3rd International ICST Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities (TridentCom)

Research Article

SWARMS: A Sensornet Wide Area Remote Management System

  • @INPROCEEDINGS{10.1109/TRIDENTCOM.2007.4444657,
        author={Charles Gruenwald and Anders Hustvedt and Aaron Beach and Richard Han},
        title={SWARMS: A Sensornet Wide Area Remote Management System},
        proceedings={3rd International ICST Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities (TridentCom)},
        proceedings_a={TRIDENTCOM},
        year={2010},
        month={5},
        keywords={},
        doi={10.1109/TRIDENTCOM.2007.4444657}
    }
    
  • Charles Gruenwald
    Anders Hustvedt
    Aaron Beach
    Richard Han
    Year: 2010
    SWARMS: A Sensornet Wide Area Remote Management System
    TRIDENTCOM
    IEEE
    DOI: 10.1109/TRIDENTCOM.2007.4444657
Charles Gruenwald1,*, Anders Hustvedt2,*, Aaron Beach2,*, Richard Han2,*
  • 1: Department of Computer Science, University of Colorado, BoulderDepartment of Computer Science, University of Colorado, Boulder
  • 2: Department of Computer Science, University of Colorado, Boulder
*Contact email: charles.gruenwald@colorado.edu, anders.hustvedt@colorado.edu, aaron.beach@colorado.edu, richard.han@colorado.edu

Abstract

Our experiences deploying a wide area wireless sensor network (WSN) in the wildfires of Idaho motivate the need for a software middleware system capable of remotely managing many sensor nodes deployed in widely disparate geographic regions. This requirement is unlike the localized focus of many traditional WSN middleware systems, which manage a group of sensor nodes deployed in a single small region, e.g. a warehouse or lab. We describe in this paper SWARMS, a wide area sensor network management system. The SWARMS architecture is designed for scalability and flexibility, while providing an infrastructure to manage in situ sensor nodes, e.g. upload code images, retrieve diagnostics, etc. To demonstrate its flexibility, we present two deployments of SWARMS, the first in a wide area weather sensor network, and the second in a local area testbed that was used by a class of graduate students. To demonstrate its scalability, we analyze the performance of SWARMS when the middleware is subject to sensor data loads of thousands of packets per second.