The smart surface network: A bus-based approach to dense sensing

• Published in: Computer networks (Amsterdam, Netherlands : 1999) Vol. 83; pp. 167 - 183
• Main Authors: Ali, Farha N., Feaster, Yvon, Zhai, Jiannan, Hallstrom, Jason O.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 04.06.2015; Elsevier Sequoia S.A
• Subjects: Algorithms; API; Application programming interface; Architecture (computers); Bus-based communication; Buses (vehicles); Communications networks; Computer architecture; Computer networks; Data buses; Dense sensing; Detection; Hardware; Hardware/software co-design; Indoor sensing; Networks; Peer to peer computing; Studies; Bus-based communication; Hardware/software co-design; Indoor sensing; Dense sensing
• ISSN: 1389-1286; 1872-7069
• DOI: 10.1016/j.comnet.2015.03.009

We present the Smart Surface Network (SSN), a hardware and software platform designed for dense sensing. Sensor nodes connected to the SSN communicate using a serial bus integrated within a mountable physical surface. The hardware architecture and bus access and communication mechanisms are implemented in a self-stabilizing manner, providing robust handling of unannounced arrivals and departures of network devices. An associated API supports a peer-to-peer communication paradigm, providing access to the physical, data link, and application layers of the bus. In this paper, we describe the SSN hardware architecture and present the bus access and peer discovery algorithms. We also discuss the design of the API and describe experimental results characterizing the fairness of the bus algorithm, the efficiency of the peer discovery algorithm, and the performance of the SSN system under varying load conditions.