Abstract
Abstract. This paper investigates the uncertainties resulting from different measure–correlate–predict (MCP) methods to project the power and energy yield from a wind farm. The analysis is based on a case study that utilises short-term data acquired from a lidar wind measurement system deployed at a coastal site in the northern part of the island of Malta and long-term measurements from the island's international airport. The wind speed at the candidate site is measured by means of a lidar system. The predicted power output for a hypothetical offshore wind farm from the various MCP methodologies is compared to the actual power output obtained directly from the input of lidar data to establish which MCP methodology best predicts the power generated. The power output from the wind farm is predicted by inputting wind speed and direction derived from the different MCP methods into windPRO® (https://www.emd.dk/windpro, last access: 8 May 2020). The predicted power is compared to the power output generated from the actual wind and direction data by using the normalised mean absolute error (NMAE) and the normalised mean-squared error (NMSE). This methodology will establish which combination of MCP methodology and wind farm configuration will have the least prediction error. The best MCP methodology which combines prediction of wind speed and wind direction, together with the topology of the wind farm, is that using multiple linear regression (MLR). However, the study concludes that the other MCP methodologies cannot be discarded as it is always best to compare different combinations of MCP methodologies for wind speed and wind direction, together with different wake models and wind farm topologies.
Highlights
The measure–correlate–predict (MCP) methodology introduces uncertainty due to its inherent statistical nature
All normalised mean-squared error (NMSE), normalised mean absolute error (NMAE) and percentage errors in the overall energy yield are shown in the following tables
These charts are computed from the wind speed and direction which are predicted by using the multiple linear regression (MLR), artificial neural networks (ANNs), decision trees (DTs) and support vector regression (SVR) MCP methodologies
Summary
The measure–correlate–predict (MCP) methodology introduces uncertainty due to its inherent statistical nature. This study uses the same wind data for the year 2016 to construct the MCP models This time the prediction is carried out for both wind speed and wind direction. Wind speed and direction are predicted for the period June– December 2015 This is done for the different MCP models. The NMAE, the NMSE and the percentage error in the overall energy yield are compared for the various methodologies and wind farm topologies. This is a study about the uncertainties introduced by the various statistical methods, which are further complicated by the wind farm layout.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
