Temperature parameter control of Q value-based Dynamic Programming with Boltzmann distribution

In order to improve the efficiency of traffic systems in the global perspective, we proposed a dynamic routing strategy, where the optimal traveling time for each Origin-Destination (OD) pair is calculated by extended Q value-based Dynamic Programming and the global optimum routes are produced by adjusting the temperature parameter in Boltzmann distribution. In this paper, how to control the temperature parameter is discussed in detail depending on the dynamic traffic conditions. What´s more, various temperature parameter control strategies of the Q value-based Dynamic Programming with Botzmann distribution are tested in the simulations. The results show that adopting suitable temperature parameter control strategy could improve the efficiency of the traffic systems effectively.