We develop a Reinforcement Learning framework for the optimal management of the operation and maintenance of power grids equipped with prognostics and health management capabilities. Reinforcement learning exploits the information about the health state of the grid components. Optimal actions are identified maximizing the expected profit, considering the aleatory uncertainties in the environment. To extend the applicability of the proposed approach to realistic problems with large and continuous state spaces, we use Artificial Neural Networks (ANN) tools to replace the tabular representation of the state-action value function. The non-tabular Reinforcement Learning algorithm adopting an ANN ensemble is designed and tested on the scaled-down power grid case study, which includes renewable energy sources, controllable generators, maintenance delays and prognostics and health management devices. The method strengths and weaknesses are identified by comparison to the reference Bellman's optimally. Results show good approximation capability of Q-learning with ANN, and that the proposed framework outperforms expert-based solutions to grid operation and maintenance management.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    A reinforcement learning framework for optimal operation and maintenance of power grids



    Erscheinungsdatum :

    2019-01-01



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Optimal-Tolling Using Reinforcement Learning

    Chakravarty, Sumit / Tanveer, M. Hassan / Voicu, Razvan C. et al. | IEEE | 2024



    Optimal EV Fast Charging Station Deployment Based on a Reinforcement Learning Framework

    Zhao, Zhonghao / Lee, Carman K. M. / Ren, Jingzheng et al. | IEEE | 2023


    An IoT-Enabled Stochastic Operation Management Framework for Smart Grids

    Wang, Bo / Ma, Hengrui / Wang, Fei et al. | IEEE | 2023