In this paper, learning algorithms are leveraged to advance power system protection. Advancements in power system protection have come in different forms such as the development of new control strategies and the introduction of a new system architecture such as a microgrid. In this paper, we propose two learning schemes to make accurate predictions and optimal decisions related to power system protection and microgrid control. First, we present a neural network approach to learn a classifier that can predict stable reconnection timings for an islanded sub-network. Second, we present a learning-based control scheme for power system protection based on the policy rollout. In the proposed scheme, we incorporate online simulation using the commercial PSS/e simulator. Optimal decisions are obtained in real time to prevent cascading failures as well as maximize the load served. We validate our methods with the dynamics simulator and test cases RTS-96 and Poland.


    Access

    Download


    Export, share and cite



    Title :

    Learning Schemes for Power System Protection


    Contributors:

    Publication date :

    2018-01-03



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629





    Organic protection schemes for modern helicopters

    Hyde, P.W. | Engineering Index Backfile | 1959


    Protection of aerodromes in planning schemes

    Brueton, B.F. | Engineering Index Backfile | 1937



    Aspects of lighting protection schemes for radomes

    Aked, A. / Powell, C.W. / Ryan, H.M. et al. | Tema Archive | 1985