Curriculum Based Reinforcement Learning of Grid Topology Controllers to Prevent Thermal Cascading

no code implementations • 18 Dec 2021 • Amarsagar Reddy Ramapuram Matavalam, Kishan Prudhvi Guddanti, Yang Weng, Venkataramana Ajjarapu

To address the challenge of the large optimization space, a curriculum-based approach with reward tuning is incorporated into the training procedure by modifying the environment using network physics for enhanced agent learning.

reinforcement-learning Reinforcement Learning (RL) +1

Data-driven Identification of Nonlinear Power System Dynamics Using Output-only Measurements

no code implementations • 4 Oct 2021 • Pranav Sharma, Venkataramana Ajjarapu, Umesh Vaidya

The developed method of Extended Subspace Identification (ESI) is suitable for systems with output measurements when all the dynamics states are not observable.

Information Based Data-Driven Characterization of Stability and Influence in Power Systems

no code implementations • 24 Oct 2019 • Subhrajit Sinha, Pranav Sharma, Venkataramana Ajjarapu, Umesh Vaidya

In this paper, we provide a purely data-driven technique for small-signal stability classification (voltage or angle stability) and influence characterization for a power network.