An Artificial Intelligence-Based Predictive Framework for Power Forecasting Using Nano-Electronic Sensors in Hybrid Renewable Energy System

This paper presents a novel Artificial Intelligence-based Predictive Framework for Power Forecasting in Hybrid Renewable Energy Systems employing Electronic Sensors in the quickly changing field of renewable energy systems. The research aims to address the challenges associated with predicting power generation in complex hybrid systems integrating various renewable sources and also make the better consideration of nanotechnology using various electronic sensors. The proposed framework provides an advanced technique for accurate and efficient power forecasting by fusing the Grey Wolf Optimizer (GWO) with Radial Basis Function Neural Network (RBFNN). By combining the strengths of RBFNN and GWO, it is possible to optimize the forecasting model’s parameters and improve its capacity to adjust to the changing needs of hybrid renewable energy systems. This method’s novelty lies in its ability to dynamically adjust to changing conditions, ensuring robust and precise power predictions. The initial step itself initiates with data collection for which certain nano-electronic devices are enrolled in the framework like sensors. The study includes a detailed explanation of the proposed method, emphasizing the collaborative strength of RBFNN and GWO in optimizing predictive models. Performance analysis includes thorough evaluations using accepted metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The outcomes highlight the suggested framework’s exceptional prediction powers and highlight its potential as a cutting-edge tool for power forecasting optimization in hybrid renewable energy systems. The present study provides significant contributions to the area by presenting a viable approach to increase the production of renewable energy’s dependability and efficiency.