Vehicular ad hoc networks (VANETs) are characterized by high mobility of nodes and frequent changes in the network topology, which significantly complicates the process of routing data packets.It has been shown that traditional routing protocols are unable to promptly follow these changes and cannot be efficiently used in VANETs for vehicle to vehicle (V2V) communications.This is the reason why protocols based on reinforcement learning (RL) have been developed.These protocols enable constant monitoring of changes in the network environment, and adaptation of the routing process to those changes.In this paper, an analysis and comparison of the traditional and RL based routing protocols are performed in VANET scenario.The Ad hoc on-demand distance vector routing protocol (AODV) and AODV with Expected transmission count (ETX) metric are chosen as the representatives of traditional routing protocols, while the Adaptive routing protocol based on reinforcement learning (ARPRL) is chosen as the representative of routing protocols based on RL.The simulation results show that the ARPRL protocol has significantly better network performance in terms of packet loss ratio (PLR) and end-to-end delay (E2ED) in urban VANET scenario.
The needs of users of postal services are becoming more and more demanding for postal operators day by day.The environment in which the postal sector develops is constantly changing.Achieving quality standards, keeping pace with technological solutions, and developing new services and business models are real challenges for postal service operators.Within this paper, an overview of the current state of the postal services market, both at the global level and in the Republic of Serbia, is given.Also, following the conclusions of the Report of the Universal Postal Union on the development of postal traffic for the year 2022, a presentation of possible directions for the development of postal services through two advanced services is given: the sharing economy and sustainable logistics.
The growth of available information on the Internet and enormous diversity in user's behaviour indicate the exceptional importance of service personalization.Creating of the individual user profile is a key activity that precedes service personalization.Forming an automated user profile is the main challenge in development of the personalized applications that fully meet needs of the user.This research includes the information that needs to be modelled to represent different user profiles, how the information is collected, how to construct the user profile and finally how the user profile is used to deliver a personalized service.The proposed user profiling process includes three basic activities: data collection, user profile construction and personalization.Paper gives the comparison of the user profile methods and techniques.The findings showed that proposed user profiling process improves construction of the accurate user profile for effective service personalization.
Road safety key performance indicators (KPI) are the indicators reflecting those operational conditions of the road traffic system that are influencing the system's safety performance.The automated process of KPIs data collection, accompanied by advanced smart solutions in urban areas, smart in-car solutions, etc. is expected in the near future.The European Commission developed a set of common methodological guidelines for the data collection and estimation of the KPIs in the European Union countries.Internet of Vehicles is an emerging technology approach that can be expected to become a promising solution to overcome serious traffic issues.The objective of this paper is to explore the process of road safety KPIs data collection and sharing using Internet of Vehicles networking.In that context, a star rating of driver's behavior could be done, and such data could be shared aiming to better improve drivers' safety behavior.
The number and locations of facilities represent the most important decisions when modeling service networks.The facility location problem in the context of service networks is predetermined by the investment costs and/or achieving a certain standard of satisfying users' demand.Systems designed in this way are based on the idea that they will function in regular exploitation conditions, without any interference.However, various adverse events caused by intent, unintentional human activities, technological disasters or natural disasters can lead to a partial or complete cessation of the service networks.For the first time, this paper highlights the importance of the impact assessment of disruption events on the service networks where the r-interdiction median location model is presented as a potential solution approach in a case when these events occur.Also, an extensive overview of the state-of-the-art literature is provided.Finally, a numerical example of the determination of the most vulnerable points of service networks is given to illustrate the effects of potential disruptions, as well as appropriate preventive actions that eliminate or at least mitigate those situations.
