Reinforcement Learning Based Passengers Assistance System for Crowded Public Transportation in Fog Enabled Smart City

Crowding in city public transportation systems is a primary issue that causes delay in the mobility of passengers. Moreover, scheduled and unscheduled events in a city lead to excess crowding situations at the metro or bus stations. The Internet of Things (IoT) devices could be used for data collection, which are related to crowding situations in a smart city. The fog computing data centers located in different zones of a smart city can process and analyze the collected data to assist the passengers how to commute smoothly with minimum waiting time in the crowded situation. In this paper, Q-learning based passengers assistance system is designed to assist the commuters in finding less crowded bus and metro stations to avoid long queues of waiting. The traffic congestion and crowded situation data are processed in the fog computing data centers. From our experimental results, it is found that our proposed method can achieve higher reward values, which can be used to minimize the passengers’ waiting time with minimum computational delay as compared to the cloud computing platform.