Research on Integrated Data Acquisition Method of wind Power Generation based on Deep Learning

• Published in: 2020 IEEE International Conference on Industrial Application of Artificial Intelligence (IAAI) pp. 481 - 485
• Main Authors: Qu, Ming-Fei, Ma, Dong-Bao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 25.12.2020
• Subjects: computerised instrumentation; current sensor; data acquisition; Data filling; Data integration acquisition; data redundancy; deep learning; deep learning (artificial intelligence); direction meter; DTS tool; electric current measurement; electric sensing devices; Filling; integrated acquisition method; integrated collection method; integrated data acquisition method; missing data integration; power engineering computing; Redundancy; solar power data integration; solar power generation data; SQL; SQL Server 2008; velocity measurement; voltage measurement; voltage sensor; wind power generation; wind power plants; Wind speed; wind speed meter
• DOI: 10.1109/IAAI51705.2020.9332835

The traditional integrated collection method of power generation data uses analog separation components, which are subject to many interference factors of charging and discharging, resulting in the problems of redundancy and data loss in the integrated collection of data. In order to solve the above problems, this paper studies the integrated data acquisition method of wind power generation based on deep learning. Use current sensor, voltage sensor, wind speed and direction meter and other sensing devices to collect data in the process of wind and solar power generation, and use SQL Server 2008 to establish a database to store the collected wind and solar power data. On this basis, deep learning is used to fill the missing data in the database, and then DTS tool is used to complete the data integration after filling. Through comparison experiments with traditional methods, it can be seen that the integrated acquisition method based on deep learning can effectively reduce data redundancy and lack, and has better reliability.