Scalable IoT architecture for balancing performance and security in mobile crowdsensing systems

Abstract

Crowdsourcing aims to deliver services and content by aggregating contributions from a large user population. For mobile networks and IoT systems, crowdsourcing is used to gather and process sensor data from mobile devices (crowdsensing), in order to deliver real-time, context-aware services and possibly support user collaboration in extended geographic areas. In applications like geonsensitive navigation, location-based activity sharing and recommendations, the challenge of adequate service quality and user experience may be at stake, as the services are provided securely to an ever-growing user population. This happens due to the inherent trade-off between security and real-time performance that ultimately sets in doubt any scalability prospect beyond a certain user-interaction load. This work introduces a publish-subscribe architecture for mobile crowdsensing systems, which can be transparently scaled up to higher usage load, while retaining adequate performance and security by load balancing into multiple MQTT brokers. The security support combines a lightweight TLS implementation with an integrated mechanism for two-level access control: user-device interactions and message topics. We provide proof-of-concept measurements that show how our solution scales to increasing interaction loads through load-balancing the processing cost that includes the overhead of the security mechanisms applied. The system architecture was implemented in a vehicular crowdsensing navigation network that allows to exchange navigation information at real-time, for improved routing of vehicles to their destination.