QoS Aware and Fault Tolerance Based Software-Defined Vehicular Networks Using Cloud-Fog Computing

Sensors

Samreen Hussain¹  Hira Zahid²  Sidra Abid Syed²  Asif Umer³  Abdul Waheed⁴  Fahad Azim⁵  Munaf Rashid⁶  Cesar Vargas-Rosales⁷  Mahdi Zareei⁷ 

[1] Begum Nusrat Bhutto Women University, Sukkur 65400, Pakistan;Department of Biomedical Engineering, Faculty of ESTM, Ziauddin University, Karachi 74600, Pakistan;Department of Computer Science & Information Technology, Hazara University, Mansehra 21120, Pakistan;Department of Computer Science, Northern University, Nowshera 24100, Pakistan;Department of Electrical Engineering, Faculty of ESTM, Ziauddin University, Karachi 74600, Pakistan;Department of Electrical and Software Engineering, Faculty of ESTM, Ziauddin University, Karachi 74600, Pakistan;Tecnologico de Monterrey, School of Engineering and Sciences, Zapopan 45201, Mexico;

关键词: vehicular ad-hoc network;    quality of service;    priority basis scheduling;    safety/non-safety messages;    response time;    fault-tolerance;   

DOI  :  10.3390/s22010401

来源: DOAJ

【 摘 要 】

Software-defined network (SDN) and vehicular ad-hoc network (VANET) combined provided a software-defined vehicular network (SDVN). To increase the quality of service (QoS) of vehicle communication and to make the overall process efficient, researchers are working on VANET communication systems. Current research work has made many strides, but due to the following limitations, it needs further investigation and research: Cloud computing is used for messages/tasks execution instead of fog computing, which increases response time. Furthermore, a fault tolerance mechanism is used to reduce the tasks/messages failure ratio. We proposed QoS aware and fault tolerance-based software-defined V vehicular networks using Cloud-fog computing (QAFT-SDVN) to address the above issues. We provided heuristic algorithms to solve the above limitations. The proposed model gets vehicle messages through SDN nodes which are placed on fog nodes. SDN controllers receive messages from nearby SDN units and prioritize the messages in two different ways. One is the message nature way, while the other one is deadline and size way of messages prioritization. SDN controller categorized in safety and non-safety messages and forward to the destination. After sending messages to their destination, we check their acknowledgment; if the destination receives the messages, then no action is taken; otherwise, we use a fault tolerance mechanism. We send the messages again. The proposed model is implemented in CloudSIm and iFogSim, and compared with the latest models. The results show that our proposed model decreased response time by 50% of the safety and non-safety messages by using fog nodes for the SDN controller. Furthermore, we reduced the execution time of the safety and non-safety messages by up to 4%. Similarly, compared with the latest model, we reduced the task failure ratio by 20%, 15%, 23.3%, and 22.5%.

【 授权许可】

Unknown