An Online-Learning Sequence Prediction Model for Grid Alarms
Zhenyuan Zhang, Jian Li, Jianhua Zhou, Peng Wang, Qi ping Huang · 2020 Asia Energy and Electrical Engineering Symposium (AEEES) · 2020
Smart grid devices emit quantities of alarm signals all the time. These alarms are related because of the physical relations of these devices. These relations make the sequences of grid alarms predictable. A sequence prediction model based on Markov property is proposed to predict grid alarm sequences. And the online learning strategy of this model is proposed to implement the real-time training and prediction on runtime. A set of grid alarm sequences is used to verify the effectiveness of the model. The result of this prediction model can assist the operation of smart grids.