Subjects: Computer Science >> Computer Application Technology submitted time 2022-11-02 Cooperative journals: 《桂林电子科技大学学报》
Abstract： The data distribution algorithm in Ceph distributed system only takes the capacity as the standard for selecting
storage nodes, and does not consider the network state and node load of storage nodes. In the replica mode, when a storage
node in the three replicas needs to be repaired, too high node load or network load will lead to a large node repair delay. To
solve this problem, a fault-tolerant node selection algorithm based on Ceph (FTNSC) is proposed. Firstly, the software defined
network technology is used to obtain the real-time network state and node load information as the data support of the
node selection method; Then, a multi-attribute decision-making mathematical model considering the node load information is
established to determine the location of the primary storage node; Finally, the artificial bee colony algorithm is used to obtain
the optimal secondary storage node according to the network state and node performance with the primary storage node.
Experimental results show that compared with the existing methods, the proposed method can improve the performance of
data storage nodes and reduce the data repair delay when nodes fail.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-05-18 Cooperative journals: 《计算机应用研究》
Abstract： As Software Defined Network (SDN) is increasingly widely used in various scenarios, a new challenge for SDN to support dynamic requirements of various applications begin to emerge. Digital Twin (DT) can enhance the capabilities of SDN in aspects of real-time analysis, deduction, and network control, and consequently satisfy the dynamic requirements of various applications. Whereas, current DT constructing schemes for SDN usually suffer from the challenges of strict delay constraint, heavy computing overhead, and low cooperating efficiency. To address the above issue, this paper proposes a novel Variable Granularity-Digital Twin (VGDT) according to the application requirement and available computing resource. Based on the distribution characteristic of the computing resource in the network, VGDT builds a cooperatively optimizing model to ensure the delay and effectiveness of the DT for SDN. Then, this paper proposes a hybrid coding genetic algorithm to solve this model, which can achieve the best granularity and the DT placement policy. The simulation results show the performance of VGDT. Compared with current DT, VGDT has higher integrity and validity of digital twin model under limited computing resource.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-05-10 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the data plane configuration problem caused by overlapping forwarding paths of different applications in SDN network, this paper proposes a Boolean function-based network reachability verification method. First, it abstracts the network topology into port topology and calculates the port adjacency matrix; then generates the path space of the network and the forwarding function of each port, and calculates the path function of each path; finally, it judges the accessibility of path from the satisfiability of path function. Through simulation experiments, this paper studies the influence of factors such as network topology and flow rule scale on the algorithm verification efficiency, and the performance of the proposed method is compared with APV and DASDA. Experimental results show that the proposed method can effectively detect flow rule configuration problems in SDN networks. As the number of loops in the network increases and the size of the flow rules grows, the time overhead required to verify the network gradually increases. Among them, the network topology has a great influence on the path generation time, and the generation time of the forwarding function is mainly affected by the scale of the flow rule. Compared with APV and DASDA, the time to verify is shortened by an average of about 53.76% and 27.74%, respectively.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-05-10 Cooperative journals: 《计算机应用研究》
Abstract： This paper proposed the Non-cooperative Game Theory-based of load-reduction Master Controller Reselection model in Software Defined Networking to address the multi-controller load imbalance problem, called GTMCR. To begin with, the discriminating overload controller utilized the Overload Dynamic Thresholds approach (ODT) . Next, the migration of switches followed a Priority Decision Switching Strategy (PDSS) . Finally, the constructed optimization model took the load balancing degree of controller clusters, average total delay and switch migration cost as utility functions. To prevent the global optimal solution from slipping into the local optimum, the solution value of optimal deployment used the Genetic Algorithm for Improved Multi-objective Optimization (GAIMO) with the addition of a similarity operator to boost the algorithm's convergence speed and the accuracy of the global optimal solution. The experimental results show that this mechanism effectively balances the control plane load while achieving the goal of optimizing network performance.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-04-07 Cooperative journals: 《计算机应用研究》
Abstract： To solve the inconsistency of flow rules between the control plane and data plane caused by SDN data plane software and hardware faults, configuration faults, etc. , this paper proposed a P4-based Consistency Verification mechanism for SDN control-data plane (P4CV) . P4CV firstly sent probes with a specific structure to the data plane, and then each P4 switch inserted its runtime information of flow rules in the data plane into the probes. Finally, P4CV adopted the consistency-verification algorithm, based on symbolic execution, to compare the configuration from the control plane and telemetry information from the data plane. The simulation results show that the single path verification time of P4CV is not affected by the network topology and is only linearly related to the number of nodes on the path. In a multipath forwarding scenario, with the same network scale and traffic rules configured, P4CV generates only 0.06‰ of bandwidth overhead and reduces the verification time by 42% compared with the existing scheme.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-04-07 Cooperative journals: 《计算机应用研究》
Abstract： Due to the increasing demand for rich multimedia services, Internet of vehicles needs to provide massive equipment connections to meet the needs of high spectrum efficiency and low delay. Software Defined Network (SDN) , caching and Non-Orthogonal Multiple Access (NOMA) technologies are considered as potential solutions to effectively solve these key challenges. Therefore, this paper proposed a cache aided NOMA power allocation scheme for software defined vehicular network. Firstly, according to the characteristics of vehicles always moving at high speed in Internet of vehicles, the scheme proposed a new cluster head selection algorithm. The arriving road traffic will be predicted with the help of SDN to realize adaptive vehicle clustering. Secondly, the scheme introduced a cache aided NOMA strategy. Each vehicle uses NOMA principle to cache and request files in the file cache stage. Thirdly, for the two cluster head vehicle communication scenarios under the condition of double Nakagami-m fading, the scheme proposed an optimal power allocation strategy. The optimization problem is formulated as finding the optimal power curve of each vehicle, so as to maximize the probability of successfully decoding the target file on each vehicle. Finally, numerical simulation and theoretical analysis show that the performance of the proposed cache aided NOMA power allocation scheme is significantly better than the conventional NOMA and cache aided Orthogonal Multiple Access (OMA) .
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-05-10 Cooperative journals: 《计算机应用研究》
Abstract： Mobile edge computing technology combines IT service environments and cloud computing technologies at the edge of the network to improve the computing and storage capabilities of edge networks while reducing network operations and service delivery delays. Vehicular networks integrating MEC, could meet the strict requirements of vehicle service delay and communication reliability, as well as improve the quality of service for vehicle users. This paper studied and analyzed MEC applications in vehicular networks. Firstly, it provided a brief on the basic concept and architecture of MEC, and its typical application scenarios. Thereafter, it described a comprehensive survey of relevant research in the area of MEC-based vehicular networks along with a focus on the current SDN-related works on MEC-based vehicular networks, as well as several use cases. Finally, this paper discussed the main problems and challenges to deploy MEC in vehicular networks; and analyzed the future research directions on these areas.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-28 Cooperative journals: 《计算机应用研究》
Abstract： To optimize communication efficiency and reduce the data transmission of shuffle in large-scale clusters running for MapReduce jobs, a distributed collaborative data mapping model was built based on the strategy, which is designed by replacing the communication locality by storing locality. Then the local features of jobs are extracted by random sampling and machine learning method in order to realize the effective deployment of Map tasks. Finally, the good communication links are selected based on the software define network technology due to with the global flexible control capabilities. And the Map Tasks are scheduled to such nodes. Experimental results show that it has better optimization effect on shuffle-intensive jobs. The communication delay is reduced by 4.3% to 5.8%. This solution can reduce Shuffle traffic and data migration delay. It is suitable for various scheduling strategies and network topologies.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-03 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the problems of log detection accuracy and long delay of DDoS(Distributed Denial-of-Service) attacks in the software definition networks, This paper proposed a real time DDoS security system of software definition networks based on kernel functions. Firstly, it abstracted the packet header fields of software definition networks periodly, and formed the abstracted information as matrices; then, it adopted the Mahalanobis distance to analyze the significant change of continuous feature vectors, and it designed two kernel functions to evaluate the behavior flows of attacks; lastly, the attackers are identified by the spectral clustering technique and the covariance statistical information. Experimental results based on the real software definition networks show that the proposed security system realizes a good detection accuracy, and performs a reasonable processing time.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the problem of performance bottleneck and overload in upper layer caused by software-defined network flooding attacks, this paper proposed a software-defined network flooding attack detection method based on distributed SOM and k-means clustering. The DSOM controller at the application layer first sent the existing data set to the switch which had the DSOM extension package integrated and it trained the DSOM mapping on each switch. Then, it consolidated the DSOM mapping within a predetermined time. Finally, the DSOM controller sent the merged DSOM mapping to all OpenFlow switches and used k-means clustering to complete the final classification. Experimental results show that the DSOM scheme can effectively detect abnormal traffic and solve bottleneck problems, which has certain advantages over traditional methods. In addition, the proposed method improves the response speed of the system to attack traffic and at the same time it brings less overhead to the network system.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》
Abstract： The traditional methods may cause network congestion and load imbalance when scheduling the elephant flows in data center networks. To deal with these isuses, this paper proposed scheme ACO-SDN, which is based on ACO (ant colony) algorithm in SDN(Software Defined Network) data center networks. It built an ILP（Integral Linear Programing）model according to the flow scheduling problem, with the object of minimize the maximum link utilization. Then, it employed ant colony algorithm to solve the ILP model through redefining its parameters and operations. The optimal route was obtained for of rerouting elephant flows. The experimental results show that, in comparisons with ECMP(Equal-Cost multi-path Routing) and GFF (Global First Fit) algorithms, ACO-SDN algorithm lowers down the maximum link utilization rate, and effectively improves the network bisection bandwidth of networks.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-09-12 Cooperative journals: 《计算机应用研究》
Abstract： With the rapid growth of traffic data, the traditional static network service model is increasingly unable to meet the needs of the applications. In traditional network architecture, the relationship between service and dedicated hardware devices is tightly coupled, which results in the drawbacks of network resources cannot share and new network business is difficult to integrate. As the network continues to expand, traditional management and deployment requires more cost to deploy new services. With the rising of Network Virtualization and the development of Software Defined Network, the concept of service function chain has come into being. A service function chain is composed of one or more virtual network functions to provide a complete end-to-end service for the network. The service function chain aims to reduce the cost of network construction and operation and improve the utilization of network resources and improve the speed of network and service deployment. In this paper, the current service function chain system research and its application in industry are elaborated The development and application of service function chain are summarized. This paper will put forward a heuristic greedy algorithm with two different heuristic values. And comparing the exhaustive method in the time complexity and results of delay optimization. In the result, we can figure out that the heuristic greedy algorithm is more suitable for industrial network. Finally, this paper will discuss the modeling and drawback of service function chain present in present.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-06-19 Cooperative journals: 《计算机应用研究》
Abstract： To safeguard the efficient implementation of airborne communications missions, this paper developed a coding aware opportunistic routing scheme which had advantages of both SDN and network coding, aiming at the insufficient of timeliness, reliability and overhead in the interaction of routing information for the airborne backbone networks. Following the basic idea of coding aware opportunistic routing, this routing scheme structured a forwarding consumption function combining the distance of nodes and the coding gains to assign priorities of candidate nodes, thus it could improve the network transmission efficiency. Besides, this routing scheme designed the feedback mechanism of the control message and the structure of flow table, thus it could reduce the control overhead. The simulation results show that this routing scheme can adapt to airborne communication, in addition, it can reduce the transmission delay and routing overhead while it can greatly improve the network throughput and transmission rate.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-06-19 Cooperative journals: 《计算机应用研究》
Abstract： For the software-defined networking(SDN) environment, the existing service function chaining(SFC) deployment method failed to fully consider the resource utilization of the entire network, and this paper proposed a service chaining optimal deployment mechanism based on the efficient heuristic algorithm. Firstly, this paper gave the overall structure of the service chaining deployment, and introduced an integer linear programming(ILP) model. Secondly, this paper proposed an efficient heuristic algorithm. That algorithm run in "first sort after greed" manner and effectively used network resources and balanced load, under the constraints of resource and delay. Finally, the obtained simulation results show that our proposed algorithm reduces the load balancing and time complexity while improving the request acceptance rate, compared to other deployment algorithms.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-06-19 Cooperative journals: 《计算机应用研究》
Abstract： The software defined network (SDN) realizes the flexible control of the network through the controller, so the placement of the controller is critical to the overall performance of the network. This paper proposed an improved improved binary particle swarm optimization (IBPSO) algorithm to solve the controller placement problem. IBPSO algorithm determines the current value of particles based on both the global optimal and the individual optimal, thus weakening the influence of particle current value on the next iteration, and accelerating the convergence, which leaded to a better final result. The simulation results show that compared with the BPSO algorithm, the controller placement scheme obtained by this algorithm can significantly reduce the number of controllers while realizing the load balancing of the controller.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-20 Cooperative journals: 《计算机应用研究》
Abstract： In order to solve the problems of poor load balancing caused by dynamic scheduling in data center networks(DCN) , this paper proposed a dynamic load balancing algorithm based on flow scheduling selection(DLBFSS) . Firstly, DLBFSS calculates the equal-cost shortest path for each large flow on the congested link and removes the path with insufficient bandwidth. Then, the available throughput of each remaining path for large flows was calculated, and the path with maximum available throughput was selected as the optimal scheduling path. Finally, the congestion probability of each large flow was defined by considering the flow bandwidth and the load of the optimal path, and the congestion probability was used for large flow scheduling selection. The experimental results show that DLBFSS can reduces the network delay, improves the flow bandwidth utilization and ensures load balancing compared with ECMP(equal-cost multi-path) and typical large flow scheduling algorithms.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-18 Cooperative journals: 《计算机应用研究》
Abstract： Software defined network (SDN) is a novel network architecture separating control plane and forwarding plane. SDN has been favored by the industry because of its flexibility and controllability. However, SDN usually employs the best paths to forward packets, which is difficult to deal with the node or link failures in the network. In order to improve the availability of SDN network, this paper proposed an intra-domain routing protection scheme based on SDN (RPBSDN) . The scheme could calculate multiple backup next hops for each source-destination, and guaranteed loop-freeness of the induced forwarding path by the underlying partial order of the nodes. The experimental results show that the scheme not only has small computational complexity, but also greatly improve the availability of the network.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-18 Cooperative journals: 《计算机应用研究》
Abstract： The virtual network function in the security service chain decouples the traditional network security functions from the hardware devices, making the deployment of service functions more dynamic and extensible. However, the rational allocation of the VNF to the node and the efficient scheduling of the VNF on the node still need to be solved urgently. To this end, this paper presented a solution using optimization algorithm based on the software defined network and network function virtualization environment. First, this paper made an example of resource allocation and scheduling problem and formalizes the objective. Then, this paper proposed a resource allocation scheme based on greedy algorithm and a resource scheduling scheme based on hybrid bee colony algorithm to solve the problem coordinately. Finally, the simulation experiment is designed to verify the time complexity and the improvement of total resource cost and total service income of the proposed algorithm. Meanwhile, it compared the hybrid bee colony algorithm with the traditional bee colony algorithm, indicating that the former has better convergence rate.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-18 Cooperative journals: 《计算机应用研究》
Abstract： Due to the complex structure of space-ground integration network, it has characteristics of heterogeneous, dynamic, intermittent connectivity and high exposure, it is necessary to study the special access authentication architecture and method in order to ensure security. The software defined network adopts the idea of separating control surface from data surface, so this paper proposed a new access authentication architecture which combined software defined network and space-ground integration network to realize flexibility. It consisted of detailed description of the authentication architecture and process, and it could realize security protection and resources optimization control. Then according to the characteristics of the architecture, this paper put forward 7 attributes of influencing access point decision, and presented the calculating formula of each attribute. In addition, an access point decision algorithm was proposed based on Analytic Hierarchy Process and Technique for Order Preference by Similarity to an Ideal Solution. Simulation experiments show that the algorithm can select the best access point and it can achieve reasonable utilization of resources.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-18 Cooperative journals: 《计算机应用研究》
Abstract： Software-Defined Networking separates the control layer and the data layer. Data forwarding is unified management by the control layer in SDN. However, equipment integrity authentication mechanism is not consummate between the control layer and the data layer. If the falsified equipment tries to connect the network, the whole network will face serious security problems. For ensuring that the connection was established after proving the equipment credible and integrated and that network is available, this paper proposed a project of trusted connection based on SDN. Combing the trusted network remote device authentication technology and using the trusted platform module as trusted support, the project added integrity certification to linking process of data forwarding devices and controllers. According to the爀xperiment, the project is suitable for actual network environment.
Hits
Hits
Downloads
Comment
YES