A Q-Learning and Fuzzy Logic-Based Hierarchical Routing Scheme in the Intelligent Transportation System for Smart Cities

A vehicular ad hoc network (VANET) is the major element of intelligent transportation system (ITS). The purpose ITS to increase road safety and manage movement vehicles. known as one main components smart cities. As a result, there are critical challenges such routing in these networks. Recently, many scholars have worked on this challenge VANET. They used machine learning techniques learn proceeding networks adaptively independently. In paper, Q-learning fuzzy logic-based hierarchical protocol (QFHR) proposed for VANETs. This technique consists three phases: identifying traffic conditions, algorithm at intersection level, level. first phase, each roadside unit (RSU) stores table, which includes information about conditions related four sections connected corresponding intersection. Then, RSUs use Q-learning-based method discover best path between different intersections. Finally, vehicles section choose foremost relay node. simulation QFHR has been executed simulator version 2 (NS2), its results presented comparison with IRQ, IV2XQ, QGrid, GPSR two scenarios. scenario analyzes result based packet sending rate (PSR). scenario, gets better delivery by 2.74%, 6.67%, 22.35%, 29.98% decreases delay 16.19%, 22.82%, 34.15%, 59.51%, lowers number hops 6.74%, 20.09%, 2.68%, 12.22% compared GPSR, respectively. However, it increases overhead approximately 9.36% 11.34% IRQ Moreover, second evaluates regard signal transmission radius (STR). PDR 3.45%, 8%, 23.29%, 26.17% 19.86%, 34.26%, 44.09%, 68.39% reduces 14.13%, 32.58%, 7.71%, 21.39% higher than (11.26%) IV2XQ (25%).