Future Heterogeneous Networks

<p>The workshop FutureHetNets 2011 on "Highly Controllable Dynamic Heterogeneous Networking" was held on March 24--25, 2011 at NASA Ames Research Center in Mountain View, California. It was sponsored by the Large Scale Networking Coordinating Group (LSN) of the Networking and Information Technology Research and Development (NITRD) interagency community, and supported by the National Science Foundation (NSF) and NASA. The workshop brought together 74 leading researchers from US institutions to discuss the research and development activities needed to enable the end-to-end, scalable, highly controllable, secure heterogeneous networks of the future.</p><p>The workshop was designed to uncover tough networking problems, especially those driven by the properties of new physical layer communication systems, and explore architecture constructs that may provide realistic solutions for the realization of an integrated heterogeneous network. Workshop participants were encouraged to consider fundamental architectural changes, covering the entire stack from the Physical to the Application Layers that hold the potential for major breakthroughs in heterogeneous network performance.</p><p>Computing power will increase dramatically in the near future with the development of advanced multi-core processors and cloud computing and storage. The limiting factor on how fast new applications will develop is the availability of high network speeds and much better quality of service at reasonable costs. Device technologies and hardware subsystems are mature enough to provide at least two orders of magnitude increase in network speeds. However, left to incremental developments, the current Internet architecture will not be able to support heterogeneous applications over heterogeneous networks at affordable costs. The principal reason is that the current architectural partitioning of networks into layers has run its course and is approaching the saturation point for further major improvements.