An algorithm for practical power curve estimation of wind turbines

Abstract

Practical power curve estimation is necessary for evaluating the actual power output of a wind farm; since a power curve provided by the wind turbine manufacture will be different with the actual power curve following several years of operation. It can be estimated using the collected power output data including wind power generation and wind speed. This data is commonly ill-distributed due to a noticeable number of outliers, which impose a serious bias to the estimation models obtained from this data. It introduces an interesting challenge in estimation of a power curve. In this paper, an intelligent algorithm is proposed for estimating a power curve using the measured data while modeling and bias errors, imposed to the estimation model by the outliners, are minimized. More specifically, this algorithm is designed based on the Statistical Analysis Software (SAS) programming software package in order to facilitate analyzing and managing big datasets of wind speed and wind power generation. The effectiveness and practical application of the proposed algorithm is demonstrated using a real-world dataset.