研究目的
Developing a new islanding detection method with the help of machine learning and signal processing technique to ensure proper remote monitoring of the grid integrated photovoltaic (PV) system.
研究成果
An islanding detection technique is developed with the help of machine learning algorithm. The training accuracy is obtained to be 97.9% for 16.9 seconds of training time. The fault is detected within 0.2 seconds when checked with unknown data. The obtained results are better than conventional methodology results.
研究不足
The paper does not explicitly mention the limitations of the research.
1：Experimental Design and Method Selection:
A simulation of 1kW grid connected PV system is performed. Signals such as voltage, current and frequency are recorded at point of common coupling (PCC). Features of recorded signals are extracted using wavelet transformation. The extracted features are used to form an islanding scenarios matrix. The matrix is further utilized to train a classifier using machine learning algorithm.
2：Sample Selection and Data Sources:
The data is collected from the simulation of the grid connected PV system.
3：List of Experimental Equipment and Materials:
Not explicitly mentioned.
4：Experimental Procedures and Operational Workflow:
The process involves recording signals at PCC, extracting features using wavelet transformation, forming an islanding scenarios matrix, and training a classifier.
5：Data Analysis Methods:
The classifier's performance is evaluated based on training accuracy and training time.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
