240 results about "Global network" patented technology

The invention relates to the technical field of power system dispatching, and discloses a multi-agent reinforcement learning active power distribution network area coordination method and system, and the method comprises the steps: dividing a power distribution network into a plurality of areas, and each area is managed by an agent; collecting observation information; inputting the observation information into an upper reinforcement learning strategy network, and outputting control parameters; inputting the control parameters into a target function of the lower-layer local physical optimization model, and solving an output setting point of the equipment under the condition of meeting the safety operation constraint; constructing a De-POMDP problem, and obtaining a reward signal of each agent; a sequential updating mechanism is introduced, global network parameters are optimized, and corresponding decisions are obtained; and inputting the multi-agent decision into the global active power distribution network model to obtain the total operation cost, feeding back the total operation cost as an award to the reinforcement learning strategy network, updating global network parameters, and converging to obtain an optimal decision. According to the invention, regional wind-solar-storage multi-energy scheduling can be effectively optimized, and energy balance in the region is realized.

The invention belongs to the technical field of network security, and particularly relates to an intelligent association and global situation risk monitoring method based on multi-source data, which comprises the following steps: acquiring a multi-source heterogeneous data set; the multi-source heterogeneous data set is preprocessed, and preprocessed multi-source data is obtained; obtaining an attack behavior association graph according to the multi-source data, and performing anomaly detection on the association graph by using a graph neural network to obtain an explicit attack link and a potential attack link; obtaining a network security situation dynamic graph based on the explicit attack link and the potential attack link; and generating a risk assessment report according to the network security situation dynamic graph, triggering a corresponding security policy, and performing risk monitoring according to the security policy. According to the method, the accuracy and response speed of threat detection are remarkably improved, the global network security situation awareness capability is enhanced, and an intelligent solution is provided for security protection in a complex network environment.

The invention provides an SDN (Software Defined Network) inter-domain traffic engineering method based on reinforcement learning, which comprises the following steps of: deploying a data traffic demand monitoring platform and a control system, and constructing a global network topological graph; calculating a short link identifier for the link in the network and distributing the short link identifier to each network device; flow judgment is carried out, upward notification is carried out according to requirements, and pre-operation of intelligent routing is cooperatively completed; deploying a reinforcement learning model in the total intelligent body, outputting an optimal cross-domain path strategy to the cooperative controller, disassembling the optimal cross-domain path strategy into flow table rules which can be executed by each domain, and issuing the flow table rules to local controllers of related domains; and each local controller pushes the flow table configuration to the domain switching equipment to complete the forwarding decision of the flow. According to the method, a complete closed-loop process of flow measurement, intelligent decision making, cross-domain control and path issuing is realized, feasible reference is provided for actual deployment of an intelligent network, and the method has good engineering popularization value and is suitable for intelligent scheduling scenes such as an operator backbone network, an industrial internet and metro edge cloud.

The invention discloses a network communication dynamic optimization method based on multi-module collaboration, and relates to the technical field of network communication, a dual-mode communication module is deployed at each network node, and the network communication dynamic optimization method comprises the following steps: each network node broadcasts own existence information and power line channel characteristics through an HPLC (High Performance Liquid Chromatography) channel of the dual-mode communication module; each network node scans surrounding wireless networks through an HRF channel of the dual-mode communication module and reports own wireless channel quality information to the gateway; the global state sensing module collects all information and constructs a global network view containing physical topology and a channel quality map. A dual-mode cooperation mechanism, a machine learning prediction model and a dynamic decision strategy can adapt to complex dynamic environments such as power line noise fluctuation and wireless interference change, and communication parameters can be autonomously optimized without manual intervention; and meanwhile, the modular design is convenient to expand to a multi-mode communication scene, and has a wide application prospect.

The invention relates to the technical field of supply chain risk early warning, in particular to a supply chain risk early warning method based on deep learning, and the method comprises the steps: obtaining supply chain data, extracting a material circulation relation between supply chain nodes, constructing a node relation graph, and employing a graph neural network to achieve the aggregation of the features of the nodes and adjacent nodes. And space correlation characteristics in the global network are extracted, and a multi-stage transmission and diffusion path of the risk is effectively modeled. And then, splicing node space features and historical time sequence features, inputting the spliced features into a long-short-term memory network, dynamically capturing the evolution trend of node risks along with time, identifying periodic fluctuations and sudden anomalies, and improving the prediction precision of the risk trend. And finally, a multi-layer perceptron is adopted to carry out nonlinear mapping and feature fusion on risk time sequence features output by the long-short-term memory network, node risk scores are generated, real-time early warning of high-risk nodes is realized accordingly, and the accuracy and timeliness of supply chain risk monitoring are greatly improved.

The invention discloses a network optimization method based on an online conference, which relates to the technical field of real-time audio and video transmission, and comprises the following steps: in a transnational network, deploying monitoring probes at nodes participating in the online conference for monitoring network parameters such as network delay, bandwidth, packet loss rate and jitter in real time; the method comprises the following steps: processing network parameters and predicting abnormity by using a statistical analysis algorithm and a time sequence model to obtain network condition information, and then combining global network topology and using a reinforcement learning Q-Learning model and a graph neural network GNN topology prediction algorithm; according to the method, the network condition is monitored and predicted in real time, the optimal transmission path is output by using the reinforcement learning Q-Learning model and the GNN topology prediction algorithm, the bandwidth fluctuation is predicted through the LSTM, the packet loss rate is predicted based on the Bayesian network, the data transmission strategy is optimized, the network delay, the packet loss rate and the jitter are effectively reduced, and the network performance is improved. And the smoothness and the stability of the conference are improved.

The invention provides a network fault node automatic detection and roundabout path planning method, which comprises the following steps of: acquiring optical power and bit error rate of an optical fiber link, and recording abnormal time point and position information; obtaining a strong electromagnetic interference influence weight map; generating a deterioration trend curve; obtaining a health degree score of each optical fiber segment, and generating a health degree distribution map; probability distribution of fault nodes is determined, whether the nodes are fault points is judged according to the probability distribution, and a fault node position set is generated; obtaining a roundabout path planning scheme; and calculating a global network health state perception score to obtain an optimized global network health state diagram. The invention further discloses a corresponding storage medium. According to the invention, the reliability and stability of the optical fiber network can be effectively improved, and the efficiency and accuracy of fault detection and processing can be improved.

The invention provides a hierarchical deep reinforcement learning routing protocol method based on a multi-link ad hoc network, relates to the technical field of communication routing, and solves the problem that the calculation efficiency in the current multi-link ad hoc network is degraded. The method comprises the following steps: firstly, constructing and dynamically updating a global network view for all nodes in a network, and further constructing a route selection model which is divided into a high-level controller and a low-level controller; a high-level controller plans a route from a global perspective and balances a global load, and a low-level controller selects a target node according to a planning result of the high-level controller and distributes an optimal communication link for the target node in combination with link state information; training and optimization of the network of each controller are carried out independently, external rewards are introduced to a high-level controller, and internal rewards are introduced to a low-level controller; the external reward is used for optimizing the overall performance of the high-level controller; the internal reward is used as an index value of the low-level controller for feeding back the link state in real time, and collaborative optimization of the high-level controller and the low-level controller is achieved.

The embodiment of the invention provides a network security validity verification and quantitative evaluation method and system, and relates to the technical field of network security, and the method comprises the steps: obtaining global dynamic threat intelligence and a multi-dimensional global network security risk data source, and carrying out the preprocessing; constructing a global feature engineering system based on heterogeneous information network atlas and sequence analysis, forming a feature vector matrix, and mapping the feature vector matrix into an index state vector; inputting the feature vector matrix, the index state vector and the external environment information vector into an evaluation model, dynamically adjusting the weight of the feature vector matrix of each dimension, and outputting the validity score of each safety control point; based on the score, calculating a safety effectiveness index based on a time decay factor; identifying a weak link based on the index, and performing simulation verification to obtain a simulation attack actual measurement result; and an error vector is constructed based on the result and the validity score, and parameter adjustment and weight calibration are carried out. According to the scheme, the accuracy and the real-time performance of network security evaluation are improved.

Examples provide improved methods for managing wireless network connectivity for a mobile device. Examples include receiving a network map that defines geographic availability of a first wireless network; determining that the first wireless network is accessible within a travel segment of a travel plan based on comparing geographic location data associated with the travel segment to the geographic availability of the first wireless network from the network map; creating a network plan that includes the travel segment and an associated connectivity waypoint, the connectivity waypoint defining when to alter connectivity status with the first wireless network; and causing the mobile device to alter connectivity status with the first wireless network based on proximity to the connectivity waypoint.

The invention discloses a wireless data uploading method and system for an industrial internet of things, and relates to the field of wireless data processing, and the method comprises the steps: firstly, comprehensively considering the inherent service attributes of data to determine the initial service priority of the data; meanwhile, terminal side sensing data and global network state data obtained from the gateway are fused, and a more accurate and comprehensive network quality score is calculated through double-source information. Finally, the initial priority and the network quality are dynamically combined according to the two key dimensions, and a final transmission strategy is generated. According to the method, a data uploading decision is no longer static and one-dimensional, but a two-dimensional dynamic decision which can be adaptively adjusted according to a real-time network condition, so that the sending opportunity or mode of the high-priority data is intelligently adjusted when the network is congested, the blocking of key services due to blind sending is effectively avoided, and the service quality is improved. And the robustness and the high efficiency of data uploading in a complex industrial environment are ensured.

The invention discloses a machine learning enhanced real-time hydraulic modeling method for a water supply network. The method comprises the following steps: acquiring position numbers of sensors in the water supply network and correspondingly acquired historical hydraulic data; based on position numbers of sensors in the water supply network and time nodes in an acquisition period, constructing a sensor sampling matrix corresponding to each monitoring target, and filling historical hydraulic data into the corresponding sensor acquisition matrixes to form a training set; constructing an initial model; constructing a physical constraint loss function and training the initial model by using the training set to obtain a hydraulic prediction model for predicting a global hydraulic state; and inputting the sensor acquisition matrix of the monitoring target in the water supply pipe network into the hydraulic prediction model to output global pipe network hydraulic data. The invention further provides a real-time hydraulic monitoring system for the water supply network. The model constructed by the method provided by the invention can realize real-time estimation of the hydraulic state of the water supply network, and provides accurate data support for daily maintenance of the water supply network.

The invention relates to a congestion control method and device for network equipment, computer equipment and a medium. The method comprises the following steps: acquiring global network state information of the network equipment; and performing multi-dimensional congestion measurement calculation on the global network state information by adopting a preset weighting function to obtain a congestion measurement value of each node. And identifying one or more bottleneck nodes and / or one or more congestion paths from the network equipment based on a set congestion metric threshold value and each congestion metric value. And determining target path configuration from the plurality of available paths according to each bottleneck node and / or each congestion path. And performing flow distribution on each node on the one or more available paths according to the target path configuration. According to the method, the global network state information of various network devices is comprehensively considered, and multi-dimensional congestion measurement calculation and dynamic path selection are combined, so that cross-device end-to-end congestion control is realized, and the overall congestion response capability and reliability of the network devices are improved.

The invention relates to a side cloud collaborative adaptive workflow scheduling method and system, and belongs to the technical field of distributed computing and artificial intelligence. The method comprises the following steps of: firstly, in a macroscopic candidate screening stage, reducing problem granularity through task clustering, and obtaining balance between utilization and exploration based on a weighted distance probabilistic preferential strategy; then, in a collaborative scheduling decision-making stage, a global network state diagram is constructed through a graph neural network, deep spatial features of nodes and neighborhoods of the nodes are extracted, context-aware state representation is formed, and a reinforcement learning agent makes an optimal collaborative decision in multiple options such as local execution, edge migration or cloud unloading according to the state representation; and finally, in a local adaptive optimization stage, performing fine-grained optimization after the task is issued, dynamically adjusting a scheduling frequency and a multi-target weight through an online learning mechanism, realizing balance between a task deadline and a resource utilization rate, and ensuring efficient and robust execution of a node level.

The invention discloses a remote sensing image change detection method, and relates to the technical field of computer vision and image processing, and the method comprises the steps: inputting a preprocessed dual-time image of a target region into a remote sensing image change detection model, and outputting a change probability graph of the target region; the remote sensing image change detection model is obtained by training a global network model by adopting a training set, and the global network model comprises an initial network model and a classifier; the initial network model is constructed on the basis of a transform model; performing thresholding processing on the change probability graph of the target area to obtain a binary change detection graph of the target area; the initial network model comprises a pyramid segmentation attention feature enhancement module, a cross-spatio-temporal feature interaction module, a cross-scale attention transformer module and a cross-level pyramid transformer module. According to the invention, the accuracy and reliability of remote sensing image change detection are improved.

The invention relates to the technical field of network slicing, and discloses a wireless network multi-link communication method based on dynamic link configuration. The method comprises the following steps: collecting state data of heterogeneous links such as cellular links, Wi-Fi links and satellites in real time, and constructing a global network state view; analyzing the network slice SLA and converting the network slice SLA into a quantitative performance constraint; predicting the future performance of the link by using a gating circulation unit neural network; generating a global optimal data flow routing and distribution strategy meeting the QoS (Quality of Service) requirements of the slices in the central controller based on reinforcement learning; and compiling the strategy into a configuration instruction and issuing the configuration instruction to the terminal and the access point for execution. The system comprises a state sensing module, a strategy analysis module, a prediction modeling module, a strategy generation module and a configuration execution module. By means of predictive planning and intelligent decision making, dynamic, fine and on-demand scheduling of heterogeneous resources is achieved, and the network resource utilization rate and the multi-service service quality guarantee capacity are remarkably improved.

A predictive artificial intelligence (AI) engine is trained phase offsets measured between global network satellite system (GNSS) derived clocks and precision timing protocol (PTP) derived clocks and network parameters including network impairment metrics in a packet network. The predictive AI engine may predict which PTP input source should be selected by a network element, phase offset(s) to be applied to the PTP input source, and which network element(s) should apply phase offset(s). Other embodiments are disclosed.

The invention relates to the field of forged image detection, and provides a forged image detection method and device, a medium and a product, and the method comprises the steps: dividing an input image into a plurality of local regions, and constructing a region dependence graph of the local regions; extracting local style features from the region dependence graph by using a local network model; extracting global style features of the input image by using the global network model; performing attention fusion on the local style features and the global style features by using an attention model to obtain a fusion vector; performing image forgery detection on the fusion vector by using a classifier; wherein the local network model, the global network model, the attention model and the classifier are optimized through training. According to the invention, high identification accuracy and robustness can be maintained in detection scenes of scarce samples, local detail forgery and cross-domain forgery.

The invention belongs to the technical field of power networks, and particularly relates to a power network vulnerability analysis system and method based on virtual attack and defense deduction, and the system comprises a data collection module which is used for collecting various data of a power network, the various types of data comprise network topology structure data, equipment configuration data, operation state data and security log data; and the threat intelligence integration module is used for collecting and integrating global network security threat intelligence and establishing a data interface with a threat intelligence platform to realize automatic synchronization and updating of the threat intelligence. Through continuous virtual attack and defense deduction, an attack and defense strategy is optimized in combination with a machine learning algorithm, a novel attack means can be simulated, and the power network security state can be monitored in real time. Even if an unprecedented attack mode appears, potential threats can be quickly identified through attack and defense confrontation, the discovery capability of novel and unknown vulnerabilities is greatly improved, and network security risks are responded in time.

The invention relates to the technical field of education big data analysis, in particular to a student information intelligent management system based on big data, comprising a data convergence module used for converging multi-source heterogeneous behavior data streams of target students in campus Internet of Things and interaction logs of the target students in a digital learning platform in real time to obtain an original time sequence data vector set; and the feature generation module is used for carrying out cross-modal time domain alignment and wavelet coherent transformation on the original time sequence data vector set so as to generate a multi-scale spatial-temporal feature map representing the individual learning and living states of the students. According to the invention, global network time protocol synchronization timestamp synchronization and Kalman filtering interpolation are introduced through the data aggregation module, and the feature generation module adopts remoley wavelet transform and wavelet coherence spectrum analysis, so that the phase locking relationship of online interaction and offline behaviors of students on a time-frequency domain can be quantified; therefore, the learning and living states of the students can be more comprehensively described.

The invention discloses a network resource allocation method, electronic equipment and a storage medium, and the method comprises the steps: taking a current excitation parameter issued by a global decision model in a cloud platform as a weighted item of a reward function of a domain-level decision model; the decision model in a single domain is controlled to realize the optimal local network resource and consider the optimal global network performance of the cross-domain network at the same time; according to the global decision model, quantizing the global income index after each candidate operation is executed so as to determine a global resource allocation strategy; and finally, the network resource allocation state of each data center is adjusted through the network controller deployed in each data center, and the domain-level decision model is deployed in a plurality of data centers in different regions. Through the method, the technical problem that cross-domain network resources in a cloud environment cannot be reasonably allocated in related technologies is solved, and the technical effect of intelligently and cooperatively allocating local network resources and global network resources in a domain is realized.

The invention provides a training method of an index recommendation model and an index recommendation method and system.The training method comprises the steps that workloads and a candidate index set are obtained, and in the nth iteration, for each sub-network, recommendation indexes corresponding to the workloads are determined from the candidate index set so as to determine the local gradient of each sub-network, the index recommendation model comprises a plurality of sub-networks, updates parameters of the global network based on the local gradients corresponding to the sub-networks, and updates parameters corresponding to the sub-networks based on the updated parameters of the global network, the index recommendation model comprises the global network obtained through training convergence, and the index recommendation model is used for recommending index configuration for the to-be-recommended workloads. The training speed is greatly increased, and the stability and generalization ability of the index recommendation model can be improved.

The invention discloses a network load balancing distributed strategy optimization method. The method comprises the following steps: acquiring node load data; a gravity and repulsive force field is simulated to dynamically adjust load distribution; each data center node deploys a load balancing agent, and a task allocation strategy is dynamically adjusted through multi-agent reinforcement learning training; resource allocation optimization: based on a resource allocation optimization target, optimizing allocation from tasks to nodes with the target of minimizing data transmission cost and calculation delay and satisfying resource constraints at the same time; and the load index and the actual task delay of each node are monitored in real time, and the overall performance of the system is evaluated. The method can adapt to load fluctuation of the ground; the reward function ensures that the proxy not only optimizes local performance in a high dynamic scene, but also maintains the stability of a global network structure; the load attention mechanism enables the agent to dynamically pay attention to nodes with lower load and better delay.

The invention discloses an Internet of Things card intelligent management method and system based on multiple operators, and relates to the field of multi-operator network collaborative management, and the method comprises the steps: collecting network service quality data, a network state, a multi-operator network and an available bandwidth index, encrypting a device identifier and a service type, and transmitting the encrypted device identifier and service type to an intelligent management platform; distributing a virtual user identification module identity, and generating a terminal exclusive key; an operator trains a local long-short-term memory network quality prediction model based on local network data to obtain a model gradient, and encrypts the model gradient generated by terminal exclusive key training to obtain an encrypted model gradient; and performing decryption and aggregation calculation on the encryption model gradient through a security aggregation algorithm to generate global network quality prediction model parameters. According to the invention, through an innovative federal learning encryption gradient aggregation mechanism and a block chain intelligent settlement system, efficient collaborative management of the Internet of Things cards of multiple operators is realized.

The invention discloses a congestion-aware network-on-chip fault-tolerant routing method and a congestion-aware network-on-chip fault-tolerant routing system, and relates to the technical field of computer network communication. Comprising the steps of 1, creating an on-chip network fault-tolerant routing system, 2, deploying a network monitoring module at each router node, and generating routing configuration based on real-time data, and 3, when a network is congested and / or failed, measuring the congestion degree through the network monitoring module according to the size of an idle cache at an input end, and determining the weight W of a path according to the congestion degree; step 4, collecting link and routing node fault information and an input cache state through the network monitoring module, reporting the information to an upper computer management module, updating global network state information by the upper computer management module according to received data collected by the network monitoring module, generating routing configuration in combination with a routing rule, and sending the routing configuration to the network monitoring module; and real-time routing configuration is issued to each routing node through the configuration module.

The application discloses a kind of virtual-real fusion registration satellite internet digital twin deduction evaluation methods, comprising: S1.Satellite internet global network data is acquired, network data is collected and time synchronization interpolation is carried out, and network equipment data matrix is constructed;S2.based on network equipment data matrix, establish satellite network basic routing topology graph;S3.based on satellite network basic routing topology graph, construct by user satellite network dynamic service demand vector, establish satellite network dynamic routing model;S4.based on network dynamic routing model, establish satellite internet digital twin deduction model;S5.based on internet digital twin deduction model, introduce real data and carry out pseudo-real correction, realize the virtual-real fusion digital twin dynamic deduction of all stages;S6.multiple dimensions index and evaluation function are established, and score is calculated.The application can overcome virtual-real mapping distortion, evaluation dimension single and dynamic adaptability insufficient and other problems, complete accurate deduction evaluation to satellite internet.

The present invention belongs to the field of aerospace technology and relates to a digital twin system for low-orbit giant star constellations and a construction method thereof. The system includes a data management module that comprehensively manages the real-time data, vertical data, horizontal data, simulation data, and fusion data of the giant star constellation system; a model management module that dynamically constructs and comprehensively characterizes the geometric, physical, behavioral, rules, and constraint characteristics of complex physical systems from different dimensions, different spatial scales, and different time scales; an information management module utilizes these multi-scale and multi-level characteristic information to perform local to global network reconstruction of the low-orbit giant star constellation system and restore the complete information network; a collaborative coupling mechanism of data interconnection, information exchange, and model interoperability is adopted to achieve efficient and real-time monitoring and management, providing a solution for digital, visual, and intelligent supervision.

The invention discloses a drug recommendation method based on a beta variational auto-encoder, and relates to the technical field of digital medical treatment, and the method comprises the steps: carrying out the extraction and fusion enhancement of diagnosis information and operation information in treatment record data through the combination of a GRU network and a bidirectional attention mechanism; patients and drugs are regarded as nodes, and drug use records of the patients are regarded as hyperedges, so that a heterogeneous hypergraph is constructed, drug combination information, patient individual differences and a complex association relationship between the patients and the drugs are reserved to the maximum extent, and the model is more accurate when processing new patients and rare illness conditions. A global network structure can be better utilized to find a potential medicine combination mode; a beta variational auto-encoder architecture is adopted to obtain potential features of a patient and a drug, and a drug combination required by the patient is predicted according to the embedded features of the patient and the embedded features of the drug, so that the stability of the model is improved.

The invention relates to the technical field of cloud computing resource management, and discloses a storage and computing resource dynamic recombination management method, system, device and medium, which comprises the following steps: constructing a hierarchical management architecture comprising a local control center and a global network control center, constructing a uniform resource topology view of the whole network through a heartbeat mechanism and metadata reporting, automatic registration and state monitoring of calculation and storage resources are realized; multi-target task scheduling is carried out by adopting an improved genetic algorithm fused with a greedy strategy, and on the premise of meeting service quality constraints, localization processing of calculation tasks is preferentially realized to reduce network overhead; an elastic telescoping mechanism based on an ARIMA-LSTM mixed time sequence prediction model is introduced, and through deep learning of historical load data, a load peak value is pre-judged in advance and the scale of a resource pool is dynamically adjusted. According to the method, the global utilization rate of heterogeneous resources is effectively improved, and lossless rapid expansion and dynamic recombination of storage and calculation resources are realized.

The invention relates to the technical field of robot control, in particular to a multi-mechanical-arm electric power cooperative adjustment system and method based on federal reinforcement learning, and the method comprises the steps that a local controller receives sensor data, generates state information and generates a control signal through a local Q network model; the edge computing server collects local Q network model parameters, generates global Q network model parameters and distributes the global Q network model parameters; the two-dimensional reward calculation module calculates a reward value based on the current and temperature data, and the self-adaptive weight adjustment module dynamically adjusts the reward weight; an action mask module determines an effective action set, and a state prediction module predicts a state after action execution; the momentum buffer module records historical learning experience to adjust the learning rate; the parameter aggregation module calculates aggregation weights to generate global parameters, and the knowledge migration module controls parameter distribution according to model performance differences; a federal reinforcement learning framework is adopted, and a two-dimensional reward and adaptive weight adjustment mechanism is adopted, so that balance between short-term performance and long-term stability is achieved.