Huayi Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Huayi Wu has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Zhao Xu
The Hong Kong Polytechnic University
13 shared publications - Minghao Wang
State Key Laboratory of Internet of Things for Smart City and Department of Electrical and Computer Engineering, University of Macau, Macau, SAR, China
3 shared publications - Mingbo Liu
School of Electric Power Engineering, South China University of Technology, Guangzhou, China
2 shared publications Xianzhuo Sun
2 shared publications- Youwei Jia
Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen 518055, China
2 shared publications Guoxin Tang
The Hong Kong Polytechnic University,Electrical Engineering Department,Hong Kong,China
1 shared publication
Latest Publications
- 31 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (7) , 13992-14002
Hybrid Quantum-Transformer Network-Based Probabilistic Multi-Energy Flow Calculation in Integrated Energy System
Probabilistic energy flow (PEF) is a fundamental task for the operation of conventional model-based integrated energy systems (IESs), electricity–gas–heating coupled systems, while challenged by heavy computational burdens and uncertainties introduced by renewable energy sources (RES). To overcome this bottleneck, a novel data-driven hybrid quantum-transformer network (HQTN) is proposed for fast PEF calculation. Specifically, the classical TN captures the dynamic spatial uncertainty features via a novel graph attention mechanism to model the uncertain fluctuating RES features. In addition, a quantum neural network (QNN) is proposed to extract the high-dimensional, complex relationships of IES operational data, thereby improving calculational accuracy. Case studies are conducted on both IEEE 33-node electric/20-node gas/17-node heating and 118-node electric/48-node gas/14-node heating systems. The experimental evaluation results verify that the proposed approach achieves high accuracy and maintains strong computational performance in PEF calculation.
- 31 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (7) , 13992-14002
Hybrid Quantum-Transformer Network-Based Probabilistic Multi-Energy Flow Calculation in Integrated Energy System
Probabilistic energy flow (PEF) is a fundamental task for the operation of conventional model-based integrated energy systems (IESs), electricity–gas–heating coupled systems, while challenged by heavy computational burdens and uncertainties introduced by renewable energy sources (RES). To overcome this bottleneck, a novel data-driven hybrid quantum-transformer network (HQTN) is proposed for fast PEF calculation. Specifically, the classical TN captures the dynamic spatial uncertainty features via a novel graph attention mechanism to model the uncertain fluctuating RES features. In addition, a quantum neural network (QNN) is proposed to extract the high-dimensional, complex relationships of IES operational data, thereby improving calculational accuracy. Case studies are conducted on both IEEE 33-node electric/20-node gas/17-node heating and 118-node electric/48-node gas/14-node heating systems. The experimental evaluation results verify that the proposed approach achieves high accuracy and maintains strong computational performance in PEF calculation.
- 19 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 17 (1) , 697-708
Prototype Federated Reinforcement Learning for Voltage Regulation in Distribution Systems With Physics-Aware Spatial-Temporal Graph Perception
Online voltage regulation in active distribution systems faces challenges stemming from privacy protection concerns and uncertainties introduced by renewable energy sources. To address these issues, a novel spatial-temporal transformer-based prototype federated reinforcement learning (STT-PFRL) model is proposed to mitigate voltage deviations while ensuring data privacy. Specifically, STT-PFRL operating within a decentralized framework trains the model by transmitting local prototype information between a central data server and local agents, avoiding raw data privacy leakage. Besides, a novel physics-aware spatial-temporal transformer network is proposed to improve the voltage regulation policy learning stability against uncertainties by embedding the spatial-temporal graphical physics information into the data aggregation process. Furthermore, the prototype learning-based federated soft actor-critic (ProtoFedSAC) algorithm incorporates a prototype layer to utilize diverse feature representations, thereby enhancing the model’s ability to handle heterogeneity in environmental data. Simulation results on 33- and 118-node distribution systems demonstrate the superior effectiveness and efficiency of STT-PFRL in voltage regulation.
- 19 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 17 (1) , 697-708
Prototype Federated Reinforcement Learning for Voltage Regulation in Distribution Systems With Physics-Aware Spatial-Temporal Graph Perception
Online voltage regulation in active distribution systems faces challenges stemming from privacy protection concerns and uncertainties introduced by renewable energy sources. To address these issues, a novel spatial-temporal transformer-based prototype federated reinforcement learning (STT-PFRL) model is proposed to mitigate voltage deviations while ensuring data privacy. Specifically, STT-PFRL operating within a decentralized framework trains the model by transmitting local prototype information between a central data server and local agents, avoiding raw data privacy leakage. Besides, a novel physics-aware spatial-temporal transformer network is proposed to improve the voltage regulation policy learning stability against uncertainties by embedding the spatial-temporal graphical physics information into the data aggregation process. Furthermore, the prototype learning-based federated soft actor-critic (ProtoFedSAC) algorithm incorporates a prototype layer to utilize diverse feature representations, thereby enhancing the model’s ability to handle heterogeneity in environmental data. Simulation results on 33- and 118-node distribution systems demonstrate the superior effectiveness and efficiency of STT-PFRL in voltage regulation.
- 10 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 12 (2) , 1186-1197
Meta-Learning Enhanced Physics-Informed Graph Attention Convolutional Network for Distribution Power System State Estimation
Promptly perceiving distribution system states is challenged by frequent topology changes and uncertain power injections. To address these issues, a Meta-learning enhanced physics-informed graph attention convolutional network (Meta-PIGACN) model is proposed to handle topological variability in distribution system state estimation (DSSE). Specifically, physics information is integrated into the graph convolutional network, enabling a physics-informed edge-weighting process that incorporates physical information to control the aggregation of neighboring nodes. Besides, the graph attention mechanism automatically adjusts the importance of different neighboring nodes, allowing the capture and preservation of inherent system features across varying topologies, thereby improving state estimation accuracy. Furthermore, meta-learning is proposed to acquire empirical knowledge across multiple topologies so that the model can rapidly adapt to new configurations through iterative gradient descent updates even in large-scale systems. The simulation results based on the 33/118/1746-node distribution systems show the high accuracy and efficiency of the proposed model.
- 10 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 12 (2) , 1186-1197
Meta-Learning Enhanced Physics-Informed Graph Attention Convolutional Network for Distribution Power System State Estimation
Promptly perceiving distribution system states is challenged by frequent topology changes and uncertain power injections. To address these issues, a Meta-learning enhanced physics-informed graph attention convolutional network (Meta-PIGACN) model is proposed to handle topological variability in distribution system state estimation (DSSE). Specifically, physics information is integrated into the graph convolutional network, enabling a physics-informed edge-weighting process that incorporates physical information to control the aggregation of neighboring nodes. Besides, the graph attention mechanism automatically adjusts the importance of different neighboring nodes, allowing the capture and preservation of inherent system features across varying topologies, thereby improving state estimation accuracy. Furthermore, meta-learning is proposed to acquire empirical knowledge across multiple topologies so that the model can rapidly adapt to new configurations through iterative gradient descent updates even in large-scale systems. The simulation results based on the 33/118/1746-node distribution systems show the high accuracy and efficiency of the proposed model.
- 22 August 2024
- Published by Elsevier in Applied Energy
- Vol. 376
Customized decentralized autonomous organization based optimal energy management for smart buildings
- 22 August 2024
- Published by Elsevier in Applied Energy
- Vol. 376
Customized decentralized autonomous organization based optimal energy management for smart buildings
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (10) , 12262-12274
Multi-Energy Load Forecasting in Integrated Energy Systems: A Spatial-Temporal Adaptive Personalized Federated Learning Approach
Short-term forecasting of multienergy loads is of paramount significance for integrated energy systems operation. The central forecasting framework is confronted with the privacy disclosure issue. Besides, the intricate interdependencies among diverse energy loads present an opportunity to improve prediction accuracy. To this end, a privacy-preserving spatial-temporal adaptive personalized federated learning model is proposed in this article. Specifically, the proposed federated learning-based decentralized framework enables the sharing of local model weights while ensuring the confidentiality of raw measurement data. Besides, the spatial-temporal transformer leverages the self-attention mechanism to synchronously capture the complex dynamic dependencies among different types of energy load demand. Furthermore, the adaptive local aggregation mechanism is proposed to personalize the local model to address the data heterogeneity and subsequently improve forecasting accuracy. The proposed model is applied to a publicly available dataset. The results show that the proposed model can achieve highly efficient and effective forecasting accuracy.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (10) , 12262-12274
Multi-Energy Load Forecasting in Integrated Energy Systems: A Spatial-Temporal Adaptive Personalized Federated Learning Approach
Short-term forecasting of multienergy loads is of paramount significance for integrated energy systems operation. The central forecasting framework is confronted with the privacy disclosure issue. Besides, the intricate interdependencies among diverse energy loads present an opportunity to improve prediction accuracy. To this end, a privacy-preserving spatial-temporal adaptive personalized federated learning model is proposed in this article. Specifically, the proposed federated learning-based decentralized framework enables the sharing of local model weights while ensuring the confidentiality of raw measurement data. Besides, the spatial-temporal transformer leverages the self-attention mechanism to synchronously capture the complex dynamic dependencies among different types of energy load demand. Furthermore, the adaptive local aggregation mechanism is proposed to personalize the local model to address the data heterogeneity and subsequently improve forecasting accuracy. The proposed model is applied to a publicly available dataset. The results show that the proposed model can achieve highly efficient and effective forecasting accuracy.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 15 (3) , 2639-2651
Optimal Volt/Var Control for Unbalanced Distribution Networks With Human-in-the-Loop Deep Reinforcement Learning
This paper proposes a human-in-the-loop deep reinforcement learning (HL-DRL)-based VVC strategy to simultaneously reduce power losses, mitigate voltage violations and compensate for voltage unbalance in three-phase unbalanced distribution networks. Instead of fully trusting DRL actions made by deep neural networks, a human intervention module is proposed to modify dangerous actions that violate operation constraints during offline training. This module refers to well-designed human guidance rules based on voltage-reactive power sensitivities, which regulate PV reactive power to sequentially address local voltage violation and unbalance issues to obtain safe transitions. To efficiently and safely learn the optimal control policy from these training samples, a human-in-the-loop soft actor-critic (HL-SAC) solution method is then developed. Different from the standard SAC algorithm, an online switch mechanism between action exploration and human intervention is designed. The actor network loss function is modified to incorporate human guidance terms, which alleviates the inconsistency of the updating direction of actor and critic networks. A hybrid experience replay buffer including both dangerous and safe transitions is also used to facilitate the learning process towards human actions. Comparative simulation results on a modified IEEE 123-bus unbalanced distribution system demonstrate the effectiveness and superiority of the proposed method in voltage control.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 15 (3) , 2639-2651
Optimal Volt/Var Control for Unbalanced Distribution Networks With Human-in-the-Loop Deep Reinforcement Learning
This paper proposes a human-in-the-loop deep reinforcement learning (HL-DRL)-based VVC strategy to simultaneously reduce power losses, mitigate voltage violations and compensate for voltage unbalance in three-phase unbalanced distribution networks. Instead of fully trusting DRL actions made by deep neural networks, a human intervention module is proposed to modify dangerous actions that violate operation constraints during offline training. This module refers to well-designed human guidance rules based on voltage-reactive power sensitivities, which regulate PV reactive power to sequentially address local voltage violation and unbalance issues to obtain safe transitions. To efficiently and safely learn the optimal control policy from these training samples, a human-in-the-loop soft actor-critic (HL-SAC) solution method is then developed. Different from the standard SAC algorithm, an online switch mechanism between action exploration and human intervention is designed. The actor network loss function is modified to incorporate human guidance terms, which alleviates the inconsistency of the updating direction of actor and critic networks. A hybrid experience replay buffer including both dangerous and safe transitions is also used to facilitate the learning process towards human actions. Comparative simulation results on a modified IEEE 123-bus unbalanced distribution system demonstrate the effectiveness and superiority of the proposed method in voltage control.
- 7 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 492-496
Generator Self-Excitation and System Over-Voltage Calculation of Black Start in Power Grid
Generator self-excitation and system over-voltage may threaten system's devices, leading to failure again during the black start recovery process. To address this problem, this paper leverages the overvoltage calculation method for the target grid frame in the black start partition to compile a set of calculation models for generator self-excitation, no-load long line overvoltage, load rejection overvoltage at the end of long line and terminal single-phase grounding non-fault phase overvoltage to strengthen the power system's security. These models are applied to analyze generator self-excitation and system over-voltage the for the target grid in the black start partition of the Shanxi power grid so that feasible black start plan can be obtained. Then, the proposed models are simulated and verified via the PSCAD/EMTDC electromagnetic transient software, which demonstrates the effectiveness and efficiency of the proposed models to satisfy operation requirements for the black start scheme to maintain the security operation of the power system.
- 7 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 492-496
Generator Self-Excitation and System Over-Voltage Calculation of Black Start in Power Grid
Generator self-excitation and system over-voltage may threaten system's devices, leading to failure again during the black start recovery process. To address this problem, this paper leverages the overvoltage calculation method for the target grid frame in the black start partition to compile a set of calculation models for generator self-excitation, no-load long line overvoltage, load rejection overvoltage at the end of long line and terminal single-phase grounding non-fault phase overvoltage to strengthen the power system's security. These models are applied to analyze generator self-excitation and system over-voltage the for the target grid in the black start partition of the Shanxi power grid so that feasible black start plan can be obtained. Then, the proposed models are simulated and verified via the PSCAD/EMTDC electromagnetic transient software, which demonstrates the effectiveness and efficiency of the proposed models to satisfy operation requirements for the black start scheme to maintain the security operation of the power system.
- 11 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 17 (2) , 3127-3137
Adaptive Distributed Graph Model for Multiple-Line Outage Identification in Large-Scale Power System
The real-time outage identification and localization of a potentially large number of transmission line outages is of vital importance while fairly challenging under limited measurement resources. To address this issue, an adaptive distributed graph model (ADGM) is innovatively proposed for multiple-line outage identification to hedge limited measurement and noise in the large-scale power system. By integrating a novel Laplacian convolution (LC) operation, the proposed ADGM is forceful in capturing the non-Euclidian structure of nodal voltage phase angle measurement to tackle the real-time outage identification problem effectively with measurement noise. On top of this, a novel breadth walk (BW) operation is proposed to exclude redundant measurement so that enhanced outage identification accuracy can be achieved under measurement lost. BW is then incorporated with LC to release the ADGM from numerous parameters' training burden to achieve the large-scale system outage identification. Numerical simulations are carried out based on the IEEE 30/118/300-node and Polish 2383-node testing systems, which verify the effectiveness, efficiency, and robustness of the proposed model.
- 11 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 17 (2) , 3127-3137
Adaptive Distributed Graph Model for Multiple-Line Outage Identification in Large-Scale Power System
The real-time outage identification and localization of a potentially large number of transmission line outages is of vital importance while fairly challenging under limited measurement resources. To address this issue, an adaptive distributed graph model (ADGM) is innovatively proposed for multiple-line outage identification to hedge limited measurement and noise in the large-scale power system. By integrating a novel Laplacian convolution (LC) operation, the proposed ADGM is forceful in capturing the non-Euclidian structure of nodal voltage phase angle measurement to tackle the real-time outage identification problem effectively with measurement noise. On top of this, a novel breadth walk (BW) operation is proposed to exclude redundant measurement so that enhanced outage identification accuracy can be achieved under measurement lost. BW is then incorporated with LC to release the ADGM from numerous parameters' training burden to achieve the large-scale system outage identification. Numerical simulations are carried out based on the IEEE 30/118/300-node and Polish 2383-node testing systems, which verify the effectiveness, efficiency, and robustness of the proposed model.
- 4 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 14 (1) , 297-308
Unrolled Spatiotemporal Graph Convolutional Network for Distribution System State Estimation and Forecasting
Timely perception of distribution system states is critical for the control and operation of power grids. Recently, it has been seriously challenged by the dramatic voltage fluctuations induced by high renewables. To address this issue, an Unrolled Spatiotemporal Graph Convolutional Network (USGCN) is proposed for distribution system state estimation (DSSE) and forecasting with augmented consideration of the underlying complex spatiotemporal correlations of renewable energy sources (RES). Specifically, the interconnection among individual spatial graphs of adjacent time steps will lead to an unrolled spatiotemporal graph and benefit the synchronous capture of spatial and temporal correlations to achieve enhanced accuracy. On top of this, the node-embedding technique is employed in the unrolled spatiotemporal convolutional layer to reveal the hidden nonlinear spatiotemporal correlations of RES outputs without relying on full prior knowledge. Moreover, the proposed USGCN stacks the unrolled spatiotemporal convolutional layers, leading to the perception of longtime correlations to obtain effective ahead-of-time state forecasting results robustly. The simulation results have been provided to verify the accuracy and efficiency of the proposed model in 118-node and 1746-node distribution systems.
- 4 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 14 (1) , 297-308
Unrolled Spatiotemporal Graph Convolutional Network for Distribution System State Estimation and Forecasting
Timely perception of distribution system states is critical for the control and operation of power grids. Recently, it has been seriously challenged by the dramatic voltage fluctuations induced by high renewables. To address this issue, an Unrolled Spatiotemporal Graph Convolutional Network (USGCN) is proposed for distribution system state estimation (DSSE) and forecasting with augmented consideration of the underlying complex spatiotemporal correlations of renewable energy sources (RES). Specifically, the interconnection among individual spatial graphs of adjacent time steps will lead to an unrolled spatiotemporal graph and benefit the synchronous capture of spatial and temporal correlations to achieve enhanced accuracy. On top of this, the node-embedding technique is employed in the unrolled spatiotemporal convolutional layer to reveal the hidden nonlinear spatiotemporal correlations of RES outputs without relying on full prior knowledge. Moreover, the proposed USGCN stacks the unrolled spatiotemporal convolutional layers, leading to the perception of longtime correlations to obtain effective ahead-of-time state forecasting results robustly. The simulation results have been provided to verify the accuracy and efficiency of the proposed model in 118-node and 1746-node distribution systems.