Jiajun Duan
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
Jiajun Duan has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Di Shi
New Mexico State University
6 shared publications - Zhehan Yi
GEIRI North America
4 shared publications - Zhiwei Wang
GEIRI North America, Santa Clara, California United States
4 shared publications - Cheng Wang
School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China
2 shared publications - Hao Xu
Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV 89557, USA
2 shared publications - Hui Jiang
College of Physical and Optoelectronic Engineering, Shenzhen University, Shenzhen, China
2 shared publications
Latest Publications
- 27 April 2025
- Published by Springer Nature
- p. 344-351
Modern Rail Transit Traction Power Supply System Compatible with Solar Energy Storage
- 27 April 2025
- Published by Springer Nature
- p. 344-351
Modern Rail Transit Traction Power Supply System Compatible with Solar Energy Storage
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1076-1080
An AI Combined with Mathematical Analysis Energy Management System for Active Distribution Network
In recent years, a notable breakthrough has been made in artificial intelligence (AI) as well as smart grid. Even though it is exciting to see more and more AI-based industrial applications, the big concern of its reliability and interoperability has not been well addressed, especially for critical systems such as the power grid. Therefore, an AI combined with a mathematical analysis method is proposed for active distribution system (ADS) management. First, the classic deep reinforcement learning (DRL) method is applied to realize the data-driven optimal control. Due to the practice limitation, the purely data-driven solution is easily dropped into local optimal points. Thus, the auxiliary mathematical analysis is added to solve this problem. The proposed control method is tested on a typical ADS. The methodology of this work can be generalized into other application systems to overcome the black-box characteristics of deep learning methods.
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1076-1080
An AI Combined with Mathematical Analysis Energy Management System for Active Distribution Network
In recent years, a notable breakthrough has been made in artificial intelligence (AI) as well as smart grid. Even though it is exciting to see more and more AI-based industrial applications, the big concern of its reliability and interoperability has not been well addressed, especially for critical systems such as the power grid. Therefore, an AI combined with a mathematical analysis method is proposed for active distribution system (ADS) management. First, the classic deep reinforcement learning (DRL) method is applied to realize the data-driven optimal control. Due to the practice limitation, the purely data-driven solution is easily dropped into local optimal points. Thus, the auxiliary mathematical analysis is added to solve this problem. The proposed control method is tested on a typical ADS. The methodology of this work can be generalized into other application systems to overcome the black-box characteristics of deep learning methods.
- 18 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (2) , 1637-1645
Latency Compensation and Prediction for Wireless Train to Ground Communication Network Based on Hybrid LSTM Model
This paper proposes a novel method compensate for the communication imperfection of wireless train-to-ground communication network (WT2GCN). WT2GCN has an unavoidable transmission delay, which wastes the expensive investment of wired network and impacts the economic operation of the energy management for the rail transit system. Instead of upgrading the WT2GCN, which will lead to unnecessary costs, this paper has developed an accurate prediction method to forecast the WT2GCN measurement based on the long short-term memory (LSTM) and high-degree polynomial linear regression (HPLR) technique. To capture different characteristics of physical parameters, multiple LSTM and HPLR models are specifically designed to predict various measurements. In addition, the attention mechanism is applied to help exact the key information of features. Then, a steady-state model is derived for a priori evaluation of WT2GCN measurement prediction with non-delayed electric measurements. A detailed implementation illustration of the proposed methodology is also presented. Finally, the developed platform is tested with the actual data and implemented in one practical rail transit project of China Metro. The real-time operating result has fully demonstrated the effectiveness of the proposed method.
- 18 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (2) , 1637-1645
Latency Compensation and Prediction for Wireless Train to Ground Communication Network Based on Hybrid LSTM Model
This paper proposes a novel method compensate for the communication imperfection of wireless train-to-ground communication network (WT2GCN). WT2GCN has an unavoidable transmission delay, which wastes the expensive investment of wired network and impacts the economic operation of the energy management for the rail transit system. Instead of upgrading the WT2GCN, which will lead to unnecessary costs, this paper has developed an accurate prediction method to forecast the WT2GCN measurement based on the long short-term memory (LSTM) and high-degree polynomial linear regression (HPLR) technique. To capture different characteristics of physical parameters, multiple LSTM and HPLR models are specifically designed to predict various measurements. In addition, the attention mechanism is applied to help exact the key information of features. Then, a steady-state model is derived for a priori evaluation of WT2GCN measurement prediction with non-delayed electric measurements. A detailed implementation illustration of the proposed methodology is also presented. Finally, the developed platform is tested with the actual data and implemented in one practical rail transit project of China Metro. The real-time operating result has fully demonstrated the effectiveness of the proposed method.
- Open Access
- 20 May 2022
- Published by Frontiers Media SA in Frontiers in Oncology
- Vol. 12, 816297
Advances in Imaging in Evaluating the Efficacy of Neoadjuvant Chemotherapy for Breast Cancer
Neoadjuvant chemotherapy (NAC) is increasingly widely used in breast cancer treatment, and accurate evaluation of its response provides essential information for treatment and prognosis. Thus, the imaging tools used to quantify the disease response are critical in evaluating and managing patients treated with NAC. We discussed the recent progress, advantages, and disadvantages of common imaging methods in assessing the efficacy of NAC for breast cancer.
- 20 May 2022
- Published by Frontiers Media SA in Frontiers in Oncology
- Vol. 12, 816297
Open AccessAdvances in Imaging in Evaluating the Efficacy of Neoadjuvant Chemotherapy for Breast Cancer
Neoadjuvant chemotherapy (NAC) is increasingly widely used in breast cancer treatment, and accurate evaluation of its response provides essential information for treatment and prognosis. Thus, the imaging tools used to quantify the disease response are critical in evaluating and managing patients treated with NAC. We discussed the recent progress, advantages, and disadvantages of common imaging methods in assessing the efficacy of NAC for breast cancer.
- 10 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 368-372
Design and Implementation of Vulnerability Attack and Utilization Platform Based on Container Virtualization
With the rapid development of the Internet, various vulnerabilities have brought great pressure to network security. However, the practitioners of network security are in short supply. One of the main reasons is that vulnerability testing is difficult to learn for beginners. Therefore, a graphical operation platform is designed and implemented. The graphical interface is designed and developed based on Web system, and the virtual environment is developed based on Docker. The attack method is implemented by encapsulating the Metasploit framework. It has the functions of virtual environment management, port scanning data management, attack mode selection and attack result output, etc. This platform can effectively reduce the amount of code that beginners need to master, and enable users to have an overall understanding of vulnerability testing in network security.
- 10 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 368-372
Design and Implementation of Vulnerability Attack and Utilization Platform Based on Container Virtualization
With the rapid development of the Internet, various vulnerabilities have brought great pressure to network security. However, the practitioners of network security are in short supply. One of the main reasons is that vulnerability testing is difficult to learn for beginners. Therefore, a graphical operation platform is designed and implemented. The graphical interface is designed and developed based on Web system, and the virtual environment is developed based on Docker. The attack method is implemented by encapsulating the Metasploit framework. It has the functions of virtual environment management, port scanning data management, attack mode selection and attack result output, etc. This platform can effectively reduce the amount of code that beginners need to master, and enable users to have an overall understanding of vulnerability testing in network security.
- 18 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 36 (6) , 5465-5475
DDPG-Based Multi-Agent Framework for SVC Tuning in Urban Power Grid With Renewable Energy Resources
The uncertain nature of renewable energy resources (RERs) and fast demand response lead to recurring voltage violations in the power systems, which causes frequent transformer tap shifting and capacitor switching. Therefore, this paper resorts to the static var compensators (SVCs) to manage the bus voltages based on the multi-agent deep reinforcement learning (MA-DRL) algorithm. The proposed scheme includes several system agents and SVC agents to collaboratively adjust the injected reactive power to restrict the bus voltages within the normal range. All the agents are trained centrally and executed separately, which requires minimum communication cost. The IEEE 14-bus system, IEEE 300-bus system, and China 157-node urban power grid are used to verify the effectiveness of the proposed method.
- 18 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 36 (6) , 5465-5475
DDPG-Based Multi-Agent Framework for SVC Tuning in Urban Power Grid With Renewable Energy Resources
The uncertain nature of renewable energy resources (RERs) and fast demand response lead to recurring voltage violations in the power systems, which causes frequent transformer tap shifting and capacitor switching. Therefore, this paper resorts to the static var compensators (SVCs) to manage the bus voltages based on the multi-agent deep reinforcement learning (MA-DRL) algorithm. The proposed scheme includes several system agents and SVC agents to collaboratively adjust the injected reactive power to restrict the bus voltages within the normal range. All the agents are trained centrally and executed separately, which requires minimum communication cost. The IEEE 14-bus system, IEEE 300-bus system, and China 157-node urban power grid are used to verify the effectiveness of the proposed method.
- Top Cited Papers
- 10 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 36 (6) , 5525-5536
A Deep Reinforcement Learning-Based Multi-Agent Framework to Enhance Power System Resilience Using Shunt Resources
Existing power system resilience enhancement methods, such as proactive generation rescheduling, movable sources dispatch, and network topology reconfiguration, do not explore the capability and flexibility of shunts to maintain voltage stability during and after disrupting events. Besides, existing methods rely on accurate system models that are not easily scalable for large integrated power grids. In this paper, a data-driven multi-agent framework based on a deep-reinforcement-learning algorithm is proposed to overcome the computation and scalability concerns related to precise system models and to plan for the deployment of shunts for power system resilience enhancement. Specifically, voltage violations due to outages of multiple lines during windstorms are taken as an example of a power system resilience improvement problem. Then, a multi-agent based hybrid soft actor critic (HSAC) algorithm is developed for offline siting and sizing as well as online controlling of shunt reactive power compensators to enhance voltage resilience. The HSAC algorithm is derived from the fundamental SAC algorithms that contain both continuous and discrete action spaces. The proposed multi-agent framework learns from previous experiences and eventually gets trained to determine proper locations and sizes for shunts to avoid voltage violations during multiple line failures. The proposed approach is demonstrated on the IEEE 57-bus and IEEE 300-bus systems. The results show that the proposed multi-agent framework is effective for installation planning and controlling of shunts to enhance power system resilience.
- 10 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 36 (6) , 5525-5536
Top Cited PapersA Deep Reinforcement Learning-Based Multi-Agent Framework to Enhance Power System Resilience Using Shunt Resources
Existing power system resilience enhancement methods, such as proactive generation rescheduling, movable sources dispatch, and network topology reconfiguration, do not explore the capability and flexibility of shunts to maintain voltage stability during and after disrupting events. Besides, existing methods rely on accurate system models that are not easily scalable for large integrated power grids. In this paper, a data-driven multi-agent framework based on a deep-reinforcement-learning algorithm is proposed to overcome the computation and scalability concerns related to precise system models and to plan for the deployment of shunts for power system resilience enhancement. Specifically, voltage violations due to outages of multiple lines during windstorms are taken as an example of a power system resilience improvement problem. Then, a multi-agent based hybrid soft actor critic (HSAC) algorithm is developed for offline siting and sizing as well as online controlling of shunt reactive power compensators to enhance voltage resilience. The HSAC algorithm is derived from the fundamental SAC algorithms that contain both continuous and discrete action spaces. The proposed multi-agent framework learns from previous experiences and eventually gets trained to determine proper locations and sizes for shunts to avoid voltage violations during multiple line failures. The proposed approach is demonstrated on the IEEE 57-bus and IEEE 300-bus systems. The results show that the proposed multi-agent framework is effective for installation planning and controlling of shunts to enhance power system resilience.
- Top Cited Papers
- 23 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 35 (6) , 4644-4654
A Data-Driven Multi-Agent Autonomous Voltage Control Framework Using Deep Reinforcement Learning
The complexity of modern power grids keeps increasing due to the expansion of renewable energy resources and the requirement of fast demand responses, which results in a great challenge for conventional power grid control systems. Existing autonomous control approaches for the power grid requires an accurate system model and a powerful computational platform, which is difficult to scale up for the large-scale energy system with more control options and operating conditions. Facing these challenges, this paper proposes a data-driven multi-agent power grid control scheme using a deep reinforcement learning (DRL) method. Specifically, the classic autonomous voltage control (AVC) problem is taken as an example and formulated as a Markov Game with a heuristic method to partition agents. Then, a multi-agent AVC (MA-AVC) algorithm based on a multi-agent deep deterministic policy gradient (MADDPG) method that features centralized training and decentralized execution is developed to solve the AVC problem. The proposed method can learn from scratch and gradually master the system operation rules by input and output data. In order to demonstrate the effectiveness of the proposed MA-AVC algorithm, comprehensive case studies are conducted on an Illinois 200-Bus system considering load/generation changes, N-1 contingencies, and weak centralized communication environment.
- 23 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 35 (6) , 4644-4654
Top Cited PapersA Data-Driven Multi-Agent Autonomous Voltage Control Framework Using Deep Reinforcement Learning
The complexity of modern power grids keeps increasing due to the expansion of renewable energy resources and the requirement of fast demand responses, which results in a great challenge for conventional power grid control systems. Existing autonomous control approaches for the power grid requires an accurate system model and a powerful computational platform, which is difficult to scale up for the large-scale energy system with more control options and operating conditions. Facing these challenges, this paper proposes a data-driven multi-agent power grid control scheme using a deep reinforcement learning (DRL) method. Specifically, the classic autonomous voltage control (AVC) problem is taken as an example and formulated as a Markov Game with a heuristic method to partition agents. Then, a multi-agent AVC (MA-AVC) algorithm based on a multi-agent deep deterministic policy gradient (MADDPG) method that features centralized training and decentralized execution is developed to solve the AVC problem. The proposed method can learn from scratch and gradually master the system operation rules by input and output data. In order to demonstrate the effectiveness of the proposed MA-AVC algorithm, comprehensive case studies are conducted on an Illinois 200-Bus system considering load/generation changes, N-1 contingencies, and weak centralized communication environment.