Traffic Signal Control with Autonomic Features

Abstract

Inspired by diverse organic systems, autonomic computing is a rapidly growing field in computing science. To highlight this advancement, this chapter summarises the autonomic features utilised in a traffic signal control in the form of an operational control system, not simply a simulation study. In addition, the real-time simulation is used to refine the raw sensor data into a comprehensive picture of the traffic situation. We apply the multi-agent approach both for controlling the signals and for modelling the prevailing traffic situation. In contrast to most traffic signal control studies, the basic agent is one signal (head) also referred to as a signal group. The multi-agent process occurs between individual signal agents, which have autonomy to negotiate their timing, phasing, and priorities, limited only by the traffic safety requirements. The key contribution of this chapter lies not in a single method but rather in a combination of methods with autonomic properties. This unique combination involves a real-time microsimulation together with a signal group control and fuzzy logic supported by self-calibration and self-optimisation. The findings here are based on multiple research projects conducted at the Helsinki University of Technology (now Aalto University). Furthermore, we outline the basic concepts, methods, and some of the results. For detailed results and setup of experiments, we refer to the previous publications of the authors.