软件定义网络(software-defined networks,SDN)流量调度提升网络性能和资源利用率、实现节能和负载均衡至关重要.传统的多目标优化算法在高流量和网络动态性增加的情况下显著影响算法的收敛速度,难以满足复杂网络环境的多样化需求.针对...软件定义网络(software-defined networks,SDN)流量调度提升网络性能和资源利用率、实现节能和负载均衡至关重要.传统的多目标优化算法在高流量和网络动态性增加的情况下显著影响算法的收敛速度,难以满足复杂网络环境的多样化需求.针对此问题,提出了一种基于深度强化学习的流量预测在线路由算法——OTPR-DRL:根据流量特征预测关键流和普通流,结合网络状态和流量信息建立线性规划问题获得关键流路由的最优解.为满足普通流不同服务质量(quality of service,QoS)需求,引入通用效用函数实现多目标优化,通过多智能体和优先级经验回放机制为普通流选择路由.实验结果表明,在高流量强度下,OTPR-DRL与现有的算法相比,提高了收敛速度,至少降低了10.26%的网络传输时延,3.09%的丢包率,提高了1.70%的吞吐率.展开更多
目的/意义建设基于软件定义网络(software defined networking,SDN)架构的网络安全平台,以增强医院云计算安全防护。方法/过程基于SDN架构构建网络安全平台,并与入侵检测系统联动形成主动防御系统。对比分析平台应用前后租户横向攻击数...目的/意义建设基于软件定义网络(software defined networking,SDN)架构的网络安全平台,以增强医院云计算安全防护。方法/过程基于SDN架构构建网络安全平台,并与入侵检测系统联动形成主动防御系统。对比分析平台应用前后租户横向攻击数量、攻击成功率、策略无阻断业务数、勒索软件加密数据量和安全团队操作工时等指标,验证平台的有效性。结果/结论基于SDN架构的网络安全平台可有效识别并阻断恶意流量,增强对医院云计算的安全防护。展开更多
Cyber-Physical System (CPS) devices are increasing exponentially. Lacking confidentiality creates a vulnerable network. Thus, demanding the overall system with the latest and robust solutions for the defence mechanism...Cyber-Physical System (CPS) devices are increasing exponentially. Lacking confidentiality creates a vulnerable network. Thus, demanding the overall system with the latest and robust solutions for the defence mechanisms with low computation cost, increased integrity, and surveillance. The proposal of a mechanism that utilizes the features of authenticity measures using the Destination Sequence Distance Vector (DSDV) routing protocol which applies to the multi-WSN (Wireless Sensor Network) of IoT devices in CPS which is developed for the Device-to-Device (D2D) authentication developed from the local-chain and public chain respectively combined with the Software Defined Networking (SDN) control and monitoring system using switches and controllers that will route the packets through the network, identify any false nodes, take preventive measures against them and preventing them for any future problems. Next, the system is powered by Blockchain cryptographic features by utilizing the TrustChain features to create a private, secure, and temper-free ledger of the transactions performed inside the network. Results are achieved in the legitimate devices connecting to the network, transferring their packets to their destination under supervision, reporting whenever a false node is causing hurdles, and recording the transactions for temper-proof records. Evaluation results based on 1000+ transactions illustrate that the proposed mechanism not only outshines most aspects of Cyber-Physical systems but also consumes less computation power with a low latency of 0.1 seconds only.展开更多
当前移动互联的社会背景与网络环境对移动数据的管理与相关网络的建设提出更高要求,中国移动需要采取合理措施持续优化数据中心与软件定义网络(software defined network,SDN),确保满足最新的移动互联发展需求。基于此,概述中国移动数...当前移动互联的社会背景与网络环境对移动数据的管理与相关网络的建设提出更高要求,中国移动需要采取合理措施持续优化数据中心与软件定义网络(software defined network,SDN),确保满足最新的移动互联发展需求。基于此,概述中国移动数据中心与SDN,深入探讨中国移动数据中心SDN架构构建策略与技术应用要点,以供相关人员参考。展开更多
Small angle x-ray scattering(SAXS)is an advanced technique for characterizing the particle size distribution(PSD)of nanoparticles.However,the ill-posed nature of inverse problems in SAXS data analysis often reduces th...Small angle x-ray scattering(SAXS)is an advanced technique for characterizing the particle size distribution(PSD)of nanoparticles.However,the ill-posed nature of inverse problems in SAXS data analysis often reduces the accuracy of conventional methods.This article proposes a user-friendly software for PSD analysis,GranuSAS,which employs an algorithm that integrates truncated singular value decomposition(TSVD)with the Chahine method.This approach employs TSVD for data preprocessing,generating a set of initial solutions with noise suppression.A high-quality initial solution is subsequently selected via the L-curve method.This selected candidate solution is then iteratively refined by the Chahine algorithm,enforcing constraints such as non-negativity and improving physical interpretability.Most importantly,GranuSAS employs a parallel architecture that simultaneously yields inversion results from multiple shape models and,by evaluating the accuracy of each model's reconstructed scattering curve,offers a suggestion for model selection in material systems.To systematically validate the accuracy and efficiency of the software,verification was performed using both simulated and experimental datasets.The results demonstrate that the proposed software delivers both satisfactory accuracy and reliable computational efficiency.It provides an easy-to-use and reliable tool for researchers in materials science,helping them fully exploit the potential of SAXS in nanoparticle characterization.展开更多
Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for opti...Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for optimal coverage,ranking further refines their execution order to detect critical faults earlier.This study investigates machine learning techniques to enhance both prioritization and ranking,contributing to more effective and efficient testing processes.We first employ advanced feature engineering alongside ensemble models,including Gradient Boosted,Support Vector Machines,Random Forests,and Naive Bayes classifiers to optimize test case prioritization,achieving an accuracy score of 0.98847 and significantly improving the Average Percentage of Fault Detection(APFD).Subsequently,we introduce a deep Q-learning framework combined with a Genetic Algorithm(GA)to refine test case ranking within priority levels.This approach achieves a rank accuracy of 0.9172,demonstrating robust performance despite the increasing computational demands of specialized variation operators.Our findings highlight the effectiveness of stacked ensemble learning and reinforcement learning in optimizing test case prioritization and ranking.This integrated approach improves testing efficiency,reduces late-stage defects,and improves overall software stability.The study provides valuable information for AI-driven testing frameworks,paving the way for more intelligent and adaptive software quality assurance methodologies.展开更多
空天地一体化网络作为6G技术的关键组成,在整合天基、空基和地基网络时,面临节点异构性、业务多样性等挑战,进而引发资源分配、竞争及故障风险等问题。基于此,聚焦基于软件定义网络(software defined network,SDN)与网络功能虚拟化(netw...空天地一体化网络作为6G技术的关键组成,在整合天基、空基和地基网络时,面临节点异构性、业务多样性等挑战,进而引发资源分配、竞争及故障风险等问题。基于此,聚焦基于软件定义网络(software defined network,SDN)与网络功能虚拟化(network functions virtualization,NFV)的空天地一体化网络任务部署与恢复,首先阐述了空天地一体化网络系统架构,介绍了各层网络构成、SDN和NFV原理及其相关应用,然后,针对上述挑战,以服务功能链技术为抓手,提出了面向任务的服务功能链优化部署、利用智能算法实现动态调度、通过匹配博弈算法完成失效恢复等策略,最后,构建了一个用例,设定节点部署、服务功能链建模等,验证了所提策略在提升服务功能链完成效率以及应对资源故障方面的有效性,旨在为空天地一体化网络资源管理提供理论基础。展开更多
文摘软件定义网络(software-defined networks,SDN)流量调度提升网络性能和资源利用率、实现节能和负载均衡至关重要.传统的多目标优化算法在高流量和网络动态性增加的情况下显著影响算法的收敛速度,难以满足复杂网络环境的多样化需求.针对此问题,提出了一种基于深度强化学习的流量预测在线路由算法——OTPR-DRL:根据流量特征预测关键流和普通流,结合网络状态和流量信息建立线性规划问题获得关键流路由的最优解.为满足普通流不同服务质量(quality of service,QoS)需求,引入通用效用函数实现多目标优化,通过多智能体和优先级经验回放机制为普通流选择路由.实验结果表明,在高流量强度下,OTPR-DRL与现有的算法相比,提高了收敛速度,至少降低了10.26%的网络传输时延,3.09%的丢包率,提高了1.70%的吞吐率.
文摘目的/意义建设基于软件定义网络(software defined networking,SDN)架构的网络安全平台,以增强医院云计算安全防护。方法/过程基于SDN架构构建网络安全平台,并与入侵检测系统联动形成主动防御系统。对比分析平台应用前后租户横向攻击数量、攻击成功率、策略无阻断业务数、勒索软件加密数据量和安全团队操作工时等指标,验证平台的有效性。结果/结论基于SDN架构的网络安全平台可有效识别并阻断恶意流量,增强对医院云计算的安全防护。
基金funded by Ajman University,AU-Funded Research Grant 2023-IRG-ENIT-22.
文摘Cyber-Physical System (CPS) devices are increasing exponentially. Lacking confidentiality creates a vulnerable network. Thus, demanding the overall system with the latest and robust solutions for the defence mechanisms with low computation cost, increased integrity, and surveillance. The proposal of a mechanism that utilizes the features of authenticity measures using the Destination Sequence Distance Vector (DSDV) routing protocol which applies to the multi-WSN (Wireless Sensor Network) of IoT devices in CPS which is developed for the Device-to-Device (D2D) authentication developed from the local-chain and public chain respectively combined with the Software Defined Networking (SDN) control and monitoring system using switches and controllers that will route the packets through the network, identify any false nodes, take preventive measures against them and preventing them for any future problems. Next, the system is powered by Blockchain cryptographic features by utilizing the TrustChain features to create a private, secure, and temper-free ledger of the transactions performed inside the network. Results are achieved in the legitimate devices connecting to the network, transferring their packets to their destination under supervision, reporting whenever a false node is causing hurdles, and recording the transactions for temper-proof records. Evaluation results based on 1000+ transactions illustrate that the proposed mechanism not only outshines most aspects of Cyber-Physical systems but also consumes less computation power with a low latency of 0.1 seconds only.
文摘当前移动互联的社会背景与网络环境对移动数据的管理与相关网络的建设提出更高要求,中国移动需要采取合理措施持续优化数据中心与软件定义网络(software defined network,SDN),确保满足最新的移动互联发展需求。基于此,概述中国移动数据中心与SDN,深入探讨中国移动数据中心SDN架构构建策略与技术应用要点,以供相关人员参考。
基金Project supported by the Project of the Anhui Provincial Natural Science Foundation(Grant No.2308085MA19)Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA0410401)+2 种基金the National Natural Science Foundation of China(Grant No.52202120)the National Key Research and Development Program of China(Grant No.2023YFA1609800)USTC Research Funds of the Double First-Class Initiative(Grant No.YD2310002013)。
文摘Small angle x-ray scattering(SAXS)is an advanced technique for characterizing the particle size distribution(PSD)of nanoparticles.However,the ill-posed nature of inverse problems in SAXS data analysis often reduces the accuracy of conventional methods.This article proposes a user-friendly software for PSD analysis,GranuSAS,which employs an algorithm that integrates truncated singular value decomposition(TSVD)with the Chahine method.This approach employs TSVD for data preprocessing,generating a set of initial solutions with noise suppression.A high-quality initial solution is subsequently selected via the L-curve method.This selected candidate solution is then iteratively refined by the Chahine algorithm,enforcing constraints such as non-negativity and improving physical interpretability.Most importantly,GranuSAS employs a parallel architecture that simultaneously yields inversion results from multiple shape models and,by evaluating the accuracy of each model's reconstructed scattering curve,offers a suggestion for model selection in material systems.To systematically validate the accuracy and efficiency of the software,verification was performed using both simulated and experimental datasets.The results demonstrate that the proposed software delivers both satisfactory accuracy and reliable computational efficiency.It provides an easy-to-use and reliable tool for researchers in materials science,helping them fully exploit the potential of SAXS in nanoparticle characterization.
文摘Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for optimal coverage,ranking further refines their execution order to detect critical faults earlier.This study investigates machine learning techniques to enhance both prioritization and ranking,contributing to more effective and efficient testing processes.We first employ advanced feature engineering alongside ensemble models,including Gradient Boosted,Support Vector Machines,Random Forests,and Naive Bayes classifiers to optimize test case prioritization,achieving an accuracy score of 0.98847 and significantly improving the Average Percentage of Fault Detection(APFD).Subsequently,we introduce a deep Q-learning framework combined with a Genetic Algorithm(GA)to refine test case ranking within priority levels.This approach achieves a rank accuracy of 0.9172,demonstrating robust performance despite the increasing computational demands of specialized variation operators.Our findings highlight the effectiveness of stacked ensemble learning and reinforcement learning in optimizing test case prioritization and ranking.This integrated approach improves testing efficiency,reduces late-stage defects,and improves overall software stability.The study provides valuable information for AI-driven testing frameworks,paving the way for more intelligent and adaptive software quality assurance methodologies.
文摘空天地一体化网络作为6G技术的关键组成,在整合天基、空基和地基网络时,面临节点异构性、业务多样性等挑战,进而引发资源分配、竞争及故障风险等问题。基于此,聚焦基于软件定义网络(software defined network,SDN)与网络功能虚拟化(network functions virtualization,NFV)的空天地一体化网络任务部署与恢复,首先阐述了空天地一体化网络系统架构,介绍了各层网络构成、SDN和NFV原理及其相关应用,然后,针对上述挑战,以服务功能链技术为抓手,提出了面向任务的服务功能链优化部署、利用智能算法实现动态调度、通过匹配博弈算法完成失效恢复等策略,最后,构建了一个用例,设定节点部署、服务功能链建模等,验证了所提策略在提升服务功能链完成效率以及应对资源故障方面的有效性,旨在为空天地一体化网络资源管理提供理论基础。
