42 results about "Topology management" patented technology

The invention proposes a smart park energy consumption management system and method based on artificial intelligence, and relates to the technical field of smart park energy consumption management, and the system comprises a data collection module which collects original time sequence energy consumption data and equipment state information; the data preprocessing module is used for performing data quality processing on the original time sequence energy consumption data to obtain preprocessed time sequence energy consumption data; the topology management module is used for constructing an energy consumption relation graph and generating node topology representation characteristics; the feature engineering module is used for obtaining a space-time-business joint feature tensor; the anomaly monitoring module is used for obtaining an anomaly score and outputting anomaly positioning information based on an interpretable analysis method; and the visual display module is used for generating an alarm report and performing visual display. According to the invention, accurate anomaly identification and intelligent positioning analysis of multi-level and multi-energy-type energy consumption data of the park can be realized, and the automation level and the operation and maintenance efficiency of park energy management are improved.

The invention relates to the technical field of intelligent learning planning, and discloses an intelligent learning planning system based on multi-dimensional learning data driving. Comprising a main control module, a multi-modal data acquisition module, a data quality enhancement module, a multi-modal feature fusion module, a dynamic strategy planning module, a man-machine intention alignment module, a knowledge topology management module, an evaluation and federal optimization module and an auxiliary visualization module, and the main control module is used for coordinating operation of each module and data scheduling; the multi-modal data acquisition module acquires HRV, EDA and other physiological signals through a wearable device, records a fixation track and an alpha wave proportion through an eye tracker / electroencephalograph, and receives a user instruction in real time through a voice interaction device. According to the method, the dynamic adaptability is higher, full-process dynamic adjustment of stage division-parameter fine adjustment-load balance is achieved through hierarchical reinforcement learning and NSGA-III optimization, and a learning path can be flexibly adapted according to the real-time state (such as sudden fatigue and rapid knowledge point mastering) of a user.

The application discloses a product service network simulation platform based on multiple agents, and belongs to the field of service computing and simulation platform. The simulation platform comprises an agent template library, a digital twin interface, a topology manager and a simulation controller. The agent template library provides agents for representing roles in the product service network, and configures a predefined element attribute template for each agent. Each agent further comprises an agent memory set, which is divided into a short-term working memory, a long-term fact memory, a situational memory and a reflective memory. The digital twin interface acquires and records external simulation environment data in real time or periodically, ensures that the historical data is auditable, and inputs the data into the agents. The topology manager is used for mapping the interaction relationship of the roles in the product service network into the interaction relationship between the agents. The simulation controller is used for simulating each agent. The application breaks through the bottleneck of computational efficiency and scalability, and reduces the technical threshold of complex simulation construction and analysis.

This invention provides a satellite network topology management method and system based on feeder link switching. The method includes: constructing a continuously time-varying network topology model, and storing the availability sequence, available bandwidth sequence, and propagation delay of each link; responding to new service requests and obtaining the source satellite node and the target ground station; selecting the target feeder link and its effective connection period based on link status information; screening inter-satellite links that are continuously connected within the time period to form a candidate set, and calculating the average propagation delay and minimum available bandwidth of each link to construct a temporary topology; calculating the transmission path from the source satellite node through inter-satellite links and the target feeder link to the target ground station on the temporary topology; and locally updating the available bandwidth sequence of each link on the path according to the path and bandwidth requirements. This invention achieves efficient management of highly dynamic satellite-ground networks through feeder link event-driven and continuously time-varying modeling, improving service continuity and reducing management overhead.

The invention discloses a distributed computing system based on a fungal hypha network topology structure. The distributed computing system comprises a topology management module which generates a dynamic connection signal by simulating biological behaviors of fungal hypha growth and fusion; the signal diffusion module receives the dynamic connection signal and generates a routing diffusion signal, and the routing diffusion signal asynchronously propagates a state and an instruction between nodes by simulating a chemical signal transduction mode in a hypha network; the resource scheduling module receives the route diffusion signal and generates a task scheduling signal; the node collaboration module receives the task scheduling signal and generates a collaboration computing signal, and the collaboration computing signal is used for coordinating a plurality of computing nodes to jointly execute a single distributed task; the topology management module also receives a node state feedback signal from the node cooperation module. According to the distributed computing system based on the fungal hypha network topology structure, the problem that a distributed system lacks self-adaption, high robustness and low-energy-consumption consensus can be solved.

The application provides a multi-chip link management method and device in a multi-chip verification environment. A programmable topology management module is used to maintain a global link mapping relationship database, and then a link mapping pair representing a link is added to the global link mapping relationship database. When data transmission between chips is required, the receiving end chip identifier of the target link is determined through the global link mapping relationship database, and then the verification data of the data transmission request is routed to the receiving end chip through the target link. Since the link mapping pair is configured through the global link mapping relationship database, the connection relationship of the chips is decoupled from the hardware, thereby achieving dynamic management of the topology connection and the connection of the link, reducing the step of manual configuration, reducing the risk of human error, thereby reducing the verification cost and improving the verification efficiency.

The invention discloses an electroencephalogram auditory attention recognition incremental learning method, device and equipment and a medium, and the method comprises the steps: carrying out the preprocessing and time-frequency feature extraction of a multi-channel electroencephalogram signal, and obtaining a global time sequence context feature through a convolutional attention network; a dynamic self-organizing incremental neural network module is constructed, and similarity matching and topology management are carried out through a prototype node set; wasserstein distance is introduced to measure data distribution difference, and when a threshold value is exceeded, an adaptive expansion mechanism is triggered; key parameters are restrained by combining an elastic weight solidification mechanism, and catastrophic forgetting is prevented. According to the method, continuous online learning in a non-stationary electroencephalogram signal environment is realized, self-adaptive distribution drifting can be realized without retraining the whole network, the accuracy, robustness and long-term stability of auditory attention recognition are remarkably improved, and the method can be widely applied to the fields of brain-computer interfaces, intelligent hearing-aid equipment, neural rehabilitation and the like.

One example method includes receiving network topology information delivered by a topology manager, where the data center includes a plurality of servers, a plurality of electrical switches, and at least one optical cross-connect device. A data flow can be obtained. A routing policy can be configured for the data flow based on the network topology information, where the routing policy includes any one or a combination of the following routing policies: a first routing policy, where the first routing policy indicates to forward the data flow through an optical channel in the at least one optical cross-connect device; a second routing policy, where the second routing policy indicates to split the data flow into at least two sub-data flows for forwarding; or a third routing policy, where the third routing policy indicates to forward the data flow through an electrical switch of the plurality of electrical switches.

The invention relates to the crossing field of multi-agent control and space exploration technologies, and provides a multi-agent reinforcement learning formation control method and system for a rarefied Mars atmosphere in order to overcome the applicability defect of an existing multi-agent formation control method in an extreme Mars environment. The method comprises the following steps: firstly, sensing and accurately estimating a mars rarefied atmosphere state in real time, and providing reliable environment input for a control decision; secondly, an optimal control instruction is generated for each unmanned aerial vehicle through a multi-agent reinforcement learning framework; state information asynchronization caused by communication time delay and packet loss is processed through a communication and time delay compensation strategy, and real-time performance and stability of formation control are guaranteed; and finally, formation topology dynamic adjustment in a fault scene is realized through formation topology management and an adaptive reconstruction strategy, so that the fault-tolerant capability of the system to member faults is improved, and continuous execution of a Mars exploration task is ensured. The method can be widely applied to deep space exploration tasks such as Mars surface exploration, topographic mapping and resource exploration.

A topology management method, device, equipment and network are disclosed. The method is applied to the field of communication. A first device and a second device are connected through a port. The first device is located in a first network, and the second device is located in a second network. The first network and the second network are independent. The method comprises the following steps: sending a topology query request message to the second device, and receiving a topology query response message from the second device. The two newly connected devices send topology query request messages to each other, discover the topology structure of the network where the opposite end device is located, and perform a merging operation with the local topology graph to obtain a merged topology graph. That is, topology discovery can be completed through one topology query request. The topology graph of the network where the device is located is updated in real time, and the topology convergence speed is significantly improved.

The application discloses a peripheral dynamic loading and bus interconnection modeling method based on QEMUProxyAPI and belongs to the field of hardware modeling.The peripheral dynamic loading and bus interconnection modeling method based on QEMUProxyAPI comprises the following steps: establishing a ProxyAPI interface layer;constructing a device loading and topology management layer;creating and realizing devices in sequence according to a dependency relationship;automatically constructing a system topology and address mapping;realizing master-slave device interconnection;and realizing automatic signal connection.The application solves the problems that the prior art is prone to causing incompatible plug-ins, is difficult to realize module reuse, seriously affects maintenance and transplantation, and lacks rapid iteration capability.The application realizes cross-platform peripheral modeling interface standardization, guarantees that devices are connected on correct buses, enables IRQ / GPIO to be directly bound through names, improves the readability and maintainability of a system, and realizes cross-platform compatibility.

The invention relates to a vehicle network topology management method and related equipment. The method is applied to a vehicle, and a network topology structure of the vehicle comprises a main node and a first-level node connected with the main node. When it is detected that the vehicle is powered on, the main node sends a first topological node detection message to all first-level nodes in communication connection with the main node; and in response to the received first topological node detection message, the first-level node determines whether the first-level node itself is a newly added first-level node. And if the first-level node determines that the first-level node is the newly-added first-level node, replying a first newly-added node message to the main node. And the main node updates first-level network information corresponding to the network topology structure of the vehicle according to the first newly-added node message. According to the invention, the main node can update the first-level network information of the network topology structure according to the first newly-added node message, so that the network topology structure of the vehicle can be updated, and the vehicle can obtain the network topology structure belonging to the vehicle.

The present disclosure relates to techniques for determining optimal routing paths for computing devices in a network, including selecting an optimal gateway among a number of available gateways. The techniques include gathering data regarding characteristics of a network, including gateways and network access nodes (NANs) in at least one access network. The characteristics can include, e.g., supported frequency bands, communication protocols, signal-to-noise ratio, power, signal noise and quality, slicing information, and whether a network vender is a standalone network vendor or a non-standalone network vendor. In one aspect, the characteristics are obtained using the Mobile Broadband Interface Model (MBIM). The characteristics can be used by devices in determining routing paths based on requirements of individual flows and / or workflows of individual application instances.

The invention discloses a box-user relation automatic identification method and system based on an intelligent measurement switch, and the method comprises the steps: transmitting a feature signal through the intelligent measurement switch, receiving the response of an electric energy meter, and extracting a multi-dimensional feature comprising time domain, frequency domain and wavelet packet frequency band energy; the NTB zero-crossing detection technology of HPLC is utilized to identify the physical phase of the electric energy meter and perform ABC three-phase classification; the multi-dimensional features and the phase information are input into a pre-trained AI judgment model, the model adopts a CNN-RF mixed structure to perform feature screening, and a LightGBM classifier outputs a box household affiliation probability; based on the judgment result, three-phase fitting and abnormity elimination are carried out in combination with the impedance consistency principle of the loop in front of the meter, and a final box user topology is generated; and the identification result is actively reported to the marketing master station through the communication module. According to the invention, high-precision and full-automatic identification and dynamic maintenance of the box-user relationship are realized, and the intelligent level of topology management of the low-voltage power distribution network is remarkably improved.

The invention discloses a wireless Mesh network dynamic topology sensing method based on a distribution consistency protocol. The method comprises the following steps: initializing network nodes; judging whether the nodes can communicate or not based on the Euclidean distance between the nodes and a preset communication range, and establishing a neighbor relationship; each node periodically executes the Gossip protocol; the receiving node processes the Gossip message; and the node updates position information according to the own mobile model, recalculates the distance between the adjacent nodes, and updates the neighbor connection state. The method mainly solves the problems that network topology sensing is not timely and network connectivity is difficult to maintain in a node high-speed moving scene in the prior art. According to the method, the bottleneck of centralized control is avoided, the dynamic property, the stability and the adaptivity of wireless Mesh network topology management are remarkably improved while the overall connectivity of the network and the consistency of topology views are ensured, and the method is particularly suitable for a wireless self-organizing network environment in which nodes move frequently and the network state changes dynamically.

This invention discloses a distributed cache coherence system and method based on CXL tunnel transmission coherent bus, belonging to the fields of distributed computing and high-speed interconnect bus technology. Addressing the technical shortcomings of existing distributed architectures based on the CXL protocol, such as high cross-node cache coherence latency, inability to scale without interruption, and low deployment density, this invention encapsulates the coherent bus messages inside the master computing node into the CXL link layer Flit unit for tunnel transmission through a protocol conversion unit. It maps the remote CXL memory pool to the local coherent bus home node, and simultaneously includes a dynamic, uninterrupted topology management mechanism, a high-speed signal and power supply integrated interconnection interface, and an integrated electromagnetic shielding heat dissipation structure. This invention reduces cross-node memory access latency by more than 70% compared to existing solutions, achieves cluster availability of 99.999%, and increases deployment density by more than 40%. It can be widely applied in scenarios such as artificial intelligence computing clusters, heterogeneous computing resource pooling, and distributed memory databases.

The invention discloses a system and a method for automatically aggregating, decomposing and presenting a network topology and an event path, and the system comprises a topology management module which is used for managing basic data of the network topology, drawing collected network equipment information and a connection relation into a logical topology, and grouping topology nodes; the event management module is used for providing all management functions of security events from collection and extraction to visual presentation; the data storage module is used for storing related data generated by the system; and the view display module is used for displaying the network topology and the security events, and displaying automatic aggregation and decomposition of the network topology, the security events and event paths through detection and judgment of user view angle transformation and view scaling adjustment. According to the invention, the readability of the topology view is improved.

A physical security management system for securing a site monitored by security devices. The security management system comprises a topology database storing a topological model of the site; a network interface adapted for obtaining security data from the security devices; an input interface adapted for obtaining first user input from an input device defining first topological area and a relationship between the first topological area and at least one second topological area; a topology management engine coupled to the topological database, the topology management engine adapted for interpreting the first user input to configure the topological model to represent the first topological area and the relationship between the first topological area and the at least one second topological area; and an output interface adapted for causing display, via the display device, of at least part of the topological model following said updating thereof.

The invention relates to a method for verifying an Ethernet configuration of an automation system comprising a plurality of industrial devices, the method comprising obtaining a device identifier of each industrial device, an indication of a device port, and an indication of a device port connection. Device Ethernet parameters are obtained, and a system object model of the Ethernet configuration of the automation system is instantiated based on the device identifiers, the device ports, the device port connections, and the Ethernet parameters. The system object model allows to apply predefined rules to generate a graph model representing the Ethernet configuration. As known from graph theory, a loop detection can be applied to the generated graph model by a depth-first search. A verification result can be indicated based on a result of the loop detection. The invention also relates to a generic Ethernet object model, and to a topology manager.

The present application relates to the technical field of foundation pit monitoring, in particular to a self-repairing wireless sensor network foundation pit monitoring system and method, which integrates multi-source heterogeneous data collection, self-diagnosis processing, predictive failure management, network topology management and intelligent resource scheduling modules to achieve high-precision (±0.5mm) displacement monitoring. The system uses multi-dimensional information fusion and preprocessing to improve sensing capability, and uses a hierarchical health assessment system to comprehensively monitor node and network status, laying a foundation for fault prediction and active maintenance. The system can dynamically adjust network topology structure and optimize resource allocation using reinforcement learning algorithms, effectively performing node task allocation, communication power control and sampling frequency adjustment, and significantly improving the efficiency and reliability of foundation pit monitoring.

The embodiment of the application provides a routing method and device based on on-satellite processing, constructs a dynamic network topology according to a satellite constellation operation period and a link building rule by adopting a time slicing division mechanism. A gateway station pre-annotates time slicing and network topology corresponding relation data to a satellite node storage. After receiving data, the satellite node realizes autonomous routing calculation based on a network topology corresponding to a current time slicing, and determines a next hop forwarding node by adopting a shortest path algorithm. Through a dynamic routing recalculation mechanism of a relay node, data is guaranteed to be transmitted to a target node along an optimal path. The method effectively solves the deficiencies of traditional technologies in real-time routing, topology management and on-satellite processing, and significantly improves the performance of a satellite communication network.

This invention relates to the field of communication and computing technology, specifically to a computing power network architecture, computing power allocation method, and apparatus, comprising: a millimeter-wave communication layer, a distributed computing power layer, and an intelligent control layer; the millimeter-wave communication layer includes multiple millimeter-wave communication nodes for establishing high-speed wireless transmission links within a target area and acquiring channel quality parameters of the high-speed wireless transmission links; each millimeter-wave communication node employs hybrid beamforming technology and achieves high-directional transmission through a multi-antenna array; the distributed computing power layer includes multiple computing power nodes distributed according to a computing power resource gradient, for providing available computing power resources and reporting computing power status parameters; the intelligent control layer receives computing tasks, acquires channel quality parameters and computing power status parameters, and performs task offloading strategy calculation, computing power-aware routing calculation, and dynamic topology management based on the computing tasks, channel quality parameters, available computing power resources, and computing power status parameters.

This invention discloses a topology manager, relating to the field of optical quantum computing technology. The topology manager includes a topology matrix loading module, a topology self-checking module, and a topology update module. All modules are pure hardware integrated circuits, with no software processor involved in the core control throughout the entire process. The topology matrix loading module loads the topology matrix data, the topology self-checking module performs verification on the topology matrix, and the topology update module receives topology update instructions and atomically updates the topology matrix data. This invention implements topology management of optical interferometric networks through pure hardware, effectively improving the speed and reliability of topology loading, verification, and updating, and supporting dynamic topology updates during system operation.

The invention relates to a method for realizing network equipment management configuration through an FC bus, belongs to the technical field of communication, and solves the problem of complex network equipment management configuration in the prior art. The network device comprises a first main switching device, a second main switching device, branch switching devices and optical fiber nodes which are connected through an FC bus. The method comprises the following steps: when power-on initialization is carried out, a first main switching device and a second main switching device carry out topology management on the network device and determine a routing cascade and a device ID of the network device; the management node performs parameter query and parameter configuration on each network device through the FC bus based on the routing cascade and the device ID of the network device; and the management node is any one optical fiber node in network equipment. The management configuration of the network equipment is realized.

The invention discloses a dynamic networking system based on a hierarchical network structure and a topology management method thereof. The system comprises a primary network construction module and a secondary network construction module, the primary network construction module is used for constructing a primary mesh network as a collaborative network for the selected data center node by adopting a decentralized mesh network topological structure, so that metadata of the data center node can be spread in the collaborative network, and a user can check the health state and metadata information of the node; the secondary network construction module is used for constructing a tree network by taking each data center node as a root node and realizing hierarchical management on nodes for executing collaborative tasks in the data center nodes, and a father node in the tree network has metadata of all child nodes of the father node; the data center node and the node executing the cooperative task are communicated through a bidirectional SSL protocol, and node identity credible authentication and metadata synchronization are achieved. According to the invention, dynamic credible verification of node identities can be realized.

The invention belongs to the technical field of network security verification, and particularly relates to a virtuality and reality combined cyberspace anti-mapping verification system. According to the system, a dynamically evolvable simulation verification environment is constructed through a virtual cluster dynamic recombination technology, a resource pooling scheduling engine and an anti-mapping transformation strategy. The method specifically comprises the steps that a server resource pooling module dynamically allocates physical resources; the virtualization engine generates heterogeneous nodes including a virtual machine and a virtual router; the anti-mapping module resists network scanning through dynamic topological transformation and a traffic confusion strategy; the topology management module is used for maintaining network topology information of different experiments and surveying and mapping / surveying and mapping resisting data in the experiment process through a database; the real-time visualization module monitors the cluster state and supports environment snapshot import / export; and the user authentication module realizes hierarchical authority management. The method solves the problems that the static topology of an existing verification system is easily identified by surveying and mapping and the resource utilization rate is low, and the authenticity and the concealment of network security testing are remarkably improved.

Methods, systems, and devices for wireless communications are described. A network entity may receive an indication that a first entity is a first wireless access backhaul (WAB) node including a first mobile terminal function and a first network entity function. The network entity may perform one or more actions associated with operation of the first WAB node based at least in part on receiving the indication.

The invention relates to the technical field of all-optical networks, in particular to a network topology management method and device and related equipment. The method is applied to the controller. The method comprises the following steps: receiving link layer discovery protocol LLDP information reported by each piece of network equipment of a nanotube, and obtaining connection information of a light splitting box of the nanotube and each piece of network equipment; comparing the LLDP information with the connection information, and judging whether target LLDP information and connection information with repeated network equipment interfaces exist or not; and if it is judged that target LLDP information and connection information with repeated network equipment interfaces exist, network topology drawing is carried out based on other LLDP information except the target LLDP information in the LLDP information and the connection information. In this way, the topological link relationship between the network devices and between the light splitting box and the network devices in the FTTR scene after the light splitting box expansion network is added can be correctly displayed.

The embodiment of the invention provides a topology management method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of software and information security. The method comprises the steps that in response to starting of a topological graph management assembly, a topology editing page is generated, the topology editing page comprises a plurality of node assemblies, in response to editing of the node assemblies, topology nodes are generated, connecting edges corresponding to the topology nodes are determined, the topology nodes are marked with corresponding risk information, and the risk information is generated based on the topology nodes and the connecting edges. And generating a target topological graph, displaying the target topological graph and risk information corresponding to the topological nodes, traversing all the topological nodes in response to a saving instruction, converting a traversing result and original graph data of the target topological graph into data in a predetermined format, and uploading the data to a server. According to the embodiment of the invention, the topology drawing efficiency is improved by setting the topology editing page, the topology and risk information is visually displayed and reliably stored, the complete cycle management of the topology information is realized, and the efficiency of topology management is improved.

A system for infrastructure dependency mapping of an enterprise IT environment includes an application cross-dependency mapping engine configured to generate a multi-tier call hierarchy that, between and within each tier, maps the IT environment across a plurality of software applications of different types via which the IT environment is implemented. The system also includes a topology manager configured to, map the multi-tier call hierarchy to infrastructure elements of the IT enterprise environment, and thereby generate an infrastructure map.