LEARNABLE EVOLUTION MODEL: Evolutionary Processes Guided by Machine Learning
Machine Learning - Special issue on multistrategy learning
A genetic algorithm for a bi-objective capacitated arc routing problem
Computers and Operations Research
A deterministic tabu search algorithm for the capacitated arc routing problem
Computers and Operations Research
Learning with case-injected genetic algorithms
IEEE Transactions on Evolutionary Computation
| Hi-index | 12.05 |
The Extended Capacitated Arc Routing Problem (ECARP) is a challenging vehicle routing problem with numerous real-world applications. We propose an improved evolutionary approach to cope with the ECARP in this research. The exploitation of heuristic information characterizes our approach. Two kinds of heuristic information, Arc Assignment Priority Information and Performance Information of Operators, are learned from the obtained near-optimal ECARP solutions. The Arc Assignment Priority Information is employed to decide one suitable broken position for the crossover and mutation operation, while the Performance Information of Operators is used to select an appropriate operator for the operations of selection, crossover and mutation. The effectiveness of our approach is demonstrated by 20 instances with up to 100 nodes and 360 arcs.