Application of vector ordinal optimization to the transportation systems with agent based modelling

As the computing technology develops, micro-simulation becomes more and more important in the Intelligent Transportation Systems (ITS) research, because it can provide detailed descriptions of the system. However, for a multi-agent systems (MAS) modelling of an ITS, the computation burden is large, as it involves the computation of the state changing of all the agents. Further, if we consider simulation based optimization, which can be simply understood as an intelligent way of running a number of micro-simulations, the computation burden is huge. Moreover, there are multiple objective optimization problems in the ITS. The Vector Ordinal Optimization (VOO) method is a powerful tool for multi-objective optimization. In this paper, we apply VOO to the problem of optimizing the stop times and delay time of an ITS. We test the method on a 4 intersection lattice road network, and on the 18 intersection road network of the Zhongguancun area of Beijing. Compared with the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) method, the VOO method can achieve a speedup of factor of more than 150, with only a little sacrifice of performance.