6. DISCUSSION AND CONCLUSION
Under conditions when congestion in traffic networks is a common occurrence, there is significant practical meaning in studying the dynamic shortest path problem. In this paper, we analyzed the spatial distribution characteristics and dynamics of a traffic network; we analyzed the characteristics of a genetic algorithm and an ant colony algorithm; discussed the basic method and strategy to integrate the genetic algorithm into an ant colony algorithm; and based on that we developed a novel dynamic shortest path algorithm. Our goal was to find effective methods to identify the optimal path in a dynamic traffic network. In order to study the performance of the new algorithm, an experiment was designed to test its performance. The experimental results showed that the proposed algorithm had a much-improved performance compared with the unmodified ant colony algorithm; therefore, the novel algorithm is practicable From the above experimental results, it can be known that it is very effective that integrating ant colony algorithm and genetic algorithm to find the shortest path between two nodes in the traffic network. In the hybrid algorithm, the excellent performance of ant colony algorithm and genetic algorithm are fully exhibited. In this paper, the characteristics of the traffic network are taken into account during the process of searching the shortest path, therefore, the intelligent algorithms make full use of their excellent performance and the efficiency of the algorithm is greatly improved. Genetic algorithms and ant colony algorithms are intelligent optimization algorithms with fine properties. The main purpose of fusing the two intelligence algorithms was to enhance the problem solving ability of the algorithm in order to obtain better quality solutions than the traditional algorithms.
