A Network Selection Scheme with Adaptive Criteria Weights for 5G Vehicular Systems Emmanouil Skondras 1 , Angelos Michalas 2 , Nikolaos Tsolis 1 , Dimitrios D. Vergados 1 1 Department of Informatics, University of Piraeus, Piraeus, Greece, Email: {skondras, tsolis, vergados}@unipi.gr 2 Department of Informatics Engineering, Technological Educational Institute of Western Macedonia, Kastoria, Greece, Email: amichalas@kastoria.teiwm.gr Abstract—Fifth Generation Vehicular Cloud Computing (5G- VCC) systems use heterogeneous network access technologies to fulfill the requirements of modern vehicular services. Efficient network selection algorithms are required to satisfy the con- straints of Driver Assistance (DA) services, Passengers Enter- tainment and Information (PEnI) services and Medical (MED) services that provided to vehicular users. The presence of MED services affects the importance of other services in situations where patients with immediate health status exist within the vehicle. This paper proposes a network selection scheme which considers the patient health status to adapt the importance of each service. The scheme consists of two Fuzzy Multi Attribute Decision Making (FMADM) algorithms: the Trapezoidal Fuzzy Adaptive Analytic Network Process (TF-AANP) to calculate the relative importance of each vehicular service and the selection criteria, as well as the Trapezoidal Fuzzy Topsis with Adaptive Criteria Weights (TFT-ACW) to accomplish the ranking of the candidate networks. Both algorithms use Interval-Valued Trapezoidal Fuzzy Numbers (IVTFN). Performance evaluation shows that the suggested method outperforms existing algorithms by satisfying the constraints of MED services when the patient health status becomes immediate. I. I NTRODUCTION In a typical 5G-VCC system, vehicles are equipped with On-Board Units (OBUs) with computational, storage and communication resources. Vehicles communicate with each other, as well as with a Cloud infrastructure through the available Access Networks. The Cloud infrastructure offers vehicular services, including Driver Assistance (DA) services, Passengers Entertainment and Information (PEnI) services, as well as Medical (MED) services with strict Quality of Service (QoS) requirements. Indicatively, DA services include Naviga- tion Assistance (NAV) [1] and Parking Assistance (PRK) [2] services. Accordingly, PEnI services include Conversational Video (CV) [3], Voice over IP (VoIP) [4], Buffered Streaming (BS) [5] and Web Browsing (WB) [6] services. Finally, MED services include Live Healthcare Video (LHVideo) [7], Med- ical Images (MedImages) [8], Health Monitoring (HMonitor- ing) [9] and Clinical Data Transmission (CData) [10] services. The presence of MED services raises questions about the importance of other services in situations where there are patients with immediate health status within the vehicle. Thus, the importance of each service, along with the patient’s health status must be considered during the network selection. Several Fuzzy Multiple Attribute Decision Making (FMADM) methods have been proposed for network selection. FMADM methods utilize linguistic variables, triangular fuzzy numbers, trapezoidal fuzzy numbers etc. to model network attributes and their respective weights. Such methods include the Fuzzy AHP - TOPSIS (FAT) [11], the Fuzzy AHP - SAW (FAS) [11], the Fuzzy SAW (FSAW) [12], the Fuzzy AHP MEW (FAM) [11] and the Fuzzy AHP - ELECTRE (FAE) [13]. However, the existing algorithms consider only the selection criteria weights for each service, while they don’t take into consideration the relative importance between the services. Thus, in such cases, the services obtain equal importance with each other, which occurs to inappropriate network selections where MED services are provided to passengers with immediate health status, along with DA or PEnI services. In such cases, MED services must obtain higher importance than the other services during the network selection process, in order the most appropriate network to be selected for satisfying their strict constraints. In this paper, an improved version of the Trapezoidal Fuzzy Topsis (TFT) [14] method is proposed. The scheme consists of two FMADM algorithms, namely the Trapezoidal Fuzzy Adaptive Analytic Network Process (TF- AANP) to calculate the relative importance of the vehicular services and the selection criteria, as well as the Trapezoidal Fuzzy Topsis with Adaptive Criteria Weights (TFT-ACW) to accomplish the ranking of the candidate networks. The remainder of the paper is as follows: Section II de- scribes the proposed scheme, while Section III presents the simulation setup and the evaluation results. Finally, section IV concludes the discussed work. II. THE PROPOSED NETWORK SELECTION SCHEME The proposed method consists of two MADM algorithms: the Trapezoidal Fuzzy Adaptive Analytic Network Process (TF-AANP) to calculate the relative importance of the services and of the selection criteria, as well as the Trapezoidal Fuzzy Topsis with Adaptive Criteria Weights (TFT-ACW) to accomplish the ranking of the candidate networks. Interval- Valued Trapezoidal Fuzzy Numbers (IVTFN) [15] are used for the representation of both criteria values and their importance weights.