Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
| Hi-index | 0.00 |
We have designed a new urban travel route optimization model in combination with a new microscopic simulation paradigm. The core of the system stands over the assumption that we can have a traffic network with an Advanced Traffic Information System (ATIS) installed that advises drivers at every intersection as to which direction to take, depending of their destination. We have implemented a parallel Genetic Algorithm, running over a Beowulf cluster that performs a real-time optimization yielding that set of advised routes. By these means we propose an implicitly adaptable, expandable and flexible solution for the traveler route assignment problem, in order to maximize the performance of an urban network. Although in Dynamic Traffic Assignment (DTA) a rigorous Wardrop's User Equilibrium --- [6] --- cannot be fully carried out, we have developed a set of experiment aiming to see if there is a visible tendency to a User Equilibrium state for the proposed model. Results are encouraging.