Time filter

Source Type

Qin J.,National University of Defense Technology | Qin J.,China Electrical Equipment and Systems Engineering Ltd. | Chen S.,China Electrical Equipment and Systems Engineering Ltd. | Guo C.,China Electrical Equipment and Systems Engineering Ltd. | Du Y.,China Electrical Equipment and Systems Engineering Ltd.
IEEE Transactions on Device and Materials Reliability | Year: 2014

The sensitivity of single-event effects (SEEs) in nanoscale CMOS for body-biasing circuits has been investigated. For PMOS hits, it is found that forward-biasing the body for high-speed applications can suppress the SET pulses greatly. Reverse-biasing the body for low-power applications, however, does not reduce the SEE vulnerability compared with operation when the body grounded. The body-biasing voltage has no impact on SEE sensitivity for NMOS hits. © 2001-2011 IEEE. Source

Lin C.,Tsinghua University | Deng Y.,China Electrical Equipment and Systems Engineering Ltd. | Jiang Y.,Norwegian University of Science and Technology
Frontiers of Computer Science | Year: 2013

Performance evaluation plays a crucial role in the design of network systems. Many theoretical tools, including queueing theory, effective bandwidth and network calculus, have been proposed to providemodeling mechanisms and results. While these theories have been widely adopted for performance evaluation, each has its own limitation. With that network systems have become more complex and harder to describe, where a lot of uncertainty and randomness exists, to make performance evaluation of such systems tractable, some compromise is often necessary and helpful. Stochastic network calculus (SNC) is such a theoretical tool. While SNC is a relatively new theory, it is gaining increasing interest and popularity. In the current SNC literature, much attention has been paid on the development of the theory itself. In addition, researchers have also started applying SNC to performance analysis of various types of systems in recent years. The aim of this paper is to provide a tutorial on the new theoretical tool. Specifically, various SNC traffic models and SNC server models are reviewed. The focus is on how to apply SNC, for which, four critical steps are formalized and discussed. In addition, a list of SNC application topics/areas, where there may exist huge research potential, is presented. © 2013 Higher Education Press and Springer-Verlag Berlin Heidelberg. Source

Li X.,National University of Defense Technology | Guo C.,National University of Defense Technology | Guo C.,China Electrical Equipment and Systems Engineering Ltd. | Wang H.,National University of Defense Technology
Jisuanji Yanjiu yu Fazhan/Computer Research and Development | Year: 2012

Virtual network mapping problem, which attempts to map different virtual networks on the same substrate network, is an extremely challenging problem. A constraint optimization based mapping method is proposed to solve the problem. In this method, the process of solving the problem is divided into two phases, node mapping phase and link mapping phase, which are all NP-hard. The former phase maps the virtual nodes to the substrate nodes, and the latter phase maps the virtual links to the substrate paths. Node-mapping algorithm and link-mapping algorithm are proposed to solve the node mapping phase and the link mapping phase, respectively. Node-mapping algorithm adopts the thinking of greedy algorithm, mainly considering the available resources which are supplied by substrate nodes and distances among the nodes, in order to maintain load balancing. Meanwhile, an access control mechanism is also proposed to filter the unmoral virtual networks for the purpose of increasing the resource utilization. Link-mapping algorithm is based on the result of node mapping phase, and it adopts the thinking of distributed constraint optimization problem in artificial intelligence. The algorithm can guarantee the optimal solution, namely the minimum cost of mapping the virtual links. Finally, simulation experiments are conducted and the results show that the method performs very well. Source

Li X.,National University of Defense Technology | Wang H.,National University of Defense Technology | Guo C.,China Electrical Equipment and Systems Engineering Ltd. | Ding B.,National University of Defense Technology
Advanced Materials Research | Year: 2012

There are large numbers of infrastructure resources in network virtualization environment (NVE), how to quickly and accurately find the resources that virtual network required is a challenging problem. Pointing to this problem, a resource finding mechanism for network virtualization environment (NVERFM) is proposed. NVERFM is mainly comprised of three modules, virtual resources publishing module (VRPM), virtual resources clustering framework (VRCF), and virtual resources finding module (VRFM). VRPM is responsible for publishing the infrastructure resources to VRCF; and the published information contains functional and non-functional attributes. VRCF is responsible for classifying the published information into different clustering according to the attributes from high priority to low priority. VRFM mainly completes resource finding based on resource similarity principle. Finding the resource clustering that meet the user's requirements; and then combinatorial auction mechanism is used to help users choose the optimal infrastructure resource. Finally, experiments are used to validate NVERFM, and the results show that NVERFM can not only help users find the optimal resource, but also improve the efficiency. © (2012) Trans Tech Publications, Switzerland. Source

Guo C.,National University of Defense Technology | Guo C.,China Electrical Equipment and Systems Engineering Ltd. | Wang T.,National University of Defense Technology
2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010 | Year: 2010

Software runtime state provides rich information to do various analysis of the system. However, the current runtime monitoring techniques entangle state fetching logic and corresponding processing logic, which limits the use of the state information and doesn't support information synthesizing either. In this paper, we proposed a runtime state fetching method which separates them. We designed a State Fetching Description language (SFDL) to describe state monitoring requirement, and implemented a compiling framework to compile the SFDL into monitor probes, gather runtime state information and store them in a general form for future use. Such design separates the state fetching logic from information processing logic, liberates the runtime state information from specific usage and makes it possible to synthesize runtime state information which is important for distributed system to get the overall state. In the end, we applied our approach to performance tuning on a distributed system. Based on the obtained detailed running state, we are able to identify some performance bottlenecks and improve the software. © 2010 IEEE. Source

Discover hidden collaborations