 minutes averaged and/or high-frequency data?”.

Answers to this research question were found by following a set-up methodology, partially based on International Electrotechnical Commission (IEC) standards and with an added purpose for high-frequency data. This analysis was carried out for 14 turbines divided over 3 turbine clusters, with each turbine cluster accompanied by a MET mast, performing independent site measurements. The analysis only considers unwaked turbine sectors. After filtering and correlating the data sets, a cloud analysis and overall & directional performance analysis were carried out to understand the influence of the site as well as the influence of turbine controls to underperformance. The cloud analysis investigated deviating turbine behaviour, where the overall & directional performance analysis focused on the influence of the site on turbine performance.

The set-up methodology and analysis led to the following findings: on average, after data filtering, wind turbines perform 95% compared to the performance numbers the manufacturer delivers. There is a big difference in performance between the two turbine types at the site. Overall, the turbulence intensity (TI) class A turbines are performing better than the TI class B turbines. From the overall & directional performance analysis, bad performance (>-5% compared to the warranted performance) was seen for sectors with a complex orography, as well as for sectors with few elevation deviation or forestry. The cloud analysis revealed performance improvement potential for multiple turbine control regions. The high-frequency data gave additional unique insights in turbine performance, only visible in higher resolution. Moreover, it clarified turbine behaviour visible in 10 minutes averaged data.