An efficient cloud–assisted best–parking algorithm for BikeNet. (20th August 2014)

• Record Type: Journal Article
• Authors: Chang, Hong–Yi; Huang, Shih–Chang; Lin, Yuan–Wei
• Is Part Of: International journal of ad hoc and ubiquitous computing. Volume 16:Number 2(2014)
• Page Start: 136
• Page End: 148
• Publication Date: 2014-08-20
• Subjects: BikeNet -- bike networks -- cloud computing -- MapReduce -- best parking -- cycling -- bicycles -- parking spaces -- simulation -- bike parking -- bike stations; Ubiquitous computing -- Periodicals; Embedded computer systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Wireless communication systems -- Periodicals; Computer architecture -- Periodicals; 004.2
• Languages: English
• ISSNs: 1743-8225

Abstract

Numerous countries have implemented public bike policies. Users can rent a bike in one place, and return it at a different location. However, users that change to another type of transport may spend considerable time searching for a parking space for the bike. This study proposes an efficient best–parking (BP) algorithm for bike networks. This mechanism efficiently offers bike users route with parking spaces nearby destination. This study also presents a parallel BP algorithm based on the MapReduce model to accelerate the computation of the ideal route for parking. Simulation results show that the performance of the proposed algorithm is ~70% better than that of the aggregating data dissemination (ADD) algorithm and 91% better than that of the parking space discovery (PSD) algorithm. The proposed BP algorithm collects parking–space information only as needed. Therefore, the BP communication overhead is considerably lower than that of ADD or PSD algorithms.