Data-driven adaptive Lyapunov function based graphical deep convolutional neural network for smart grid congestion management

Abstract

Optimal power flow by leveraging network grid topology will ensure stable operation of the smart grid. Energy management in grid-connected systems aimed to reduce computational non-linearities and ensure reliable operation of the smart grid. The conventional method manages congestion with optimal scheduling for every 10–15 min. Hence congestion in the smart grid occurs during secured energy distribution. In smart grid, instant congestion and energy management are needed. This research, work is devoted to a novel data-driven adaptive Lyapunov function with a Graphical Deep Convolutional Neural Network (GDCNN) regulated optimal flow by accurate energy management. By employing novel Graph theory-based network, the congestion data are obtained to train the proposed GDCNN. A Comparison of obtained results with existing baseline methods has been carried for claiming the novelties of proposed GDCNN. It is observed, that compared to existing machine learning-based extended subspace identification techniques. Our method has better optimal power regulation within 1.8 s by controlling power sources. Also, numerical simulation on IEEE 68 bus system shows the proposed GDCNN have superior performance, reliability, and optimal energy management. This by integrating the benefits of adaptive Lyapunov function and graphical convolutional network.