Min Zhou

Title: Min Zhou and Deep Learning for Flexible-Topology Power Flow

Introduction

Min Zhou is an inventor based in Hong Kong, CN, whose patent work addresses the use of deep learning to solve optimal power flow problems in electrical power systems. The supplied information lists 1 patent and identifies City University of Hong Kong as his company.

Latest Patents

Zhou’s listed patent is “Deep learning-based approach for solving optimal power flow problems with flexible topology.” It describes a method for solving multiple optimal power flow equations for an AC electrical power system with different topologies and admittances.

The method embeds multiple topologies in a continuous admittance space. A deep neural network receives load inputs and line admittances, then determines voltage magnitudes and phase angles for the system’s buses. Power flow equations are used to reconstruct active and reactive power generation from those values and the load inputs. The approach is designed to handle changes in network topology within a unified framework.

Career Highlights

The available information connects Zhou’s patent activity with City University of Hong Kong. His listed invention applies deep learning to a technical challenge in power system analysis: solving optimal power flow problems across flexible network configurations.

Collaborations

Minghua Chen is identified as Zhou’s coworker. The supplied details do not specify whether Chen is a co-inventor or describe a particular collaboration on the patent.

Conclusion

Min Zhou’s listed patent combines deep neural networks and power flow equations to address optimal power flow across changing electrical network topologies.