Applying Adaptive Genetic Algorithm for Heterogeneous Vehicle Routing Problem with Asymmetric Distance and Fuzzy Demand (HVRPADFD)

Abstract

This study proposes an improved Genetic Algorithm (GA) so-called Adaptive Genetic Algorithm (AGA) and introduces a new variant of Vehicle Routing Problem (VRP) inspired from liquid fertilizer distribution in Indramayu, Indonesia. This case is basically the combination of some VRP variants where the company has a heterogeneous vehicle with asymmetric distance and fuzzy demand (HVRPADFD). Given that VRP is NP-Hard, this study utilizes AGA as a metaheuristics algorithm. AGA has been modified in terms of self-tuning parameter feature and reproduction modification to remove the exhaustive tuning parameter process and enhance the effectivity of the algorithm simultaneously. AGA is then integrated with the fuzzy set theory based on chance-constrained programming to handle the fuzziness. The verification is also done by comparing AGA with original GA and Ant Colony Optimization (ACO) in solving HVRPADFD. The result shows that AGA is statistically better than others in terms of effectivity. AGA also has faster computational time and is more consistent. The sensitivity analysis is also done to understand the risk of fuzzy demand against traveling distance.