Abstract

With the miniaturization of computing, communication and sensor devices, sensor networks are becoming increasingly attractive for a wide range of applications, such as homeland security and environment monitoring (e.g., pollution detection).
Since sensor networks will be employed for critical applications (ranging from homeland security to hazard detection), timeliness becomes a critical issue in particular when the system is subject to a dynamic workload. In fact, unpredictable changes of the environment that a sensor network has to interact with, trigger different network actions generating such a dynamic workload.
Two innovative approaches, called "Implicit EDF" and "Collaborative Resource Allocation" will be presented, which have been developed to address the new challenges (i.e., temporal predictability and dynamic workloads) faced by sensor networks. These approaches allow us to effectively and efficiently optimize a wireless sensor network performance, while still providing real-time guarantee.

Marco Caccamo is an Assistant Professor of the Dept. of Computer Science at University of Illinois. He graduated cum laude in Computer Engineering at University of Pisa in 1997. He received a PhD in Computer Engineering from Scuola Superiore S.Anna in 2002. His research interests include real-time operating systems, real-time scheduling and resource management, wireless sensor networks, and quality of service control in next generation digital infrastructures.