Hoa T.M. Nguyen
Hoa T.M. Nguyen has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Andy H. F. Chow
Department of Systems Engineering, City University of Hong Kong, Hong Kong, SAR, China
5 shared publications - Cheng-Shuo Ying
Department of Systems Engineering and Engineering Management, City University of Hong Kong, Hong Kong
2 shared publications Kwai-Sang Chin
1 shared publicationZhongyang Lu
1 shared publication
Latest Publications
- 17 May 2022
- Published by Elsevier in Transportation Research Part B: Methodological
- Vol. 161, 36-59
Multi-agent deep reinforcement learning for adaptive coordinated metro service operations with flexible train composition
- 17 May 2022
- Published by Elsevier in Transportation Research Part B: Methodological
- Vol. 161, 36-59
Multi-agent deep reinforcement learning for adaptive coordinated metro service operations with flexible train composition
- Open Access
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Adaptive Rail Transit Network Operations with a Rollout Surrogate-Approximate Dynamic Programming Approach
This paper presents an adaptive optimization framework for dynamic rail transit network operations with use of a rollout surrogate-approximate dynamic programming method. The optimization algorithm derives coordinated decisions of service schedules and train unit deployment with respect to prevailing passenger demand. Considering the computational effectiveness needed for real-time applications, a state-dependent surrogate function is incorporated to approximate the costs associated with operational decisions over future stages. The surrogate approximation is updated iteratively via a temporal difference learning process with feeding of observations made from the transit network. The proposed framework is implemented and tested on a real-world scenario in Hong Kong Light Rail Transit (LRT) network. The results reveal that the proposed framework is able to reduce significantly the total passengers' waiting times over existing plans with reasonable computational time via use of the surrogate approximation. This suggests the potential of the proposed optimizer for real time applications in large-scale rail transit networks.
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Open AccessAdaptive Rail Transit Network Operations with a Rollout Surrogate-Approximate Dynamic Programming Approach
This paper presents an adaptive optimization framework for dynamic rail transit network operations with use of a rollout surrogate-approximate dynamic programming method. The optimization algorithm derives coordinated decisions of service schedules and train unit deployment with respect to prevailing passenger demand. Considering the computational effectiveness needed for real-time applications, a state-dependent surrogate function is incorporated to approximate the costs associated with operational decisions over future stages. The surrogate approximation is updated iteratively via a temporal difference learning process with feeding of observations made from the transit network. The proposed framework is implemented and tested on a real-world scenario in Hong Kong Light Rail Transit (LRT) network. The results reveal that the proposed framework is able to reduce significantly the total passengers' waiting times over existing plans with reasonable computational time via use of the surrogate approximation. This suggests the potential of the proposed optimizer for real time applications in large-scale rail transit networks.
- Open Access
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Pareto Network Optimization with Environmental Measures Via Surrogate-Assisted Cross Entropy Method
This paper presents a multi-objective optimization framework for general road networks with both mobility and environmental measures. The problem is formulated as a bi-level program in which the decisions of network-wide speed limits and tolls are sought to minimize both traffic induced congestion and emission subject to equilibrium flows. Solutions are computed by using a multi-objective cross-entropy method. With the vast decision space and computational time needed, we introduce the use of surrogate function to approximate the evaluation of the performances of the decision settings in the optimization process. The proposed framework is applied and tested on a calibrated and validated Hong Kong road network scenario. The results show that the proposed surrogate-assisted computational framework could deliver significant improvement over existing settings in reasonable computational time. This study contributes to green transport management and urban sustainable policies with use of advanced transport network modeling and optimization techniques.
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Open AccessPareto Network Optimization with Environmental Measures Via Surrogate-Assisted Cross Entropy Method
This paper presents a multi-objective optimization framework for general road networks with both mobility and environmental measures. The problem is formulated as a bi-level program in which the decisions of network-wide speed limits and tolls are sought to minimize both traffic induced congestion and emission subject to equilibrium flows. Solutions are computed by using a multi-objective cross-entropy method. With the vast decision space and computational time needed, we introduce the use of surrogate function to approximate the evaluation of the performances of the decision settings in the optimization process. The proposed framework is applied and tested on a calibrated and validated Hong Kong road network scenario. The results show that the proposed surrogate-assisted computational framework could deliver significant improvement over existing settings in reasonable computational time. This study contributes to green transport management and urban sustainable policies with use of advanced transport network modeling and optimization techniques.