So far, my works consist of 2 topics as shown below. Below are my selected publications. For more details, please check my Google Scholar.
In the future, I wish to do more intetresing works on stochastic optimization. (Stochastic optimization-related works are upcoming soon!)
1. Deep Reinforcement Learning
In the past few years, deep reinforcement learning (DRL) has been widely used in power systems. However, most of the existing works are based on centralized DRL algorithms, which are not suitable for large-scale power systems. We have developed a decentralized DRL algorithms to solve this problem.
-
H. Xu, Guannan Qu, “A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control,” in IEEE Transactions on Smart Grid, 2024. (Under review)link
-
H. Xu, Guannan Qu, “A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Distributed Converter-based Microgrid Voltage Control”, in NeurIPS 2023 Workshop. (Poster)link
2. Specialized Simulation Algorithms
In many cases, simulation is the best tools to analyze some complex systems, since it’s the most straightforward way to understand the system. However, simulation is often time-consuming and inefficient, especially for large-scale systems. Specifically, we focus on the simulation of power electronics-based power systems (PEPS). We have developed several specialized simulation algorithms to accelerate the simulation of PEPS.
-
H. Xu et al., “Topology-Aware Matrix Partitioning Method for FPGA Real-Time Simulation of Power Electronics Systems,” IEEE Trans. Ind. Electron., 2023.link
-
H. Xu et al., “Numerical Derivative-based Flexible Integration Algorithm for Power Electronic Systems Simulation Considering Nonlinear Components,” IEEE Trans. Ind. Electron., 2023.link
-
H. Xu et al., “FPGA-Based Implicit-Explicit Real-time Simulation Solver for Railway Wireless Power Transfer with Nonlinear Magnetic Coupling Components,” IEEE Transactions on Transportation Electrification, 2023.link