Crowd-based Smart Parking

From NetSysLab

Jump to: navigation, search

The goal of this project is to explore the basic design principles applicable to an array of crowdsourcing-based applications by investigating a specific case study, namely the smart parking system. Through simulations, we show that the strategies behind crowdsourcing can heavily influence the utility of such applications. Equally importantly, we show that tolerating a certain level of freeriding increases the social benefits while maintaining quality of service level offered. Our findings provide designers with a better understanding of mobile crowdsourcing features and help guide successful designs.

Our contributions in this study fall in two categories: On the one hand, we demonstrate, through simulations, that mobile crowdsourcing is a feasible and cost effective approach to deploy a smart parking system. On the other hand, we regard this application as a case study to demystify some rumors that have influenced the design of mobile crowdsourcing-based applications for a long time. We find that recruiting more participants may not necessarily lead to a better performance if the crowdsourcer fails to coordinate people’s behavior in the context of these applications. We show that people can provide valuable data even through the simplest manual operation in a dynamic mobile environment if they are coordinated. We also discover that a proper policy to deal with free-riders will improve social benefits without sacrificing the quality of the crowdsourcing-based service. These findings can serve as a catalyst to facilitate the development of similar mobile applications and help double the number of success stories.

This work explores a preliminary set of factors that could influence the performance of similar applications. We will further our study by comparing the features between centralized and crowdsourcing-based approaches and try to provide a mechanism to generate cost-effective alternatives to those expensive centralized solutions.


People

Xiao Chen
Elizeu Santos-Neato
Matei Ripeanu


Publications

[1] Crowd-based Smart Parking: A Case Study for Mobile Crowdsourcing, Xiao Chen, Elizeu Santos-Neto, Matei Ripeanu, 5th International Conference on MOBILe Wireless MiddleWARE, Operating Systems, and Applications(MOBILWARE 2012), Berlin, Germany. pdf
[2] Crowdsourcing for On-street Smart Parking, Xiao Chen, Elizeu Santos-Neto, Matei Ripeanu, Second ACM International Symposium on Design and Analysis of Intelligent Vehicular Networks and Applications (DIVANet’12) (Accepted) pdf poster slides