Visible to the public Enhancing Security and Resilience of Bulk Power Systems via Multisource Big Data Learning

TitleEnhancing Security and Resilience of Bulk Power Systems via Multisource Big Data Learning
Publication TypeConference Paper
Year of Publication2017
AuthorsGuan, L., Zhang, J., Zhong, L., Li, X., Xu, Y.
Conference Name2017 IEEE Power Energy Society General Meeting
KeywordsBig Data, composability, feature extraction, machine learning, multisource big data, power system big data complexity, power system security, power system security and resilience, power system stability, privacy, pubcrawl, resilience, Resiliency, security and stability defense framework, Stability analysis

In this paper, an advanced security and stability defense framework that utilizes multisource power system data to enhance the power system security and resilience is proposed. The framework consists of early warning, preventive control, on-line state awareness and emergency control, requires in-depth collaboration between power engineering and data science. To realize this framework in practice, a cross-disciplinary research topic -- the big data analytics for power system security and resilience enhancement, which consists of data converting, data cleaning and integration, automatic labelling and learning model establishing, power system parameter identification and feature extraction using developed big data learning techniques, and security analysis and control based on the extracted knowledge -- is deeply investigated. Domain considerations of power systems and specific data science technologies are studied. The future technique roadmap for emerging problems is proposed.

Citation Keyguan_enhancing_2017