Supports air-traffic management, combat management and C4ISR systems with thousands of sensors and millions of updates per second
BOSTON, MA, Embedded Systems Conference—October 28, 2008—Real-Time Innovations (RTI), The Real-Time Middleware Experts, today announced scalability and performance enhancements to RTI Data Distribution Service, its real-time messaging middleware. These new features significantly ease the integration of large-scale real-time applications with high-capacity networked sensors that are often used in radar and imaging applications.
RTI's network-centric architecture makes it well suited for integration with the GIG.
With these enhancements, systems can now efficiently scale to thousands of sensors and millions of data updates per second, both of which are one to three orders of magnitude higher than with traditional integration middleware. This allows real-time systems—including those designed for air-traffic management; combat management; and command, control, communications, computers, intelligence, surveillance and reconnaissance (C4ISR)—to analyze more data from more sensors for increased situational awareness and improved tactical decision-making.
RTI Data Distribution Service eases sensor integration by decoupling the software embedded within sensors from the applications that consume sensor data. RTI Data Distribution Service automatically connects sensors and applications by discovering which sensors and data are available and then distributing data of interest to each application. Because individual software components are loosely coupled, sensors and applications can be added or updated without impacting any other system component, thus maximizing survivability and minimizing long-term software maintenance costs.
This network-centric integration approach makes RTI Data Distribution Service well suited for deployment in dynamic environments such as defense systems. Applications can automatically discover and take advantage of newly connected sensors or adapt to sensors that are no longer accessible—without any software or configuration changes. This allows deployment at the network edge, where system administration may not be practical. It also allows applications to easily scale as they are integrated into systems of systems and with the Global Information Grid (GIG).
RTI Data Distribution Service complies with the Object Management Group (OMG) Data Distribution Service for Real-Time Systems (DDS) application programming interface and the DDS Wire Interoperability Protocol, which is the Real-Time Publish Subscribe (RTPS) protocol. DDS is widely used as an integration standard by major defense and infrastructure programs. It is a mandated standard for publish-subscribe messaging by the U.S. Department of Defense Information Technology Standards Registry (DISR). Programs that have adopted DDS include the U.S. Navy's DDG 1000 and FORCEnet, the U.S. Army's Future Combat Systems (FCS), and the joint Air Force, Navy and Defense Information Systems Agency's (DISA) Net-Centric Enterprise Solutions for Interoperability (NESI).
"RTI is excited to enhance its support for net-centric and GIG integration by extending our middleware solution to allow integration of high-capacity networked sensors with command-and-control centers and combat platforms," commented Edwin de Jong, director of Core Product Management and Strategy at RTI. "By providing interoperability between enterprise servers and desktops running Linux, UNIX and Windows operating systems and sensors running real-time operating systems (RTOSs), RTI makes it possible to seamlessly integrate networked sensors that jointly output millions of updates per second with data-processing and management resources."
The enhanced scalability and performance of RTI Data Distribution Service are derived from two major new capabilities: content-based routing using multicast and batching of small data updates into larger datagrams for more efficient transmission.
With content-based routing, data is partitioned across multicast groups based on its content. For example, a track-management or multi-sensor data-fusion application can group radar tracks by geographic region and assign a unique multicast address to each region. The network switch will then automatically route data updates to the appropriate processing servers based on the multicast addresses that correspond to each server's regions of interest. This enables massive scalability because any application or network segment only needs to be able to accommodate data of interest; aggregate throughput is limited only by the switching fabric. Without multicast addressing, aggregate throughput is constrained by the capacity of a network segment and the ability of a sensor or data consumer to filter out unneeded messages in software.
Support for batching of small data updates into larger network-level packets further increases throughput by minimizing invocations of the underlying transport and protocol stack. This significantly reduces CPU overhead and allows applications to better utilize network capacity. As a result, individual sensors or applications can sustain update rates of more than one million messages per second with standard Gigabit Ethernet.
This represents an improvement factor of 100 to 1,000 when compared to traditional middleware solutions. RTI Data Distribution Service can also optimally utilize the bandwidth available on low-bandwidth, high-delay and lossy networks such as satellite and wireless. For example, RTI can take advantage of up to 91 percent of the theoretical maximum bandwidth on a 256 kilobit satellite link, such as a very small aperture terminal (VSAT).
Batching support for RTI Data Distribution Service is generally available today. Content-based routing using multicast is available today as a preview release and will be generally available in the first quarter of 2009. RTI Data Distribution Service supports the Windows, Linux, Solaris and AIX operating systems on desktop and server platforms and the INTEGRITY, LynxOS, QNX, VxWorks, Windows CE and Windows Mobile real-time and embedded operating systems. Application programming interfaces are available for C, C++, Java, real-time Java (RTSJ), .NET and Ada.
About RTI Data Distribution Service
RTI Data Distribution Service is a high-performance messaging solution for the development and integration of applications that require low latency, high throughput, high scalability, deterministic responses and minimal consumption of network, processor and memory resources. RTI Data Distribution Service meets the unique and demanding requirements of mission-critical real-time systems, including the ability to run in dynamic and autonomous environments and over unreliable or low-bandwidth networks such as wireless and satellite links.
Real-Time Innovations (RTI) provides high-performance infrastructure solutions for the development, deployment and integration of real time, data-driven applications. RTI's messaging, caching and Complex Event Processing (CEP) capabilities deliver dramatic improvements in latency, throughput and scalability while slashing cost of ownership. The company's software and design expertise have been leveraged in a broad range of industries including defense, intelligence, simulation, industrial control, transportation, finance, medical and communications. Founded in 1991, RTI is privately held and headquartered in Sunnyvale, CA. For more information, please visit www.rti.com.
# # #
RTI, Real-Time Innovations, RTI Data Distribution Service, Connext and 1RTI are registered trademarks or trademarks of Real-Time Innovations, Inc. All other trademarks are property of their respective companies.