The demands of programmability have become more and more exigent as novel network services appear, such as E-commerce, social softwares, and online videos. Commodity multi-core CPUs have been widely applied in network...The demands of programmability have become more and more exigent as novel network services appear, such as E-commerce, social softwares, and online videos. Commodity multi-core CPUs have been widely applied in network packet processing to get high programmability and reduce the time-to-market. However,there is a great gap between the packet processing performance of commodity multi-core and that of the traditional packet processing hardware, e.g., NP(Network Process). Recently, optimization of the packet processing performance of commodity multi-cores has become a hot topic in industry and academia. In this paper, based on a detailed analysis of the packet processing procedure, firstly we identify two dominating overheads, namely the virtual-to-physical address translation and the packet buffer management. Secondly, we make a comprehensive survey on the current optimization methods. Thirdly, based on the survey, the heterogeneous architecture of the commodity multi-core + FPGA is proposed as a promising way to improve the packet processing performance.Fourthly, a novel Self-Described Buffer(SDB) management technology is introduced to eliminate the overheads of the allocation and deallocation of the packet buffers offloaded to FPGA. Then, an evaluation testbed, named PIOT(Packet I/O Testbed), is designed and implemented to evaluate the packet forwarding performance. I/O capacity of different commodity multi-core CPUs and the performance of optimization methods are assessed and compared based on PIOT. At last, the future work of packet processing optimization on multi-core CPUs is discussed.展开更多
The packet size of bainitic steel can be refined by a specialrelaxation-precipitation-control phase transformation (RFC) technology. When processed by RPCprocess, the low carbon bainitic steel composes of two kinds of...The packet size of bainitic steel can be refined by a specialrelaxation-precipitation-control phase transformation (RFC) technology. When processed by RPCprocess, the low carbon bainitic steel composes of two kinds of main intermediate transformationphases. One is ultra-fine lath-like bainitic ferrite and the lath is less than 1μm in width andabout 6 μm in length; the alignment of laths forms a refined packet, and the size of packets isabout 5-7 μm in length and about 3-4μm in width. The other is acicular structure. The morphologyand distribution of these acicular structures are influenced by relaxation process, the thin andshort acicular structures cut the prior austenite grain and refine the bainitic packet size. For theoptimum relaxation time, the packet size can be refined to the finest. The mechanical propertiesare influenced by relaxation time and the 800 MPa grade low carbon bainitic steel with excellenttoughness can be obtained by RPC process.展开更多
This paper presents a novel method for radar emitter signal recognition. First, wavelet packet transform （WPT） is introduced to extract features from radar emitter signals. Then, rough set theory is used to select t...This paper presents a novel method for radar emitter signal recognition. First, wavelet packet transform （WPT） is introduced to extract features from radar emitter signals. Then, rough set theory is used to select the optimal feature subset with good discriminability from original feature set, and support vector machines （SVMs） are employed to design classifiers. A large number of experimental results show that the proposed method achieves very high recognition rates for 9 radar emitter signals in a wide range of signal-to-noise rates, and proves a feasible and valid method.展开更多
Design and implementation of Internet of Things (IoT) systems require platforms with smart things and components. Two dominant architectural approaches for developing IoT systems are mashup-based and model-based appro...Design and implementation of Internet of Things (IoT) systems require platforms with smart things and components. Two dominant architectural approaches for developing IoT systems are mashup-based and model-based approaches. Mashup approaches use existing services and are mainly suitable for less critical, personalized applications. Web development tools are widely used in mashup approaches. Model-based techniques describe a system on a higher level of abstraction, resulting in very expressive modelling of systems. The article uses Cisco packet tracer 7.2 version, which consists of four subcategories of smart things—home, smart city, industrial and power grid, to design an IoT based control system for a fertilizer manufacturing plant. The packet tracer also consists of boards—microcontrollers (MCU-PT), and single boarded computers (SBC-PT), as well as actuators and sensors. The model facilitates flexible communication opportunities among things—machines, databases, and Human Machine Interfaces (HMIs). Implementation of the IoT system brings finer process control as the operating conditions are monitored online and are broadcasted to all stakeholders in real-time for quicker action on deviations. The model developed focuses on three process plants;steam raising, nitric acid, and ammonium nitrate plants. Key process parameters are saturated steam temperature, fuel flowrates, CO and SO<sub>x</sub> emissions, converter head temperature, NO<sub>x</sub> emissions, neutralisation temperature, solution temperature, and evaporator steam pressure. The parameters need to be monitored in order to ensure quality, safety, and efficiency. Through the Cisco packet tracer platform, a use case, physical layout, network layout, IoT layout, configuration, and simulation interface were developed.展开更多
An analysis of the received signal of array antennas shows that the received signal has multi-resolution characteristics, and hence the wavelet packet theory can be used to detect the signal. By emplying wavelet packe...An analysis of the received signal of array antennas shows that the received signal has multi-resolution characteristics, and hence the wavelet packet theory can be used to detect the signal. By emplying wavelet packet theory to adaptive beamforming, a wavelet packet transform-based adaptive beamforming algorithm (WP-ABF) is proposed . This WP-ABF algorithm uses wavelet packet transform as the preprocessing, and the wavelet packet transformed signal uses least mean square algorithm to implement the ~adaptive beamforming. White noise can be wiped off under wavelet packet transform according to the different characteristics of signal and white under the wavelet packet transform. Theoretical analysis and simulations demonstrate that the proposed WP-ABF algorithm converges faster than the conventional adaptive beamforming algorithm and the wavelet transform-based beamforming algorithm. Simulation results also reveal that the convergence of the algorithm relates closely to the wavelet base and series; that is, the algorithm convergence gets better with the increasing of series, and for the same series of wavelet base the convergence gets better with the increasing of regularity.展开更多
网络负载均衡器是实现网络功能虚拟化(network function virtualization,NFV)的重要功能组件,通过其准确的业务负载分担,运营商可以灵活、高效地实现业务能力增强和容量扩展.基于DPDK技术框架设计实现了面向NFV的高性能4层网络负载均衡...网络负载均衡器是实现网络功能虚拟化(network function virtualization,NFV)的重要功能组件,通过其准确的业务负载分担,运营商可以灵活、高效地实现业务能力增强和容量扩展.基于DPDK技术框架设计实现了面向NFV的高性能4层网络负载均衡机制及系统HVLB,能够灵活部署运行于主流虚拟化平台.HVLB整体采用软件定义网络(software defined networking,SDN)思想设计,实现调度策略制订和数据转发的有效分离.在转发端基于用户空间实现多核多队列高效数据处理架构,同时保证各处理队列间的数据访问隔离和任务处理均衡;在控制端基于网络链路和计算相结合的综合能力作为NF选择和转发策略的制订依据,在实施业务数据准确分发的基础上保障了网络性能.基于KVM的原型系统实验结果表明:与现有LVS系统相比,HVLB极大地提升了数据包处理与转发性能,并实现了64字节UDP数据包的线速转发.展开更多
基金supported by National High-tech R&D Program of China(863 Program)(Grant No.2015AA0156-03)National Natural Science Foundation of China(Grant No.61202483)
文摘The demands of programmability have become more and more exigent as novel network services appear, such as E-commerce, social softwares, and online videos. Commodity multi-core CPUs have been widely applied in network packet processing to get high programmability and reduce the time-to-market. However,there is a great gap between the packet processing performance of commodity multi-core and that of the traditional packet processing hardware, e.g., NP(Network Process). Recently, optimization of the packet processing performance of commodity multi-cores has become a hot topic in industry and academia. In this paper, based on a detailed analysis of the packet processing procedure, firstly we identify two dominating overheads, namely the virtual-to-physical address translation and the packet buffer management. Secondly, we make a comprehensive survey on the current optimization methods. Thirdly, based on the survey, the heterogeneous architecture of the commodity multi-core + FPGA is proposed as a promising way to improve the packet processing performance.Fourthly, a novel Self-Described Buffer(SDB) management technology is introduced to eliminate the overheads of the allocation and deallocation of the packet buffers offloaded to FPGA. Then, an evaluation testbed, named PIOT(Packet I/O Testbed), is designed and implemented to evaluate the packet forwarding performance. I/O capacity of different commodity multi-core CPUs and the performance of optimization methods are assessed and compared based on PIOT. At last, the future work of packet processing optimization on multi-core CPUs is discussed.
基金This work was financially supported by National Key Basic Research and Development Program of China (No.G1998061507) and Niobium Steel Development Project of CITIC-CBMM (No.2002RMJS-KY001)
文摘The packet size of bainitic steel can be refined by a specialrelaxation-precipitation-control phase transformation (RFC) technology. When processed by RPCprocess, the low carbon bainitic steel composes of two kinds of main intermediate transformationphases. One is ultra-fine lath-like bainitic ferrite and the lath is less than 1μm in width andabout 6 μm in length; the alignment of laths forms a refined packet, and the size of packets isabout 5-7 μm in length and about 3-4μm in width. The other is acicular structure. The morphologyand distribution of these acicular structures are influenced by relaxation process, the thin andshort acicular structures cut the prior austenite grain and refine the bainitic packet size. For theoptimum relaxation time, the packet size can be refined to the finest. The mechanical propertiesare influenced by relaxation time and the 800 MPa grade low carbon bainitic steel with excellenttoughness can be obtained by RPC process.
文摘This paper presents a novel method for radar emitter signal recognition. First, wavelet packet transform （WPT） is introduced to extract features from radar emitter signals. Then, rough set theory is used to select the optimal feature subset with good discriminability from original feature set, and support vector machines （SVMs） are employed to design classifiers. A large number of experimental results show that the proposed method achieves very high recognition rates for 9 radar emitter signals in a wide range of signal-to-noise rates, and proves a feasible and valid method.
文摘Design and implementation of Internet of Things (IoT) systems require platforms with smart things and components. Two dominant architectural approaches for developing IoT systems are mashup-based and model-based approaches. Mashup approaches use existing services and are mainly suitable for less critical, personalized applications. Web development tools are widely used in mashup approaches. Model-based techniques describe a system on a higher level of abstraction, resulting in very expressive modelling of systems. The article uses Cisco packet tracer 7.2 version, which consists of four subcategories of smart things—home, smart city, industrial and power grid, to design an IoT based control system for a fertilizer manufacturing plant. The packet tracer also consists of boards—microcontrollers (MCU-PT), and single boarded computers (SBC-PT), as well as actuators and sensors. The model facilitates flexible communication opportunities among things—machines, databases, and Human Machine Interfaces (HMIs). Implementation of the IoT system brings finer process control as the operating conditions are monitored online and are broadcasted to all stakeholders in real-time for quicker action on deviations. The model developed focuses on three process plants;steam raising, nitric acid, and ammonium nitrate plants. Key process parameters are saturated steam temperature, fuel flowrates, CO and SO<sub>x</sub> emissions, converter head temperature, NO<sub>x</sub> emissions, neutralisation temperature, solution temperature, and evaporator steam pressure. The parameters need to be monitored in order to ensure quality, safety, and efficiency. Through the Cisco packet tracer platform, a use case, physical layout, network layout, IoT layout, configuration, and simulation interface were developed.
文摘An analysis of the received signal of array antennas shows that the received signal has multi-resolution characteristics, and hence the wavelet packet theory can be used to detect the signal. By emplying wavelet packet theory to adaptive beamforming, a wavelet packet transform-based adaptive beamforming algorithm (WP-ABF) is proposed . This WP-ABF algorithm uses wavelet packet transform as the preprocessing, and the wavelet packet transformed signal uses least mean square algorithm to implement the ~adaptive beamforming. White noise can be wiped off under wavelet packet transform according to the different characteristics of signal and white under the wavelet packet transform. Theoretical analysis and simulations demonstrate that the proposed WP-ABF algorithm converges faster than the conventional adaptive beamforming algorithm and the wavelet transform-based beamforming algorithm. Simulation results also reveal that the convergence of the algorithm relates closely to the wavelet base and series; that is, the algorithm convergence gets better with the increasing of series, and for the same series of wavelet base the convergence gets better with the increasing of regularity.
文摘网络负载均衡器是实现网络功能虚拟化(network function virtualization,NFV)的重要功能组件,通过其准确的业务负载分担,运营商可以灵活、高效地实现业务能力增强和容量扩展.基于DPDK技术框架设计实现了面向NFV的高性能4层网络负载均衡机制及系统HVLB,能够灵活部署运行于主流虚拟化平台.HVLB整体采用软件定义网络(software defined networking,SDN)思想设计,实现调度策略制订和数据转发的有效分离.在转发端基于用户空间实现多核多队列高效数据处理架构,同时保证各处理队列间的数据访问隔离和任务处理均衡;在控制端基于网络链路和计算相结合的综合能力作为NF选择和转发策略的制订依据,在实施业务数据准确分发的基础上保障了网络性能.基于KVM的原型系统实验结果表明:与现有LVS系统相比,HVLB极大地提升了数据包处理与转发性能,并实现了64字节UDP数据包的线速转发.
