Rodrigues Sandy, Mütter Gerhard, Ramos Helena Geirinhas, Morgado-Dias F
Instituto de Telecomunicacoes of the Instituto Superior Tecnico of the University of Lisbon, 1049-001 Lisbon, Portugal.
Laboratory for Robotics and Systems in Engineering (LARSyS), Madeira Interactive Technologies (M-ITI) and Institute and Interactive Technologies Institute (ITI), 9020-105 Funchal, Portugal.
Entropy (Basel). 2020 Feb 11;22(2):205. doi: 10.3390/e22020205.
Photovoltaic (PV) system energy production is non-linear because it is influenced by the random nature of weather conditions. The use of machine learning techniques to model the PV system energy production is recommended since there is no known way to deal well with non-linear data. In order to detect PV system faults, the machine learning models should provide accurate outputs. The aim of this work is to accurately predict the DC energy of six PV strings of a utility-scale PV system and to accurately detect PV string faults by benchmarking the results of four machine learning methodologies known to improve the accuracy of the machine learning models, such as the data mining methodology, machine learning technique benchmarking methodology, hybrid methodology, and the ensemble methodology. A new hybrid methodology is proposed in this work which combines the use of a fuzzy system and the use of a machine learning system containing five different trained machine learning models, such as the regression tree, artificial neural networks, multi-gene genetic programming, Gaussian process, and support vector machines for regression. The results showed that the hybrid methodology provided the most accurate machine learning predictions of the PV string DC energy, and consequently the PV string fault detection is successful.
光伏（PV）系统的能源生产是非线性的，因为它受到天气条件随机性的影响。由于目前尚无有效处理非线性数据的方法，因此建议使用机器学习技术对光伏系统的能源生产进行建模。为了检测光伏系统故障，机器学习模型应提供准确的输出。这项工作的目的是通过对四种已知可提高机器学习模型准确性的机器学习方法（如数据挖掘方法、机器学习技术基准测试方法、混合方法和集成方法）的结果进行基准测试，准确预测公用事业规模光伏系统六个光伏串的直流能量，并准确检测光伏串故障。本文提出了一种新的混合方法，该方法结合了模糊系统的使用和一个包含五个不同训练机器学习模型的机器学习系统的使用，这五个模型分别是回归树、人工神经网络、多基因遗传编程、高斯过程和支持向量机回归。结果表明，混合方法对光伏串直流能量提供了最准确的机器学习预测，因此光伏串故障检测成功。
