Better prediction tools for future solar and wind power are crucial to reducing the requirement for controlling energy associated with the conventional power facilities. For optimal power grid integrating of highly variable wind power output, a strong forecast is extremely crucial. In this part, we concentration on wind power for the near run projections and conduct a wind unification study in the western United States using data from the National Research Conducted by the university (NREL). Our approach derives functional connections directly from data, unlike physical systems that rely on exceedingly difficult differential calculus. By recasting the prediction problem as a regression problem, we investigate several regression methodologies such as regression models, k-nearest strangers, and regression algorithms. In our testing, we look at projections for specific machines along with power from the wind parks, proving that a classification algorithm for predicting short-term electricity generation is feasible.