Tianfeng Chu
Tianfeng Chu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Jiacheng Li
College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China
2 shared publications - Shunjiang Wang
School of Electrical and Control Engineering, Liaoning Technical University, Huludao 125000, China
2 shared publications - Xun Dou
College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing 211816, China
2 shared publications - Haifeng Luo
College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China
1 shared publication - Tianyi Zhu
Electric Power Research Institute of State Grid Liaoning Electric Power Co., China
1 shared publication - Tong Wang
Electric Power Research Institute of State Grid Liaoning Electric Power Co., China
1 shared publication
Latest Publications
- 15 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 16 (4) , 2659-2668
Optimal Energy Storage Configuration for Primary Frequency Regulation Performance Considering State of Charge Partitioning
The proportion of renewable energy in the power system continues to rise, and its intermittent and uncertain output has had a certain impact on the frequency stability of the grid. Therefore, a multi-type energy storage (ES) configuration method considering State of Charge (SOC) partitioning and frequency regulation performance matching is proposed for primary frequency regulation. Firstly, the Automatic Generation Control (AGC) signal is decomposed and reconstructed using the variational mode decomposition (VMD) method. Specifically, by combining the charge and discharge characteristics of Li-ion battery and flywheel energy storage (FES), component signals of different frequencies are allocated to different ES systems. Secondly, a multi-type ES capacity allocation optimization model considering SOC partitioning is developed, with the objective function being the minimization of the whole life-cycle planning cost of ES. Finally, based on actual data from a region in North China, the proposed method is verified by analyzing case studies under different scenarios. The results demonstrate that the method can effectively reduce computation time, optimize ES operating conditions, and thus lower the whole life-cycle planning cost of ES.
- 15 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 16 (4) , 2659-2668
Optimal Energy Storage Configuration for Primary Frequency Regulation Performance Considering State of Charge Partitioning
The proportion of renewable energy in the power system continues to rise, and its intermittent and uncertain output has had a certain impact on the frequency stability of the grid. Therefore, a multi-type energy storage (ES) configuration method considering State of Charge (SOC) partitioning and frequency regulation performance matching is proposed for primary frequency regulation. Firstly, the Automatic Generation Control (AGC) signal is decomposed and reconstructed using the variational mode decomposition (VMD) method. Specifically, by combining the charge and discharge characteristics of Li-ion battery and flywheel energy storage (FES), component signals of different frequencies are allocated to different ES systems. Secondly, a multi-type ES capacity allocation optimization model considering SOC partitioning is developed, with the objective function being the minimization of the whole life-cycle planning cost of ES. Finally, based on actual data from a region in North China, the proposed method is verified by analyzing case studies under different scenarios. The results demonstrate that the method can effectively reduce computation time, optimize ES operating conditions, and thus lower the whole life-cycle planning cost of ES.
- 9 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 61 (1) , 1363-1373
Adaptive Encoder-Decoder Model Considering Spatio-Temporal Features for Short-Term Power Prediction of Distributed Photovoltaic Station
Considering the impact of operation and maintenance costs and technology, there is generally a lack of sufficient meteorological observation devices within the distributed photovoltaic (PV) station group. The deviation of the collected meteorological data and the PV power data error caused by software and hardware limitations will directly lead to the reduction of model prediction accuracy. To tackle this problem, this paper proposes a short-term prediction method with adaptive spatio-temporal codec structure for distributed PV power prediction, which adapts to the prediction requirements of different data input and different weather conditions and improves the prediction accuracy. First, the Random Forest algorithm (RF) and Pearson Correlation Coefficient (PCC) are used to sort the feature importance and select the key input data. Second, a spatio-temporal feature encoder-decoder model based on Long Short Term Memory Network (LSTM) and Spatio-Temporal Attention mechanism (STA) is proposed to adapt to spatio-temporal feature mining under different weather conditions. Third, an adaptive prediction framework based on pre-fusion and post-fusion is designed to meet the needs of comprehensive feature learning under the input of different amounts of data and further improve the prediction accuracy. Comprehensive experiments have been conducted on real data from different stations in Jiangsu, China, to confirm the superior performance of the proposed model.
- 9 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 61 (1) , 1363-1373
Adaptive Encoder-Decoder Model Considering Spatio-Temporal Features for Short-Term Power Prediction of Distributed Photovoltaic Station
Considering the impact of operation and maintenance costs and technology, there is generally a lack of sufficient meteorological observation devices within the distributed photovoltaic (PV) station group. The deviation of the collected meteorological data and the PV power data error caused by software and hardware limitations will directly lead to the reduction of model prediction accuracy. To tackle this problem, this paper proposes a short-term prediction method with adaptive spatio-temporal codec structure for distributed PV power prediction, which adapts to the prediction requirements of different data input and different weather conditions and improves the prediction accuracy. First, the Random Forest algorithm (RF) and Pearson Correlation Coefficient (PCC) are used to sort the feature importance and select the key input data. Second, a spatio-temporal feature encoder-decoder model based on Long Short Term Memory Network (LSTM) and Spatio-Temporal Attention mechanism (STA) is proposed to adapt to spatio-temporal feature mining under different weather conditions. Third, an adaptive prediction framework based on pre-fusion and post-fusion is designed to meet the needs of comprehensive feature learning under the input of different amounts of data and further improve the prediction accuracy. Comprehensive experiments have been conducted on real data from different stations in Jiangsu, China, to confirm the superior performance of the proposed model.
- Open Access
- 24 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 350-353
Novel integration graphical modeling method for the connection topology relationship of electrical equipment in distribution network
Various power systems in the distribution network generate a large amount of power information data every day. And it is of great significance for power data monitoring to dynamically display them in a visualized way. Therefore, a visualization platform can display the status of the distribution network accurately. The related power information data can intuitively respond to the changes in the distribution network, so that the dispatchers can determine the operating status of the power grid quickly. Firstly, a data model is built for power equipment in this paper. And a topology model is built for connection relationship between power equipment according to common information model (CIM) to design the corresponding data structure and database. Secondly, a graphical element model is proposed for power equipment based on SVG technology to realize the electrical graphical element template applicable to distribution network. Thirdly, the connection relationship of distribution network is analyzed by topology analysis method. And a topology model is formed containing only topological nodes and topological islands. Finally, the topological analysis of the connection relationship of the distribution network is carried out by topological analysis method containing only topological nodes and topological islands. It is used to topology the connection relationship of the electrical equipment in the distribution network. The topological results are stored in the database for use in other dispatch functions.
- 24 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 350-353
Open AccessNovel integration graphical modeling method for the connection topology relationship of electrical equipment in distribution network
Various power systems in the distribution network generate a large amount of power information data every day. And it is of great significance for power data monitoring to dynamically display them in a visualized way. Therefore, a visualization platform can display the status of the distribution network accurately. The related power information data can intuitively respond to the changes in the distribution network, so that the dispatchers can determine the operating status of the power grid quickly. Firstly, a data model is built for power equipment in this paper. And a topology model is built for connection relationship between power equipment according to common information model (CIM) to design the corresponding data structure and database. Secondly, a graphical element model is proposed for power equipment based on SVG technology to realize the electrical graphical element template applicable to distribution network. Thirdly, the connection relationship of distribution network is analyzed by topology analysis method. And a topology model is formed containing only topological nodes and topological islands. Finally, the topological analysis of the connection relationship of the distribution network is carried out by topological analysis method containing only topological nodes and topological islands. It is used to topology the connection relationship of the electrical equipment in the distribution network. The topological results are stored in the database for use in other dispatch functions.