Abstract
With the technological advancements, practical challenges of establishing long-distance communication should be addressed using hop-oriented routing networks. However, long-distance data transmissions usually deteriorate the quality of service (QoS) especially in terms of considerable communication delay. Therefore, in the presented work, a reward-based routing mechanism is proposed that aims at minimizing the overall delay which is evaluated under various scenarios. The routing process involved a refined CH selection mechanism based on a mathematical model until a threshold simulation is not attained. The illustrations for the coverage calculations of CH in the route discovery are also provided for possible routes between the source and the destination to deliver quality service. Based on this information, the data gathered from the past simulations is passed to the learning mechanism using the Q-learning model. The work is evaluated in terms of throughput, PDR, and first dead node in order to achieve minimal transmission delay. Furthermore, area variation is also involved to investigate the effect of an increase in the deployment area and number of nodes on a Q-learning-based mechanism aimed to minimize the delay. The comparative analysis against four existing studies justifies the success of the proposed mechanism in terms of throughput, first dead node, and delay analysis.