Related Experiment Videos
Policy planning under uncertainty: efficient starting populations for simulation-optimization methods applied to
Gordon H Huang1, Jonathan D Linton, Julian Scott Yeomans
1Faculty of Engineering, University of Regina, Regina, SK S4S 0A2, Canada. Huangg@uregina.ca
Journal of Environmental Management
|June 14, 2005
Summary
This study introduces GESO, a hybrid approach combining evolutionary simulation-optimization (ESO) and grey programming (GP) to efficiently generate multiple policy alternatives for complex planning problems with uncertainty.
Area of Science:
- Environmental planning
- Operations research
- Computational intelligence
Background:
- Stochastic system components necessitate advanced modeling techniques.
- Grey programming (GP) is effective for environmental planning with uncertain data.
- Evolutionary simulation-optimization (ESO) offers versatile problem-modeling capabilities.
Purpose of the Study:
- To develop a hybrid approach combining ESO and GP for policy planning.
- To create a method for efficiently generating multiple policy alternatives (MGA).
- To address planning challenges in systems with significant uncertainty.
Main Methods:
- Integration of Evolutionary Simulation-Optimization (ESO) with Grey Programming (GP) into a novel GESO approach.
- Application of GESO to a municipal solid waste (MSW) management case study.
- Demonstration of the modelling-to-generate-alternatives (MGA) capability.
Main Results:
- GESO efficiently generates multiple policy alternatives meeting system criteria.
- The hybrid GESO approach proves effective for complex planning scenarios.
- Successful illustration using a municipal solid waste management case in Ontario, Canada.
Conclusions:
- GESO provides a powerful tool for policy planning under uncertainty.
- The MGA capability is valuable for large-scale, real-world planning problems.
- The GESO methodology is adaptable to various planning applications beyond MSW systems.