The Center for Net-Centric and Cloud Software and Systems (NCSS) performs basic research to completely restructure software and systems for networked and cloud computing environments.
There has been a shift in military and civilian services from platform-based systems, which work independently, to network-centric, integrated computing infrastructures for operating, for example, planes, ships and missiles. But current systems lack effective integration, which is detrimental to their availability, security, interoperability, and cost. Most contemporary approaches to net-centric software seek to "patch" the existing system. The patch solution makes interoperability even more complex. NCSS' goal is to upgrade net-centric software from the ground up.
NCSS research includes developing and verifying secure, resilient, and efficient software and hardware. As these applications will be available via networks, and since some of the most important applications will be time critical and potentially life-sustaining, the development of net-centric software demands flawless handling of security and dependability.
To achieve these goals, the Center's academic institutions bring complementary expertise in hardware systems, including emerging processing architectures and accelerators and memory technologies; service-oriented architectures, software service composition, and quality of service when running on net-centric and cloud computing systems; and communication systems, signal processing, and protocols.
Emerging processing and memory technologies
NCSS has evaluated three organizations using 3D dynamic random-access memory (DRAM), and phase change memory (PCM): 3D DRAM as main memory; 3D DRAM as last-level cache; and 3D DRAM and PCM together as main memory. NCSS has characterized memory access behaviors of applications and designed technique to dynamically adapt the memory organization to the changing memory access behavior of applications. It has also explored embedding small processing elements on the logic layer of 3D stacked memories (that is, processing in memory, or PIM) and explored different types of processing architectures as PIM cores, including simple reduced instruction set computer architectures, reconfigurable dataflow architectures, and graphics processing unit. NCSS is evaluating these emerging technologies for their suitability for net-centric and common cloud-based applications.
Good private cloud-based system architectures, using a goal-oriented approach
The fast-growing cloud computing paradigm makes it possible to use unprecedented amounts of computing resources at lower costs, and it provides other benefits such as fast provisioning and reliability. In designing a robust architecture for a cloud-based system that meets the goals of all stakeholders, the numbers, types, and layouts of devices must be factored in from the earliest stages of design. NCSS investigated a goal-oriented simulation approach for cloud-based system design whereby stakeholder goals are captured and, together with such domain characteristics as workflows, used to create a simulation model as a proxy for the cloud-based system architecture.
Cloud security assessment, using an ontological approach
NCSS uses ontologies to capture both vulnerabilities and cloud system configurations, relying on a variety of sources for capturing vulnerabilities, including the National Vulnerability Database. By so doing, NCSS has developed tools that can be used to query about a given IT system configuration to evaluate the security posture of the system and propose mitigation techniques. NCSS also uses ontologies to capture security service level agreements (SSLAs) and privacy policies offered by service and infrastructure providers. Ontologies for SSLAs can be used to understand the security agreements of a provider, to negotiate desired security levels, and to audit the compliance of a provider with respect to federal regulations (such as the Health Insurance Portability and Accountability Act).