A stochastic multi-objective optimization decision model for energy facility allocation: a case of liquefied petroleum gas station
- 14 Downloads
To mitigate air pollution problem, the government has been planning to build more liquefied petroleum gas stations to motivate drivers to use liquefied petroleum gas vehicles in Taiwan. Such facility allocation problem is a multi-objective optimization process considering spatial variation in the need of refueling. This study presents a stochastic multi-objective optimization model for liquefied petroleum gas station allocation (SMOMLSA) that integrates a nondominated sorting genetic algorithm II with a Monte Carlo simulation to optimally allocate liquefied petroleum gas stations according to three trade-off objectives, including investment performance, energy conversion, and business opportunity. Monte Carlo simulation procedure generates the starting location of a taxicab car in need of refueling in the spatial grid based on a probability distribution. Nondominated sorting genetic algorithm II resolves the station location problem with these multi-objectives. The SMOMLSA was validated by conducting a real-world case study. Result depicts that the SMOMLSA can provide information on the optimal allocation of liquefied petroleum gas stations for minimizing construction costs, minimizing average refueling distance for vehicles, and maximizing potential customers.
KeywordsMonte Carlo simulation (MCS) Stochastic multi-objective optimization Nondominated sorting genetic algorithm II Alternative energy
This work was supported in part by the Ministry of Science and Technology of Taiwan under Project MOST108-2218-E-224 -004 -MY3 and the Ministry of Education of Taiwan under the Higher Education Sprout Project. We thank to Bill Thornton who provided the editorial assistance and English language editing.
Compliance with ethical standards
Conflicts of interest
The authors declare no conflict of interest.
- Ishibuchi H, Shibata Y (2004) Mating scheme for controlling the diversity-convergence balance for multiobjective optimization. In: Deb K (ed) Genetic and evolutionary computation—GECCO 2004, vol 3102. Lecture notes in computer science. Springer, Berlin, pp 1259–1271. https://doi.org/10.1007/978-3-540-24854-5_121 CrossRefGoogle Scholar
- Yang M-D, Chen Y-P, Lin Y-H, Ho Y-F, Lin J-Y (2016) Multiobjective optimization using nondominated sorting genetic algorithm-II for allocation of energy conservation and renewable energy facilities in a campus. Energy Build 122:120–130. https://doi.org/10.1016/j.enbuild.2016.04.027 CrossRefGoogle Scholar