DDoS attack detection and defense based on hybrid deep learning model in SDN

Software defined network (SDN) is a new kind of network technology,and the security problems are the hot topics in SDN field,such as SDN control channel security,forged service deployment and external distributed denial of service (DDoS) attacks.Aiming at DDoS attack problem of security in SDN,a DDoS attack detection method called DCNN-DSAE based on deep learning hybrid model in SDN was proposed.In this method,when a deep learning model was constructed,the input feature included 21 different types of fields extracted from the data plane and 5 extra self-designed features of distinguishing flow types.The experimental results show that the method has high accuracy,it’s better than the traditional support vector machine (SVM) and deep neural network (DNN) and other machine learning methods.At the same time,the proposed method can also shorten the processing time of classification detection.The detection model is deployed in SDN controller,and the new security policy is sent to the OpenFlow switch to achieve the defense against specific DDoS attack.     

Scalable performance evaluation of a hybrid optical switch

This paper provides new loss models for a hybrid optical switch (HOS) combining optical circuit switching (OCS) and optical burst switching (OBS). Exact blocking probabilities are computed when 1) no priority is given to either circuits or bursts and 2) circuits are given preemptive priority over bursts. Because it is difficult to exactly compute in realistic scenarios, computationally scalable approximations are derived for the blocking probability. The sensitivity of the analytical results to burst length and circuit holding-time distributions is quantified by simulation. It is demonstrated how the proposed approximations can be used for multiplexing-gain evaluation of a hybrid switch. In addition, the extension of the proposed single-node model to a network model composed of OCS, OBS, and hybrid switches is outlined.     

Evaluation of packet scheduling in hybrid optical/electrical switch

This paper presents a hybrid optical/electrical switch for high-capacity future network development. A switch architecture to provide packet switching by solving contention in wavelength and time domains is considered relying on available optical and electrical technology. Physical and logical aspects regarding switch feasibility and management, in relation to the hybrid nature of the switch, are addressed. Scheduling algorithms to support multi-service packet forwarding are compared with optimally exploit optical and electrical subsystems according to traffic characteristics and needs. The main outcomes of the paper suggest criteria to design high-capacity packet switches, based on present-day technology constraints and quality of service requirements, to achieve a fair balance between optical transparency and loss performance.     

HPSIN: a new hybrid P2P spatial indexing network

Geographic information system(GIS)is increasingly managing very large sets of data,hence a centralized data index may not always provide the most scalable solution.Recently,the peer to peer(P2P)networks have become very popular for sharing information in a totally decentralized manner.In this paper,a new hybrid P2P spatial indexing network(HPSIN)is proposed,which combines distributed quad-tree with distributed Hash table(DHT)based Chord network to maintain both query efficiency and system load balance.In addition,a simple theoretical model based on opened queueing network for HPSIN is established.Assuming each peer as M/M/1 queueing processor in the model,fundamental characteristics of the system is captured,and expression of average query delay is obtained in close form.The theoretical analysis and numerical computing results show that there exists an optimum point of tradeoff between efficiency and load balance.By setting a proper value of start index level ls for different network scale and query rate,HPSIN will achieve the minimum overall query delay,therefore,can adapt to different P2P application environments.     

The Tera project: a hybrid queueing ATM switch architecture for LAN

The Tera ATM LAN project at Carnegie Mellon University addresses the interconnection of hundreds of workstations in the Electrical and Computer Engineering Department via an ATM-based network. The Tera network architecture consists of switched Ethernet clusters that are interconnected using an ATM network. This paper presents the Tera network architecture, including an Ethernet/ATM network interface, the Tera ATM switch, and its performance analysis. The Tera switch architecture for asynchronous transfer mode (ATM) local area networks (LAN's) incorporates a scalable nonblocking switching element with hybrid queueing discipline. The hybrid queueing strategy includes a global first-in first-out (FIFO) queue that is shared by all switch inputs and dedicated output queues with small speedup. Due to hybrid queueing, switch performance is comparable to output queueing switches. The shared input queue design is scalable since it is based on a Banyan network and N FIFO memories. The Tera switch incorporates an optimal throughput multicast stage that is also based on a Banyan network. Switch performance is evaluated using queueing analysis and simulation under various traffic patterns     

Analysis of an optical hybrid switch

This paper provides new loss models for an OCS/OBS optical hybrid switch. Exact results for the blocking probability based on an analysis, of a 3-dimension state-space Markov chain is derived when circuits are given preemptive priority over bursts and are allowed to wait a certain amount of time if all wavelengths are busy in the desired output link. Because it is difficult to-exactly compute the blocking probability in realistic scenarios, we derive a. computationally scalable approximation for the blocking probability reducing the 3-dimension state space into a single dimension.     

Performance analysis of a multicast switch

The performance of a multicast switch, a space division switch in which a packet at an input port is routed to a subset of the output ports, is discussed. The delay under the assumption of input port buffering is determined. The system is modeled as an independent set of M/G/1 queues. A key assumption in the analysis is that output port contention is settled by random selection among the contending input ports. In order to justify this as well as the other assumptions, a Monte-Carlo simulation of the system is devised. Numerical results from the analysis and simulation of the system are presented     

Bipolar transistor carrier-injected optical modulator/switch: Proposal and analysis

Bipolar transistor structures can be used, instead of conventional p-n (p-i-n) junctions, to realize high-speed optical modulators and switches, which are operated by free-carrier injection. Some basic results obtained by the theoretical analysis of the structure applied to a DH X crossing are presented, with emphasis on the switching speed. It is shown that switching times can be as fast as 60 ps for the required ON-OFF optical switching, which is considerably faster than those expected for a diode structure.     

SDN/NFV的挑战

网络云化的趋势日益明显,SDN/NFV作为其中的关键技术,受到了通信业界的广泛关注,不仅在标准化组织中不断完善,还在产业链多个环节得到了试验验证。SDN和NFV在快深入发展、不断推进的同时,也面临许多挑战和问题,如统一资源协同性、互操作性和性能等,需要得到针对性的应对和解决。     

Performance analysis of a duplex multicast switch

A multicast switching architecture called a duplex multicast switch is proposed, and several switch control algorithms are developed. A duplex multicast switch, with two point-to-point routing nets, has potential to provide significantly better performance than a simplex multicast switch by reducing the output loadings of routing nets. To fully realize its potential, two call distribution algorithms, cluster distribution and spread distribution, are developed. Cluster distribution is partitioned into partial search cluster distribution and exhaustive search cluster distribution based on search policies, and the performance of the three algorithms is analyzed by the arrival modulation technique. The results show that a spread distribution eliminates most slot contention blocking and achieves near-optimal performance     

Polarisation-independent LiNbO3 4×4 matrix switch

The first polarisation independent LiNbO₃ strictly non-blocking 4×4 matrix switch has been developed. This matrix switch has a 4-6 dB insertion loss at any incident polarisation with 1.3 μm wavelength and about 30 V switching voltage     

Extremely low loss 4*4 GaAs/AlGaAs optical matrix switch

A 4*4 GaAs/AlGaAs optical matrix switch with an extremely low loss of 1.6 dB has been developed. This low loss switch was achieved by layer structure modification, to reduce free-carrier absorption, reduction of plasma damage while dry etching, and an improvement in the crystal quality.<>     

Face age classification based on a deep hybrid model

Face age estimation, a computer vision task facing numerous challenges due to its potential applications in identity authentication, human–computer interface, video retrieval and robot vision, has been attracting increasing attention. In recent years, the deep convolutional neural networks (DCNN) have achieved state-of-the-art performance in age classification of face images. We propose a deep hybrid framework for age classification by exploiting DCNN as the raw feature extractor along with several effective methods, including fine-tuning the DCNN into a fine-tuned deep age feature extraction (FDAFE) model, introducing a new method of feature extracting, applying the maximum joint probability classifier to age classification and a strategy to incorporate information from face images more effectively to improve estimation capabilities further. In addition, we pre-process the original image to represent age information more accurately. Based on the discriminative and compact framework, state-of-the-art performance on several face image data sets has been achieved in terms of classification accuracy.     

SDN/NFV组网技术标准

软件定义网络(SDN)/网络功能虚拟化(NFV)技术为降低网络构件成本,实现灵活组网提出了便利的方案,是信息通信技术(ICT)产业发展不可缺少的重要支撑。通过对中国通信标准化协会(CCSA)未来数据网络特别工作组(TC1 SWG3)在SDN/NFV组网应用场景、组网体系架构以及基于SDN/NFV的各种业务组网体系架构等方面的技术标准的介绍,认为SDN/NFV将成为未来网络的候选技术之一,TC1SWG3在后续的工作中将研究采用SDN/NFV技术的未来数据网络相关标准,服务行业应用。     

Efficient analysis of quasi-optical filters by a hybrid MoM/BI-RMEmethod

This paper presents a novel algorithm for the analysis of quasi-optical filters, consisting of thick metal screens perforated periodically with arbitrarily shaped apertures. The algorithm is based on the widely used method of moments (MoM) in conjunction with entire domain basis functions. Its flexibility, accuracy, and rapidity depend on the use of the boundary integral-resonant mode expansion (BI-RME) method in the numerical determination of the basis functions. A computer code has been developed based on this algorithm. The analysis of two different quasi-optical filters operating at 8 GHz and 280 GHz is reported and compared with experimental data as well as with other simulations. In both cases, the whole analysis requires few seconds on a standard workstation and the theoretical results show a very good agreement with the measured data in a wide frequency band. The capability of the MoM/BI-RME approach to handle completely arbitrary shapes is highlighted in the second example. In this case, in fact, the fabrication process causes small deformations of the nominal shape of the apertures, which must be accounted for, since they play an important role in the frequency response of the filter     

TORUS-switch: a scalable internal speed-up ATM switch architectureand its 5 Gbit/s switch LSI

A high speed and scalable ATM switch architecture, the TORUS-switch, is proposed. The switch is an internal speed-up crosspoint switch with cylindrical configuration. The self-bit-synchronisation technique is adopted to achieve high speed cell transmission without requiring high-density implementation technology. Distributed contention control based on the fixed output-precedence scheme is adopted. This control is so simple that the control circuit is achieved with only one gate in each crosspoint. A TORUS-switch is fabricated as an ultrahigh speed crosspoint LSI using the advanced Si-bipolar process. Measured results confirm that the TORUS-switch can be used to realise an expandable terabit-rate ATM switch that is also efficient     

Performance Analysis of SDN/OpenFlow Controllers: POX Versus Floodlight

Software-Defined Networking (SDN) is an emerging network architecture that is adaptable, dynamic, cost-effective, and manageable. The SDN architecture is a form of network virtualization where the network controlling functions and forwarding functions are decoupled. A setup and configuration task of a control plane to work as an SDN controller is explained in this paper. This paper includes a brief survey of different SDN based OpenFlow-enabled controllers available in various programmable languages. This paper mainly focuses on two OpenFlow-enabled controllers, namely, POX—a Python-based controller and Floodlight—a Java-based controller. A performance comparison of both controllers is tested over different network topologies by analyzing network throughput and round-trip delay using an efficient network simulator called Mininet. A single, linear, tree and custom (user-defined) topologies are designed in Mininet by enabling external controllers. It is obtained that, a percentage improvement in round-trip time for Floodlight over POX is 11.5, 13.9, 19.6 and 14.4% for single, linear, tree and custom topology respectively. Similarly, a percentage improvement in throughput for Floodlight over POX is 5.4, 8.9, 3.8 and 4.9% for single, linear, tree and custom topology respectively.     

Integrated lossless InGaAsP/InP 1-to-4 optical switch

The fabrication and performance of a 1-to-4 channel optical splitter/combiner are described. The design is based on the integration of a number of twin-guide amplifiers interconnected by active ridge waveguides. Lossless operation is seen fiber-to-fiber for all four ports for TE input light, with a 3-dB bandwidth of 20 nm     

Monolithically integrated 4*4 InGaAsP/InP laser amplifier gate switch arrays

Monolithically integrated 4*4 semiconductor laser amplifier gate switch arrays comprising 24 integrated laser amplifiers have been fabricated and evaluated. Net positive optical gain between fibres, high extinction ratio, and low crosstalk are reported.<>