Improved Convolutional Neural Network and Heuristic Technique based on Forecasting and Sizing of Hybrid Renewable Energy System

Abstract

Aims & Objective: The fast depletion of fossil fuels and the growing awareness of environmental protection has become a concerning topic. Because of this fact, the researchers are working for a long time to generate electrical energy sources due to the intermittent nature of unconventional energy sources such as solar, wind geothermal, tidal, and biomass as a sustainable, cost-effective, and environmentally friendly alternative for conventional energy sources. These systems are interconnected and full-fill demands as well as energy storage, which subsequently formed a complex hybrid renewable energy system. Hence, forecasting of energy generation, sizing of equipment is essential for the economic feasibility of a complex hybrid system. Also necessary for the design analysis. Methodology: In this research article, the proposed Functional Link Convolutional Neural Network (FLCNN) is applied to forecast the energy generation from the hybrid solar and wind energy system. Also, the Jaya algorithm has been applied to find the optimal sizing of the solar and wind based hybrid renewable energy system. Results & Discussion: The proposed method is simple in design and implementation, and it also reduces computational complexity and time. The proposed FLCNN technique has been compared with various other Machine Learning (ML) methodology, such as Convolutional Neural Network (CNN), Random Forest (RF), and Xg-Boost. In sizing, Jaya is compared with other heuristic techniques such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Cat Swarm Optimization (CSO). Conclusion: The proposed FLCNN and Jaya optimization techniques successfully applied for tasks like energy forecasting and sizing of the renewable energy system.