Officials of the U.S. Defense Advanced Research Projects Agency (DARPA) in Arlington, Va., announced $10 million contract to Raytheon BBN on Tuesday for a research project under the Dispersed Computing (DCOMP) program, which focuses on algorithms for dispersed mission-aware computation; programmable nodes and protocol stacks; and technology integration.
The DARPA DCOMP program seeks to produce software instantiations of algorithms and protocol stacks that leverage pervasive, physically dispersed computing platforms to boost application and network performance by orders of magnitude.
Examples of such computer architectures include network elements, radios, smart phones, or sensors with programmable execution environments; and portable micro-clouds of different form factors.
Military users with significant computing requirements typically depend today on access to large, shared data centers to which they backhaul their images, video, or network log files for processing, DARPA officials explain.
Yet the cost and latency of this backhaul sometimes can cause problems in different operational scenarios -- especially when network throughput is severely limited or when the user application requires a near real-time response.
In these conditions users could benefit from using taskable computing power that available locally. The DCOMP program seeks scalable decision systems that enable secure, collective tasking of computing assets in a mission-aware fashion by users with competing demands, and across large numbers of heterogeneous computing platforms, officials say.
These systems must be able to operate in environments where network connectivity is variable and degraded, and enable users to move code to data, and data to code to suit users, applications, and mission needs best.
The DCOMP program also seeks new kinds of network protocols that avoid drawbacks involved with confining application-layer and transport-layer protocol logic to the end points that act as sources and sinks of the data. Today programmable, secure high-speed information processing within the network now is technically feasible.
The project seeks to create programmable platforms networked computation points (NCPs) that use DCOMP software. An NCP could execute functions in support of user applications, network protocol stacks, or both.
Related: DARPA seeks to develop real-time intelligence processor to uncover patterns in vast data
Raytheon BBN experts will develop algorithms and control mechanisms to enable efficient use of networked, geographically dispersed, heterogeneous computing capabilities.
These algorithms will benefit users whose tight constraints on latency make interactions with distant data centers difficult, and whose computational complexity may preclude sole reliance on the user’s end device. In such cases using computing power from nearby networked computation points may enhance user performance.
New algorithms also could help with processing sensor data when users are limited to nearby computers to reduce the need for high-volume backhaul of unprocessed information to distant data centers.
Algorithms must be able to rank the importance of available computer resources among competing tasks and users. Systems should be able to scale to thousands of simultaneous users and computing locations.
On this contract Raytheon BBN will do the work in Cambridge, Mass., and should be finished by April 2021. For more information contact Raytheon BBN online at www.raytheon.com/ourcompany/bbn, or DARPA at www.darpa.mil.
Learn more: search the Aerospace & Defense Buyer's Guide for companies, new products, press releases, and videos
