Visual Query Method for Large Blackouts Based on Knowledge Graph

Large blackouts are inevitable and happen from time to time. At present, a large amount of data about large blackouts is published on the Internet. Though many outstanding works have achieved great success for analysis of the reasons. How to process large scale data in Chinese on the internet for reason analysis is still a great challenge. To tackle this problem, we propose a visual query method for large blackouts based on the knowledge graph. The web crawler and knowledge graph have been employed in this paper. Firstly, a great amount of data in Chinese is crawled from the internet. Secondly, information about the event entity, relation and attribute can be extracted with a deep learning method. Thirdly, a large blackouts knowledge graph can be built from the information related to those events. Finally, visual queries of nodes, relations, and paths for large blackouts based on the knowledge graph are implemented. In this paper, a visual query method for large blackouts information, relations between different accidents, the path among entity nodes is present. it can help to analyze a large amount of data about large blackouts to improve the safety of the power system.

[1]  Evan Mills,et al.  An Insurance Perspective on U.S. Electric Grid Disruption Costs , 2016 .

[2]  Faizullah Khan,et al.  Blackout Avoidance through Intelligent Load Shedding in Modern Electrical Power Utility Network , 2018 .

[3]  B A Carreras,et al.  Complex dynamics of blackouts in power transmission systems. , 2004, Chaos.

[4]  Cui Tao,et al.  Constructing Biomedical Knowledge Graph Based on SemMedDB and Linked Open Data , 2018, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[5]  P. Hines,et al.  Large blackouts in North America: Historical trends and policy implications , 2009 .

[6]  Pierluigi Siano,et al.  Challenges and Opportunities of Load Frequency Control in Conventional, Modern and Future Smart Power Systems: A Comprehensive Review , 2018, Energies.

[7]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[8]  S. Talukdar,et al.  Trends in the history of large blackouts in the United States , 2008, 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century.

[9]  Shahriar Khan,et al.  Largest blackouts around the world: Trends and data analyses , 2016, 2016 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE).

[10]  Xiaocheng Feng,et al.  Effective LSTMs for Target-Dependent Sentiment Classification , 2015, COLING.

[11]  Pierluigi Siano,et al.  A Survey on Power System Blackout and Cascading Events: Research Motivations and Challenges , 2019, Energies.

[12]  Yang Xiang,et al.  X-A-BiLSTM: a Deep Learning Approach for Depression Detection in Imbalanced Data , 2018, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[13]  Mladen Kezunovic,et al.  Predicting weather-associated impacts in outage management utilizing the GIS framework , 2015, 2015 IEEE PES Innovative Smart Grid Technologies Latin America (ISGT LATAM).

[14]  James S. Thorp,et al.  Analysis of electric power system disturbance data , 2001, Proceedings of the 34th Annual Hawaii International Conference on System Sciences.

[15]  Zhiyong Feng,et al.  LSTM with sentence representations for document-level sentiment classification , 2018, Neurocomputing.