Social Drive: A Crowdsourcing-based Vehicular Social Networking System for Green Transportation Xiping Hu 1 , Victor C. M. Leung 1 , Kevin Garmen Li 1 , Edmond Kong 1 , Haochen Zhang 1 , Nambiar Shruti Surendrakumar 2 , Peyman TalebiFard 1 1 Dept. of Electrical & Computer Engineering, The University of British Columbia, Vancouver, Canada V6T 1Z4 2 Dept. of Computer Science, Birla Institute of Technology & Science-Pilani, Dubai {xipingh, vleung}@ece.ubc.ca ABSTRACT This paper presents Social Drive, a novel crowdsourcing-based vehicular social networking (VSN) system for green transportation. Social Drive integrates the standard vehicular On- Board Diagnostics (OBD) module, leverages the advantages of cloud computing and popular social networks, and incorporates a novel rating mechanism about the fuel economy of drivers. Based on these, Social Drive provides a user-friendly mobile application on smartphones targeting drivers, which enables a seamless and economic solution that promote drivers’ awareness of their driving behaviors regarding fuel economy of specific trips. Our practical experiments have demonstrated that Social Drive works efficiently with low battery consumption and low networking overhead on popular mobile devices. Categories and Subject Descriptors C.2.4 [Computer Systems Organization]: COMPUTER COMMUNICATION NETWORKS - Distributed Systems - Distributed applications. General Terms Design, Human Factors, Economics. Keywords Vehicular social networks, mobile application, database, cloud. 1. INTRODUCTION Everyday, a large number of urban dwellers spend hours traveling along the same routes at about the same time on their commute to and from work. Their travel patterns are highly predicable and regular. Consequently, there is an opportunity to form recurring virtual mobile communication networks and social communities between these travelers or their vehicles in the form of vehicular social networks (VSNs) [1]. Unlike conventional mobile social networks, where the participants are humans who converse with one another using mobile phones, the participants of VSNs are heterogeneous, and include vehicles, devices onboard vehicles, as well as drivers, passengers, and pedestrians. Thus, three types of relationships are found in VSNs: (i) between human and human, (ii) between human and machine, and (iii) between machine and machine. Previous research has shown that knowledge from the social interactions between nodes can help to improve the performance of mobile systems [2-4]. Therefore, it is anticipated that VSN applications can be effectively used for many purposes. The three most common types of applications over VSNs are: (a) Safety improvements: applications that improve the safety of drivers, passengers and pedestrians by notifying them about any dangerous situations on the roads [5]; (b) Traffic management: applications that provide users with up-to-date traffic information and recommendations that enable them to make better decisions to reduce travel time, and hence improving traffic flow and driving efficiency; (c) Entertainment: applications that enable the streaming, downloading, or sharing of multimedia files over the VSN [6]. In this paper, we focus on the second type of VSN applications. With the popular use of smart phones and other mobile devices, especially for social networking applications, people can easily interact and share information with each other anytime and anywhere. There is a remarkable trend to leverage mobile devices and applications to enable crowdsourcing in order to address a diversity of problems that involve real-time data collection and processing, and collaborations among a large number of participants in mobile environments to contribute their experience in an effective and economical manner [7]. Crowdsourcing not only potentially brings huge economic benefits, but also leads to revolutions in many aspects of our daily lives. Thus, a connection exists naturally between VSN and crowdsourcing, where VSN applications can be developed to address many crowdsourcing problems, while crowdsourcing could be an emerging strategy to improve the user experience and efficiency of VSN applications. Currently, a number of crowdsourcing based mobile applications that target green transportation have been successfully applied to vehicular application scenarios, such as UbiGreen [8], Cyber- physical bike [9], GreenGPS [10], and HyDi [11]. However, most of them focus on the functionalities of the applications themselves, but not much has been considered about how to enable the users in vehicular environments to participant in such applications easily and widely; e.g., a friendly user interface (UI) is lacking in many of these applications, and most of them have not leveraged the advantages of popular social networks to support large groups of users. Moreover, a seamless and comprehensive solution that could support real-world deployment of VSN applications is also lacking. This paper fills the gaps identified above by proposing Social Drive, a crowdsourcing-based VSN system for green Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. DIVANet’13, November 3- 8, 2013, Barcelona, Spain. Copyright 2013 ACM 978-1-4503-2358-1/13/11 ...$15.00.