Zero Trust Network(ZTN)enhances network security through strict authentication and access control.However,in the ZTN,optimizing flow control to improve the quality of service is still facing challenges.Software Define...Zero Trust Network(ZTN)enhances network security through strict authentication and access control.However,in the ZTN,optimizing flow control to improve the quality of service is still facing challenges.Software Defined Network(SDN)provides solutions through centralized control and dynamic resource allocation,but the existing scheduling methods based on Deep Reinforcement Learning(DRL)are insufficient in terms of convergence speed and dynamic optimization capability.To solve these problems,this paper proposes DRL-AMIR,which is an efficient flow scheduling method for software defined ZTN.This method constructs a flow scheduling optimization model that comprehensively considers service delay,bandwidth occupation,and path hops.Additionally,it balances the differentiated requirements of delay-critical K-flows,bandwidth-intensive D-flows,and background B-flows through adaptiveweighting.Theproposed framework employs a customized state space comprising node labels,link bandwidth,delaymetrics,and path length.It incorporates an action space derived fromnode weights and a hybrid reward function that integrates both single-step and multi-step excitation mechanisms.Based on these components,a hierarchical architecture is designed,effectively integrating the data plane,control plane,and knowledge plane.In particular,the adaptive expert mechanism is introduced,which triggers the shortest path algorithm in the training process to accelerate convergence,reduce trial and error costs,and maintain stability.Experiments across diverse real-world network topologies demonstrate that DRL-AMIR achieves a 15–20%reduction in K-flow transmission delays,a 10–15%improvement in link bandwidth utilization compared to SPR,QoSR,and DRSIR,and a 30%faster convergence speed via adaptive expert mechanisms.展开更多
Accurate early classification of elephant flows(elephants)is important for network management and resource optimization.Elephant models,mainly based on the byte count of flows,can always achieve high accuracy,but not ...Accurate early classification of elephant flows(elephants)is important for network management and resource optimization.Elephant models,mainly based on the byte count of flows,can always achieve high accuracy,but not in a time-efficient manner.The time efficiency becomes even worse when the flows to be classified are sampled by flow entry timeout over Software-Defined Networks(SDNs)to achieve a better resource efficiency.This paper addresses this situation by combining co-training and Reinforcement Learning(RL)to enable a closed-loop classification approach that divides the entire classification process into episodes,each involving two elephant models.One predicts elephants and is retrained by a selection of flows automatically labeled online by the other.RL is used to formulate a reward function that estimates the values of the possible actions based on the current states of both models and further adjusts the ratio of flows to be labeled in each phase.Extensive evaluation based on real traffic traces shows that the proposed approach can stably predict elephants using the packets received in the first 10% of their lifetime with an accuracy of over 80%,and using only about 10% more control channel bandwidth than the baseline over the evolved SDNs.展开更多
The rise of time-sensitive applications with broad geographical scope drives the development of time-sensitive networking(TSN)from intra-domain to inter-domain to ensure overall end-to-end connectivity requirements in...The rise of time-sensitive applications with broad geographical scope drives the development of time-sensitive networking(TSN)from intra-domain to inter-domain to ensure overall end-to-end connectivity requirements in heterogeneous deployments.When multiple TSN networks interconnect over non-TSN networks,all devices in the network need to be syn-chronized by sharing a uniform time reference.How-ever,most non-TSN networks are best-effort.Path delay asymmetry and random noise accumulation can introduce unpredictable time errors during end-to-end time synchronization.These factors can degrade syn-chronization performance.Therefore,cross-domain time synchronization becomes a challenging issue for multiple TSN networks interconnected by non-TSN networks.This paper presents a cross-domain time synchronization scheme that follows the software-defined TSN(SD-TSN)paradigm.It utilizes a com-bined control plane constructed by a coordinate con-troller and a domain controller for centralized control and management of cross-domain time synchroniza-tion.The general operation flow of the cross-domain time synchronization process is designed.The mecha-nism of cross-domain time synchronization is revealed by introducing a synchronization model and an error compensation method.A TSN cross-domain proto-type testbed is constructed for verification.Results show that the scheme can achieve end-to-end high-precision time synchronization with accuracy and sta-bility.展开更多
With the evolution of next-generation communication networks,ensuring robust Core Network(CN)architecture and data security has become paramount.This paper addresses critical vulnerabilities in the architecture of CN ...With the evolution of next-generation communication networks,ensuring robust Core Network(CN)architecture and data security has become paramount.This paper addresses critical vulnerabilities in the architecture of CN and data security by proposing a novel framework based on blockchain technology that is specifically designed for communication networks.Traditional centralized network architectures are vulnerable to Distributed Denial of Service(DDoS)attacks,particularly in roaming scenarios where there is also a risk of private data leakage,which imposes significant operational demands.To address these issues,we introduce the Blockchain-Enhanced Core Network Architecture(BECNA)and the Secure Decentralized Identity Authentication Scheme(SDIDAS).The BECNA utilizes blockchain technology to decentralize data storage,enhancing network security,stability,and reliability by mitigating Single Points of Failure(SPoF).The SDIDAS utilizes Decentralized Identity(DID)technology to secure user identity data and streamline authentication in roaming scenarios,significantly reducing the risk of data breaches during cross-network transmissions.Our framework employs Ethereum,free5GC,Wireshark,and UERANSIM tools to create a robust,tamper-evident system model.A comprehensive security analysis confirms substantial improvements in user privacy and network security.Simulation results indicate that our approach enhances communication CNs security and reliability,while also ensuring data security.展开更多
Distributed denial of service(DDoS)attacks are common network attacks that primarily target Internet of Things(IoT)devices.They are critical for emerging wireless services,especially for applications with limited late...Distributed denial of service(DDoS)attacks are common network attacks that primarily target Internet of Things(IoT)devices.They are critical for emerging wireless services,especially for applications with limited latency.DDoS attacks pose significant risks to entrepreneurial businesses,preventing legitimate customers from accessing their websites.These attacks require intelligent analytics before processing service requests.Distributed denial of service(DDoS)attacks exploit vulnerabilities in IoT devices by launchingmulti-point distributed attacks.These attacks generate massive traffic that overwhelms the victim’s network,disrupting normal operations.The consequences of distributed denial of service(DDoS)attacks are typically more severe in software-defined networks(SDNs)than in traditional networks.The centralised architecture of these networks can exacerbate existing vulnerabilities,as these weaknesses may not be effectively addressed in this model.The preliminary objective for detecting and mitigating distributed denial of service(DDoS)attacks in software-defined networks(SDN)is to monitor traffic patterns and identify anomalies that indicate distributed denial of service(DDoS)attacks.It implements measures to counter the effects ofDDoS attacks,and ensure network reliability and availability by leveraging the flexibility and programmability of SDN to adaptively respond to threats.The authors present a mechanism that leverages the OpenFlow and sFlow protocols to counter the threats posed by DDoS attacks.The results indicate that the proposed model effectively mitigates the negative effects of DDoS attacks in an SDN environment.展开更多
In Software-Defined Networks(SDNs),determining how to efficiently achieve Quality of Service(QoS)-aware routing is challenging but critical for significantly improving the performance of a network,where the metrics of...In Software-Defined Networks(SDNs),determining how to efficiently achieve Quality of Service(QoS)-aware routing is challenging but critical for significantly improving the performance of a network,where the metrics of QoS can be defined as,for example,average latency,packet loss ratio,and throughput.The SDN controller can use network statistics and a Deep Reinforcement Learning(DRL)method to resolve this challenge.In this paper,we formulate dynamic routing in an SDN as a Markov decision process and propose a DRL algorithm called the Asynchronous Advantage Actor-Critic QoS-aware Routing Optimization Mechanism(AQROM)to determine routing strategies that balance the traffic loads in the network.AQROM can improve the QoS of the network and reduce the training time via dynamic routing strategy updates;that is,the reward function can be dynamically and promptly altered based on the optimization objective regardless of the network topology and traffic pattern.AQROM can be considered as one-step optimization and a black-box routing mechanism in high-dimensional input and output sets for both discrete and continuous states,and actions with respect to the operations in the SDN.Extensive simulations were conducted using OMNeT++and the results demonstrated that AQROM 1)achieved much faster and stable convergence than the Deep Deterministic Policy Gradient(DDPG)and Advantage Actor-Critic(A2C),2)incurred a lower packet loss ratio and latency than Open Shortest Path First(OSPF),DDPG,and A2C,and 3)resulted in higher and more stable throughput than OSPF,DDPG,and A2C.展开更多
Internet Exchange Point(IXP)is a system that increases network bandwidth performance.Internet exchange points facilitate interconnection among network providers,including Internet Service Providers(ISPs)andContent Del...Internet Exchange Point(IXP)is a system that increases network bandwidth performance.Internet exchange points facilitate interconnection among network providers,including Internet Service Providers(ISPs)andContent Delivery Providers(CDNs).To improve service management,Internet exchange point providers have adopted the Software Defined Network(SDN)paradigm.This implementation is known as a Software-Defined Exchange Point(SDX).It improves network providers’operations and management.However,performance issues still exist,particularly with multi-hop topologies.These issues include switch memory costs,packet processing latency,and link failure recovery delays.The paper proposes Enhanced Link Failure Rerouting(ELFR),an improved mechanism for rerouting link failures in software-defined exchange point networks.The proposed mechanism aims to minimize packet processing time for fast link failure recovery and enhance path calculation efficiency while reducing switch storage overhead by exploiting the Programming Protocol-independent Packet Processors(P4)features.The paper presents the proposed mechanisms’efficiency by utilizing advanced algorithms and demonstrating improved performance in packet processing speed,path calculation effectiveness,and switch storage management compared to current mechanisms.The proposed mechanism shows significant improvements,leading to a 37.5%decrease in Recovery Time(RT)and a 33.33%decrease in both Calculation Time(CT)and Computational Overhead(CO)when compared to current mechanisms.The study highlights the effectiveness and resource efficiency of the proposed mechanism in effectively resolving crucial issues inmulti-hop software-defined exchange point networks.展开更多
Core power is a key parameter of nuclear reactor.Traditionally,the proportional-integralderivative(PID)controllers are used to control the core power.Fractional-order PID(FOPID)controller represents the cutting edge i...Core power is a key parameter of nuclear reactor.Traditionally,the proportional-integralderivative(PID)controllers are used to control the core power.Fractional-order PID(FOPID)controller represents the cutting edge in core power control research.In comparing with the integer-order models,fractional-order models describe the variation of core power more accurately,thus provide a comprehensive and realistic depiction for the power and state changes of reactor core.However,current fractional-order controllers cannot adjust their parameters dynamically to response the environmental changes or demands.In this paper,we aim at the stable control and dynamic responsiveness of core power.Based on the strong selflearning ability of artificial neural network(ANN),we propose a composite controller combining the ANN and FOPID controller.The FOPID controller is firstly designed and a back propagation neural network(BPNN)is then utilized to optimize the parameters of FOPID.It is shown by simulation that the composite controller enables the real-time parameter tuning via ANN and retains the advantage of FOPID controller.展开更多
Software-defined satellite networks(SDSNs)play an essential role in future networks.Due to the diverse service scenarios,SDSN faces the demand of packet processing for heterogeneous protocols.Existing packet switching...Software-defined satellite networks(SDSNs)play an essential role in future networks.Due to the diverse service scenarios,SDSN faces the demand of packet processing for heterogeneous protocols.Existing packet switching typically works on one single protocol.For protocol-heterogeneous users,existing packet switch architectures have to construct multiple protocol-specific switching instances,resulting in severe resource waste.In this article,we propose the heterogeneous protocol-independent packet switch architecture(HISA).HISA employs a fast parsing structure to achieve efficient heterogeneous packet parsing and a novel match-action pipeline to achieve shared packet processing among heterogeneous users.HISA can also support the online configuration of switching behaviors.Use cases illustrate the effectiveness of applying HISA in SDSN.Numerical results show that compared to existing packet switching,HISA can significantly improve the resource utilization of SDSN.展开更多
Synergistically and simultaneously enhancing strength and ductility has been a major challenge for the development and applications of titanium matrix composites.Herein,a new design methodology for Ti_(2)Cu/Ti_(6)Al4V...Synergistically and simultaneously enhancing strength and ductility has been a major challenge for the development and applications of titanium matrix composites.Herein,a new design methodology for Ti_(2)Cu/Ti_(6)Al4V composites with superior strength and ductility is reported.展开更多
The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to case...The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to cases wherein a single region changes at a specified location of the core.However,when the neutron field changes are complex,the accurate identification of the individual changed regions becomes challenging,which seriously affects the accuracy and stability of the neutron field recon-struction.Therefore,this study proposed a dual-task hybrid network architecture(DTHNet)for off situ reconstruction of the core neutron field,which trained the outermost assembly reconstruction task and the core reconstruction task jointly such that the former could assist the latter in the reconstruction of the core neutron field under core complex changes.Furthermore,to exploit the characteristics of the ex-core detection signals,this study designed a global-local feature upsampling module that efficiently distributed the ex-core detection signals to each reconstruction unit to improve the accuracy and stability of reconstruction.Reconstruction experiments were performed on the simulation datasets of the CLEAR-I reactor to verify the accuracy and stability of the proposed method.The results showed that when the location uncertainty of a single region did not exceed nine and the number of multiple changed regions did not exceed five.Further,the reconstructed ARD was within 2%,RD_(max)was maintained within 17.5%,and the number of RD≥10%was maintained within 10.Furthermore,when the noise interference of the ex-core detection signals was within±2%,although the average number of RD≥10%increased to 16,the average ARD was still within in 2%,and the average RD_(max)was within 22%.Collectively,these results show that,theoretically,the DTHNet can accurately and stably reconstruct most of the neutron field under certain complex core changes.展开更多
With the rapid development of low-orbit satellite com-munication networks both domestically and internationally,space-terrestrial integrated networks will become the future development trend.For space and terrestrial ...With the rapid development of low-orbit satellite com-munication networks both domestically and internationally,space-terrestrial integrated networks will become the future development trend.For space and terrestrial networks with limi-ted resources,the utilization efficiency of the entire space-terres-trial integrated networks resources can be affected by the core network indirectly.In order to improve the response efficiency of core networks expansion construction,early warning of the core network elements capacity is necessary.Based on the inte-grated architecture of space and terrestrial network,multidimen-sional factors are considered in this paper,including the number of terminals,login users,and the rules of users’migration during holidays.Using artifical intelligence(AI)technologies,the regis-tered users of the access and mobility management function(AMF),authorization users of the unified data management(UDM),protocol data unit(PDU)sessions of session manage-ment function(SMF)are predicted in combination with the num-ber of login users,the number of terminals.Therefore,the core network elements capacity can be predicted in advance.The proposed method is proven to be effective based on the data from real network.展开更多
Software-Defined Networking(SDN)improves network management by separating its control logic from the underlying hardware and integrating it into a logically centralized control unit,termed the SDN controller.SDN adapt...Software-Defined Networking(SDN)improves network management by separating its control logic from the underlying hardware and integrating it into a logically centralized control unit,termed the SDN controller.SDN adaptation is essential for wireless networks because it offers enhanced and data-intensive services.The initial intent of the SDN design was to have a physically centralized controller.However,network experts have suggested logically centralized and physically distributed designs for SDN controllers,owing to issues such as a single point of failure and scalability.This study addressed the security,scalability,reliability,and consistency issues associated with the design of distributed SDN controllers.Moreover,the security issues of an enterprise related to multiple physically distributed controllers in a software-defined wireless local area network(SD-WLAN)were emphasized,and optimal solutions were suggested.展开更多
By decoupling control plane and data plane,Software-Defined Networking(SDN) approach simplifies network management and speeds up network innovations.These benefits have led not only to prototypes,but also real SDN dep...By decoupling control plane and data plane,Software-Defined Networking(SDN) approach simplifies network management and speeds up network innovations.These benefits have led not only to prototypes,but also real SDN deployments.For wide-area SDN deployments,multiple controllers are often required,and the placement of these controllers becomes a particularly important task in the SDN context.This paper studies the problem of placing controllers in SDNs,so as to maximize the reliability of SDN control networks.We present a novel metric,called expected percentage of control path loss,to characterize the reliability of SDN control networks.We formulate the reliability-aware control placement problem,prove its NP-hardness,and examine several placement algorithms that can solve this problem.Through extensive simulations using real topologies,we show how the number of controllers and their placement influence the reliability of SDN control networks.Besides,we also found that,through strategic controller placement,the reliability of SDN control networks can be significantly improved without introducing unacceptable switch-to-controller latencies.展开更多
As a new networking paradigm,Software-Defined Networking(SDN)enables us to cope with the limitations of traditional networks.SDN uses a controller that has a global view of the network and switch devices which act as ...As a new networking paradigm,Software-Defined Networking(SDN)enables us to cope with the limitations of traditional networks.SDN uses a controller that has a global view of the network and switch devices which act as packet forwarding hardware,known as“OpenFlow switches”.Since load balancing service is essential to distribute workload across servers in data centers,we propose an effective load balancing scheme in SDN,using a genetic programming approach,called Genetic Programming based Load Balancing(GPLB).We formulate the problem to find a path:1)with the best bottleneck switch which has the lowest capacity within bottleneck switches of each path,2)with the shortest path,and 3)requiring the less possible operations.For the purpose of choosing the real-time least loaded path,GPLB immediately calculates the integrated load of paths based on the information that receives from the SDN controller.Hence,in this design,the controller sends the load information of each path to the load balancing algorithm periodically and then the load balancing algorithm returns a least loaded path to the controller.In this paper,we use the Mininet emulator and the OpenDaylight controller to evaluate the effectiveness of the GPLB.The simulative study of the GPLB shows that there is a big improvement in performance metrics and the latency and the jitter are minimized.The GPLB also has the maximum throughput in comparison with related works and has performed better in the heavy traffic situation.The results show that our model stands smartly while not increasing further overhead.展开更多
Software.defined networking(SDN) enables third.part companies to participate in the network function innovations. A number of instances for one network function will inevitably co.exist in the network. Although some o...Software.defined networking(SDN) enables third.part companies to participate in the network function innovations. A number of instances for one network function will inevitably co.exist in the network. Although some orchestration architecture has been proposed to chain network functions, rare works are focused on how to optimize this process. In this paper, we propose an optimized model for network function orchestration, function combination model(FCM). Our main contributions are as following. First, network functions are featured with a new abstraction, and are open to external providers. And FCM identifies network functions using unique type, and organizes their instances distributed over the network with the appropriate way. Second, with the specialized demands, we can combine function instances under the global network views, and formulate it into the problem of Boolean linear program(BLP). A simulated annealing algorithm is designed to approach optimal solution for this BLP. Finally, the numerical experiment demonstrates that our model can create outstanding composite schemas efficiently.展开更多
Software-defined network(SDN)is a new form of network architecture that has programmability,ease of use,centralized control,and protocol independence.It has received high attention since its birth.With SDN network arc...Software-defined network(SDN)is a new form of network architecture that has programmability,ease of use,centralized control,and protocol independence.It has received high attention since its birth.With SDN network architecture,network management becomes more efficient,and programmable interfaces make network operations more flexible and can meet the different needs of various users.The mainstream communication protocol of SDN is OpenFlow,which contains aMatch Field in the flow table structure of the protocol,which matches the content of the packet header of the data received by the switch,and completes the corresponding actions according to the matching results,getting rid of the dependence on the protocol to avoid designing a new protocol.In order to effectively optimize the routing forSDN,this paper proposes a novel algorithm based on reinforcement learning.The proposed technique canmaximize numerous objectives to dynamically update the routing strategy,and it has great generality and is not reliant on any specific network state.The control of routing strategy is more complicated than many Q-learning-based algorithms due to the employment of reinforcement learning.The performance of the method is tested by experiments using the OMNe++simulator.The experimental results reveal that our PPO-based SDN routing control method has superior performance and stability than existing algorithms.展开更多
Based on the analysis of data centre(DC) traffic pattern, we introduced a holistic software-defined optical DC solution. Architecture-on-Demand based hybrid optical switched(OPS/OCS) data centre network(DCN) fabric is...Based on the analysis of data centre(DC) traffic pattern, we introduced a holistic software-defined optical DC solution. Architecture-on-Demand based hybrid optical switched(OPS/OCS) data centre network(DCN) fabric is introduced, which is able to realise different inter-and intra-cluster configurations and dynamically support diverse traffic in the DC. The optical DCN is controlled and managed by a software-defined networking(SDN) enabled control plane to achieve high programmability. Moreover, virtual data centre(VDC) composition is developed as an application of such softwaredefined optical DC to create VDC slices for different tenants.展开更多
When applying Software-Defined Networks(SDN) to WANs,the SDN flexibility enables the cross-domain control to achieve a better control scalability.However,the control consistence is required by all the cross-domain ser...When applying Software-Defined Networks(SDN) to WANs,the SDN flexibility enables the cross-domain control to achieve a better control scalability.However,the control consistence is required by all the cross-domain services,to ensure the data plane configured in consensus for different domains.Such consistence process is complicated by potential failure and errors of WANs.In this paper,we propose a consistence layer to actively and passively snapshot the cross-domain control states,to reduce the complexities of service realizations.We implement the layer and evaluate performance in the PlanetLab testbed for the WAN emulation.The testbed conditions are extremely enlarged comparing to the real network.The results show its scalability,reliability and responsiveness in dealing with the control dynamics.In the normalized results,the active and passive snapshots are executed with the mean times of 1.873 s and 105 ms in135 controllers,indicating its readiness to be used in the real network.展开更多
Federated learning(FL)activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging ...Federated learning(FL)activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging processes.However,in large-scale heterogeneous Internet of Things(IoT)cellular networks,massive multi-dimensional model update iterations and resource-constrained computation are challenging aspects to be tackled significantly.This paper introduces the system model of converging softwaredefined networking(SDN)and network functions virtualization(NFV)to enable device/resource abstractions and provide NFV-enabled edge FL(eFL)aggregation servers for advancing automation and controllability.Multi-agent deep Q-networks(MADQNs)target to enforce a self-learning softwarization,optimize resource allocation policies,and advocate computation offloading decisions.With gathered network conditions and resource states,the proposed agent aims to explore various actions for estimating expected longterm rewards in a particular state observation.In exploration phase,optimal actions for joint resource allocation and offloading decisions in different possible states are obtained by maximum Q-value selections.Action-based virtual network functions(VNF)forwarding graph(VNFFG)is orchestrated to map VNFs towards eFL aggregation server with sufficient communication and computation resources in NFV infrastructure(NFVI).The proposed scheme indicates deficient allocation actions,modifies the VNF backup instances,and reallocates the virtual resource for exploitation phase.Deep neural network(DNN)is used as a value function approximator,and epsilongreedy algorithm balances exploration and exploitation.The scheme primarily considers the criticalities of FL model services and congestion states to optimize long-term policy.Simulation results presented the outperformance of the proposed scheme over reference schemes in terms of Quality of Service(QoS)performance metrics,including packet drop ratio,packet drop counts,packet delivery ratio,delay,and throughput.展开更多
基金supported in part by Scientific Research Fund of Zhejiang Provincial Education Department under Grant Y202351110in part by Huzhou Science and Technology Plan Project under Grant 2024YZ23+1 种基金in part by Research Fund of National Key Laboratory of Advanced Communication Networks under Grant SCX23641X004in part by Postgraduate Research and Innovation Project of Huzhou University under Grant 2024KYCX50.
文摘Zero Trust Network(ZTN)enhances network security through strict authentication and access control.However,in the ZTN,optimizing flow control to improve the quality of service is still facing challenges.Software Defined Network(SDN)provides solutions through centralized control and dynamic resource allocation,but the existing scheduling methods based on Deep Reinforcement Learning(DRL)are insufficient in terms of convergence speed and dynamic optimization capability.To solve these problems,this paper proposes DRL-AMIR,which is an efficient flow scheduling method for software defined ZTN.This method constructs a flow scheduling optimization model that comprehensively considers service delay,bandwidth occupation,and path hops.Additionally,it balances the differentiated requirements of delay-critical K-flows,bandwidth-intensive D-flows,and background B-flows through adaptiveweighting.Theproposed framework employs a customized state space comprising node labels,link bandwidth,delaymetrics,and path length.It incorporates an action space derived fromnode weights and a hybrid reward function that integrates both single-step and multi-step excitation mechanisms.Based on these components,a hierarchical architecture is designed,effectively integrating the data plane,control plane,and knowledge plane.In particular,the adaptive expert mechanism is introduced,which triggers the shortest path algorithm in the training process to accelerate convergence,reduce trial and error costs,and maintain stability.Experiments across diverse real-world network topologies demonstrate that DRL-AMIR achieves a 15–20%reduction in K-flow transmission delays,a 10–15%improvement in link bandwidth utilization compared to SPR,QoSR,and DRSIR,and a 30%faster convergence speed via adaptive expert mechanisms.
基金supported by the National Natural Science Foundation of China(61962016)the Ministry of Science and Technology of China(G2022033002L)+1 种基金National Natural Science Foundation of Guangxi(2022JJA170057)Guangxi Education Department’s Project on Improving the Basic Research Ability of Young and Middleaged Teachers in Universities(2023ky0812,Research on Statistical Network Delay Predictions in Large-scale SDNs).
文摘Accurate early classification of elephant flows(elephants)is important for network management and resource optimization.Elephant models,mainly based on the byte count of flows,can always achieve high accuracy,but not in a time-efficient manner.The time efficiency becomes even worse when the flows to be classified are sampled by flow entry timeout over Software-Defined Networks(SDNs)to achieve a better resource efficiency.This paper addresses this situation by combining co-training and Reinforcement Learning(RL)to enable a closed-loop classification approach that divides the entire classification process into episodes,each involving two elephant models.One predicts elephants and is retrained by a selection of flows automatically labeled online by the other.RL is used to formulate a reward function that estimates the values of the possible actions based on the current states of both models and further adjusts the ratio of flows to be labeled in each phase.Extensive evaluation based on real traffic traces shows that the proposed approach can stably predict elephants using the packets received in the first 10% of their lifetime with an accuracy of over 80%,and using only about 10% more control channel bandwidth than the baseline over the evolved SDNs.
基金supported in part by National Key R&D Program of China(Grant No.2022YFC3803700)in part by the National Natural Science Foundation of China(Grant No.92067102)in part by the project of Beijing Laboratory of Advanced Information Networks.
文摘The rise of time-sensitive applications with broad geographical scope drives the development of time-sensitive networking(TSN)from intra-domain to inter-domain to ensure overall end-to-end connectivity requirements in heterogeneous deployments.When multiple TSN networks interconnect over non-TSN networks,all devices in the network need to be syn-chronized by sharing a uniform time reference.How-ever,most non-TSN networks are best-effort.Path delay asymmetry and random noise accumulation can introduce unpredictable time errors during end-to-end time synchronization.These factors can degrade syn-chronization performance.Therefore,cross-domain time synchronization becomes a challenging issue for multiple TSN networks interconnected by non-TSN networks.This paper presents a cross-domain time synchronization scheme that follows the software-defined TSN(SD-TSN)paradigm.It utilizes a com-bined control plane constructed by a coordinate con-troller and a domain controller for centralized control and management of cross-domain time synchroniza-tion.The general operation flow of the cross-domain time synchronization process is designed.The mecha-nism of cross-domain time synchronization is revealed by introducing a synchronization model and an error compensation method.A TSN cross-domain proto-type testbed is constructed for verification.Results show that the scheme can achieve end-to-end high-precision time synchronization with accuracy and sta-bility.
基金supported by the Beijing Natural Science Foundation(L223025,4242003)Qin Xin Talents Cultivation Program of Beijing Information Science&Technology University(QXTCP B202405)。
文摘With the evolution of next-generation communication networks,ensuring robust Core Network(CN)architecture and data security has become paramount.This paper addresses critical vulnerabilities in the architecture of CN and data security by proposing a novel framework based on blockchain technology that is specifically designed for communication networks.Traditional centralized network architectures are vulnerable to Distributed Denial of Service(DDoS)attacks,particularly in roaming scenarios where there is also a risk of private data leakage,which imposes significant operational demands.To address these issues,we introduce the Blockchain-Enhanced Core Network Architecture(BECNA)and the Secure Decentralized Identity Authentication Scheme(SDIDAS).The BECNA utilizes blockchain technology to decentralize data storage,enhancing network security,stability,and reliability by mitigating Single Points of Failure(SPoF).The SDIDAS utilizes Decentralized Identity(DID)technology to secure user identity data and streamline authentication in roaming scenarios,significantly reducing the risk of data breaches during cross-network transmissions.Our framework employs Ethereum,free5GC,Wireshark,and UERANSIM tools to create a robust,tamper-evident system model.A comprehensive security analysis confirms substantial improvements in user privacy and network security.Simulation results indicate that our approach enhances communication CNs security and reliability,while also ensuring data security.
基金supported by the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support(QU-APC-2025).
文摘Distributed denial of service(DDoS)attacks are common network attacks that primarily target Internet of Things(IoT)devices.They are critical for emerging wireless services,especially for applications with limited latency.DDoS attacks pose significant risks to entrepreneurial businesses,preventing legitimate customers from accessing their websites.These attacks require intelligent analytics before processing service requests.Distributed denial of service(DDoS)attacks exploit vulnerabilities in IoT devices by launchingmulti-point distributed attacks.These attacks generate massive traffic that overwhelms the victim’s network,disrupting normal operations.The consequences of distributed denial of service(DDoS)attacks are typically more severe in software-defined networks(SDNs)than in traditional networks.The centralised architecture of these networks can exacerbate existing vulnerabilities,as these weaknesses may not be effectively addressed in this model.The preliminary objective for detecting and mitigating distributed denial of service(DDoS)attacks in software-defined networks(SDN)is to monitor traffic patterns and identify anomalies that indicate distributed denial of service(DDoS)attacks.It implements measures to counter the effects ofDDoS attacks,and ensure network reliability and availability by leveraging the flexibility and programmability of SDN to adaptively respond to threats.The authors present a mechanism that leverages the OpenFlow and sFlow protocols to counter the threats posed by DDoS attacks.The results indicate that the proposed model effectively mitigates the negative effects of DDoS attacks in an SDN environment.
基金fully supported by GUET Excellent Graduate Thesis Program(Grant No.19YJPYBS03)Innovation Project of Guangxi Graduate Education(Grant No.YCBZ2022109)New Technology Research University Cooperation Project of the 34th Research Institute of China Electronics Technology Group Corporation,2021(Grant No.SF2126007)。
文摘In Software-Defined Networks(SDNs),determining how to efficiently achieve Quality of Service(QoS)-aware routing is challenging but critical for significantly improving the performance of a network,where the metrics of QoS can be defined as,for example,average latency,packet loss ratio,and throughput.The SDN controller can use network statistics and a Deep Reinforcement Learning(DRL)method to resolve this challenge.In this paper,we formulate dynamic routing in an SDN as a Markov decision process and propose a DRL algorithm called the Asynchronous Advantage Actor-Critic QoS-aware Routing Optimization Mechanism(AQROM)to determine routing strategies that balance the traffic loads in the network.AQROM can improve the QoS of the network and reduce the training time via dynamic routing strategy updates;that is,the reward function can be dynamically and promptly altered based on the optimization objective regardless of the network topology and traffic pattern.AQROM can be considered as one-step optimization and a black-box routing mechanism in high-dimensional input and output sets for both discrete and continuous states,and actions with respect to the operations in the SDN.Extensive simulations were conducted using OMNeT++and the results demonstrated that AQROM 1)achieved much faster and stable convergence than the Deep Deterministic Policy Gradient(DDPG)and Advantage Actor-Critic(A2C),2)incurred a lower packet loss ratio and latency than Open Shortest Path First(OSPF),DDPG,and A2C,and 3)resulted in higher and more stable throughput than OSPF,DDPG,and A2C.
文摘Internet Exchange Point(IXP)is a system that increases network bandwidth performance.Internet exchange points facilitate interconnection among network providers,including Internet Service Providers(ISPs)andContent Delivery Providers(CDNs).To improve service management,Internet exchange point providers have adopted the Software Defined Network(SDN)paradigm.This implementation is known as a Software-Defined Exchange Point(SDX).It improves network providers’operations and management.However,performance issues still exist,particularly with multi-hop topologies.These issues include switch memory costs,packet processing latency,and link failure recovery delays.The paper proposes Enhanced Link Failure Rerouting(ELFR),an improved mechanism for rerouting link failures in software-defined exchange point networks.The proposed mechanism aims to minimize packet processing time for fast link failure recovery and enhance path calculation efficiency while reducing switch storage overhead by exploiting the Programming Protocol-independent Packet Processors(P4)features.The paper presents the proposed mechanisms’efficiency by utilizing advanced algorithms and demonstrating improved performance in packet processing speed,path calculation effectiveness,and switch storage management compared to current mechanisms.The proposed mechanism shows significant improvements,leading to a 37.5%decrease in Recovery Time(RT)and a 33.33%decrease in both Calculation Time(CT)and Computational Overhead(CO)when compared to current mechanisms.The study highlights the effectiveness and resource efficiency of the proposed mechanism in effectively resolving crucial issues inmulti-hop software-defined exchange point networks.
文摘Core power is a key parameter of nuclear reactor.Traditionally,the proportional-integralderivative(PID)controllers are used to control the core power.Fractional-order PID(FOPID)controller represents the cutting edge in core power control research.In comparing with the integer-order models,fractional-order models describe the variation of core power more accurately,thus provide a comprehensive and realistic depiction for the power and state changes of reactor core.However,current fractional-order controllers cannot adjust their parameters dynamically to response the environmental changes or demands.In this paper,we aim at the stable control and dynamic responsiveness of core power.Based on the strong selflearning ability of artificial neural network(ANN),we propose a composite controller combining the ANN and FOPID controller.The FOPID controller is firstly designed and a back propagation neural network(BPNN)is then utilized to optimize the parameters of FOPID.It is shown by simulation that the composite controller enables the real-time parameter tuning via ANN and retains the advantage of FOPID controller.
基金supported by the National Natural Science Foundation of China(62101300,62341130)the Youth Fund Program of the Beijing National Research Center for Information Science and Technology under Grant BNR2021RC01012the Open Research Fund Program of the Beijing National Research Center for Information Science and Technology under Grant BNR2021KF02001.
文摘Software-defined satellite networks(SDSNs)play an essential role in future networks.Due to the diverse service scenarios,SDSN faces the demand of packet processing for heterogeneous protocols.Existing packet switching typically works on one single protocol.For protocol-heterogeneous users,existing packet switch architectures have to construct multiple protocol-specific switching instances,resulting in severe resource waste.In this article,we propose the heterogeneous protocol-independent packet switch architecture(HISA).HISA employs a fast parsing structure to achieve efficient heterogeneous packet parsing and a novel match-action pipeline to achieve shared packet processing among heterogeneous users.HISA can also support the online configuration of switching behaviors.Use cases illustrate the effectiveness of applying HISA in SDSN.Numerical results show that compared to existing packet switching,HISA can significantly improve the resource utilization of SDSN.
基金supported by the National Natural Science Foundation of China(NSFC,No.52271138)the Key Research and Development Projects of Shaanxi Province(Nos.2023-YBGY-433 and 2024GX-YBXM-356)+1 种基金Xi'an Talent Program Young Innovative Talents(No.XAYC 2023030)the Science and Technology Development Plan Project of Shaanxi Province(No.S2024-JC-QN-2642).
文摘Synergistically and simultaneously enhancing strength and ductility has been a major challenge for the development and applications of titanium matrix composites.Herein,a new design methodology for Ti_(2)Cu/Ti_(6)Al4V composites with superior strength and ductility is reported.
基金supported by the National Natural Science Foundation of China(No.12305344)the 2023 Anhui university research project of China(No.2023AH052179).
文摘The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to cases wherein a single region changes at a specified location of the core.However,when the neutron field changes are complex,the accurate identification of the individual changed regions becomes challenging,which seriously affects the accuracy and stability of the neutron field recon-struction.Therefore,this study proposed a dual-task hybrid network architecture(DTHNet)for off situ reconstruction of the core neutron field,which trained the outermost assembly reconstruction task and the core reconstruction task jointly such that the former could assist the latter in the reconstruction of the core neutron field under core complex changes.Furthermore,to exploit the characteristics of the ex-core detection signals,this study designed a global-local feature upsampling module that efficiently distributed the ex-core detection signals to each reconstruction unit to improve the accuracy and stability of reconstruction.Reconstruction experiments were performed on the simulation datasets of the CLEAR-I reactor to verify the accuracy and stability of the proposed method.The results showed that when the location uncertainty of a single region did not exceed nine and the number of multiple changed regions did not exceed five.Further,the reconstructed ARD was within 2%,RD_(max)was maintained within 17.5%,and the number of RD≥10%was maintained within 10.Furthermore,when the noise interference of the ex-core detection signals was within±2%,although the average number of RD≥10%increased to 16,the average ARD was still within in 2%,and the average RD_(max)was within 22%.Collectively,these results show that,theoretically,the DTHNet can accurately and stably reconstruct most of the neutron field under certain complex core changes.
基金This work was supported by the National Key Research Plan(2021YFB2900602).
文摘With the rapid development of low-orbit satellite com-munication networks both domestically and internationally,space-terrestrial integrated networks will become the future development trend.For space and terrestrial networks with limi-ted resources,the utilization efficiency of the entire space-terres-trial integrated networks resources can be affected by the core network indirectly.In order to improve the response efficiency of core networks expansion construction,early warning of the core network elements capacity is necessary.Based on the inte-grated architecture of space and terrestrial network,multidimen-sional factors are considered in this paper,including the number of terminals,login users,and the rules of users’migration during holidays.Using artifical intelligence(AI)technologies,the regis-tered users of the access and mobility management function(AMF),authorization users of the unified data management(UDM),protocol data unit(PDU)sessions of session manage-ment function(SMF)are predicted in combination with the num-ber of login users,the number of terminals.Therefore,the core network elements capacity can be predicted in advance.The proposed method is proven to be effective based on the data from real network.
文摘Software-Defined Networking(SDN)improves network management by separating its control logic from the underlying hardware and integrating it into a logically centralized control unit,termed the SDN controller.SDN adaptation is essential for wireless networks because it offers enhanced and data-intensive services.The initial intent of the SDN design was to have a physically centralized controller.However,network experts have suggested logically centralized and physically distributed designs for SDN controllers,owing to issues such as a single point of failure and scalability.This study addressed the security,scalability,reliability,and consistency issues associated with the design of distributed SDN controllers.Moreover,the security issues of an enterprise related to multiple physically distributed controllers in a software-defined wireless local area network(SD-WLAN)were emphasized,and optimal solutions were suggested.
基金supported in part by the National High Technology Research and Development Program(863 Program)of China under Grant No.2011AA01A101the National High Technology Research and Development Program(863 Program)of China under Grant No.2013AA01330the National High Technology Research and Development Program(863 Program)of China under Grant No.2013AA013303
文摘By decoupling control plane and data plane,Software-Defined Networking(SDN) approach simplifies network management and speeds up network innovations.These benefits have led not only to prototypes,but also real SDN deployments.For wide-area SDN deployments,multiple controllers are often required,and the placement of these controllers becomes a particularly important task in the SDN context.This paper studies the problem of placing controllers in SDNs,so as to maximize the reliability of SDN control networks.We present a novel metric,called expected percentage of control path loss,to characterize the reliability of SDN control networks.We formulate the reliability-aware control placement problem,prove its NP-hardness,and examine several placement algorithms that can solve this problem.Through extensive simulations using real topologies,we show how the number of controllers and their placement influence the reliability of SDN control networks.Besides,we also found that,through strategic controller placement,the reliability of SDN control networks can be significantly improved without introducing unacceptable switch-to-controller latencies.
文摘As a new networking paradigm,Software-Defined Networking(SDN)enables us to cope with the limitations of traditional networks.SDN uses a controller that has a global view of the network and switch devices which act as packet forwarding hardware,known as“OpenFlow switches”.Since load balancing service is essential to distribute workload across servers in data centers,we propose an effective load balancing scheme in SDN,using a genetic programming approach,called Genetic Programming based Load Balancing(GPLB).We formulate the problem to find a path:1)with the best bottleneck switch which has the lowest capacity within bottleneck switches of each path,2)with the shortest path,and 3)requiring the less possible operations.For the purpose of choosing the real-time least loaded path,GPLB immediately calculates the integrated load of paths based on the information that receives from the SDN controller.Hence,in this design,the controller sends the load information of each path to the load balancing algorithm periodically and then the load balancing algorithm returns a least loaded path to the controller.In this paper,we use the Mininet emulator and the OpenDaylight controller to evaluate the effectiveness of the GPLB.The simulative study of the GPLB shows that there is a big improvement in performance metrics and the latency and the jitter are minimized.The GPLB also has the maximum throughput in comparison with related works and has performed better in the heavy traffic situation.The results show that our model stands smartly while not increasing further overhead.
基金supported by the China Postdoctoral Fund Project (No.44603)the National Natural Science Foundation of China (No.61309020)+1 种基金the National key Research and Development Program of China (No.2016YFB0800100, 2016YFB0800101)the National Natural Science Fund for Creative Research Groups Project(No.61521003)
文摘Software.defined networking(SDN) enables third.part companies to participate in the network function innovations. A number of instances for one network function will inevitably co.exist in the network. Although some orchestration architecture has been proposed to chain network functions, rare works are focused on how to optimize this process. In this paper, we propose an optimized model for network function orchestration, function combination model(FCM). Our main contributions are as following. First, network functions are featured with a new abstraction, and are open to external providers. And FCM identifies network functions using unique type, and organizes their instances distributed over the network with the appropriate way. Second, with the specialized demands, we can combine function instances under the global network views, and formulate it into the problem of Boolean linear program(BLP). A simulated annealing algorithm is designed to approach optimal solution for this BLP. Finally, the numerical experiment demonstrates that our model can create outstanding composite schemas efficiently.
基金The researchers would like to thank the Deanship of Scientific Research,Qassim University for funding the publication of this project.
文摘Software-defined network(SDN)is a new form of network architecture that has programmability,ease of use,centralized control,and protocol independence.It has received high attention since its birth.With SDN network architecture,network management becomes more efficient,and programmable interfaces make network operations more flexible and can meet the different needs of various users.The mainstream communication protocol of SDN is OpenFlow,which contains aMatch Field in the flow table structure of the protocol,which matches the content of the packet header of the data received by the switch,and completes the corresponding actions according to the matching results,getting rid of the dependence on the protocol to avoid designing a new protocol.In order to effectively optimize the routing forSDN,this paper proposes a novel algorithm based on reinforcement learning.The proposed technique canmaximize numerous objectives to dynamically update the routing strategy,and it has great generality and is not reliant on any specific network state.The control of routing strategy is more complicated than many Q-learning-based algorithms due to the employment of reinforcement learning.The performance of the method is tested by experiments using the OMNe++simulator.The experimental results reveal that our PPO-based SDN routing control method has superior performance and stability than existing algorithms.
基金performed in the Projects " LIGHTNESS : Low latency and high throughput dynamic network infrastructures for high performance datacentre interconnects" (No. 318606) "COSIGN: Combining Optics and SDN In next Generation data centre Networks" (No. 619572) supported by European Commission FP7
文摘Based on the analysis of data centre(DC) traffic pattern, we introduced a holistic software-defined optical DC solution. Architecture-on-Demand based hybrid optical switched(OPS/OCS) data centre network(DCN) fabric is introduced, which is able to realise different inter-and intra-cluster configurations and dynamically support diverse traffic in the DC. The optical DCN is controlled and managed by a software-defined networking(SDN) enabled control plane to achieve high programmability. Moreover, virtual data centre(VDC) composition is developed as an application of such softwaredefined optical DC to create VDC slices for different tenants.
基金supported by the National Basic Research Program of China (2012CB315903)the Program for Key Science and Technology Innovation Team of Zhejiang Province(2011R50010,2013TD20)+3 种基金the National High Technology Research Program of China(2015AA016103)the National Natural Science Foundation of China(61379118)the Research Fund of ZTE CorporationJiaxing Science and Technology Project (No.2014AY21021)
文摘When applying Software-Defined Networks(SDN) to WANs,the SDN flexibility enables the cross-domain control to achieve a better control scalability.However,the control consistence is required by all the cross-domain services,to ensure the data plane configured in consensus for different domains.Such consistence process is complicated by potential failure and errors of WANs.In this paper,we propose a consistence layer to actively and passively snapshot the cross-domain control states,to reduce the complexities of service realizations.We implement the layer and evaluate performance in the PlanetLab testbed for the WAN emulation.The testbed conditions are extremely enlarged comparing to the real network.The results show its scalability,reliability and responsiveness in dealing with the control dynamics.In the normalized results,the active and passive snapshots are executed with the mean times of 1.873 s and 105 ms in135 controllers,indicating its readiness to be used in the real network.
基金This work was funded by BK21 FOUR(Fostering Outstanding Universities for Research)(No.5199990914048)this research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(NRF-2020R1I1A3066543)In addition,this work was supported by the Soonchunhyang University Research Fund.
文摘Federated learning(FL)activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging processes.However,in large-scale heterogeneous Internet of Things(IoT)cellular networks,massive multi-dimensional model update iterations and resource-constrained computation are challenging aspects to be tackled significantly.This paper introduces the system model of converging softwaredefined networking(SDN)and network functions virtualization(NFV)to enable device/resource abstractions and provide NFV-enabled edge FL(eFL)aggregation servers for advancing automation and controllability.Multi-agent deep Q-networks(MADQNs)target to enforce a self-learning softwarization,optimize resource allocation policies,and advocate computation offloading decisions.With gathered network conditions and resource states,the proposed agent aims to explore various actions for estimating expected longterm rewards in a particular state observation.In exploration phase,optimal actions for joint resource allocation and offloading decisions in different possible states are obtained by maximum Q-value selections.Action-based virtual network functions(VNF)forwarding graph(VNFFG)is orchestrated to map VNFs towards eFL aggregation server with sufficient communication and computation resources in NFV infrastructure(NFVI).The proposed scheme indicates deficient allocation actions,modifies the VNF backup instances,and reallocates the virtual resource for exploitation phase.Deep neural network(DNN)is used as a value function approximator,and epsilongreedy algorithm balances exploration and exploitation.The scheme primarily considers the criticalities of FL model services and congestion states to optimize long-term policy.Simulation results presented the outperformance of the proposed scheme over reference schemes in terms of Quality of Service(QoS)performance metrics,including packet drop ratio,packet drop counts,packet delivery ratio,delay,and throughput.
