In the past few years we are witnessing increased interest in the research of inter-vehicle communications. Due to vehicle specific movement patterns new algorithms and solutions have to be developed. Clustering is a technique for grouping nodes in geographical vicinity together, making the network more robust and scalable. This article presents an overview of proposed clustering algorithms for use in vehicular ad-hoc network (VANET). We survey different clustering algorithms and highlight their objectives, features, specialties and possible limitations. Varieties of different approaches have been observed whereby typically each one focuses on different performance metric. Diverse are also complexities of algorithms and the input data they use and relay on. With this article, readers can have a more thorough and delicate understanding of ad hoc clustering and the research trends in this area. The most promising solutions show the significance of reused concepts from the field of social network analysis.
展开▼