Texas Tech University
University of Arizona
Last Reviewed: 01/30/2020
Fundamental research and development in cloud and autonomic computing methods and their application to a broad range of needs for industry and government partners.
The scope of the CAC center broadly encompasses cloud computing systems and applications and the use of autonomic computing methods for the management of these and other IT systems. CAC activities on cloud computing cut across several layers of IT systems, including: hardware platforms for computing, storage and networking; design of data centers that aggregate platforms to provide cloud services; systems software and distributed computing middleware providing programming interfaces and management primitives within and across multiple cloud data centers; applications that leverage the on-demand and scalable nature of cloud platforms; and cyber-security. CAC activities on autonomic computing focus on methods, architectures and technologies for the design, implementation, integration and evaluation of computing systems and applications that are capable of achieving desired behaviors without the involvement of users or administrators. At the intersection of cloud computing and autonomic computing, the center's activities aim to achieve self-management capabilities within and across the layers of cloud computing systems and applications in order to enable independent operation, minimize cost and risk, accommodate complexity and uncertainty, and enable systems of systems with large numbers of components.
Autonomic computing engines and applications
Consolidated and virtualized datacenter centers and clouds have become the dominant computing platforms in industry and research for enabling complex and compute-intensive applications. As scales, operating costs and energy requirements increase, however, maximizing efficiency, cost-effectiveness, and utilization of these systems becomes paramount. Furthermore, the complexity, dynamism, and often time-critical nature of application workloads makes on-demand scalability, integration of geographically distributed resources and incorporation of utility computing services extremely critical. Finally, the heterogeneity and dynamics of the system, application, and computing environment require context-aware dynamic scheduling and runtime management. CAC research focuses on developing autonomic computing and applications frameworks that can address these challenges and support a wide range of applications.
As the computing and communication capabilities of devices rapidly increases, device networks and peer-to-peer systems provide opportunities for enabling self-organizing distributed systems that are scalable and resilient to failures, and that provide value-added services such as automation of business processes. Security, quality-of-service (QoS), reliability and minimal power consumption are key factors for success of such systems. CAC research is this area is directed toward developing self-organizing networks that respond to dynamic network configurations while ensuring high performance, fault tolerance and security and integrating these networks with virtualization techniques to provide seamless peer connectivity to a wealth of existing, unmodified applications.
Autonomic defense systems are critical to the survivability of the information infrastructure that covers all aspects of our life. These systems of systems and their services must detect and protect against all types of network attacks, known or unknown. They require precise models of both attacks and normal behaviors which are hard to obtain due to sophisticated attacks and the extremely dynamic nature of the Internet. The CAC has developed long-standard expertise through advanced modeling and deployment of real-world capable systems using autonomic methods for network threat assessment, mitigation, and defense.
With the rapid growth of servers and applications spurred by the Internet, the power consumption of servers has become critically important and must be efficiently managed. According to the EPA and estimates from the International Energy Agency, data centers in the US are responsible for about 1.8 percent of total U.S. electricity consumption, emitting over 50 million metric tons of carbon dioxide per year, and approximately 1 percent of global energy use. Increasing the efficiency of hardware and software is important to keep electricity demand from data center operations from growing in proportion to the current exponential growth in demand for IT services. CAC research in this area targets the development of a theoretical framework and a general methodology for autonomic power and performance management of high-performance distributed systems.
The explosive growth in scale and functionality of enterprise software systems and underlying IT infrastructures has resulted in complex systems whose control and timely management is rapidly exceeding human ability. Significant management challenges are resulting from, among other factors, their size, the complexity and distributed nature of their architectures, and the complexity and diversity of services provided. CAC research in this area is dedicated to the development and integration of autonomic techniques for monitoring, modeling, configuring, controlling, and optimizing the behaviors of applications, services, and resources, to ensure their robust and resilient operation in the face of these challenges.
Virtualized data centers
IT management, power consumption, and cooling costs make up an increasingly significant percentage of the overall cost of operating large data centers. These centers are used by banks, investment firms, IT service providers, and other large enterprises. Virtual machines provide a layer that is ideally positioned to provide fine-grained resource monitoring and control capabilities that are well-suited for the monitoring and execution phases in an autonomic computing framework. CAC is working to develop self-monitoring and self-optimization techniques which, when applied to the management of virtualized containers, can lead to increased efficiencies in resource utilization and reduced costs of provisioning.
The NSF CAC Center focuses on advances in algorithms, methods, standards, and tools for cloud and highly automated computing systems. The Phase-II program of CAC will continue research and development in areas including: 1) code development and Application Programming Interface (API) design for data acquisition, procedural, and workflow control; 2) high-performance data analytics and visualization in the cloud and autonomic computing settings; 3) improvements to practical applications of methods that use these and other cloud and autonomic computing techniques and methods; 4) standards implementations and design for cloud software and underlying infrastructure; and 5) applications of the above to data center control based in both industry and academic arenas. The CAC participating universities pursue these overall themes while remaining open to new and emerging opportunities that relate to the needs of current and future industry members or that come up through pursuit of the program of research.
Prominent research laboratories at all four university sites contribute resources to the Center for Autonomic Computing. CAC is affiliated with the following research groups: