LAUSR

Wind energy installation numbers have witnessed a sharp increase in the recent past. Additionally, wind farms are seen as an effective and potent part of the interconnected power system. Significant variations in the wind speed pose a challenge for wind farm operators to provide accurate forecasts. In this manuscript, three hybrid wind farms, each comprising of wind turbines and battery energy storage systems, are located in the vicinity of each other and are assumed to deliver power to a utility grid. Fuzzy-based Multi-criteria decision-making techniques are applied to this cluster of three hybrid wind farms to determine the best strategy. Machine learning-based LSSVR method is utilized for wind speed forecasting and penalty cost estimation. Fuzzy TOPSIS and Fuzzy COPRAS evaluated and potential reversal of rankings is also explored. With a cumulative priority score of 0.4573 and 99.3 for dataset X1, both, fuzzy TOPSIS and fuzzy COPRAS respectively indicate that A3, that is, paying penalty for power borrowed from a neighboring wind farm is the best alternative for a hybrid wind farm. This study gives new insights into decision-making, specifically for hybrid wind farms.