A Novel Approach for Day-Ahead Hourly Building-Integrated Photovoltaic Power Prediction by Using Feature Engineering and Simple Weather Forecasting Service

• Published in: Energies (Basel) Vol. 16; no. 22; p. 7477
• Main Authors: Jeong, Jinhwa, Lee, Dongkyu, Chae, Young Tae
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.11.2023
• Subjects: Accuracy; Algorithms; Alternative energy sources; artificial neural network (ANN); building-integrated photovoltaic (BIIPV); Emission standards; Energy management systems; Energy resources; feature engineering; Machine learning; Neural networks; Radiation; Regression analysis; Renewable resources; sensitivity analysis; short-term prediction; Solar energy industry; Weather forecasting; weather forecasting service; South Korea

Although the accuracy of short-term prediction of building-integrated photovoltaics is essential to making an optimal decision on the management of the generated electricity, the weather forecasting service in many countries provides insufficient features for improving the prediction accuracy of the...