Search

Often designated as a UML profile for system modeling, SysML brings some changes that enhance the possibilities of describing systems specificities, but raise new criticisms on the language interpretation. In the last SysML standard document, the new concepts are presented in an informal manner and the revised ones are often described in a way that makes difficult the appreciation of the changes. The internal block diagram, which replaces the UML composite structure diagram, is of interest regarding the innovative concepts it introduces in the old notation. We propose, in this paper, to formalize the semantics related to both of its structure and behavior. To conduct the formalization in an efficient manner, we go towards a semantic domain that fits the diagram characteristics. Hierarchical Colored Petri Nets constitute an appropriate choice. The formalization is validated by model checking. A case study, based on a system that meets the specific features SysML has been intended to model, illustrates the approach throughout the paper. [ABSTRACT FROM PUBLISHER]

To enhance the computer resource access of mobile nursing carts in the healthcare field, it is necessary to provide a continuous wireless mechanism. Because the web-based utilization might switch among diverse applications, a design for a one-to-many switching tunnel is necessary. This paper illustrates a revised version of our original one-to-one stream control transmission protocol tunnel (SCTP-Tunnel) software. This middleware is implemented by the ANSI C programming language on the Ubuntu operating system, and the related coding techniques are disclosed. A complete experimental measurement of this one-to-many SCTP-Tunnel for different data packets is also demonstrated. The turn-around times per data packet in the application layer for small (1 kB~1 MB) and large (5 MB~1 GB) numbers of data packets are approximate 29.005 ms and 6.424 ms, respectively. Such system software can be simply integrated with electronic healthcare services and ubiquitously utilized in the healthcare field. [ABSTRACT FROM PUBLISHER]

This paper introduces the STUNT technology principles, describes the design and implementation process of the STUNT protocol to make TCP holes between two clients in different Local area Networks to achieve clients' connection, and then solves the communication problems in multiple NAT network. [ABSTRACT FROM PUBLISHER]

The rapid development of Internet technology and the expansion of application fields about network are making the network traffic monitoring as an important part of network management. In this paper, a network traffic monitoring system is studied and designed, which can monitor network traffic of multiple computers in the network. In this paper, the socket technology and network traffic monitoring technology is introduced, the principle and structure of the system is researched and designed, data communications and network traffic monitoring are implemented in the end. Data displaying terminal and traffic monitoring terminal communicate by socket technology, access to traffic data on the computer is accessed by the application interface of the operating system. In this paper, traffic data collection and analysis method are as little as possible to take up system resources and cyber source, as accurately as possible to participate in the collection and analysis of flow data. [ABSTRACT FROM PUBLISHER]

Information modernization is an essential process for ore sinter plant. In order to improve information interaction capability, a data acquisition system is designed by integrated OPC (OLE for Process Control), networks and database technology. Its frame is schemed with three layers, i.e. industrial field devices, industrial controllers and information interaction computers. And two kinds of application instances of this frame are discussed. According requirements of data acquisition for ore sinter process, an information communication module is presented and it consists of data acquisition channel, information communication networks and data management interface. A kind of communication mechanism is designed for information interaction between instances of the data acquisition process. The mechanism includes a set of dispose schemes for abnormal socket connecting and a data packing method for information interaction. With Visual C++ programming tool and object orient method, the communication module is realized by combined socket technique. Industrial application indicates that the proposed frame and its instances in this paper are flexible and valid schemes for sinter data acquisition. [ABSTRACT FROM PUBLISHER]

Software defined networking (SDN) promises a way to more flexible networks that can adapt to changing demands. At the same time these networks should also benefit from simpler management mechanisms. This is achieved by moving the network control out of the forwarding devices to purpose-tailored software-applications on top of a "networking operating system". Currently, the most notable representative of this approach is OpenFlow. In the OpenFlow architecture the operating system is represented by the OpenFlow controller. As the key component of the OpenFlow ecosystem, the behavior and performance of the controller are significant for the entire network. Therefore, it is important to understand these influence factors, when planning an OpenFlow-based SDN deployment. In this work, we introduce a tool to help achieving just that - a flexible OpenFlow controller benchmark. The benchmark creates a set of message-generating virtual switches, which can be configured independently from each other to emulate a certain scenario and also keep their own statistics. This way a granular controller performance analysis is possible. [ABSTRACT FROM PUBLISHER]

With advanced Electric Vehicles (EVs) techniques being introduced in these decades, EVs are expected to be widely adopted as resident vehicles due to their low greenhouse gas emission and low operating costs. Meanwhile, the resident EV charging activities will be a challenging problem for the power grid and will cause severe voltage fluctuations, high Peak-to-Average Ratio (PAR) and increasing the blackout possibility. Therefore the random and unpredictable resident EV charging activities calls for an efficient and coordinative mechanism. In this paper, the general scenario of resident EV charging activities is studied and the charging activity is analyzed by queuing theory. Based on that, the novel mechanism is proposed to coordinate the charging load and the grid peak load through wireless communication as well as to set EVs a proper charging moment. Through this mechanism, all arriving EVs can be fully charged before a specific time, and the grid peak load shall not be largely increased. A comparative study is carried out by simulating the uncontrolled charging mechanism with the proposed EV charging mechanism. And the result indicates that the proposed mechanism works efficiently on reducing the grid peak load as well as the grid PAR. [ABSTRACT FROM PUBLISHER]

For Infrastructure-as-a-Service (IaaS) clouds, stepping-stone attacks via hosted virtual machines (VMs) are critical. This type of attack uses compromised VMs as stepping stones for attacking the outside hosts. Not only compromised VMs but also IaaS providers are regarded as attackers. For self-protection, IaaS clouds should perform active response against stepping-stone attacks. However, it is difficult to stop only outgoing attacks at edge firewalls of clouds because edge firewalls can use only information in network packets. In this paper, we propose a new self-protection mechanism against stepping-stone attacks for IaaS clouds, which is called xFilter. xFilter is a packet filter running in the virtual machine monitor (VMM) underlying VMs and achieves pinpoint active response by using VM introspection. VM introspection enables xFilter in the VMM to obtain information on packet senders directly from the memory of VMs. When xFilter detects outgoing attacks, it automatically generates appropriate filtering rules with information on sender processes. Our experiments showed that xFilter could stop only outgoing attacks as much as possible. The performance degradation due to xFilter was less than 13% in usual cases. [ABSTRACT FROM PUBLISHER]

The paper has the purpose to evaluate the performance of the lightweight TCP/IP protocol stack using the digital signal processor Blackfin BF537. The applications of such embedded system are in sensor networking, voice over IP (VoIP) communications and process control in industrial environments. The performance of LwIP stack has been evaluated using the evaluation board EZ-KIT. In this paper we demonstrated that the LwIP stack has good performance, comparable with the TCP/IP stack implementation in operating systems like Linux or Windows. Furthermore, a framework for developing embedded networking applications is provided. [ABSTRACT FROM PUBLISHER]

As the variety of web client devices proliferates, web developers are often required to implement different versions of their applications to support both high-end and low-end devices. Based on existing web standards, we propose a new web application framework that allows web worker processes to be offloaded from weak clients to powerful servers in a seamless manner. As a result, developers can simply create applications that target on high-end devices, and expect our framework to help low-end devices run their applications through process offloading. [ABSTRACT FROM PUBLISHER]

Secure Shell (SSH) is a multi-channel security protocol running over the Transmission Control Protocol (TCP), which offers channels for several services over a secured connection, such as remote shells and connection forwarding. In this paper we introduce a method for using SSH over the Stream Control Transmission Protocol (SCTP), a transport protocol supporting multi-homing and multi-streaming. We examine benefits of this adaptation, which can be made available to generic applications with SSH's connection forwarding without further changes. The results also apply to other application protocols supporting a concept similar to channels. [ABSTRACT FROM PUBLISHER]

We present an approach for implementing open source simulation tools in the field of semiconductor device and process simulation based on our execution framework ViennaX. We apply a modular concept, where functionality is separated into plugins, which in turn can be combined to form full-fledged simulation tools by utilizing ViennaX's task graph approach. Due to the applied plugin concept, a high degree of flexibility is introduced, as components can be easily exchanged. Simulation results are shown, depicting the applicability of our approach for different tools. [ABSTRACT FROM PUBLISHER]

Recently for the transmission of high-capacity video file between sites for manufacturing high-definition used by broadcasting company the Public Network is used a lot, the IP Public Network with QoS(Quality-of-Service) not guaranteed degenerates in performance due to different causes. In order to maximize the effectiveness of such a Network the high efficiency Network can be realized enabling the high-speed of HD video file using the connection with networks between hosts through packet creation and multi-session of Parallel TCP. This thesis is designed to test the high-speed transmission of high-capacity HD video file, and to study the plan for control of relatively fair transmission capacity to many users by the control of Socket from end to end in Public Network by making use of the transmission method using Parallel TCP Application of Open Source. [ABSTRACT FROM PUBLISHER]

This paper uses the information of the Xijiang floating production storage and offloading (FPSO) mooring system coupled with dynamic analysis of the system to generate scenarios for the most likely causes of the damage to the wires and predict if this is likely to result in further progressive damage of the mooring system. The modeling reflects the fundamentals of the Xijiang FPSO mooring system and can be used to further investigate potential causes for the mooring leg damage. The mooring dynamic analysis has been used to investigate the indicative behavior of the mooring lines under various conditions when Buoyant Turret Mooring (BTM) is connected. The model has been used to investigate the tensions, bending moments and bending radiuses near the lower socket. Further more the models have been checked to determine that they produce results of the correct order for the mooring system. [ABSTRACT FROM PUBLISHER]

Cyber hacking has been increased every year and it has resulted in severe damages and losses to companies to the extent that it may lose whole business. Recent trend of hacking shows that aims of hacking is to get personal information profile as many as possible, such as ID, residential registration number, password, etc, and to use it for other purposed. The prominent target of hacking is the database of company. This thesis aims to suggest one way data transmission method as one of network partition solutions for the purpose of protecting database where critical information is stored, even when server is attacked and damaged by hacking. The suggested architecture reduced transmission time for data exchange, a problem in existing architectures, for example between web server and Database, to enable real-time safe transmission of even large-scale data. [ABSTRACT FROM PUBLISHER]

For the hoisting software's difficulty of version update and the slowness of data interaction in web simulation, a method is presented based on B/S structure and cache design to realize the three-dimensional hoisting simulation. First, by analyzing B/S structure's characteristics, the system structure is designed. Next, combined with the hoisting function, the key information is selected, and the cache is designed. Finally, Java3D and the map structure are employed to realize web publishing and cache design. The actual operation results show that, the proposed method can increase the speed of simulation and reduce the pressure of data interaction. [ABSTRACT FROM PUBLISHER]

The four-rotor unmanned aerial vehicle (UAV), known as quadrotor UAV, has been a hot area for the research of unmanned aerial vehicles. Ground Control Station (GCS), as an essential part of quadrotor UAV system, plays a very important role in applications of quadrotor UAV. Most ordinary GCS are stand alone ones, and lack extending abilities. Considering this defect and the real requirements of monitoring and control of UAV, this paper provides a new GCS based on VC++ and Java programming techniques. The major novelty of this GCS is of the Web access to real-time flight data. Plus, the proposed GCS posses the standard functions, such as data receiving in real time, storing the data and displaying the data. Experiment results are provided to show that the GCS operates well, with good human-machine interaction and extending abilities. [ABSTRACT FROM PUBLISHER]

This paper presents a novel framework for tracing and logging C-based designs of embedded hardware/software systems. The development of this C-based Unified Logging and Tracing (CULT) framework was driven by the necessity of a common development support environment between different design disciplines and at different early design phases in which development takes place using C-based languages (C/C++/SystemC). The elaborated framework is highly configurable and scalable. It requires only minimal code changes in order to be used and it implements enhanced features as a dynamic configurable history and backtracking of signals and values. Further, we demonstrate the interconnection with assertion-based verification (ABV) in order to support design testing and validation in early design phases. The framework will be released as open-source project for establishing a vital community and for building up a tooling landscape around the basic capabilities. [ABSTRACT FROM PUBLISHER]

The quadrotor unmanned aerial vehicle (UAV) has been a focus for unmanned aerial vehicles. Ground control system (GCS) is an important part of the quadrotor UAV flight control system, and it can promote the flight performance and safety of quadrotor UAVs. In this paper, a quadrotor UAV GCS is designed and implemented, and the GCS realizes the following functions, including receiving and storing of the flight data, the real-time localization utilizing the customization of electronic maps like MapX and Google Earth, the visual display of flight states via virtual instruments and the waypoint planning. Outdoor experiments have been done to verify the GCS's performance. It can be concluded that the proposed GCS in this paper can work stably, and it can guarantee the integrity of the flight data, the accuracy of the instruments display and map localization. [ABSTRACT FROM PUBLISHER]

Networked control system, as a hotspot in the research fields of control theory and control engineering applications, is widely concerned by researchers at home and abroad. The expansibility, maintainability and reliability of industrial process control system can be greatly improved with the application of Ethernet technology. In this paper, the network controller and the controlled object are set in the different computers in the net and a simulation platform of networked control system based on Ethernet is designed, which uses the mixed programming of Visual C++ and Matlab. This kind programming adopts TCP/IP protocol and uses Socket to encapsulate into DLL so as to realize the transmission of network data. And then build simulation models in the Matlab environment on two computers at the same time, whose communication are worked by calling packaged Socket function. Through the simulations of typical controlled object in the process of industrial production, the feasibility and effectiveness of the control scheme has been proved. [ABSTRACT FROM PUBLISHER]

Automated guided vehicle (AGV) is used widely in many industrial applications to transport materials. A long-travel material transport system is designed and controlled in this paper for a unit load AGV to transfer the material pallet from AGV to the load stand and back, including a both-side three-level push-pull load-transfer mechanism and a programmable logic controller (PLC). AGV follows the path of the magnetic tapes in the floor, and locates itself according to the RFID tags beside the load stand. The PLC detects the docking position of AGV and the load stand, and controls the horizontal and vertical movement of the load-transfer mechanism by using a stepper motor and an electric push rod. The load transfer experiments of our AGV testify the performance of this material transport system. [ABSTRACT FROM PUBLISHER]

There are many different techniques used for data measurement in computer networks. In this paper we analyze different traffic measurement methods provided by Linux operating system. We implement and use these methods in network traffic measurement agent named KaTaLyzer. KaTaLyzer is aimed to provide long time monitoring and traffic measurement in computer networks. In this paper we discuss differences between traffic measurement techniques which are used in different versions of KaTaLyzer. Techniques are compared one to each other via analysis of measurement results and comparison of amount of captured and dropped data. [ABSTRACT FROM PUBLISHER]

Surge arresters are a vital component for network safety. At Medium voltage networks (Vm ≤ 52kV), dry type pluggable surge arresters are known and widely used. This solution has now been taken to the next voltage level, Vm = 72.5kV. This paper discusses the general function, application in GIS and transformers, as well as testing. [ABSTRACT FROM PUBLISHER]

In the field of electric mobility, many research efforts have been made in the recent years to analyse and develop advanced architectures and technical components for electric vehicles on the one hand. On the other hand, field tests of electric vehicles in daily use are still rare though. With that perspective, the paper describes the performance of a fleet test of electric vehicles with 70 test drivers involved. Information about the test fleet vehicles and the selection process of the test operators as well as the used measuring concepts in the cars are displayed. First results with regard to driven distances, consumer behaviour and energy consumption will be presented. [ABSTRACT FROM PUBLISHER]

This paper reports test results and reviews for the developed plug and socket-outlet applied to the 400 Vdc power systems expected to improve energy efficiency in communication sites, data centers, commercial buildings, and smart energy systems. However, there are some safety issues to use 400 Vdc power. The plug and socket outlet has a unique mechanism based on combination of a permanent magnet and mechanical contacts in the limited small space. The mechanism should solve the problems such as both arc extinguishing and protection against electric shock known as critical DC power issue for a long time. [ABSTRACT FROM PUBLISHER]

This paper presents a novel and reliable DC switch and DC socket for high voltage DC power feeding system, in which the arc does not occur when the are turned on/off and inserted/removed, respectively. The novel prototype DC switch and DC socket have been made. Both are almost same circuit configuration and operation principle and then composed of two mechanical relays and a single MOSFET. It has been tested for the proposed DC switch to protect not only the arc but also thermal problem. As a result, it is confirmed that the arc thermal problem do not occur when the MOSFET and relays are turned on/off and relays are on in steady state, respectively, and that they have the excellent performance characteristics using simple semiconductor snubbers with the overvoltage clamp function. [ABSTRACT FROM PUBLISHER]

Over the last decade, homogeneous multi-core processors emerged and became the de-facto approach for offering high parallelism, high performance and scalability for a wide range of platforms. We are now at an interesting juncture where several critical factors (smaller form factor devices, power challenges, need for specialization, etc) are guiding architects to consider heterogeneous chips and platforms for the next decade and beyond. Exploring heterogeneous architectures is challenging since it involves re-evaluating architecture options, OS implications and application development. In this paper, we describe these research challenges and then introduce a heterogeneous prototype platform called QuickIA that enables rapid exploration of heterogeneous architectures employing multiple generations of Intel processors for evaluating the implications of asymmetry and FPGAs to experiment with specialized processors or accelerators. We also show example case studies using the QuickIA research prototype to highlight its value in conducting heterogeneous architecture, OS and applications research. [ABSTRACT FROM PUBLISHER]

In this work we propose a joint energy, thermal and cooling management technique (JETC) that significantly reduces per server cooling and memory energy costs. Our analysis shows that decoupling the optimization of cooling energy of CPU & memory and the optimization of memory energy leads to suboptimal solutions due to thermal dependencies between CPU and memory and non-linearity in cooling energy. This motivates us to develop a holistic solution that integrates the energy, thermal and cooling management to maximize energy savings with negligible performance hit. JETC considers thermal and power states of CPU & memory, thermal coupling between them and fan speed to arrive at energy efficient decisions. It has CPU and memory actuators to implement its decisions. The memory actuator reduces the energy of memory by performing cooling aware clustering of memory pages to a subset of memory modules. The CPU actuator saves cooling energy by reducing the hot spots between and within the CPU sockets and minimizing the effects of thermal coupling. Our experimental results show that employing JETC results in 50.7% average energy reduction in cooling and memory subsystems with less than 0.3% performance overhead. [ABSTRACT FROM PUBLISHER]

This paper proposes a cache management scheme for mul-tiprogrammed, multithreaded applications, with the objective of obtaining maximum performance for both individual applications and the multithreaded workload mix. In this scheme, each individual application's performance is improved by increasing the priority of its slowest thread, while the overall system performance is improved by ensuring that each individual application's performance benefit does not come at the cost of a significant degradation to other application's threads that are sharing the same cache. Averaged over six workloads, our shared cache management scheme improves the performance of the combination of applications by 18%. These improvements across applications in each mix are also fair, as indicated by average fair speedup improvements of 10% across the threads of each application (averaged over all the workloads). [ABSTRACT FROM PUBLISHER]

Over the last 12 years three important dates have marked the beginning of a major paradigm shift in computing and the security models applied to protect an emerging computing environment - March 1999, January 9th, 2007, and July 2007. These dates roughly correspond to the birth of SalesForce.com, the most successful Software as a Service (SaS) provider to date, Steve Jobs introduction of the Iphone,, and the discovery of the Zeus Botnet. These innovations have been instrumental in enabling a paradigm shift in computing, away from a corporate network centric model with Windows end-point devices to what we called in this manuscript the Circa 2020 Computing Model. In the circa 2020 Computing model applications and data reside in the Cloud, the concept of an extended Trust Domain (network) disappears - there is no corporate network, and finally the end-point device is a SmartPhone owned and operated by employees - Bring Your Own Device (BYOD). In such an environment, the end-point device is not “Trusted”, and there is a high likelihood that the BYOD can be used as a channel to leak sensitive data. In this manuscript, we present a new mechanism to prevent such a situation. We called this mechanism “TrustDroid™”. TrustDroid™ is a static analyzer based on taint tracking that can be used to prevent leakage of sensitive information by an un-trusted Android SmartPhone. [ABSTRACT FROM PUBLISHER]

Android is an open-sourced mobile operating system developed by Google, which provides all the softwares including operating system, user interface and applications, and it has no proprietary barriers that block mobile industrial innovations. Android is regarded as the first really open and complete mobile software for mobile terminals. This paper illustrates to a guidance to understand the communication between PCs and Android smart phones from the prospective of developers and proposes a solution to transfer files between them in the C/S mode via Socket based on the platform Eclipse. [ABSTRACT FROM PUBLISHER]

The rapid advancement of mobile communication technologies offers innumerable opportunities for development of video monitoring system in mobile devices. This article introduces and implements the two-way monitoring system based on Java Media Framework (JMF) and Android. The system is developed based on Java, which includes the design for server in personal computer (PC) and client in Android-based devices. Both server and client can be divided into three modules: data acquisition module, data transmission module and data transformation module. Through testing, both the client and server can monitor each other. System implements the expected function. [ABSTRACT FROM PUBLISHER]

The Digital Ecosystem (DE) paradigm is a holistic management/design/integration approach that is based on the notion of self-interested, self-managing, proactive and autonomous digital entities that evolve and self-organize. This in turn leads to the emergence of complex, self-organizing behaviours within a DE due to the evolving and highly dynamic interactions of its members. These interactions are however strongly influenced by the IT environment in which the DE is situated. Interestingly, our IT environments are currently undergoing a major transformation due to the declining importance of the desktop computing model. As smartphones and tablets begin to replace the desktop as the primary means of interacting with IT resources, our IT infrastructures are adapted to serve the increasing numbers of resource-constrained, wirelessly connected mobile devices that interact with backend components hosted in a cloud. These changes of the IT environment have also a major impact on the way Digital Ecosystems can be designed and how they operate. This paper focusses on the communication challenges of mobile digital ecosystems and presents an event-oriented form of communication that ensures high-scalability and loose coupling. [ABSTRACT FROM PUBLISHER]

Chordal graphs are triangulated graphs where any cycle larger than three is bisected by a chord. Many combinatorial optimization problems such as computing the size of the maximum clique and the chromatic number are NP-hard on general graphs but have polynomial time solutions on chordal graphs. In this paper, we present a novel multithreaded algorithm to extract a maximal chordal sub graph from a general graph. We develop an iterative approach where each thread can asynchronously update a subset of edges that are dynamically assigned to it per iteration and implement our algorithm on two different multithreaded architectures -- Cray XMT, a massively multithreaded platform, and AMD Magny-Cours, a shared memory multicore platform. In addition to the proof of correctness, we present the performance of our algorithm using a test set of synthetical graphs with up to half-a-billion edges and real world networks from gene correlation studies and demonstrate that our algorithm achieves high scalability for all inputs on both types of architectures. [ABSTRACT FROM PUBLISHER]

This paper explores the J2ME and J2EE-based technology can achieve a mobile phone online games and content management platform mutual separation, and the applications needed for the GM portfolio of mobile network game system client design. The system of the client platform J2ME mobilet development on the basis of a card game as an example, the use of the MVC design model framework to improve the maintainability of the system is conducive to the development of the secondary system. Java-based features of the system with high portability, the mainstream mobile platform normal operations, reducing the cost of the migration. [ABSTRACT FROM PUBLISHER]

The current wireless network landscape comprises a plethora of technologies including WLAN, WiMAX and 3G, and not much speaks for a radical change of the state of affairs in the near future. In light of this, it becomes pivotal to facilitate vertical handover between different types of wireless networks. Although, a large number of vertical handover schemes have been proposed in the past several years, the majority of the proposed solutions reside in the network and/or link layer -- e.g., Mobile IP and various IEEE 802.21 schemes -- and relatively few are transport-layer solutions. However, we think transport-layer solutions many times are attractive, particularly in cases where there are no economic incentives to upgrade the existing network infrastructure. To this end, we have designed a lightweight, transport-level mobility framework based on the Stream Control Transmission Protocol (SCTP) and its extension for dynamic address reconfiguration. The framework API has been kept very small and closely aligned with the SCTP sockets extensions, which makes porting of existing applications fairly straightforward. To demonstrate its usefulness for low-power tablets and smart phones, we have implemented our framework on a Motorola Xoom tablet running the Android OS. Our initial proof-of-concept experiment gave satisfactory results with a handover performance on par with that of other vertical handover solutions. [ABSTRACT FROM PUBLISHER]

Over modern long fat networks, enough throughput is not obtained using TCP Reno, which is the classical standard TCP congestion avoidance algorithm. For this reason, many high performance TCPs have been proposed, such as Compound TCP (CTCP) and CUBIC TCP. Then, these proposals caused a new issue, which is fairness among these modern TCPs. For this issue, several fairness evaluations and some proposals for improving fairness have been published. However, most evaluations are executed using network simulator, so fairness in actual network elements and actual TCP implementations has not been discussed enough yet. In this paper, we present fairness evaluation among modern TCPs with actual network elements and actual TCP implementations. Our evaluations demonstrated that fairness among modern TCPs is very poor, especially in case of using CUBIC. Furthermore, we evaluated existing fairness improving method. The results show that the methods can improve fairness. [ABSTRACT FROM PUBLISHER]

One of only two new transport protocols introduced in the last 30 years is the Stream Control Transmission Protocol (SCTP). SCTP enables capabilities like additional throughput and fault tolerance for multihomed hosts. An SCTP implementation is included with the Linux kernel and another implementation called sctplib functions successfully in userspace on several platforms but unfortunately neither of these implementations have all of the latest features nor do they perform as well as the FreeBSD kernel implementation of SCTP. We were motivated to produce a portable implementation of the FreeBSD kernel SCTP stack that operates in userspace of any system because of both our desires to obtain a higher performance SCTP stack for Linux as well as to exploit recent developments in hardware virtualization and transport protocol onloading. Unlike any other userspace transport implementation for TCP or SCTP, our userspace SCTP stack simultaneously achieves similar throughput and latency as the Linux kernel TCP stack, without compromising on any of the transport's features as well as maintaining true portability across multiple operating systems and devices. We create a callback API and implement a threshold to control its usage; our userspace SCTP stack with these optimizations obtains higher throughput than the Linux kernel implementation of SCTP. We describe our userspace SCTP stack's design and demonstrate how it gives similar throughput and latency on Linux as the kernel TCP implementation, with the benefits of the new features of SCTP. [ABSTRACT FROM PUBLISHER]

TCP and other Internet transport protocols rely on series of hard-coded initial values for their connection state, particularly for the congestion control parameters. For example, recently the initial value of congestion window has been under much debate, as there is a desire to make TCP more efficient for common use cases, while not endangering its performance on scenarios with limited network bandwidth. Our take on this discussion is that there is no clear single set of initial values that would work for all cases. Earlier research has proposed sharing connection and congestion control state among multiple connections over time, but that approach is limited to sharing connections to a particular host, which is not sufficient, because services are often distributed across multiple hosts, and opening multiple connections to the same host is a rather rare use case. We aim to solve this problem by proposing the Pathlet Transport Architecture that models the network paths as a series of pathlets, and uses those as the basis of initializing and maintaining the various transport parameters, particularly those related to congestion control. We analyze our initial instantiation of the PTA architecture using ns-3 simulations for TCP congestion control parameters, and show how it improves the communication performance in various different network scenarios, where single common set of magic values would fail. [ABSTRACT FROM PUBLISHER]

After a legacy system is re-engineered, it is important to perform compatibility testing so as to identify the difference and reduce the introduced bugs. We can first apply symbolic execution to obtain an exhaustive set of test cases, then use them to check the compatibility of the old system and the new old. However, the path explosion problem of symbolic execution makes it difficult to work on realistic non-trivial applications. We show in this paper how to enhance symbolic execution, e.g. with extra constraints, path cutting, variable grouping, and test case selection, to successfully test the compatibility of an SMTP library (used in embedded systems) with around 20K lines of code. Our experience indicates that these enhancements are essential to apply symbolic execution on realistic industrial applications. [ABSTRACT FROM PUBLISHER]

This paper presents an evaluation of data delivery on Android applications implementing a health screening form. Typically, the health screening form provides an integrated view of various data (e.g. lifelog, health log, and medical history) gathered by diverse measuring devices (e.g. hear rate monitor, and inbody). From data delivering perspective, the health screening form also consists of multiple ‘Activity’ interfaces in a single application or between collaborating applications. Therefore, we need to evaluate efficiency of data delivery among ‘Activity’ interfaces in a single application or between applications. We use basic interfaces of Android platform such as ‘Intent’, ‘Broadcastreceiver’, ‘Contentprovider’ and ‘Socket’ providing a function of data transfer to evaluate delivery performance. The result of this work can contribute to select efficient data transfer interface while implementing the function of data delivery in Android application [ABSTRACT FROM PUBLISHER]

UV2 is SGI's second generation data fusion system. UV2 was designed to meet the latest challenges facing users in computation and data analysis. Its unique ability to perform both functions on a single platform enables efficient, easy to manage workflows. This platform has a hybrid infrastructure, leveraging the latest Intel® EP processors providing industry leading computational power. Due to its high bandwidth, extremely low latency NUMALink®6 (NL6) interconnect, plus vectorized synchronization and data movement, UV2 provides industry leading data intensive capability. It supports a single operating system (OS) image up to 64TB and 4K threads. Multiple OS images can be deployed on a single NL6 fabric, which has a single flat address space up to 8PB and 256K threads. These capabilities allow for extreme performance on a broad range of programming models and languages including OpenMP[1], MPI, UPC[2], CAF[3] and SHMEM. The architecture, implementation and performance of UV2 are detailed. [ABSTRACT FROM PUBLISHER]

Hadoop Distributed File System (HDFS) acts as the primary storage of Hadoop and has been adopted by reputed organizations (Facebook, Yahoo! etc.) due to its portability and fault-tolerance. The existing implementation of HDFS uses Javasocket interface for communication which delivers suboptimal performance in terms of latency and throughput. For dataintensive applications, network performance becomes key component as the amount of data being stored and replicated to HDFS increases. In this paper, we present a novel design of HDFS using Remote Direct Memory Access (RDMA) over InfiniBand via JNI interfaces. Experimental results show that, for 5GB HDFS file writes, the new design reduces the communication time by 87% and 30% over 1Gigabit Ethernet (1GigE) and IP-over-InfiniBand (IPoIB), respectively, on QDR platform (32Gbps). For HBase, the Put operation performance is improved by 26% with our design. To the best of our knowledge, this is the first design of HDFS over InfiniBand networks. [ABSTRACT FROM PUBLISHER]

Cosmology simulations are highly communication-intensive, thus it is critical to exploit topology-aware task mapping techniques for performance optimization. To exploit the architectural properties of multiprocessor clusters (the performance gap between inter-node and intra-node communication as well as the gap between inter-socket and intra-socket communication), we design and develop a hierarchical task mapping scheme for cell-based AMR (Adaptive Mesh Refinement) cosmology simulations, in particular, the ART application. Our scheme consists of two parts: (1) an inter-node mapping to map application processes onto nodes with the objective of minimizing network traffic among nodes and (2) an intra-node mapping within each node to minimize the maximum size of messages transmitted between CPU sockets. Experiments on production supercomputers with 3D torus and fat-tree topologies show that our scheme can significantly reduce application communication cost by up to 50%. More importantly, our scheme is generic and can be extended to many other applications. [ABSTRACT FROM PUBLISHER]

Breadth-First Search is an important kernel used by many graph-processing applications. In many of these emerging applications of BFS, such as analyzing social networks, the input graphs are low-diameter and scale-free. We propose a hybrid approach that is advantageous for low-diameter graphs, which combines a conventional top-down algorithm along with a novel bottom-up algorithm. The bottom-up algorithm can dramatically reduce the number of edges examined, which in turn accelerates the search as a whole. On a multi-socket server, our hybrid approach demonstrates speedups of 3.3 -- 7.8 on a range of standard synthetic graphs and speedups of 2.4 -- 4.6 on graphs from real social networks when compared to a strong baseline. We also typically double the performance of prior leading shared memory (multicore and GPU) implementations. [ABSTRACT FROM PUBLISHER]

Current ubiquitous computing technologies provide access to customized, contextual, and location-based services. Device mobility, however, is frequently associated with communication delays, link disruptions due to signal loss, and changes in IP address. As a result, connection-oriented applications may fail and node location strategies should not rely on node addresses. In this paper, we propose the use of communication sessions to create mobility-aware applications that do not break with transmission delays or disruptions. The concept of these communication sessions is embedded in the basic network socket API functions and operates transparently with the applications. Sessions provide application level support to keep track of the location of peer nodes, to detect connection disruptions, and to suspend and resume transmissions. Experiments show our approach offers superior performance of the general IP layer mobility solution, with no need to implement or adapt software at the core network infrastructure. [ABSTRACT FROM PUBLISHER]

We have designed Home Energy Management System which is able not only to collect and display data, switch off (on) the appliances, but also to deal with identification of the appliance(s) plugged-in to a single power socket sensor. For that purpose, in this paper we are proposing a data mining algorithm that analyzes the collected consumption data from different appliances in order to identify a cluster of each of the appliances, or a cluster of a group of appliances plugged-in in the same time to a single power socket sensor. We have achieved high clustering accuracy for the monitored values for the power consumption of appliances. Hence, the presented data mining algorithm enables successful identification of the operating states of the appliances plugged-in to a multi-socket extension. Additionally, we discuss the unforeseen challenging issues that appeared during the evaluation phase of the algorithm, in order to provide efficient identification of a household appliance (or group of appliances) eligible for further remote control. [ABSTRACT FROM PUBLISHER]

In this paper, we present a lightweight defense mechanism against VoIP attacks, called VoIP Shield, that can detect counterfeit or MITM modified messages as well as replay attacks without ever changing the underlying VoIP protocol. We then empirically tested our design in conjunction with deployed Vonage VoIP services against a large body of attacks including billing, call redirection, voice pharming, and complex MITM exploits. The results demonstrate that advanced VoIP protection is practical, lightweight, and can be deployed even in systems where software upgrades are impossible. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a Network Virtual Platform (NetVP) to develop and verify network accelerator like an IPsec processor. The NetVP provides on-line verification mechanism and is suitable for ESL top-down design flow, supporting developments of un-timed as well as timed models. System development using this NetVP is efficient and flexible since it allows the designer to explore design spaces such as the network bandwidth and system architecture easily. [ABSTRACT FROM PUBLISHER]