417 results about "Software-defined networking" patented technology

The invention provides a private domain live broadcast bandwidth resource allocation and routing method and system based on reinforcement learning, and relates to the technical field of computer networks, and the method comprises the steps: collecting real-time data such as the number of users, geographical distribution, terminal types, content types, network delay, packet loss rate, bandwidth utilization rate and the like in a live broadcast room, and inputting the real-time data into a pre-trained reinforcement learning model; the model is based on a state space, features are extracted by using a deep neural network, bandwidth resource constraints are combined, and a bandwidth allocation and routing strategy is generated by adopting a strategy gradient algorithm; and according to the strategy, the software defined network controller adjusts bandwidth allocation parameters and routing table configuration in real time to realize differentiated bandwidth allocation and path optimization, establishes nearby access edge nodes based on user geographical distribution, and dynamically adjusts the path during congestion.

The invention discloses a network security active defense method and system for detecting abnormal network behaviors. The method comprises the following steps: S1, constructing a virtualized isolation network environment through a software defined network technology; s2, deploying intelligent dynamic camouflage nodes in the virtualized isolation environment; s3, acquiring a disguised node attack behavior, and identifying a network abnormal behavior through a deep learning technology; s4, extracting network abnormal behavior features, and identifying potential threats through a deep learning technology; s5, a defense mechanism is automatically triggered, a honeynet is started, and abnormal behaviors and potential threats are isolated; and S6, tracing an attack path, and carrying out source positioning. The network security active defense system comprises a network construction module, a deployment module, an identification module, a honeynet, an isolation module and a tracing module. The disguised nodes are deployed through the deployment module to detect abnormal network behaviors, active defense of network security is realized through the honeynet, the isolation module and the tracing module, and the network security is improved.

The embodiment of the invention provides a security authentication method, device and system for a test platform, and a storage medium, and relates to the technical field of network security. The method comprises the following steps: performing fingerprint acquisition on virtual and real equipment to generate a unique identifier, dynamically slicing based on a software defined network to form an isolated test environment, and injecting a zero-trust access strategy associated with the fingerprint; and based on the zero-trust access policy and the device fingerprint, allocating a minimum permission through an attribute-based access control model, continuously evaluating device behaviors to calculate a dynamic trust score, and adaptively updating the permission according to the trust score. By constructing a full-process security certification system and through multi-dimensional mechanism cooperation, dynamic risk perception and timely strategy adjustment, fine-grained control of virtual and real equipment access in an industrial control scene is realized, the dynamic adaptability and risk resistance of a test platform in a complex network environment are improved, and the test efficiency is improved. Equipment access safety, authority distribution minimization and behavior monitoring continuity are ensured, and the safety risk of the industrial control system is reduced.

The invention relates to the technical field of power distribution station supervision, in particular to an intelligent auxiliary and artificial intelligence visual gateway control method and system for a station building, which monitors network state parameters in real time, calculates a network quality score and dynamically selects an optimal transmission path based on a reinforcement learning algorithm. Comprising a high bandwidth mode, a low delay mode and a disaster recovery backup mode, stage processing and dynamic compression are performed on transmission data according to data types and network quality scores, link switching and a local caching mechanism are automatically triggered when a network is abnormal, and finally, multi-gateway load balancing and visual monitoring are realized through a software defined network architecture. The problem of transmission delay or interruption caused by the fact that a static data transmission framework cannot adapt to network state changes in the prior art is effectively solved, and the reliability and the real-time performance of data transmission are remarkably improved through dynamic path optimization, intelligent hierarchical transmission and a fault self-healing mechanism.

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, perform certain acts. The acts can include generating a digital twin network simulation of a physical computer network controlled through a software-defined-network (SDN) control system. The acts also can include training a routing agent model on the digital twin network simulation using a reinforcement-learning model on traffic that flows through nodes of the digital twin network simulation. The routing agent model includes a machine-learning model. The acts additionally can include deploying the routing agent model, as trained, from the digital twin network simulation to the SDN control system of the physical computer network. Other embodiments are described.

The invention discloses a road roller construction quality real-time monitoring system based on digital twinning, and relates to the technical field of road roller construction intelligent monitoring, and the road roller construction quality real-time monitoring system comprises a data acquisition module which uses a multi-modal fusion sensor network and edge calculation to comprehensively acquire and preprocess data; the digital twinborn model building module is used for modeling by combining physical-data dual drive with geological characteristics; the data transmission module is used for ensuring efficient and safe transmission by using a software defined network and a block chain; the real-time monitoring and analysis module is used for carrying out multi-scale space-time correlation analysis and generating virtual data; and the decision support module fuses deep reinforcement learning and a knowledge graph, supports man-machine cooperation decision, and provides intelligent suggestions for construction. According to the invention, the advantages are obvious, multi-modal acquisition and edge calculation ensure accurate and real-time data, a dual-drive model truly simulates construction, an advanced transmission technology ensures data safety, multi-scale analysis comprehensively evaluates quality, full-process coverage improves construction quality and management intelligence, and cost reduction and efficiency improvement are realized.

The invention discloses a hospital internal network security isolation method based on an all-optical network architecture. The method comprises the following steps: S1, dividing a hospital internal network into a plurality of virtual optical slices by using an all-optical network slicing technology; s2, performing time domain isolation by using an optical time domain multiplexing technology, and transmitting data on different optical wavelengths by using a wavelength selective switching technology; s3, monitoring and managing bandwidth allocation through a software defined network control platform; s4, traffic prediction and resource optimization are carried out based on a decision tree integration algorithm; s5, detecting potential anomalies and security threats by using the graph neural network; s6, abnormal behaviors are detected through an isolation forest algorithm, and abnormal traffic is marked and isolated; s7, recording a network traffic log through a block chain technology; and S8, when a network fault occurs, using an intelligent self-healing mechanism to automatically switch redundant optical path resources and recover the optical path. According to the invention, all-optical network slicing and artificial intelligence technologies are fully utilized, and security isolation and resource optimization of a hospital internal network are realized.

The embodiment of the invention discloses a network resource allocation method and device based on load balancing, equipment and a medium. The method comprises the following steps: segmenting a physical wireless local area network into at least two virtual network slices by adopting a network function virtualization algorithm and a software defined network algorithm, and carrying out customized configuration on the at least two virtual network slices; determining a load state and an average load of the at least two virtual network slices, and determining a network resource allocation quantity of the at least two virtual network slices according to the load state and the average load; configuring corresponding service quality parameters for the at least two virtual network slices, and allocating processing tasks of different levels according to the service quality parameters; and dynamically adjusting the network resource allocation quantities of the at least two virtual network slices according to the network resource allocation quantities and the processing tasks of the corresponding levels. By adopting the scheme, the network resources are reasonably allocated, the communication requirements of different applications can be met, and the utilization rate of the network resources is improved.

The embodiment of the invention provides a distributed medical equipment management platform and method based on a zero-trust network. In the distributed medical equipment management platform based on the zero-trust network, an edge trusted access module adopts a hardware root of trust mechanism, so that equipment accessed for the first time is connected to a temporary supply network isolated from a medical core network, and a zero-trust security normal form is followed; the distributed trust anchor point cluster constructs a distributed identity verification network based on federated learning, and the access pre-authorization authority is verified through a device distributed identity identification (DID); the dynamic permission arrangement engine injects an attribute-based access control strategy, generates a permission token in combination with network micro-segmentation, and realizes two-way encryption communication between the equipment and a target service; the intelligent isolation gateway cuts off temporary connection through a software defined network technology and sends a network access state proof through a block chain mechanism, and edge module initialization is executed by a trusted node outside the medical cloud.

The invention discloses a welding process parameter intelligent optimization system based on digital twinning, which relates to the technical field of welding intelligent manufacturing and comprises a plurality of modules, a data holographic acquisition module, a multi-modal sensor array, an advanced algorithm for noise reduction to obtain accurate data, a digital twinning model building module, a digital twinning model building module, a digital twinning model building module, a digital twinning model building module and a digital twinning model building module, a digital twinning model building module and a digital twinning model building module. In combination with a multi-physics field coupling equation and a microstructure evolution model, deep simulation is realized, a data transmission synchronization module uses terahertz and software to define a network fusion architecture, the transmission quantity is reduced through edge federation transfer learning, data consistency is ensured by dual mechanisms, an optimization algorithm fusion module fuses multiple algorithms, and the data transmission efficiency is improved. The parameter adjustment feedback module updates the model in real time according to feedback by means of multi-agent cooperation and fuzzy prediction control. By means of digital twinning, the welding process is comprehensively monitored and accurately simulated, parameters are intelligently optimized, the welding quality stability is improved, the production efficiency is improved, the frontier technology is fused, and intelligent development of the welding industry is promoted.

The invention relates to the technical field of Internet of Things communication transmission, and discloses an Internet of Things data intelligent transmission method and system, and the method comprises the steps: abstracting the performance of a multi-source heterogeneous link through a software defined network controller, dynamically generating a slice template, carrying out the traffic marking and priority scheduling, constructing a multi-path target constraint optimization model, and carrying out the optimization of the multi-path target constraint optimization model. And in combination with a network function virtualization mechanism, multi-level intelligent transmission is implemented at edge nodes, and a final transmission control instruction is generated. In the prior art, in a heterogeneous multi-network environment, low-delay, high-reliability and high-bandwidth transmission cannot be guaranteed at the same time, and especially in an industrial automation scene, technical problems that a control instruction is easy to delay and a monitoring data bandwidth is limited exist. According to the invention, the overall transmission reliability and bandwidth utilization efficiency are improved through the dynamic priority traffic scheduling based on network slices, the multipath reliability product model and the dynamic batch processing and progressive compression technology based on real-time link feedback.

The invention provides a collaborative data migration scheduling method based on topology awareness and deep reinforcement learning, and the method comprises the steps: initializing system configuration, constructing a weighted graph comprising a source server, a working machine, a target storage and network equipment, carrying out the embedded processing of a graph structure through a graph neural network, and generating a node and a path representation vector; in combination with source data, a working machine and a target storage state, constructing a system state vector, inputting the system state vector into a deep reinforcement learning agent for decision making, and outputting a composite action including data block selection, working machine selection, path indexing and migration rate suggestion; the network control module converts path information into flow rules, the flow rules are issued and executed through the software defined network controller, the task management module continuously monitors the migration state and processes failed data blocks, and the integrity and non-repeatability of migration tasks are ensured. According to the method, the defects of an existing data migration system in the aspects of task allocation, path selection, resource control and dynamic adaptability can be overcome.

The invention relates to the technical field of smart home, and discloses a gateway configuration method, system and equipment, and the method comprises the steps: obtaining a gateway connection request from the equipment, and transmitting the identification information and load information of a physical gateway to the equipment; if an access request of the equipment is received, whether the equipment is legal is verified, if the equipment is legal, a target virtual gateway corresponding to the equipment is determined based on the position information, contained in the access request, of a logic partition where the equipment is located, and an access success reply is sent to the equipment based on a physical gateway, and the physical gateway is configured to bear a plurality of virtual gateways; and performing logical partitioning of the virtual gateway based on the software defined network. According to the invention, cooperative work and reliable disaster recovery of multiple gateways in the smart home system are realized, and a flexible, efficient and reliable solution is provided for smart home application in scenes of multi-floor villas and the like.

The invention relates to the technical field of network communication and intelligent optimization, in particular to a multi-mode network global routing optimization method and device, electronic equipment and a medium. Comprising the following steps: constructing a data plane and a control plane according to a hierarchical structure of the software defined network, performing multi-modal analysis on an actual network topology of the data plane according to a modal type supported by a switch, and dividing the actual network topology into logic subnets of different modals based on a multi-modal analysis result; generating a set of N paths satisfying a preset condition between the source switch and the destination switch by using a preset path searching algorithm based on a network topology relationship between the logic subnets of different modalities; and based on the N path sets and the global controller of the control plane, generating a global route of the multi-modal network by using a preset global strategy model. Therefore, the problems that a traditional network optimization method is insufficient in collaboration and low in global characteristic utilization rate in a multi-domain data environment are solved, and the network transmission efficiency and the cross-domain collaboration capability are improved.

The invention provides a flow control method based on a software-defined network, which belongs to the technical field of data processing, and comprises the following steps of: 1, acquiring port data and link data of a switch in the software-defined network, and determining a network topology structure; 2, acquiring real-time flow data in the software defined network, and analyzing a network topology structure and the real-time flow data to determine adjustment path data; 3, determining a traffic adjustment strategy and a traffic forwarding rule based on the network topology structure and the adjustment path data; and step 4, executing the flow forwarding rule to realize the flow control of the software defined network. The method can deal with sudden flow fluctuation and link faults in the network and quickly respond, automatically optimize flow distribution and route selection, improve the bandwidth utilization rate and resource utilization rate of the network, reduce congestion and delay, adapt to a complex flow mode and a high-load and time-varying network environment, and improve the flexibility, reliability and efficiency of the network.

The invention discloses an SDN-fused multilayer QKD constellation model and a key distribution routing algorithm building method, and relates to the technical field of quantum key distribution. According to the method, orbit distribution and dynamic characteristics of a satellite in a free space are deeply analyzed, a trusted relay quantum key distribution constellation model fusing GEO / MEO / LEO three-layer orbits is provided, and a software defined networking (SDN) technology is introduced into the model, so that centralized control and efficient management are realized, and the reliability of the system is improved. A self-adaptive quantum key flow aware routing algorithm (AQKAR) is designed on the basis of a trusted relay quantum key distribution constellation model fusing GEO / MEO / LEO three-layer tracks, so that a key distribution path is dynamically optimized; a simulation result shows that compared with a traditional LEO single-layer network and a GEO / LEO double-layer network, the framework provided by the invention has the advantages that the request success rate is remarkably improved, the end-to-end network delay is lower, and meanwhile, the algorithm provided by the invention can effectively improve the flexibility of the network under the condition that the network is extremely congested.

A method for deep packet inspection (DPI) in a software defined network (SDN). The method includes configuring a plurality of network nodes operable in the SDN with at least one probe instruction; receiving from a network node a first packet of a flow, the first packet matches the at least one probe instruction and includes a first sequence number; receiving from a network node a second packet of the flow, the second packet matches the at least one probe instruction and includes a second sequence number, the second packet is a response of the first packet; computing a mask value respective of at least the first and second sequence numbers indicating which bytes to be mirrored from subsequent packets belonging to the same flow; generating at least one mirror instruction based on at least the mask value; and configuring the plurality of network nodes with at least one mirror instruction.

A method for detecting network attack based on kernel operating characteristics of a software switch, comprising: collecting kernel operating characteristic data of the software switch during network management and packet forwarding of the software switch, wherein the kernel operating characteristic data of the software switch can reflect characteristic data of a fine-grained operating state of a network; preprocessing the kernel operating characteristic data of the software switch; and inputting the preprocessed kernel operating characteristic data of the software switch into a pre-trained attack detection model to detect a potential attack behavior in a network. The method is applicable to all scenarios where the software switch is applicable, especially a software-defined network and a cloud data center, an industrial Internet, 5G, edge computing based on the software-defined network. More accurate and timely detection and early warning of potential anomalies and attack behaviors in the network can be implemented.

A distributed network that may include multiple links; and multiple physical nodes that in communication with each other via the multiple links, to form multiple redundant paths, wherein at least some of the redundant paths form a daisy chain; wherein the multiple physical nodes comprise output ports configured to interface with external hosts. The multiple physical nodes are configured to supports software defined networking (SDN).

A technique for determining security attacks in wireless communication systems is disclosed. A method implementation of the technique is performed by a controller and includes obtaining a first statistics based on an amount of messages received from at least one packet forwarding entity within a pre-defined time interval, t, wherein the first statistics is a time-domain data; obtaining a second statistics based on at least one arriving-time difference, Td, between two consecutive messages; detecting an anomaly based on the second statistics; determining, if the anomaly is detected, a security attack based on the first statistics; and initiating a security attack notification to an orchestrator.

A computer-implemented method of operating a software-defined network, the method comprising: obtaining specifications of a plurality of data plane elements which together form a path through a data plane suitable for carrying traffic associated with a category of applications and / or services; determining, based on the specifications, which one or more of a plurality of security profiles the path is capable of complying with; selecting one of the one or more security profiles to be an initial security profile; routing traffic associated with the category of applications and / or services via the path in compliance with the initial security profile; subsequently obtaining an alert that network performance conditions have worsened; and responsive thereto: selecting a different one of the plurality of security profiles, that is less resource-intensive than the initial security profile, to be a replacement security profile; and routing traffic associated with the category of applications and / or services in compliance with the replacement security profile.

The present disclosure relates generally to an SDN providing DNS resolution for a non-SDN service. In particular, the SDN hosts a first endpoint communicatively coupled with the non-SDN service. The SDN also hosts a DNS proxy in support of a second private network of a customer. A second endpoint of the customer can be accessible via the second private network The non-SDN service can send a DNS resolution request (that includes, for example, an FQDN of the second endpoint) to the first endpoint. The first endpoint forwards this request to the DNS proxy. In turn, the DNS proxy determines the IP address of the second endpoint and returns a reserved IP address corresponding to the DNS proxy and mapped to the second endpoint's IP address. The first endpoint sends this DNS resolution to the non-SDN service that then learns that the FQDN is resolved to the reserved IP address.

The invention discloses a method for automatically inspecting equipment in intelligent manufacturing, which comprises the following steps of: 1, deploying edge computing nodes, combining with 5G network slices, cleaning and compressing inspection data in real time, dividing priorities, performing low-delay transmission on key data through a special bandwidth, and locally caching or filtering non-key data; 2, developing a controller based on the software defined network, monitoring a link state, introducing a reinforcement learning algorithm, and dynamically optimizing a transmission path; 3, deploying a TinyML framework at an equipment end, integrating a model compression technology to operate a lightweight AI model, and combining sensor data to perform real-time early warning and support offline analysis; 4, constructing an incremental learning framework, dynamically updating model parameters through knowledge distillation, and only adjusting part of parameters to adapt to state change; and step 5, an analysis result is fed back to the system by using a message queue, and a patrol strategy is dynamically adjusted in combination with a rule engine to form a closed-loop optimization mechanism of data acquisition-transmission-analysis-decision.

In communication with components of a cloud platform, namely a software-defined network constructed to overlay at least one public cloud network, a controller features a virtual processor and a data store. The data store includes network address translation (NAT) processing logic configured to determine whether a control plane message from tenant resources is associated with a network address overlapping condition, which represents a first network address included in the control plane message overlaps a network address range relied upon by either (a) at least one of the components of the cloud platform or (b) a component associated with other tenant resources. The NAT processing logic is further configured to alter routing data stores that maintain routing information for each of the components of the cloud platform to substitute the first network address with a first virtual network address for subsequent data message routing.

The invention discloses a dynamic optimization method for an intelligent security convergence protection strategy of a power system, and belongs to the technical field of power system security protection. According to the method, a'perception-evaluation-decision-execution 'four-layer dynamic optimization framework is constructed; a perception layer collects multi-source data at a sampling rate greater than or equal to 1kHz through a lightweight edge agent, and the multi-source data is fused through an adversarial generative network; the evaluation layer evaluates threats by using an improved space-time diagram convolutional network in combination with a dynamic threat index; the decision-making layer introduces a depth deterministic strategy gradient algorithm to generate a protection strategy; and the execution layer deploys and feeds back a result through a software defined network. The problems of static defense, data splitting, insufficient real-time performance and the like in the traditional technology are solved. Simulation verification shows that the attack detection rate is increased to 98.7%, the strategy optimization time consumption is shortened to 457ms, the energy loss is reduced by 19.8%, and the safety protection level of the power system is effectively improved.

An automated system provides end-to-end (E2E) orchestration for machine learning (ML)-enabled and software-defined network (SDN)-enabled reactive and predictive (e.g., 5G) cell-on-drone (COD) dispatch and deployment. The system may be configured to detect or predict traffic surges (e.g., relative to typical or baseline levels) in a given cell site and orchestrate provisioning of resources, including COD deployment, to address the surge. COD deployment may involve one or more clusters or colonies of drones equipped with low-powered cellular radio access (or small cell) nodes, where each cluster includes (or is led by) one or more SDN-equipped drones that provide intelligent SDN-on-drone (SOD) functionality.

The present disclosure relates to a virtual network router for a cloud-native software-defined network architecture. In general, techniques for creating a virtual network router within a software-defined network (SDN) architecture are described. A network controller for an SDN architecture system may include a processing circuit configured to execute a configuration node and a control node. The configuration node may process a request to create a virtual network router (VNR), wherein the virtual network router may cause the network controller to interconnect a first virtual network (VN) with a second VN. The VNR may represent a logical abstraction of one or more policies that cause the import and / or export of routing information between a first VN and a second VN. The control node configures the first VN and the second VN according to the one or more policies so that routing information is imported and / or exported between the first VN and the second VN via the VNR.

The invention discloses a dynamic power management and multi-energy collaborative optimization method combined with an AI technology, and the method comprises the steps: training an AI prediction model to predict a future network load through collecting historical network flow, equipment power consumption and energy supply data; generating a power consumption optimization strategy according to the predicted network load; through a double-layer optimization algorithm, multi-energy dynamic distribution is realized; and resource scheduling is performed by using a genetic algorithm, so that resource redundancy is reduced. The method has the advantages that the traditional deep learning algorithm and the symbol AI are combined, the interpretation of the power consumption adjustment strategy is realized, the transparency of AI scheduling is improved, and the controllability and reliability are enhanced. Meanwhile, a power consumption optimization strategy is dynamically generated through dynamic programming and a heuristic algorithm, the utilization rate of renewable energy sources is increased, and traditional energy dependence is reduced. And network resources are abstracted through a software defined network technology, and a genetic algorithm is introduced for resource scheduling, so that resource redundancy is remarkably reduced, and the network utilization rate is improved.

The invention discloses a virtuality and reality combined method and system for dynamically reconstructing diversified network topology, and belongs to the technical field of novel power systems, and the method comprises the following steps: virtualizing physical equipment in a power system business scene network by using NFV to obtain virtual equipment; constructing a network architecture for realizing a service scene network of the power system by adopting a virtualization mode; physical equipment and virtual equipment in the service scene network of the power system are controlled in a centralized manner based on the SDN; and the SDN controller dynamically reconstructs the service scene network of the power system according to a set strategy. According to the invention, dynamic allocation of network resources and real-time reconstruction of topology are realized through a virtuality and reality combination technology, a software defined network technology and a network function virtualization technology, and virtualized resources and resources of physical equipment can be effectively integrated so as to quickly respond to changes of application requirements.

The present application provides a network configuration information processing method. For the process of virtual machine live migration, a function of delaying deletion of a virtual machine on an original node computer is realized on the network control plane, so that when a node in the network system sends a message for accessing the live migration virtual machine, even if the node does not refresh the corresponding relationship between the live migration virtual machine and the destination node computer, the message for accessing the live migration virtual machine can still be sent to the original node computer for relaying or processing, and the packet loss probability of the message for accessing the live migration virtual machine can be reduced in the process of virtual machine live migration and within a certain period after the virtual machine live migration is completed.