Sequential topology recovery of complex power systems based on reinforcement learning

J Wu, B Fang, J Fang, X Chen, KT Chi - Physica A: Statistical Mechanics …, 2019 - Elsevier
recovery process. To mimic the dynamic process of sequential topology recovery, we propose
a novel recovery … cascading failures triggered during the recovery process, the latter which …

Network topology-traceable fault recovery framework with reinforcement learning

T Miyamoto, G Mori, Y Suzuki, T Otani - International Conference on …, 2021 - Springer
… configuration and topology is changed. To address the above issue, this paper proposes …
reinforcement learning-based fault recovery framework by applying the reinforcement learning (…

Network topology optimization via deep reinforcement learning

Z Li, X Wang, L Pan, L Zhu, Z Wang… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
… cost minimization and multi-layer recovery. Existing topology optimization works have
developed different algorithms to solve the network topology problem with different formulations, …

Multi-agent deep reinforcement learning based decision support model for resilient community post-hazard recovery

S Yang, Y Zhang, X Lu, W Guo, H Miao - Reliability Engineering & System …, 2024 - Elsevier
… deep reinforcement learning based approach to optimally decide the repair sequence to
ensure the resilient recovery of … and topology of the community networks; (3) explore transfer …

Coordinated topology attacks in smart grid using deep reinforcement learning

Z Wang, H He, Z Wan, Y Sun - IEEE Transactions on Industrial …, 2020 - ieeexplore.ieee.org
… of a deep Q-learning algorithm for topology attack, which is … reinforcement learning,”
IEEE Trans. Smart Grid, vol. 10, no. … /link recovery strategy of power grids based on q-learning

Deep reinforcement learning-based approach for autonomous power flow control using only topology changes

I Damjanović, I Pavić, M Puljiz, M Brcic - Energies, 2022 - mdpi.com
… a novel reinforcement learning (RL)-based approach for the secure operation of power system
via autonomous topology … Overloaded lines can be recovered after 50 min (10 timesteps). …

Exploring grid topology reconfiguration using a simple deep reinforcement learning approach

M Subramanian, J Viebahn… - 2021 IEEE Madrid …, 2021 - ieeexplore.ieee.org
… rated capacity are tripped immediately, and can be recovered after 50 minutes (10 time steps).
REINFORCEMENT LEARNING APPROACH The intention of this study is to apply a rather …

A distributed coverage hole recovery approach based on reinforcement learning for Wireless Sensor Networks

F Hajjej, M Hamdi, R Ejbali, M Zaied - Ad Hoc Networks, 2020 - Elsevier
… both the overall coverage and energy consumption while recovering Coverage Holes.
Therefore, the topology control scheme induced by our proposed approach outperforms other …

Resilience-based post disaster recovery optimization for infrastructure system via Deep Reinforcement Learning

H Liang, B Moya, F Chinesta, E Chatzi - arXiv preprint arXiv:2410.18577, 2024 - arxiv.org
… -disaster recovery of infrastructure systems by leveraging Deep Reinforcement Learning (DRL…
The system topology is represented adopting a graphbased structure, where the system’s …

A graph convolution network‐deep reinforcement learning model for resilient water distribution network repair decisions

X Fan, X Zhang, X Yu - Computer‐Aided Civil and Infrastructure …, 2022 - Wiley Online Library
recovery decision-support framework by integrating the graph convolutional neural network
(CNN; GCN) into deep reinforcement learning (… considering the system topological structure. …