Identification Technology of Grid Monitoring Alarm Event Based on Natural Language Processing and Deep Learning in China

• Published in: Energies (Basel) Vol. 12; no. 17; p. 3258
• Main Authors: Bai, Ziyu, Sun, Guoqiang, Zang, Haixiang, Zhang, Ming, Shen, Peifeng, Liu, Yi, Wei, Zhinong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 23.08.2019
• Subjects: Access control; alarm information mining; Alarm systems; Algorithms; Artificial intelligence; Classification; Cognition & reasoning; convolutional neural network; Deep learning; Defects; Electric power; Fault diagnosis; Fuzzy sets; Identification; Identification methods; Integer programming; International conferences; Language; long short-term memory network; Methods; Monitoring; Monte Carlo simulation; Natural language processing; Neural networks; power grid monitoring; Short term; Systems stability; Word2vec; United States > US; China
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en12173258

Power dispatching systems currently receive massive, complicated, and irregular monitoring alarms during their operation, which prevents the controllers from making accurate judgments on the alarm events that occur within a short period of time. In view of the current situation with the low efficiency of monitoring alarm information, this paper proposes a method based on natural language processing (NLP) and a hybrid model that combines long short-term memory (LSTM) and convolutional neural network (CNN) for the identification of grid monitoring alarm events. Firstly, the characteristics of the alarm information text were analyzed and induced and then preprocessed. Then, the monitoring alarm information was vectorized based on the Word2vec model. Finally, a monitoring alarm event identification model based on a combination of LSTM and CNN was established for the characteristics of the alarm information. The feasibility and effectiveness of the method in this paper were verified by comparison with multiple identification models.