Application of System Identification Methods in Cost Estimating for Renewable Energy Projects

The article presents an analysis of the applicability of system identification methods in cost estimation for renewable energy projects.The study is based on an interdisciplinary approach that combines engineering sciences, reliability theory, and applied energy economics.Particular attention is given to the comparison of Bayesian reliability models for wind turbines, predictive monitoring architectures, evolutionary algorithms for parametric identification in photovoltaics, and optimization strategies for the operation of energy storage systems.Modern methods are considered that enable the integration of technical data into financial and economic calculations, including forecasting of operating expenses, capital costs, and key investment metrics.The study identifies key interdependencies between the accuracy of engineering models and the reliability of investment forecasts, which is especially relevant under conditions of high market volatility.A comparative analysis has shown that the application of advanced algorithms reduces uncertainty in cost estimation and increases the reliability of payback calculations.Special attention is paid to the problems of data scarcity for certain technologies, the sensitivity of metaheuristic methods to noise, and the necessity of institutional support for the implementation of identification procedures in energy planning practices.The article proposes an original classification of applied models and substantiates the need for a comprehensive approach that combines engineering and economic data.This work will be useful for researchers in the field of renewable energy, cost estimation experts, design engineers, and investors focused on the development of sustainable energy strategies.