Development Hybrid Model Deep Learning Neural Network (DL-NN) For Probabilistic Forecasting Solar Irradiance on Solar Cells To Improve Economics Value Added

Closed

Unit Three Kartini, Hariyati, Widi Aribowo, Ayusta Lukita Wardani

2022 2022 5th International Conference on Vocational Education and Electrical Engineering: The Future of Electrical Engineering, Informatics, and Educational Technology Through the Freedom of Study in the Post-Pandemic Era, ICVEE 2022 - Proceeding Conference paper Cited by 2

Abstract

A new hybrid deep convolutional neural network (CNN) method for efficient probabilistic forecasting solar irradiance approach is proposed for research to accurately quantify of solar irradiance from solar cell systems. Distinguished from combination models, a Deep Convolutional Learning Neural Network optimization model with a multilayer-based prediction model for solar irradiance in PV generation system is constructed based on a learning machine and features high reliability and computational efficiency. The proposed using deep convolutional neural network approach is validated through the proposed approach is validated through the studies on PV data from Indonesia. From the computation, the proposed hybrid Deep Convolutional Neural Network model using solar irradiance performs RMSE maximal of 12.1 W/m2 of solar irradiance. © 2022 IEEE.

Affiliations

Universitas Negeri Surabaya, Dept. Electrical Engineering, Surabaya, Indonesia

View full text (DOI) →