Pareto Network Optimization with Environmental Measures Via Surrogate-Assisted Cross Entropy Method
Authors:
- Zhongyang LuZLZhongyang Lu
- Andy H.F. ChowACAndy H.F. Chow
- Hoa T.M. NguyenHNHoa T.M. Nguyen
Preprint
- 1 January 2022
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
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.Keywords
This publication has 38 references indexed in Scilit:
- Environmentally Sustainable Toll Design for Congested Road Networks with Uncertain DemandInternational Journal of Sustainable Transportation, 2012
- Surrogate-assisted evolutionary computation: Recent advances and future challengesSwarm and Evolutionary Computation, 2011
- The cross-entropy method in multi-objective optimisation: An assessmentEuropean Journal of Operational Research, 2011
- A turning restriction design problem in urban road networksEuropean Journal of Operational Research, 2010
- Time‐Dependent Discrete Network Design Frameworks Considering Land UseComputer-Aided Civil and Infrastructure Engineering, 2010
- Dynamic system optimal traffic assignment – a state-dependent control theoretic approachTransportmetrica, 2009
- Solving the Vehicle Routing Problem with Stochastic Demands using the Cross-Entropy MethodAnnals of Operations Research, 2005
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005
- Neural network model for rapid forecasting of freeway link travel timeEngineering Applications of Artificial Intelligence, 2003
- Comparing descent heuristics and metaheuristics for the vehicle routing problemComputers & Operations Research, 2001