A data-driven approach for development of a virtual wind-speed sensor for wind turbines is presented. The virtual wind-speed sensor is built from historical wind-farm data by data-mining algorithms. Four different data-mining algorithms are used to develop models using wind-speed data collected by anemometers of various wind turbines on a wind farm. The computational results produced by different algorithms are discussed. The neural network (NN) with the multilayer perceptron (MLP) algorithm produced the most accurate wind-speed prediction among all the algorithms tested. Wavelets are employed to denoise the high-frequency wind-speed data measured by anemometers. The models built with data-mining algorithms on the basis of the wavelet-transformed data are to serve as virtual wind-speed sensors for wind turbines. The wind speed generated by a virtual sensor can be used for different purposes, including online monitoring and calibration of the wind-speed sensors, as well as providing reliable wind-speed input to a turbine controller. The approach presented in this paper is applicable to utility-scale wind turbines of any type. DOI: 10.1061/(ASCE)EY.1943-7897.0000035. (C) 2011 American Society of Civil Engineers.