Organizers

Ashok Agrawala, University of Maryland and Lui Sha, University of Illinois

Sponsors

National Science Foundation

Background

The Internet has impacted all aspects of society fundamentally changing how corporations, governments and citizens receive, manage, and deliver services. The basic architecture of the Internet has proven remarkably adaptive over various link technologies and has successfully supported a wide variety of applications. Higher layer protocols for strong security have also been successful. Advances in sensors, nano-machines, and low-power devices are enabling an entirely new class of Internet-based applications in the sensing, monitoring and control domains. The successes of the Internet have directly led to a partial adoption of its protocols into these new domains, even if they may not be particularly suited, because equipment running Internet protocols are inexpensive to obtain and easy to maintain. However, the IP based networks are not well suited for applications which have strict timing requirements. As a consequence, a number of special-purpose protocols and standards have been developed.

The proliferation of special-purpose real-time networking standards increases cost and creates inter-operability problems when these networks are linked. Further, timing constraints of protocols may be violated by the usual Internet security protocols. Finally, many of these protocols must provide absolute performance guarantees to safety-critical loops, regardless of potential component failures, denial-of-service attacks or network congestion.

Goal

Within the context of GENI, our goal is to stimulate research for inventing a new infrastructure to usher the convergence of computing, communication and the intelligent monitoring and control of our physical environment. We bring together the networking, real-time embedded systems community, and end-user communities to develop a system perspective.

We want to take a fresh look on how to invent a coherent set of networking, RTOS, middleware and QoS management protocols that are capable of providing guaranteed services without creating excessive overheads for delay tolerant applications. We want to answer the following questions.

1. How can we characterize the QoS requirements of:
   1. Loosely coupled wide area system of systems such as power generation, distribution and control as well as network centric collaborative engagement?
   2. Tightly coupled local systems such as automobile, avionics, manufacturing plants and chemical process control?
   3. Newly emerging high reliability and delay sensitive wireless based systems such as operating rooms of the future?
2. For each class, what are the MINIMAL and LOWEST COST QOS supports that GENI (the underlying networking infrastructure) must support so that your [Avionics/power/auto/space/medical] community would consider abandoning your domain specific standard?
3. How can we abstract diverse QoS requirements and construct a set of QoS mechanisms and put them at the appropriate layers within a coherent framework? What will be the structures of the control (setup and reconfigurations guarantees) and data paths (bandwidth, delay, and jitter guarantees) in a variety of core and peripheral networks including wireless network with high mobility?
4. What kind of experimentation facility do you need to demonstrate underlying mechanisms and applications at scale? How would you design a "shared" facility for the community as opposed to dedicated facility for each group to do experimentation on?
5. How would you promote collaborations among different communities to create the best framework or architectures for real time networked embedded systems?