Artificial immunity to control disturbances in public transportation systems: Concepts, mechanisms and a prototype implementation of a knowledge based decision support system.

In public transportation, the occurrence of unpredictable disturbances (e.g. accidents, delays, traffic congestion, etc.) may affect the expected execution of preset organization and pre-established timetables of transportation resources (buses, trains, metros, trams, etc.). Affected timetables may become useless, or at least deviate from expected behavior and/or performance. Unfortunately, existing literature suffers limitations with respect to the development of decision support approaches and tools that are able to help decision makers in monitoring and controlling public transportation systems, particularly at the occurrence of disturbances. Existing works are still limited with respect to dealing with several types of disturbances, and suggesting reactive decisions at execution time in such a way to maintain the performance of pre-established timetables and provide users with high quality of services (in terms of punctuality, frequency of programmed shuttles, etc.). In this paper, we show that biological immunity can provide useful principles and mechanisms that are pertinent for the management of disturbances in public transportation systems. We highlight these principles and mechanisms, associate them with application components and fully document them. To show their feasibility, we develop a prototype artificial immune system able to assist decision makers in performing several disturbance management functions, such as detection of disturbances, construction of reaction strategies, supervised learning and memory of previous experiences with disturbances. Through experimental validation, we show that immune concepts and mechanisms can yield to the design and implementation of knowledge based decision support tools that are able to deal with different kinds of disturbances, and to assist decision makers through the disturbance management process. [ABSTRACT FROM AUTHOR]