This study focuses on predicting the output power of wind turbines (WTs) using wind speed and WT operational characteristics. The main contribution of this work is a model identification method based on an adaptive neuro-fuzzy inference system (ANFIS) through multi-source data fusion on a moving window (MoW). The proposed ANFIS-MoW-based approach was applied to data in different time series windows, namely the very short-term, short-term, medium-term, and long-term time horizons. Data collected from a 30-MW wind farm on the west coast of Nouakchott (Mauritania) were used in the computational analysis. Compared to nonparametric models from the literature and models employing artificial intelligence machine learning techniques, the proposed ANFIS-MoW model demonstrated superior predictions for the output power of the WT with the fusion of very little data collected from different WTs. Moreover, for various time series windows (TSW) and meteorological conditions, additional benchmarking demonstrated that the ANFIS-MoW-based method outperformed five existing ANFIS-based models, including grid partition (ANFIS-GP), subtractive clustering (ANFIS-SC), fuzzy c-means clustering (ANFIS-FCM), genetic algorithm (ANFIS-GA), and particle swarm optimization (ANFIS-PSO). The results indicated that the suggested methodology is a promising soft-computing tool for accurately estimating the WT output power for WTs' sustainability through better control of their operation.Wind turbine; Time series horizon; Adaptive neuro-fuzzy inference system; Movingwindow approach; Power prediction