Runfeng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Runfeng Zhang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Wei Yao
Huazhong University of Science and Technology
4 shared publications - Zhongtuo Shi
State Key Laboratory of Advanced Electromagnetic Engineering and Technology, Hubei Electric Power Security and High Efficiency Key Laboratory, School of Electrical and Electronic Engineering, Huazhong University of Science and Technology, Wuhan, China
4 shared publications - Jinyu Wen
Huazhong University of Science and Technology
3 shared publications - Xiaomeng Ai
Huazhong University of Science and Technology
2 shared publications - Yong Tang
China Electric Power Research Institute, Beijing, China
2 shared publications Jinyu Wen
1 shared publication
Latest Publications
- 28 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 40 (6) , 4718-4731
A Hybrid Deep Learning Framework With Local-Global Feature Extraction for Intelligent Power System Stability Assessment
Transient simulation is the key to ensure the safe and stable operation of power systems. After large disturbances, power systems may experience transient rotor angle instability and short-term voltage instability, which share similar electrical characteristics but require different control strategies. Therefore, distinguishing the dominant instability mode (DIM) is crucial. In this paper, a novel hybrid deep learning (DL) framework is proposed to achieve accurate DIM identification by fully extracting local-global features from electricity data. In the proposed framework, an advanced graph neural network (GNN) optimized by random sampling and aggregation is constructed. It can better capture local features than traditional GNN and help to improve model generalization ability. Further, important global features are mined by employing transformer network with self-attention mechanism to improve DIM identification accuracy. In addition, the vital discrete fault features are also embedded into the neural networks to improve the performance. The proposed method improves upon existing DL models by providing a solution for integrating multi-level features extracted by different schemes and addressing the limitation of focusing on a single instability mode. Case studies conducted on an 8-machine 36-bus system and Northeast China Power Grid verify the superiority of the proposed method over other state-of-the-art DL methods.
- 28 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 40 (6) , 4718-4731
A Hybrid Deep Learning Framework With Local-Global Feature Extraction for Intelligent Power System Stability Assessment
Transient simulation is the key to ensure the safe and stable operation of power systems. After large disturbances, power systems may experience transient rotor angle instability and short-term voltage instability, which share similar electrical characteristics but require different control strategies. Therefore, distinguishing the dominant instability mode (DIM) is crucial. In this paper, a novel hybrid deep learning (DL) framework is proposed to achieve accurate DIM identification by fully extracting local-global features from electricity data. In the proposed framework, an advanced graph neural network (GNN) optimized by random sampling and aggregation is constructed. It can better capture local features than traditional GNN and help to improve model generalization ability. Further, important global features are mined by employing transformer network with self-attention mechanism to improve DIM identification accuracy. In addition, the vital discrete fault features are also embedded into the neural networks to improve the performance. The proposed method improves upon existing DL models by providing a solution for integrating multi-level features extracted by different schemes and addressing the limitation of focusing on a single instability mode. Case studies conducted on an 8-machine 36-bus system and Northeast China Power Grid verify the superiority of the proposed method over other state-of-the-art DL methods.
- 4 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 38 (6) , 5781-5793
Encoding Time Series as Images: A Robust and Transferable Framework for Power System DIM Identification Combining Rules and VGGNet
Digital simulation is very important for the safe and economic operation of power systems. Power system dominant instability mode (DIM) identification is an intractable problem in large-scale transient simulation analysis, because transient instability and short-term voltage instability are often intertwined. Deep learning is a promising way to achieve accurate DIM identification. By encoding time series as images, this paper proposes a robust and transferable DIM identification framework combining curve filtering rules and a dual-channel VGGNet (DCVGG) image recognition network. The curve filtering rules can effectively reduce the redundancy of massive time-domain features, the model parameters, and training time. A skillfully designed method is proposed to encode time series as images and improve the feature extraction capability of convolutional neural networks. The proposed DCVGG network is capable of processing rotor angle and voltage images simultaneously and has the potential to become a pre-trained model, making transfer learning between different power systems possible. Case studies conducted on 8-machine 36-bus system and Northeast China Power Grid demonstrate the proposed framework has better performance, scalability, robustness, and transferable ability than contrastive machine learning methods.
- 4 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 38 (6) , 5781-5793
Encoding Time Series as Images: A Robust and Transferable Framework for Power System DIM Identification Combining Rules and VGGNet
Digital simulation is very important for the safe and economic operation of power systems. Power system dominant instability mode (DIM) identification is an intractable problem in large-scale transient simulation analysis, because transient instability and short-term voltage instability are often intertwined. Deep learning is a promising way to achieve accurate DIM identification. By encoding time series as images, this paper proposes a robust and transferable DIM identification framework combining curve filtering rules and a dual-channel VGGNet (DCVGG) image recognition network. The curve filtering rules can effectively reduce the redundancy of massive time-domain features, the model parameters, and training time. A skillfully designed method is proposed to encode time series as images and improve the feature extraction capability of convolutional neural networks. The proposed DCVGG network is capable of processing rotor angle and voltage images simultaneously and has the potential to become a pre-trained model, making transfer learning between different power systems possible. Case studies conducted on 8-machine 36-bus system and Northeast China Power Grid demonstrate the proposed framework has better performance, scalability, robustness, and transferable ability than contrastive machine learning methods.
- 8 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 38 (6) , 5367-5380
Towards Multi-Scenario Power System Stability Analysis: An Unsupervised Transfer Learning Method Combining DGAT and Data Augmentation
With the expansion of power system simulation scale, intelligent stability analysis based on simulation data becomes more and more important. However, the changeable operating conditions and fault conditions will seriously affect the performance of the intelligent analysis model. This paper proposes an advanced unsupervised transfer learning (UTL) method combining dynamic graph attention network (DGAT) and data augmentation to identify the instability mode towards multiple known and unknown scenarios. For the pre-training stage, the DGAT model with data augmentation is used for instability mode identification based on the basic dataset. For the transfer learning stage, it starts when faced with new operating conditions or fault conditions different from the basic dataset. The UTL scheme takes the distribution differences among different categories of source domain and target domain as the loss to fine-tune the pre-trained model. Moreover, considering the difficulty of sample-labeling, the UTL scheme can make the pre-trained model adapt to them without additional labeled samples. Case studies are conducted on 8-machine 36-bus system and Northeast China Power Grid. The results verify the superiority of the DGAT model with data augmentation and confirm the UTL scheme can help the model adapt to multiple unknown scenarios.
- 8 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 38 (6) , 5367-5380
Towards Multi-Scenario Power System Stability Analysis: An Unsupervised Transfer Learning Method Combining DGAT and Data Augmentation
With the expansion of power system simulation scale, intelligent stability analysis based on simulation data becomes more and more important. However, the changeable operating conditions and fault conditions will seriously affect the performance of the intelligent analysis model. This paper proposes an advanced unsupervised transfer learning (UTL) method combining dynamic graph attention network (DGAT) and data augmentation to identify the instability mode towards multiple known and unknown scenarios. For the pre-training stage, the DGAT model with data augmentation is used for instability mode identification based on the basic dataset. For the transfer learning stage, it starts when faced with new operating conditions or fault conditions different from the basic dataset. The UTL scheme takes the distribution differences among different categories of source domain and target domain as the loss to fine-tune the pre-trained model. Moreover, considering the difficulty of sample-labeling, the UTL scheme can make the pre-trained model adapt to them without additional labeled samples. Case studies are conducted on 8-machine 36-bus system and Northeast China Power Grid. The results verify the superiority of the DGAT model with data augmentation and confirm the UTL scheme can help the model adapt to multiple unknown scenarios.