Ad hoc vehicular networks have been identified as a suitable technology for intelligent communication amongst smart city stakeholders as the intelligent transportation system has progressed. However, in a highly mobile area, the growing usage of wireless technologies creates a challenging context. To increase communication reliability in this environment, it is necessary to use intelligent tools to solve the routing problem to create a more stable communication system. Reinforcement Learning (RL) is an excellent tool to solve this problem. We propose creating a complex objective space with geo-positioning information of vehicles, propagation signal strength, and environmental path loss with obstacles (city map, with buildings) to train our model and get the best route based on route stability and hop number. The obtained results show significant improvement in the routes’ strength compared with traditional communication protocols and even with other RL tools when only one parameter is used for decision making.

No abstract

No abstract

The quality of service (QoS) perceived by end users in their access to communication services is mainly driven by transport level protocols, like TCP. Recently a protocol that implements service differentiation by appropriate modifi � at � on of the sliding window size considering the data transfer prIOrIty, called TCP TS-Prio (Transient & Static Priority) protocol, was proposed. In this paper, we propose a methodology that can be used to estimate key performance parameters, such as packet loss, queueing delays, window sizes, and throughputs. Our approach models a single TCP TS-Prio source using a Markovian chain. The superposition and interaction of several TCP sources, with service differentiation, is then analyzed. The analysis shows that TCP TS-Prio is able to offer service differentiation depending on the network congestion.

No abstract