Elevator group supervisory control system using genetic network programming - Ranking processing and node function optimization

Genetic Network Programming (GNP) has been proposed as a new method of evolutionary computations. Recently, GNP is applied to Elevator Group Supervisory Control System (EGSCS), that is, a benchmark of real world applications and its effectiveness is clarified. The EGSCS using GNP in the previous studies can control the elevator system using the conventional node functions. However, they do not have enough flexibility and generality for some uncertain factors due to the various different conditions in elevator systems. In this paper, several new frameworks of GNP for EGSCS are proposed in order to overcome the above problem considering the ranking calculation of elevators and node function optimization based on Real-coded GA. In the simulations, it is clarified that the proposed method can obtain better performances than the conventional methods.