Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1331 results about "Wide area network" patented technology

A wide area network (WAN) is a telecommunications network that extends over a large geographical area for the primary purpose of computer networking. Wide area networks are often established with leased telecommunication circuits.

Visual intelligent monitoring system and method for power distribution cabinet, computing equipment and storage medium

The invention discloses a power distribution cabinet visual intelligent monitoring system and method, computing equipment and a storage medium, and belongs to the technical field of power system equipment monitoring, the system comprises a data acquisition module, edge computing equipment, a user-defined visual interface and a cloud platform, and the modules are in communication connection through a low-power wide area network; the data acquisition module is used for acquiring running state data and environment data of the power distribution cabinet in real time; the edge computing device is used for preprocessing the collected data and evaluating the quality of the power grid, and uploading the preprocessed data to the cloud platform; and the cloud platform is used for training a deep neural network model by using historical data based on a distributed computing framework, performing anomaly detection and fault prediction on real-time data based on the trained model, triggering early warning according to a detection result, and displaying a real-time data stream view and anomaly labeling information in a self-defined visual interface. According to the scheme, the power distribution cabinet anomaly detection accuracy and the information display flexibility can be improved.
Owner:BEIJING BEIFANG YONGDA INTELLIGENT ELECTRIC CO LTD

System and methods for storage intrusion mitigation with data transport overlay tunnels and secure vaulting

The present disclosure relates to cyber-attack mitigation, information theoretic security in-motion, at-rest and storage intrusion mitigation with exclusive-path, content routing across an overlay network. Overlay network built upon Data Transport Controllers (DTC), SG nodes and SV nodes. System modules are deployed across various geo locations in a Wide Area Network, operating at the control of Universal Security Controller (USC). USC extracts system, security and storage activity telemetry data from Secure Vaults, Storage Gateways and Data Transport Controllers to orchestrate Autonomous Security Operations. SG nodes create SP fragments and store in SV nodes upon a data input operation. USC initiates an Exclusive-path content forwarding from the first SG node, across the DTC overlay through an exclusive list of DTC nodes and move it to second SG node. USC keeps the security control of SG nodes, DTC nodes and SV nodes and realize multi-vectored storage security at-rest and in-motion. SG nodes are connected to SV nodes which are micro-segmented, data vaults with restricted network reachability.
Owner:CHACKO PETER

Edge computing system with low power wide area network connectivity and autonomous or semi-autonomous machine learning

A mobile edge computing system, a communication network and a method of using a mobile edge computing device. The mobile edge computing system includes a communication module that establishes signal communication over numerous wireless communication protocols at least one of which uses a low power wide area network protocol. A logic device is made up of a distributed set of processing units including both a central processing unit and one or more processors configured for performing machine learning operations the latter of which include one or more of a graphical processor unit and a tensor processing unit. When the system receives event data that has been acquired by one or more of the communication module and a sensor, the system executes a trained machine learning model and conveys, using the low power wide area network protocol, an output that has been produced by the trained machine learning model.
Owner:CAREBAND INC

Logical path down scope analysis

A network management system (NMS) generates a hierarchical attribution graph representing different scopes at different hierarchical levels of a wide area network (WAN); obtains logical path down data indicative of operational behavior including failure events associated with logical paths of network devices over the WAN; obtains total path data indicative of a historical number of active logical paths between the network devices; and determines a scope of a logical path down issue by, for a time period of the logical path down issue, determining a score for each scope of the different scopes based on the logical path down data aggregated across the respective scope and the total path data, and determining the scope of the logical path down issue as a particular scope of the different scopes having a highest score. The NMS may identify the particular scope as a root cause of the logical path down issue.
Owner:JUNIPER NETWORKS INC

Platform and method for automated device management and infrastructure servicing

A network management platform can include a configuration management database (CMDB), an IP address management (IPAM) network device, a network security platform, and a software-defined wide area network (SDWAN). The CMDB can be configured to store configuration data of endpoint devices. The IPAM can allocate IP addresses within the network. The network security platform can be configured to enforce policies and / or manage endpoint access. The SDWAN can be utilized to configure and / or control the endpoint devices.
Owner:CELLULAR SOUTH INC DBA C SPIRE WIRELESS

Management method and device for computing power identification and resource description based on domain name system

The invention provides a method and a device for managing computing power identification and resource description based on a domain name system. Wherein the computing power identifier comprises a computing power node identifier and a computing power resource identifier, the computing power identifier is used for identifying basic static information of the computing power resource, and the resource description file is used for identifying dynamic description information of the computing power resource. According to the method, the computing power identification and the resource description information based on the domain name are fully utilized, and the domain name infrastructure, the related system and the operation mechanism are combined, so that compatible use of different types of computing power resource identifications can be realized, and meanwhile, the consistency and the accuracy of the computing power identification in the wide area network range are improved.
Owner:CHINA INTERNET NETWORK INFORMATION CENTER

Power grid infrastructure engineering material collaborative management method

The invention provides a power grid infrastructure project material collaborative management method, which comprises the following steps: analyzing historical material use, power grid construction progress and external environment data through a reinforcement learning algorithm, dynamically adjusting model parameters, and predicting material demands; a low-power-consumption wide area network and an edge computing technology are used for monitoring and analyzing material states in a warehouse and a transportation process in real time, and a result is transmitted to the central management system; based on the prediction data, an optimized material purchasing plan is automatically generated, and the purchasing strategy is dynamically adjusted by considering the arrival time, the inventory state and the supplier capability; using an improved ant colony algorithm to optimize the transportation route and time of the materials from the warehouse to the construction site; using an intelligent sensor to record the material use condition, and carrying out preliminary data processing and analysis through edge calculation; and an information management platform is established to realize information sharing and cooperative work. According to the method, the intelligence and efficiency of material management are improved by integrating multiple technologies.
Owner:STATE GRID ANHUI ELECTRIC POWER CO LTD +6

Erasure code algorithm processing method for cold and hot fragmented data in distributed storage system in local area network or wide area network

The invention relates to the field of distributed storage, in particular to an erasure code algorithm processing method for cold and hot fragmented data in a distributed storage system in a local area network or a wide area network, and solves the problems caused by using an erasure code algorithm to process cold and hot data in the prior art. The method comprises the steps of data block partitioning, a parameter strategy of data cold and hot judgment, a parameter strategy of node cold and hot judgment, data writing, an erasure code algorithm processing mechanism of different types of data, processing after erasure code algorithm processing, data cold and hot conversion processing and the like. Meanwhile, normal read-write performance is kept not affected by erasure code processing in the EC coding processing process, and the rationality of cold and hot data division in the distributed storage system is improved; layered storage and migration are performed according to cold and hot data, the read-write performance of distributed storage is considered, and the capacity utilization rate is increased; and the reliability, fault tolerance and performance of the storage system are improved.
Owner:CHENGDU HUARUI SHUXIN TECHNOLOGY CO LTD

Low-power wide area network integrated sensing and communication method based on channel sensing and reinforcement learning

The invention provides a low-power wide area network integrated sensing and communication method based on channel sensing and reinforcement learning, and the method comprises the steps: receiving an uplink signal transmitted by a terminal node through a gateway receiver, demodulating the uplink signal through employing a soft demodulation algorithm, and obtaining a bit log-likelihood ratio; the deep reinforcement learning model completes channel reconstruction of the corresponding link during communication according to the bit log-likelihood ratio; and calculating the current optimal network configuration according to the reconstructed channel so as to distribute the current optimal network configuration to each terminal node during next downlink transmission. According to the method, the key environment information is mined by using the deep reinforcement learning model, so that the gateway can allocate optimal network configuration to different terminal nodes according to the current network environment condition, and the decoding capability of the gateway is improved.
Owner:THE HONG KONG UNIV OF SCI & TECH (GUANGZHOU) +2

Methods to add zero-trust access-control to a deterministic internet network to achieve quantum safe cyber-security

Methods to add an “Admission Control / Access Control” system to control access to a “Software-Defined-Deterministic Industrial Internet of Things” (SDD-IIoT) network are described. The SDD-IIoT comprises a “Software Defined Networking” (SDN) control-plane, and many “Software-Defined-Deterministic Wide Area Networks” (SDD-WANs). The SDN control-plane comprises 3 layers of “Zero Trust Architectures”, i.e., rule-based “Attribute-Based Access Control” (ABAC) systems, where subjects can request access to resources. A controller's “Knowledge-Base” consists of a set of facts and rules, which an inference-engine processes to make access decisions. Each SDD-WAN comprises a low-complexity deterministic forwarding-plane, with many simple deterministic packet switches (D-switches), realized with “Field Programmable Gate Arrays” (FPGAs). The forwarding-plane implements “Authenticated Encrypted Deterministic Channels” (AEDCs or D-flows) directly in hardware in layer-3, using Quantum Safe ciphers. Each D-flow has a deterministic data-rate requirement, with delay and jitter requirements. The D-switches can forward encrypted data, according to pre-defined periodic (repeating) deterministic schedules. For a packet to be accepted at the destination, it must be successfully decrypted at the destination in layer-3, using a Quantum Safe cipher. Malicious packets from cyber-attackers will fail the decryption process in layer-3, and thus be detected and removed. Each enterprise has an “Enterprise-Controller”, to control access to its private resources (i.e., computers, data-bases, etc), with an extensive knowledge base of rules. Each SDD-WAN has a “WAN-Controller”, to control the communications between enterprises over the SDD-WAN. If an Enterprise-Controller or WAN-Controller approves a request to establish a new D-flow, the SDN control-plane will download deterministic schedules and secret keys to the D-switches in the forwarding-plane. An IIoT-Controller will control the communications between different SDD-WANs. In an IIoT deployment, there may be 10s of WAN-Controllers, each with 100s of Enterprise-Controllers. These collaborative controllers work together, to control access to the bandwidth of the SDD-IIoT. They can achieve exceptionally-strong cyber-security, where the expected number of successful cyber-attacks per year from external cyber-attackers with Quantum Computers, can be reduced to zero. The SDD-IIoT can achieve security comparable to that offered by “Quantum Key Distribution” (QKD) networks in practice, determined by the computational hardness of cracking Quantum Safe ciphers. The SDD-IIoT can save the industry 10s . . . $100s of billions (US dollars) per year, by exploiting low-cost FPGAs, providing a powerful incentive to innovate layer-3 of the Internet.
Owner:SZYMANSKI TADEUSZ H

Packet loss retransmission method and device, computer equipment, readable storage medium and program product

The invention relates to a lost packet retransmission method and device, computer equipment, a readable storage medium and a program product, and is applied to a receiving end, and the method comprises the following steps: receiving a data packet sent by a sending end; a first extension field is added in a target message header of an IP layer of the data packet, the first extension field is filled with a serial number, and the serial number is used for representing a sequence number of the data packet; performing packet loss detection according to the serial number in the data packet; under the condition that the lost data packet is detected, determining a target serial number of the lost data packet; and sending a retransmission request packet carrying the target serial number to the sending end, so that the sending end retransmits a data packet corresponding to the target serial number. By adopting the method, selective packet loss retransmission can be realized, that is, only the lost / delayed packets are retransmitted, the number of the retransmitted packets can be greatly reduced, the influence on the network throughput performance is reduced, and high throughput and low delay transmission of data is ensured, so that the performance of a wide area network is improved.
Owner:CHINA TELECOM CORP LTD TECHNOLOGY INNOVATION CENTER +1

Edge computing system with low power wide area network connectivity and autonomous or semi-autonomous machine learning

A wearable electronic device, a system and methods of monitoring with a wearable electronic device. The device includes a hybrid wireless communication module with wireless communication sub-modules to selectively acquire location data from both indoor and outdoor sources, as well as a wireless communication sub-module to selectively transmit an LPWAN signal to provide location information based on the acquired data. The device may also include one or more sensors to collect one or more of environmental data, activity data and physiological data. The device may transmit some or all of its acquired data to a larger system, including a cloud-based server to, in addition to providing location-based data, be used as a part of a predictive health care protocol to correlate changes in acquired data to salient indicators of the health of a wearer of the device. In one form, the predictive health care protocol uses a machine learning model.
Owner:CAREBAND INC

Wide area network issue prediction based on detection of service provider connection swapping

Techniques are described for predicting a wide area network (WAN) issue based on detection of service provider connection swapping. A cloud-based network management system (NMS) obtains connection event data for one or more network access server (NAS) devices at a site, where each event included in the connection event data comprises a connection or disconnection event of a connection session provided by a service provider. The NMS detects a number of connection swaps in the connection event data over a time window, where a connection swap includes a change from a first connection session provided by a first service provider to a second connection session provided by a second service provider. Based on the detected number of connection swaps satisfying a threshold, the NMS predicts a root cause of the connection swaps as a WAN issue and generates a notification of the predicted root cause of the connection swaps.
Owner:JUNIPER NETWORKS INC

Software defined wide area network control method

The invention discloses a software defined wide area network control method, and the method comprises the steps: receiving network state information for to-be-transmitted data through a first network composer, the network access points are node communication relations among an input network access point of to-be-transmitted data, a plurality of intermediate network access points and an output network access point and a plurality of performance indexes of corresponding node transmission links, and the intermediate network access points are network access points for realizing communication between the input network access point and the output network access point. Determining the minimum path communication cost of each transmission path for transmitting the data to be transmitted from the input network access point to the output network access point according to the node communication relationship and a plurality of performance indexes of the node transmission link; and determining the corresponding transmission path as a target transmission path for the to-be-transmitted data, and sending the target transmission path to the first network controller so as to control the corresponding network access point to realize transmission of the to-be-transmitted data according to the target transmission path.
Owner:LENOVO (BEIJING) LTD

Achieving symmetric routing using intent-based smart device groupings in a software-defined wide area network

Techniques for symmetric routing in a software-defined wide area network (SDWAN) are disclosed herein. In some aspects, the techniques described herein relate to a method including: determining a first device group, wherein the first device group includes a first router associated with a branch tag and a second router associated with a hub tag; determining a second device group, wherein the second device group includes a third router associated with and a fourth router associated with the hub tag; transmitting a first route advertisement associated with a first route from the first router to the second router to the first router; transmitting a second route advertisement associated with a second route from the first router to the third router to the first router; and preventing transmission of a third route advertisement associated with a third route from the first router to the fourth router to the first router.
Owner:CISCO TECHNOLOGY INC

A byte transparent transmission method for IoT based on H5JS local programming

ActiveCN113824783BReduce the amount of programmingLess programmingNetwork topologiesMessaging/mailboxes/announcementsMicrocontrollerMobile end
The present invention discloses a method for transparent transmission of byte of Internet of Things based on H5JS local programming, fully explores the potential application characteristics of cloud Internet of Things MQTT combined with Nodemcu, and establishes a local operation mode of Html-JS program on a mobile terminal (referring to a mobile phone or a computer) with full-range byte transparent transmission as the basis of network communication. It is proposed that cloud Internet of Things MQTT supplements the direct WeChat and sound alarm functions, and provides a local execution of Internet of Things Html-JS general program, which not only greatly reduces the user programming links, avoids low-level repetition, but also provides programming examples. Because this mode is also particularly suitable for combining with a single-chip microcomputer, and MQTT is not required in a local area network. At the same time, it is also proposed that the Nodemcu program migrates to JS or realizes program minimization through reset, as well as high-speed timing sampling, and uses a single-chip microcomputer combined with ESP-12 to batch and centrally transmit data to a mobile terminal mode connected to wifi. Such a streamlined and complete Internet of Things, from local area network to wide area network, from computer mobile phone connection to single-chip microcomputer to send WeChat, adopts mainstream technology, and is very suitable for use as a unified textbook of Internet of Things for colleges and universities.
Owner:HANGZHOU HEXUE EDUCATION TECH CO LTD

Software defined wide area network data transmission method and system based on edge computing

The invention relates to the technical field of software-defined wide area network data transmission, and discloses a software-defined wide area network data transmission method and system based on edge computing. According to the method, network state data are collected through distributed probes deployed at edge nodes, and a dynamic transmission path between the nodes is calculated after data cleaning and feature extraction. A collaborative filtering algorithm is utilized to analyze historical and real-time data to generate a transmission optimization strategy, and a fuzzy logic decision maker is combined to generate a dynamic routing strategy. And predicting a future congestion state based on network characteristics and a routing strategy, and adjusting flow scheduling parameters accordingly. And finally realizing visual display and time sequence storage of the network state data, the routing strategy and the scheduling parameters. The method can effectively reduce transmission delay and improve the utilization rate of network resources.
Owner:HANGZHOU DIANKE SMART CITY SOFTWARE CO LTD

Collaborative resource scheduling method and system based on programmable network

The invention discloses a collaborative resource scheduling method and system based on a programmable network. The method comprises the following steps: performing performance modeling on heterogeneous computing resource data in all computing resource data to obtain a uniform resource performance index; defining target computing resource data required by multi-dimensional resource demand services, and determining matching relationship information between each multi-dimensional resource demand service and the current computer cluster; in the deployment process, according to all the matching relation information, the correspondingly selected multi-dimensional resource demand service is deployed to each computer cluster; determining a shortest deployment path between the routing nodes in each computer cluster based on a Floyd algorithm; and in the actual scheduling process, executing the computing power arrangement scheme generated in the deployment process. According to the collaborative resource scheduling method and system based on the programmable network provided by the embodiment of the invention, the utilization rate of computing power resources in a wide area network can be improved, and a computing power scheduling strategy is dynamically generated.
Owner:STATE GRID ZHEJIANG ELECTRIC POWER CO LTD

End-to-end encryption with per-hop path-selection based on unique edge identities for sd-wan and multi-hop networks

A system and associated methods provide solutions for end-to-end privacy and per-hop routing and policy decision in multi-hop and Software-Defined Wide Area Networks (SD-WANs) by leveraging unique SDWAN edge identities of edge devices. The system enables end-to-end encryption between traffic source and destination sites using IPsec ESP tunnel mode, with System IPs as the outer IP addresses. The system further enables per-hop integrity protection using IPsec AH transport mode, with WAN IPs as the outer IP addresses. By having some information encrypted between a source device and a destination device and other information encapsulated between hops (e.g., between source device and an intermediate device), the system enables route and policy lookup based on destination site System-IP, along with integrity protection based on SLA-class in packet metadata for independent path selection at intermediate hops.
Owner:CISCO TECHNOLOGY INC

Distributed boundary network threat flow detection method based on GCN model

The invention particularly relates to a distributed boundary network threat flow detection method based on a GCN model, which comprises the following steps of: constructing a BGP network topological graph according to a business relationship of each autonomous system in a wide area network provided by an existing data set, endowing different weights to corresponding edges in the BGP network topological graph, and initializing node features; according to the acquired BGP network topological graph information, learning a BGP network topological graph by using a GCN model, performing graph node embedding and retaining key graph features; monitoring traffic path changes of a plurality of global routing convergent points, and detecting a path change mode with security threats in traffic by analyzing a path change difference score in real time; and summarizing abnormal traffic, associating the common prefix and the autonomous system, and giving an abnormal report. According to the method, the problems that information configuration is difficult to carry out and the model interpretability is poor during boundary network threat flow detection are solved, and meanwhile, the method has good real-time performance, interpretability and relatively high accuracy.
Owner:XIDIAN UNIV

Cloud-Based Vehicle Diagnostic System Having Specialized Data

Systems and methods for vehicle diagnostic services utilizing a diagnostic server. The systems comprise a diagnostic server that is in data communication with a service tool and the vehicle communication interface (VCI) of a vehicle. The data communication may be accomplished using a wide area network (WAN). The diagnostic server acquires diagnostic data from the VCI and generates a diagnostic report for a user to utilizing during service actions of the vehicle. Some embodiments utilize an external gateway adapter to enable data communication between the diagnostic server and vehicles lacking a native function to interface with external devices or components across networks.
Owner:BOSCH AUTOMOTIVE SERVICE SOLUTIONS INC +1

Routing architecture and method of computing power service open internet

The invention relates to the technical field of networks, in particular to a routing architecture and method of a computing power service open internet. The architecture comprises: a network access device; a network output device; a network control center; the network management device is used for generating a first arrangement result between the first network output device and the target service providing node according to the analysis result, the computing resource state and the network resource state; the network management equipment is also used for issuing the first arrangement result to the network access equipment, and sending a service request message to a wide area network routing node, so that the service request message is sent to the first network output equipment according to a specified path and strategy in the first arrangement result; and the first network output device is used for sending the service request message to the target service providing node. By implementing the technical scheme of the invention, finer, more flexible and more reliable end-to-end routing control is provided, and the guarantee of the whole process of transmission and calculation and the optimal utilization of network and calculation resources are realized.
Owner:BEIJING JIAOTONG UNIV +1

Quantum threshold resistant digital signature method and system capable of tolerating high network delay

The invention belongs to the field of passwords, and discloses an anti-quantum threshold digital signature method and system capable of tolerating high network delay. The method comprises the following steps: in a secret key generation stage, a trusted third party randomly selects a secret key and performs Shamir secret sharing on the secret key, and distributes a secret sharing value to each signer; in a distributed signature stage, each signer carries out packaging and secret sharing on a secret sharing value, a proving sub-circuit of a public key is operated based on a secure multi-party computing protocol, and each participant outputs a signature through two rounds of interaction. The anti-quantum threshold digital signature scheme has function interchangeability, that is, the signature generated by the threshold scheme and the signature generated by the original signature scheme can be verified by the same verification algorithm; meanwhile, the threshold digital signature scheme is efficient and achievable, and a threshold signature protocol in a scene of two parties of a wide area network only needs 2 seconds; moreover, the method has a better number of rounds, and the signature algorithm only needs two rounds.
Owner:INST OF SOFTWARE - CHINESE ACAD OF SCI

Security protection method and device based on industrial internet

A security protection method and device based on industrial Internet is provided. The disclosure relates to the technical field of network security and realize the isolation between the Internet and the industrial Internet platform intranet by deploying the exit firewall, and there is no restriction from the industrial Internet platform intranet to the Internet, and only necessary ports are opened from the Internet to the industrial Internet platform intranet. By deploying a regional firewall, isolation between the intranet core server and each of the secondary nodes is realized. The regional firewall is deployed on the wide area network router, and the second access policy of secondary nodes and intranet core servers is preset. After the second access policy is formulated, only the IP and service ports of specific hosts are opened, and all other accesses are prohibited.
Owner:HUANENG INFORMATION TECH CO LTD

Edge calculation optimization method of seawater parameter monitoring Internet of Things system

The invention provides an edge calculation optimization method for a seawater parameter monitoring Internet of Things system, and belongs to the technical field of edge calculation, and the method comprises the steps: constructing a seawater parameter monitoring sensor network, and calculating an energy consumption evaluation reference value based on a data change rate and a disorder degree; performing feature extraction on the seawater parameter data; deploying a double-model collaborative architecture comprising a terminal lightweight model and a center complete model; setting a dynamic energy consumption threshold judgment mechanism to allocate calculation tasks; executing lightweight edge calculation at the sensing nodes; transmitting the processed data through a low-power wide area network; the calculation center verifies and fuses the data; constructing a seawater parameter space-time distribution model; dynamically adjusting an energy consumption evaluation reference value by using a Pareto optimal solution set method; and periodically evaluating system energy consumption efficiency and updating model parameters. According to the method, dynamic balance of energy consumption and calculation efficiency of the seawater parameter monitoring system is realized, and the continuous operation capability and the monitoring reliability of the system are remarkably improved.
Owner:青岛道万科技有限公司

Dynamically associating mobile devices with different software-defined wide area networks implemented for different user groups of a single shared network fabric of a single entity

Some embodiments provide a novel method for dynamically associating mobile devices with different software-defined wide area networks (SD-WANs) implemented for different user groups of a single shared network fabric of an entity. The method identifies a mobile device trying to connect to a managed network switch. The method uses one or more mobile device management (MDM) servers to identify attributes associated with the mobile device attempting to access the shared network fabric. The method uses the identified attributes to identify an SD-WAN tenant identifier (ID) associated with an SD-WAN established for a device group including the mobile device. The method provides the SD-WAN tenant ID to the managed network switch to store in encapsulating headers that the managed network switch uses to encapsulate data message flows from the mobile device before forwarding the flows to resources in the shared network fabric.
Owner:VMWARE INC

Robot data processing server and robot program calculation method

A server includes a communication device, a storage device, and a processing unit. The communication device receives teaching points of an industrial robot from a client device by communicating with the client device via the wide area network. The storage device stores correction method data including a plurality of types of correction methods for correcting the teaching points according to a positional relationship between the robot and a workpiece during the work. The processing unit creates a correction program by applying the correction method described in the correction method data to the teaching points received by the communication device, and instructs the communication device to transmit the correction program to the client device.
Owner:KAWASAKI JUKOGYO KK

Wide area network link bandwidth monitoring

A network management system instructs a first network device to obtain one or more parameters related to a Wireless Area Network (WAN) link between the first network device and a second network device. The network management system executes a machine learning system configured to apply, to the one or more parameters related to the WAN link, a machine learning model trained with parameters of links to predict bandwidths of the links, to predict a maximum bandwidth of the WAN link. The network management system outputs an indication of the predicted maximum bandwidth of the WAN link.
Owner:JUNIPER NETWORKS INC

Route preference based on link performance

Techniques are disclosed for computing a priority of routes advertised by nodes implementing Layer-3 (L3) Multi-Node High Availability (MNHA) for a Software-Defined Wide Area Network (SD-WAN) interconnecting a first network device and a second network device according to link adherence to performance requirements. In one example, a node computes a priority for a route to the second network device based at least in part on a comparison between (1) one or more performance measurements of a link between the node and the second network device and (2) one or more performance requirements for the link. In some examples, the computed priority for the route is further based in part on a preference for the node. The node exports, to the first network device, the route to the second network device, wherein the route comprises data specifying the computed priority for the route.
Owner:JUNIPER NETWORKS INC