Zhu J.,Peking University |
Jiang Z.,Peking University |
Xiao Z.,Peking University |
Li X.,State Key Laboratory of Software Development Environment
IEEE Transactions on Computers | Year: 2011
Hypervisor-based fault tolerance (HBFT), which synchronizes the state between the primary VM and the backup VM at a high frequency of tens to hundreds of milliseconds, is an emerging approach to sustaining mission-critical applications. Based on virtualization technology, HBFT provides an economic and transparent fault tolerant solution. However, the advantages currently come at the cost of substantial performance overhead during failure-free, especially for memory intensive applications. This paper presents an in-depth examination of HBFT and options to improve its performance. Based on the behavior of memory accesses among checkpointing epochs, we introduce two optimizations, read-fault reduction and write-fault prediction, for the memory tracking mechanism. These two optimizations improve the performance by 31 percent and 21 percent, respectively, for some applications. Then, we present software superpage which efficiently maps large memory regions between virtual machines (VM). Our optimization improves the performance of HBFT by a factor of 1.4 to 2.2 and achieves about 60 percent of that of the native VM. © 1968-2012 IEEE.
Zhu Y.,State Key Laboratory of Software Development Environment |
Zhu Y.,Shanghai JiaoTong University
International Journal of Distributed Sensor Networks | Year: 2012
Detecting abnormal events represents an important family of applications for wireless sensor networks. To achieve high performance of event detection, a sensor network should stay active most of the time, which is energy inefficient for battery driven sensor networks. This paper studies the fundamental problem of bounding detection delays when the sensor network is low duty cycled. We propose a novel approach for statistically bounding detection latency for event detection in sensor networks. The key issue is the wakeup scheduling of sensor nodes and minimization of wakeup activity. We propose a lightweight distributed algorithm for coordinating the wakeup scheduling of the sensor nodes. A distinctive feature of this algorithm is that it ensures that the detection delay of any event occurring anywhere in the sensing field is statistically bounded. In addition, the algorithm exposes a convenient interface for users to define the requirement on detection latency, thereby tuning the intrinsic tradeoff between energy efficiency and event detection performance. Extensive simulations have been conducted and results demonstrate that this algorithm can successfully meet delay bound and significantly reduce energy consumption. © 2012 Yanmin Zhu.
Zhang X.,Beihang University |
Zheng Z.,State Key Laboratory of Software Development Environment |
Zheng Z.,Beihang University |
Zhu Y.,Beihang University |
Cai K.-Y.,Beihang University
Computers and Operations Research | Year: 2014
This paper focuses on the protection issues for supply systems involving random attacks, which are described as attacks whose targets cannot be predicted. We present the random-attack median fortification problem (RAMF) to identify the fortification strategy that minimizes the expected operation cost after random attacks. RAMF is formulated as an integer-linear program and solved directly using general-purpose MIP solver. Moreover, a more complex problem, the fortification median problem for disruptions caused by mixed types of attacks (FMMA), is introduced to find a balance between defending the worst-case attacks and random attacks. Solving FMMA can achieve good protection results, which are more practical in dealing with systems with mixed types of attacks, if the proportion between the types is properly estimated. We formulate FMMA as a non-linear bilevel program and extend a typical implicit enumeration (IE) algorithm to solve the problem. Finally, computational experiments demonstrate the effectiveness of both RAMF and FMMA in dealing with protective affairs involving random attacks. The efficiency of solving the formulations of RAMF and FMMA is also testified. © 2013 Elsevier Ltd.
Li Y.,State Key Laboratory of Software Development Environment |
Li Y.,Beihang University |
Xiao L.,State Key Laboratory of Software Development Environment |
Xiao L.,Beihang University
Proceedings - 3rd International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2010 | Year: 2010
Cryptosystem on conic curves, which is a new developing cryptography, becomes more widespread in these days. It is important to explore fast parallel algorithms to both encrypt and decrypt information in conic curves cryptosystem. Point-multiplication is the key operation for constructing security protocol in conic curves cryptosystem. There is no existing research focused on paralleling point-multiplication for conic curves cryptosystem. This paper presents parallel computation of point-multiplication for conic curves cryptosystem over finite field Fp and ring Zn. Research in this paper is based on our previous works about several parallel algorithms for conic curves cryptosystem. The parallel technique of point-multiplication is computing point-addition and pointdouble respectively. The performance evaluation demonstrates that our methodology could improve efficiency for conic curves cryptosystem over finite field Fp and ring Zn. © 2010 IEEE.
Qu W.-W.,Beihang University |
Zhang G.-L.,State Key Laboratory of Software Development Environment |
Zhang G.-L.,Beihang University |
Le X.-Y.,Beihang University
Wuli Xuebao/Acta Physica Sinica | Year: 2012
he relations of fusion barrier height and position to charge number and root-mean-square radus of the interacting nucleus for a projectile fusing with the different target nuclei are systematically analyzed in this paper. The nuclear potential is calculated by using the double folding model with the density-dependence nucleon-nucleon interaction (CDM3Y6). The pocket formulas are obtained for the fusion barrier height and position for a projectile fusing with the different nuclei with mass in a range from 16 to 238. The parameterized formulas can reproduce the exact barrier heights and positions only for a projectile within the accuracy of ±1%. Moreover, the results are perfectly agreeable with the experimental data, the empirical data and the results of Royer, KNS, AW and the proximity potential. © 2012 Chinese Physical Society.
Wang L.,State Key Laboratory of Software Development Environment |
Wang L.,Beihang University |
Wang Y.,Beihang University |
Zhao Y.,Beihang University
Physica A: Statistical Mechanics and its Applications | Year: 2014
Studying the function call graphs in complex software can provide significant insights into the software evolution process. We found node in- and out-degree distributions asymmetric in the call graphs of 223 versions of Linux kernel modules (V1.1.0 to V2.4.35). Nodes newly introduced in these modules tended to attach to themselves (clustering) and existing high in-degree nodes. We proposed the αβ Model to generate call graphs for different kernel modules. The model preserved asymmetry in the degree distributions and simulated the new node behaviors. Last, we discussed how the αβ Model could be used effectively to study the robustness of complex networks. © 2014 Elsevier B.V. All rights reserved.
Chen Y.,State Key Laboratory of Software Development Environment |
Chen Y.,Beihang University |
Li J.,State Key Laboratory of Software Development Environment |
Wo T.,State Key Laboratory of Software Development Environment |
And 2 more authors.
Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS | Year: 2010
Network Virtualization has recently emerged to provide scalable, customized and on-demand virtual network services over a shared substrate network. How to provide VN services with resiliency guarantees against network failures has become a critical issue, meanwhile the service resource usages should be minimized under the strict constraints such as link bandwidth capability and service resiliency guarantees etc. In this paper, we present a resource allocation algorithm to balance the tradeoff between service resource consumptions and service resiliency. By exploiting a heuristic VN mapping scheme and a restoration path selection scheme based on intelligent bandwidth sharing, the algorithm simultaneously makes cost-effective usage of network resources and protects VN services against network failures. We perform evaluations and find that the algorithm is near optimal in terms of network resource usage, especially the additional restoration bandwidth cost for resiliency protection. © 2010 IEEE.
Liu F.,State Key Laboratory of Software Development Environment |
Liu F.,Beihang University |
Lei H.,University of Chinese Academy of Sciences
Journal of Physics A: Mathematical and Theoretical | Year: 2012
Motivated by recent progress in nonequilibrium fluctuation relations, we present a generalized time reversal for stochastic master equation systems with discrete states, which is defined as a splitting of the rate matrix into irreversible and reversible parts. An immediate advantage of this definition is that a variety of fluctuation relations can be attributed to different matrix splittings. Additionally, we find that the accustomed total entropy production formula and conditions of the detailed balance must be modified appropriately to account for the reversible rate part, which was previously ignored. © 2012 IOP Publishing Ltd.
Li X.,Renmin University of China |
Li X.,State Key Laboratory of Software Development Environment |
Snoek C.M.,University of Amsterdam |
Worring M.,University of Amsterdam |
And 2 more authors.
IEEE Transactions on Multimedia | Year: 2013
Learning classifiers for many visual concepts are important for image categorization and retrieval. As a classifier tends to misclassify negative examples which are visually similar to positive ones, inclusion of such misclassified and thus relevant negatives should be stressed during learning. User-tagged images are abundant online, but which images are the relevant negatives remains unclear. Sampling negatives at random is the de facto standard in the literature. In this paper, we go beyond random sampling by proposing Negative Bootstrap. Given a visual concept and a few positive examples, the new algorithm iteratively finds relevant negatives. Per iteration, we learn from a small proportion of many user-tagged images, yielding an ensemble of meta classifiers. For efficient classification, we introduce Model Compression such that the classification time is independent of the ensemble size. Compared with the state of the art, we obtain relative gains of 14% and 18% on two present-day benchmarks in terms of mean average precision. For concept search in one million images, model compression reduces the search time from over 20 h to approximately 6 min. The effectiveness and efficiency, without the need of manually labeling any negatives, make negative bootstrap appealing for learning better visual concept classifiers. © 1999-2012 IEEE.
Fan Z.,State Key Laboratory of Software Development Environment |
Yue T.,Certus Software V and nter |
Zhang L.,State Key Laboratory of Software Development Environment
Proceedings of the ACM Symposium on Applied Computing | Year: 2013
Architecture description is critical for the development of large-scale software-intensive systems. However, there isn't a generic framework that can guide modelers through the derivation process of a domain-specific architecture modeling method (AMM). This process is usually complicated especially when the system is large-scale. In this paper, we propose a generic framework (named as GCVL) to guide modelers to devise AMMs for various domains. GCVL framework has been evaluated by applying it to derive an AMM (named as SAMM) for the ship command and control systems. SAMM is evaluated through a full-size industrial application. Results of the evaluation show that GCVL framework is applicable to define AMMs for large-scale software-intensive systems. Copyright 2013 ACM.