Deep Learning for Power System Security Assessment

José-María Hidalgo Arteaga, Fiodar Hancharou, Florian Thams, Spyros Chatzivasileiadis

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    752 Downloads (Pure)


    Security assessment is among the most fundamental functions of power system operator. The sheer complexity of power systems exceeding a few buses, however, makes it an extremely computationally demanding task. The emergence of deep learning methods that are able to handle immense amounts of data, and infer valuable information appears as a promising alternative. This paper has two main contributions. First, inspired by the remarkable performance of convolutional neural networks for image processing, we represent for the first time power system snapshots as 2-dimensional images, thus taking advantage of the wide range of deep learning methods available for image processing. Second, we train deep neural networks on a large database for the NESTA 162-bus system to assess both N-1 security and small-signal stability. We find that our approach is over 255 times faster than a standard small-signal stability assessment, and it can correctly determine unsafe points with over 99% accuracy.
    Original languageEnglish
    Title of host publicationProceedings of IEEE Powertech 2019
    Number of pages6
    Publication date2019
    ISBN (Electronic)978-1-5386-4722-6
    Publication statusPublished - 2019
    Event13th IEEE PowerTech Milano 2019: Leading innovation for energy transition - Bovisa Campus of Politecnico di Milano, Milano, Italy
    Duration: 23 Jun 201927 Jun 2019
    Conference number: 13


    Conference13th IEEE PowerTech Milano 2019
    LocationBovisa Campus of Politecnico di Milano
    OtherPowerTech is the anchor conference of the IEEE Power & Energy Society (PES) in Europe
    Internet address


    • Convolutional neural networks
    • Deep learning
    • N-l security
    • Power system images


    Dive into the research topics of 'Deep Learning for Power System Security Assessment'. Together they form a unique fingerprint.

    Cite this