In this paper, we point out that SSDs may give a new opportunity in performance enhancement of virtualization environment. By the analysis of virtio, a de-facto standard framework for virtual I/O devices and the evaluation experiments of original version of virtio, we show that in order to get better scalability for SSDs, virtio needs to be redesign on the new assumption that requests of different types from different VMs are quite independent. Under such an assumption, a new framework is designed based on virtio, which is sirtio, as we put scalability the first place. According to our evaluation, sirtio can improve the scalability of SSDs in virtualization environment.
An algorithm to reconstruct images with Least Squares Support Vector Machines (LS-SVM) and Simulated Annealing Particle Swarm Optimization (APSO) is provided, which is named as SAP. In order to overcome the soft field characteristics of ECT sensitivity field, we exercised some image samples of typical flow pattern with LS-SVM so as to predict the capacitance error caused by the soft field characteristics and then construct the fitness function of the particle swarm optimization on basis of the capacitance error. This algorithm introduces simulated annealing ideas into PSO, adopts cooling process functions to replace the inertia weight function and construct the time variant inertia weight function featured in annealing mechanism, takes use of the APSO algorithm to search for the optimized resolution of Electrical Capacitance Tomography (ECT) reconstruction image. The simulation results show that SAP algorithm is featured in quick convergence rate and higher imaging precision. Compared with Land Weber algorithm and Newton-Raphson algorithm, the quality of reconstruction image with SAP is significantly improved.
Data is the primary concern in data mining. Data Stream Mining is gaining a lot of practical significance with the huge online data generated from Sensors, Internet Relay Chats, Twitter, Facebook, Online Bank or ATM Transactions. The primary constraint in finding the frequent patterns in data streams is to perform only one time scan of the data with limited memory and requires less processing time. The concept of dynamically changing data is becoming a key challenge, what we call as data streams. In our present work, the algorithm is based on finding frequent patterns in the data streams using a tree based approach.
Computer network has realized its popularization after years of development. For its high office efficiency, computer network is widely used by enterprises and campus. However, factors such as the operating system, viruses and Trojan horses have brought serious concealed danger to network security in the process of practical application. Combined with the present situation of computer network security, the work studied the security protection design of the network. Besides, the work also analyzed the multi-port transmission technology briefly from transmission equipment and characteristics.
Sophisticated industrial worms, such as Stuxnet, Flame, Duqu, have brought much threat in industrial networks. Most existing detection methods use content pattern or aggressive activities as a clue to the existence of worms, which are ineffective against worms that don't have their pattern been known and don't behave aggressively. To detect such worms, we proposed Cloud-based Behavior Similarity Transmission Method (CBSTM). CBSTM is a cloud-based method that utilizes the fundamental feature that a worm propagates from host to host. It monitors behaviors on each host in industrial networks. When same behaviors propagate among hosts and meet given criteria, corresponding hosts are believed to be infected by worms. When the worm is detected, the found behavior sequence is used as this worm's signature to realize instant worm detection afterwards. Since CBSTM doesn't need specific characteristics of worms, it can be generally applied to detecting any worms in industrial networks. The evaluation with detecting Stuxnet confirms the effectiveness of CBSTM.
Data centers have become increasingly part of in the cloud computing. Modular data center is usual built with the shipping-containers, which encapsulate thousands of servers. However, Data centers building large-scale cloud services are hard. According to the cost-effective, this paper proposes a new interconnection network MyHeawoodk for the shipping-container based on modular data center. The goal of MyHeawoodk is clear and simple: use existing low-end commercial server with a two-port NIC to construct a large container data center. It will bring a lot of benefits: (1) without altering NIC port in the existing server; (2) The wiring is easy; (3) Facilitate the promotion, widely used. We have developed effective and reliable routing mechanism. Results from simulations show that MyHeawood is more viable interconnecting network for intra-container data center.
The work described definition and features of mathematical algorithm concept and analyzed conception and function of computer logic language. Based on the analysis, the work explored the application of mathematical algorithm in computer logical language. It included core control mode, scientific logical relations and rational software writing ideas. It is hoped that the work can provide some reference for the actual application of computer logic language.
The emergence of databases well addresses the needs of computer data management. Although data management technology is in continuous improvement and greatly improves the efficiency, it is still a problem to achieve data synchronization. The work studied the design and implementation of synchronization system based on web service-based databases. The basis of the research is data concepts and characteristics as well as factors affecting database synchronization.
Computer technology is one of the most important technologies in the 21st century, with a wide application field. It has realized its value in education field and promoted education development. Examination-oriented education urgently needs the reform with many disadvantages in China. The introduction of computer technology has changed original educational environment and made outstanding contributions on education reform, increasing a lot of new teaching facilities. Therefore, computer technology is essential in education reform. Moreover, true educational modernization has been achieved for the development and application of computer technology.
Since turbo code is adopted as a channel coding scheme by the LTE-A system, how to improve the decoding speed of turbo codes to match the high data rate requirement of LTE-A has become an important issue. In this paper, we present a novel stopping criterion which uses the statistics value of a set of multiple minimum soft decision values as a measure to stop the iterating process of turbo decoder. Simulation results show that our proposed criterion saves more iterations with little loss in BER when compared with several well-known existing criteria, which indicates it is suitable for designing high speed turbo decoder required by LTE-A systems.
With the uncertainty of the market demand, we consider the capacity and order problems by a single period dual-channel supply chain game model with one manufacturer and one retailer. The paper discusses whether ordering goods before the sale's season or not for the retailer and whether taking the strategy maximizing the whole profit or the Stackelberg game theory maximizing self-interest for the manufacturer, the leader of the supply chain. Finally, by calculation we verified that the manufacture can pursue his maximum profit and enable the retailer make orders in advance, but in reality no order in advance is the optimal policy for them.
With the popularity of the Internet, network security has been paid more and more attention. Application of network security has become important contents for lots of experts and scholars to study. This work began with the concept and features of computer network technology. Then it analyzed the threats of the computer network, including system vulnerabilities, viruses and Trojans, transport protocol, etc. Finally, it studied security measures including installing patch timely, installing anti-virus software and firewalls, developing new transport protocols, etc. It is hoped that it can provide a reference for the actual security work.
Several overlay-based solutions have been proposed to protect network servers from DoS/DDoS attacks. The common objective in the existing solutions is to prevent the attacking traffic from reaching the servers by hiding the location of target server computers. The recent evolutions in DDoS attacks, especially in the increase in the number of bots involved in a DDoS attack and in the degree of control such bots have to the hijacked host computers, cause serious threats to the overlay-based solutions. We designed and assessed the potential of the new overlay-based security architecture that addresses the recent evolutions in DDoS attacks. The new security architecture, called "Dynamic Binary User-Splits (DBUS)", is designed to protect cloud servers (a) when their legitimate users convert to DoS/DDoS attackers or (b) when DDoS attacks are launched from the legitimate users' host computers that are hijacked by DDoS coordinators. DBUS copes with the situations by sieving attacking traffic from the hijacked legitimate users' host computers using dynamic binary user splits over the migrating entry points to an overlay network. Our discrete event driven simulation suggested that DBUS will efficiently sieve DDoS attacking hosts in many different situations, when a small number of attacking hosts hide behind a large legitimate user group, or when a stampede of DDoS attacking hosts occupy the majority of incoming traffic, without requiring a large number of migrating entry points. We also found that how quickly each migrating entry point can detect excess traffic is a key to keep convergence delay short.
Power management is one of the most challenging problems in cloud computing. A cloud data center could save the amount of energy used from speed scaling. The traditional theoretical research for speed scaling usually assume the power function as the form Sα. Moreover, more comprehensive support for Quality of Service (QoS) is essential by cloud computing providers. Thus, how to dealing with the power/performance trade-off is a burning question. Motivated by improving energy efficiency of the data center, we study policies by setting the speed of the processor for both goals of minimizing the total energy cost and meeting the specified QoS performance well. We initiate a model of speed scaling with weighted power energy, the QoS parameters can be induced to a qualitative concept as the weighting factor of energy consumptions. Based on this model, we propose a resource allocation policy based on the cooperative game theory for energy-efficient management of clouds. The simulation results show the efficiency of the method.
In this paper, a Web-based scientific computing system called iMathema is introduced, which provides computing service based on the open source software Maxima and Gnuplot. iMathema has a B/S architecture, which does not require the user to learn any syntax of CASs (Computer Algebra Systems). It enables users to input math expressions visually, and then it will also return the compute results visually. Besides, it provides remote use to any device via Internet. With iMathema, users can use CASs conveniently to solve many practical problems successfully or even use it to verify whether the answer is right or not distantly. The paper has also demonstrated iMathema's structure, design principles and primary advantages.
The numerical weather prediction acts according to the atmosphere actual situation, giving certain starting value and edge value, through value computation, solution description weather successional variation process hydromechanics and thermodynamics system of equations, forecast future weather method. This paper shows how to migrate a traditional distributed scientific computing to a grid computing environment.
Trajectory monitoring based on the Global Positioning System (GPS) is the premise of providing all kinds of the personalized services based on the users' positions on the smart phones. GPS trajectory monitoring could be used to solve the elderly life monitoring which is a serious social problem in China. Owing to smart phones' energy consumption and computing resource constraints, this paper proposes a kind of GPS non-uniform sampling algorithm which is applied to the elderly daily behavior monitoring system based on the Android platform. The experimental results showed that the algorithm can significantly reduce the sampling points and the power consumption of GPS positioning module.
In cloud computing, load balancing is required to distribute the dynamic local workload evenly across all the nodes. It helps to achieve a high user satisfaction and resource utilization by ensuring an efficient and fair allocation of every computing resource. Although many load balancing schemes have been presented in Cloud computing, there is no scheme providing the elasticity and adaptive adjustment in cloud computing. In this paper, an Adaptive Load Balancing Algorithm based on load prediction model (ALBA) was proposed to improve the resource utilization. When the load in the cluster of virtual machines is lower than the minimal threshold, the ALBA scheme can callback the resources of the cluster. While the load in the cluster of virtual machines is higher than the maximum threshold, the ALBA will adaptively add new virtual machines to balance the computation load and ensure the response time. To avoid the data fluctuation causing by the real-time load acquisition, a load prediction model was introduced and used to improve the accuracy of load prediction. The extensive experiments with CloudSim demonstrate that the proposed adaptive load balancing algorithm -- ALBA, can improve the resource utilization as well as reduce the respond time of tasks.
Visual information, in particular in form of images, is becoming increasingly important, and consequently efficient and effective tools for managing these rapidly growing collections are highly sought after. Interactive image database browsing systems provide an interesting alternative to retrieval-based approaches as they let the user explore an image dataset in an intuitive fashion. Based on content-based concepts, large image collections are visualised so that visually similar images are located close to each other in the visualisation space. Once displayed, the user can then interactively browse through the image collection. The main approaches to visualising and browsing image collections are mapping-based techniques, which are based on dimensionality reduction, and clustering-based methods, that group similar images together. In this paper, we highlight how these two approaches can be effectively combined to devise an intuitive image database navigation system that has low computational requirements, both offline and online, and organises images based on colour content on a spherical visualisation space while providing hierarchical access to large image datasets.
Computer application technology has become a popular industry nowadays. Many experts and scholars are focusing on researches of improving its application efficiency now. On the basis of the concept and characteristics of computer multi-angle application, this work discussed factors affecting computer multi-angle application as well as some problems existing in its application. Besides, computer multi-angle application and its technology development were emphatically analyzed from the aspects of demand analysis and application software development.
