Optimization of Integrated Steel Plant R

This paper addresses the challenge of assessing the feasibility of wind power plant projects at sites with insufficient or no local historic wind data, a common obstacle in the context of rapidly expanding wind energy investments driven by incentive schemes across Europe. Since reliable wind speed and direction data are crucial for the optimal selection, sizing, and layout of wind turbines, the lack of such data can lead to suboptimal investment decisions and economically unjustified projects. The study proposes a method for estimating the output power of a potential wind power plant by applying a cascade-correlation neural network to historical wind measurements from nearby or remote locations. The neural network is trained to infer wind characteristics at the target site based on these surrogate data, thereby enabling prediction of the plant’s output power in the absence of direct measurements. The validity of the proposed approach is evaluated by comparing the predicted output power with actual production data from an operational wind power plant. The results show a high degree of correlation between the estimated and measured outputs, demonstrating that the method provides a robust and practical tool for preliminary feasibility assessment of wind power projects where local wind data are scarce or unavailable.