AI-based fault recognition and classification in the IEEE 9-bus system interconnected to PV systems

PV(photovoltaic) systems have been deployed more in the recent years to support green energy generation. In the recent era, grid tied PV has been sparked by the emergence of the electricity market and offers an alternative solution to traditional fossil fuel-based electricity generation. A few of the potential impacts of solar PV on grid are false tripping of feeders, unwanted tripping, unnecessary islanding, and blind protection. In this research paper, different artificial intelligence techniques are tested in order to overcome the protection challenges. The PSCAD/EMTDC software package is used to analyze a section of the power system, and an algorithm has been constructed using Python v3.8 and MATLAB 2018. On an IEEE-9 BUS power system connected to a PV source, the Artificial Neural Network, Naive Bayes, Support Vector Machine, Random Forest, and Convolution Neural Network (CNN) algorithms are implemented to classify the faults. The suggested methods are proven effective for both in-zone and out-of-zone problems on power lines interconnected with solar park. The proposed techniques have been validated using total 16,320 internal and external fault cases with a wide range of system parameters alteration. In the proposed system, the effectiveness of several machine learning and deep learning techniques is compared. The obtained results demonstrate that CNN provides greater accuracy in the presence of a PV source, but at the same time, it is appropriate for a large number of data sets. The fault classification accuracy acquired is adequate and demonstrates the adaptability of the proposed approach.

光伏（Photovoltaic，PV）系统近年来部署规模持续扩大，以支撑绿色能源发电。电力市场的兴起推动了并网光伏的发展，其可作为传统化石燃料发电的替代方案。太阳能光伏对电网存在若干潜在影响，包括馈线误跳闸、非预期跳闸、不必要孤岛以及盲区保护等问题。针对上述电网保护挑战，本研究测试了多种人工智能技术。研究采用PSCAD/EMTDC软件包对部分电力系统进行建模分析，并基于Python 3.8与MATLAB 2018构建了相关算法。在接入光伏电源的IEEE 9节点电力系统上，本研究部署了人工神经网络、朴素贝叶斯、支持向量机、随机森林以及卷积神经网络（CNN）等算法以实现故障分类。实验证明，所提方法可有效解决太阳能电站互联线路的区内与区外故障问题。研究通过共计16320组内外故障案例，并结合多组系统参数调整场景，对所提技术进行了全面验证。本研究还对比了多种机器学习与深度学习技术的应用效果。实验结果表明，在接入光伏电源的场景下，卷积神经网络（CNN）具备更高的分类精度，且适用于大规模数据集。本次研究获得的故障分类精度符合工程要求，同时验证了所提方法的适配性。