Dae-Hyun Choi
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
Dae-Hyun Choi has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Sangyoon Lee
Department of Electrical Engineering, Chonnam National University, Buk-gu, Gwangju 61186, Republic of Korea
9 shared publications - Hoang Tien Nguyen
School of Electrical and Electronics Engineering, Chung-Ang University, Seoul, South Korea
6 shared publications - Panggah Prabawa
School of Electrical and Electronics Engineering, Chung-ang University, Dongjak-gu, Seoul 156-756, Republic of Korea
5 shared publications Daranith Choeum
3 shared publications- Davye Mak
School of Electrical and Electronics Engineering, Chung-Ang University, Seoul, South Korea
3 shared publications - Le Xie
Harvard University
3 shared publications
Latest Publications
- Open Access
Energy Management of PV-Enabled Battery Charging Swapping Stations for Electric Vehicles in Active Distribution Systems Under Uncertainty
In this paper, we propose a data-driven distributionally robust optimization (DRO) framework that ensures the economical and robust operation of solar photovoltaic (PV)-integrated battery charging swapping stations (BCSSs) for electric vehicles (EVs) under uncertainties in active distribution systems with stand-alone PV systems. In the proposed framework, multiple inventory batteries in each BCSS are used through their charging and discharging real and/or reactive power scheduling to perform Volt/VAR control (VVC) along with stand-alone PV systems, and to reduce the BCSS operational cost via battery-to-battery (B2B)-based real power exchange and demand response (DR) while satisfying the desired EV battery swapping load. To handle the uncertainties in both PV generation outputs and DR-induced maximum demand reduction capability, the proposed framework is formulated as a data-driven DRO problem based on the Wasserstein metric using historical samples of the probability distributions of the uncertainties. Using a duality theory, the original Wasserstein-based DRO problem is reformulated into a tractable optimization problem that calculates the distributionally robust bounds of uncertainties using their support information. The effectiveness of the proposed framework was assessed on an IEEE 33-node power distribution system in terms of real power loss reduction via VVC and BCSS operational cost savings via B2B/DR capability.
Open AccessEnergy Management of PV-Enabled Battery Charging Swapping Stations for Electric Vehicles in Active Distribution Systems Under Uncertainty
In this paper, we propose a data-driven distributionally robust optimization (DRO) framework that ensures the economical and robust operation of solar photovoltaic (PV)-integrated battery charging swapping stations (BCSSs) for electric vehicles (EVs) under uncertainties in active distribution systems with stand-alone PV systems. In the proposed framework, multiple inventory batteries in each BCSS are used through their charging and discharging real and/or reactive power scheduling to perform Volt/VAR control (VVC) along with stand-alone PV systems, and to reduce the BCSS operational cost via battery-to-battery (B2B)-based real power exchange and demand response (DR) while satisfying the desired EV battery swapping load. To handle the uncertainties in both PV generation outputs and DR-induced maximum demand reduction capability, the proposed framework is formulated as a data-driven DRO problem based on the Wasserstein metric using historical samples of the probability distributions of the uncertainties. Using a duality theory, the original Wasserstein-based DRO problem is reformulated into a tractable optimization problem that calculates the distributionally robust bounds of uncertainties using their support information. The effectiveness of the proposed framework was assessed on an IEEE 33-node power distribution system in terms of real power loss reduction via VVC and BCSS operational cost savings via B2B/DR capability.
- Open Access
- 9 December 2025
- Published by Elsevier in Energy Reports
- Vol. 14, 5744-5755
Carbon-aware mobile energy storage system scheduling in active power distribution systems under PV and traffic uncertainties
- 9 December 2025
- Published by Elsevier in Energy Reports
- Vol. 14, 5744-5755
Open AccessCarbon-aware mobile energy storage system scheduling in active power distribution systems under PV and traffic uncertainties
- Open Access
- 1 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 115533-115547
Optimal Scheduling of Multi-Storage Tank-Based Hydrogen Refueling Stations in Distribution Systems via Joint Power and Hydrogen Peak Shaving
In an integrated power-hydrogen distribution system (IPHDS), on-site hydrogen refueling stations (HRSs) with photovoltaic (PV) systems, battery energy storage systems, electrolyzers (ELs), fuel cells, and hydrogen storage tanks (HSTs) are key devices for maintaining reliable and cost-effective IPHDS operations via power peak shaving while supporting the charging demands of hydrogen vehicles (HVs). This study proposes an optimization framework that ensures profitable and robust operations of on-site HRSs under uncertainties in IPHDSs. Compared with conventional methods that manage IPHDS operation using single HST (S-HST)-based HRSs through only power peak shaving, the proposed method performs dual-peak shaving of power and hydrogen through substations and ELs in multiple HST (M-HST)-based HRSs, respectively. The proposed optimization framework is implemented using chance-constrained optimization (CCO) to address uncertainties in PV generation outputs and HV charging demands in IPHDSs. Furthermore, the proposed CCO framework includes constraints that adjust the predicted HV charging demand, thereby satisfying the actual HV charging demand for each predetermined scheduling period. Numerical examples conducted on IPHDSs (IEEE 33-node and 69-node power distribution systems with three and five on-site HRSs) show that, compared to a method with S-HST and only power peak shaving, the proposed CCO method with M-HST based on dual-peak shaving of power and hydrogen increases the total profit by 5.88% and 8.19% on average, respectively, under varying HV charging demand adjustment period and chance-constraint violation probability.
- 1 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 115533-115547
Open AccessOptimal Scheduling of Multi-Storage Tank-Based Hydrogen Refueling Stations in Distribution Systems via Joint Power and Hydrogen Peak Shaving
In an integrated power-hydrogen distribution system (IPHDS), on-site hydrogen refueling stations (HRSs) with photovoltaic (PV) systems, battery energy storage systems, electrolyzers (ELs), fuel cells, and hydrogen storage tanks (HSTs) are key devices for maintaining reliable and cost-effective IPHDS operations via power peak shaving while supporting the charging demands of hydrogen vehicles (HVs). This study proposes an optimization framework that ensures profitable and robust operations of on-site HRSs under uncertainties in IPHDSs. Compared with conventional methods that manage IPHDS operation using single HST (S-HST)-based HRSs through only power peak shaving, the proposed method performs dual-peak shaving of power and hydrogen through substations and ELs in multiple HST (M-HST)-based HRSs, respectively. The proposed optimization framework is implemented using chance-constrained optimization (CCO) to address uncertainties in PV generation outputs and HV charging demands in IPHDSs. Furthermore, the proposed CCO framework includes constraints that adjust the predicted HV charging demand, thereby satisfying the actual HV charging demand for each predetermined scheduling period. Numerical examples conducted on IPHDSs (IEEE 33-node and 69-node power distribution systems with three and five on-site HRSs) show that, compared to a method with S-HST and only power peak shaving, the proposed CCO method with M-HST based on dual-peak shaving of power and hydrogen increases the total profit by 5.88% and 8.19% on average, respectively, under varying HV charging demand adjustment period and chance-constraint violation probability.
- 26 November 2024
- Published by Elsevier in Applied Energy
- Vol. 379
Joint peak power and carbon emission shaving in active distribution systems using carbon emission flow-based deep reinforcement learning
- 26 November 2024
- Published by Elsevier in Applied Energy
- Vol. 379
Joint peak power and carbon emission shaving in active distribution systems using carbon emission flow-based deep reinforcement learning
- 29 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (9) , 11213-11223
Learning and Unlearning to Operate Profitable Secure Electric Vehicle Charging
This study proposes a two-stage learning and unlearning framework that ensures profitable and privacy-preserving charging at electric vehicle charging stations (EVCSs) integrated with solar photovoltaic and energy storage systems (ESSs). In Stage 1, a robust dueling deep Q -network method combined with an optimization-based reward function is employed to perform the following two tasks: 1) an increase in the EVCS profit via the selection of charging poles for profitable charging scheduling of the reserved EVs based on ESS operation and 2) enhancement of the robustness to adversarial perturbations. In Stage 2, a computationally efficient machine unlearning method is adopted to protect the data privacy of the reserved EVs by completely erasing their traces of private data during unlearning. The simulation results demonstrate the advantages of the proposed framework in terms of profitable charging pole utilization, robustness against adversarial perturbations, accuracy of the unlearned EV charging model, and training time.
- 29 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (9) , 11213-11223
Learning and Unlearning to Operate Profitable Secure Electric Vehicle Charging
This study proposes a two-stage learning and unlearning framework that ensures profitable and privacy-preserving charging at electric vehicle charging stations (EVCSs) integrated with solar photovoltaic and energy storage systems (ESSs). In Stage 1, a robust dueling deep Q -network method combined with an optimization-based reward function is employed to perform the following two tasks: 1) an increase in the EVCS profit via the selection of charging poles for profitable charging scheduling of the reserved EVs based on ESS operation and 2) enhancement of the robustness to adversarial perturbations. In Stage 2, a computationally efficient machine unlearning method is adopted to protect the data privacy of the reserved EVs by completely erasing their traces of private data during unlearning. The simulation results demonstrate the advantages of the proposed framework in terms of profitable charging pole utilization, robustness against adversarial perturbations, accuracy of the unlearned EV charging model, and training time.
- Open Access
- 13 March 2024
- Published by Elsevier in Energy Reports
- Vol. 11, 3436-3449
Distributionally robust PV planning and curtailment considering cyber attacks on electric vehicle charging under PV/load uncertainties
- 13 March 2024
- Published by Elsevier in Energy Reports
- Vol. 11, 3436-3449
Open AccessDistributionally robust PV planning and curtailment considering cyber attacks on electric vehicle charging under PV/load uncertainties
- 4 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (8) , 11097-11109
Multilevel Deep Reinforcement Learning for Secure Reservation-Based Electric Vehicle Charging via Differential Privacy and Energy Storage System
This paper presents a multilevel deep reinforcement learning (DRL) algorithm for a privacy-preserving charging of reserved individual electric vehicles (EVs) and the secure operation of a smart EV charging station (EVCS) installed with a solar photovoltaic system and energy storage system (ESS). At the first level, at each charging pole, the DRL agent enhances the data privacy of the reserved EV arrival/departure times at smart EVCSs using a discrete differential privacy method, ensuring nonoverlapping charging periods. At the second level, at all charging poles, multiple DRL agents cooperate to maximize the revenue of smart EVCSs, completely satisfying their charging demands. At the third level, an ESS DRL agent minimizes the operational energy cost of the smart EVCS while performing privacy-preserving energy management of the smart EVCS by flattening the net energy consumption to an economical target value via charging and discharging the ESS. The simulation results evaluated for smart EVCS with four charging poles confirm the effectiveness of the proposed three-level DRL algorithm in view of the privacy-preserving performance with varying privacy costs, increasing revenue, and decreasing operational energy cost of smart EVCS.
- 4 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (8) , 11097-11109
Multilevel Deep Reinforcement Learning for Secure Reservation-Based Electric Vehicle Charging via Differential Privacy and Energy Storage System
This paper presents a multilevel deep reinforcement learning (DRL) algorithm for a privacy-preserving charging of reserved individual electric vehicles (EVs) and the secure operation of a smart EV charging station (EVCS) installed with a solar photovoltaic system and energy storage system (ESS). At the first level, at each charging pole, the DRL agent enhances the data privacy of the reserved EV arrival/departure times at smart EVCSs using a discrete differential privacy method, ensuring nonoverlapping charging periods. At the second level, at all charging poles, multiple DRL agents cooperate to maximize the revenue of smart EVCSs, completely satisfying their charging demands. At the third level, an ESS DRL agent minimizes the operational energy cost of the smart EVCS while performing privacy-preserving energy management of the smart EVCS by flattening the net energy consumption to an economical target value via charging and discharging the ESS. The simulation results evaluated for smart EVCS with four charging poles confirm the effectiveness of the proposed three-level DRL algorithm in view of the privacy-preserving performance with varying privacy costs, increasing revenue, and decreasing operational energy cost of smart EVCS.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 39 (1) , 2361-2364
Sample-Efficient Learning for a Surrogate Model of Three-Phase Distribution System
A surrogate model that accurately predicts distribution system voltages is crucial for reliable smart grid planning and operation. This letter proposes a fixed-point data-driven surrogate modeling method that employs a limited dataset to learn the power-voltage relationship of an unbalanced three-phase distribution system. The proposed surrogate model is designed using a fixed-point load-flow equation, and the stochastic gradient descent method with an automatic differentiation technique is employed to update the parameters of the surrogate model using complex power and voltage samples. Numerical examples in IEEE 13-bus, 37-bus, and 123-bus systems demonstrate that the proposed surrogate model can outperform surrogate models based on the deep neural network and Gaussian process regarding prediction accuracy and sample efficiency.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 39 (1) , 2361-2364
Sample-Efficient Learning for a Surrogate Model of Three-Phase Distribution System
A surrogate model that accurately predicts distribution system voltages is crucial for reliable smart grid planning and operation. This letter proposes a fixed-point data-driven surrogate modeling method that employs a limited dataset to learn the power-voltage relationship of an unbalanced three-phase distribution system. The proposed surrogate model is designed using a fixed-point load-flow equation, and the stochastic gradient descent method with an automatic differentiation technique is employed to update the parameters of the surrogate model using complex power and voltage samples. Numerical examples in IEEE 13-bus, 37-bus, and 123-bus systems demonstrate that the proposed surrogate model can outperform surrogate models based on the deep neural network and Gaussian process regarding prediction accuracy and sample efficiency.
- 27 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (5) , 8578-8589
Three-Stage Deep Reinforcement Learning for Privacy-and Safety-Aware Smart Electric Vehicle Charging Station Scheduling and Volt/VAR Control
This article proposes a three-stage privacy-and safety-aware deep reinforcement learning framework for coordinating smart electric vehicle charging stations (EVCSs) integrated with a photovoltaic system/ energy storage system (ESS) and volt/VAR control in a power distribution system. The proposed framework aims to maximize the EVCS profit and minimize the network real power loss while ensuring zero ESS state of charge (SOC) and voltage violation as well as preserving the privacy of the EVCS net load schedule data. In Stage 1 with 30-min resolution, each charging station operator (CSO) agent of the EVCS performs day-ahead profitable real power charging/discharging of the ESS without violating its SOC constraint via a safety layer during training. In Stage 2, using the $\epsilon $ -differential privacy method, the CSO agents encrypt the EVCS net load schedule data delivered from Stage 1. In Stage 3 with 5-min resolution, the distribution system operator agent conducts real-time reactive power charging/discharging of the ESSs to minimize the real power loss while removing voltage violations completely via iterative safe exploration of the agent with iteration penalties during training. The proposed framework was assessed on the IEEE 33-bus system for its privacy preserving and safety performances.
- 27 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (5) , 8578-8589
Three-Stage Deep Reinforcement Learning for Privacy-and Safety-Aware Smart Electric Vehicle Charging Station Scheduling and Volt/VAR Control
This article proposes a three-stage privacy-and safety-aware deep reinforcement learning framework for coordinating smart electric vehicle charging stations (EVCSs) integrated with a photovoltaic system/ energy storage system (ESS) and volt/VAR control in a power distribution system. The proposed framework aims to maximize the EVCS profit and minimize the network real power loss while ensuring zero ESS state of charge (SOC) and voltage violation as well as preserving the privacy of the EVCS net load schedule data. In Stage 1 with 30-min resolution, each charging station operator (CSO) agent of the EVCS performs day-ahead profitable real power charging/discharging of the ESS without violating its SOC constraint via a safety layer during training. In Stage 2, using the $\epsilon $ -differential privacy method, the CSO agents encrypt the EVCS net load schedule data delivered from Stage 1. In Stage 3 with 5-min resolution, the distribution system operator agent conducts real-time reactive power charging/discharging of the ESSs to minimize the real power loss while removing voltage violations completely via iterative safe exploration of the agent with iteration penalties during training. The proposed framework was assessed on the IEEE 33-bus system for its privacy preserving and safety performances.