151 results about "Global network" patented technology

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.

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 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.

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 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 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 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 voltage regulation and control of a power distribution system, and particularly discloses a voltage regulation and control method and system of a low-voltage flexible interconnection power distribution system. On-load voltage regulating transformer and capacitor bank action decisions considering robustness and economical efficiency can be made, and the influence of uncertainty of renewable resources on voltage stability can be effectively dealt with; the SOP voltage reactive droop control parameter optimization model is constructed by taking the minimum node voltage deviation and the system network loss as targets, and the SOP voltage reactive droop control parameter optimization model based on intraday rolling optimization can ensure that the node voltage is stable in the real-time voltage control stage of the SOP, and also considers global network loss optimization, so that the global performance of the system is improved. According to the method, dynamic characteristics and interaction influences among different voltage regulating devices are considered, sequential cooperative control among various resources is realized through day-ahead and intra-day distributed optimization and centralized local multi-stage voltage control, and the voltage out-of-limit problem of the flexible interconnection power distribution system is effectively solved. And the system voltage control effect is improved.

A method for generating a personalized model includes receiving one or more personal data samples from a user. A prototype of a personal identity is generated based on the personal data samples. The prototype of the personal identity is trained to reflect personal characteristics of the user. A network graph is generated based on the prototype of the personal identity. One or more channels of a global network are pruned based on the network graph to produce the personalized model.

The invention discloses an unmanned aerial vehicle cluster dynamic area coverage method based on deep reinforcement learning. The method comprises the following steps: constructing a multi-physical field coupling simulation environment comprising node motion, a directional antenna, a space channel and a radar detection model; based on the environment, converting a dynamic coverage problem form into a partially observable Markov decision process, a defined state, observation, action and reward mechanism, performing multi-agent training by adopting a centralized training decentralized execution framework, evaluating a joint action by using a global Critic network during training, and storing interactive experience by using an experience playback buffer area; based on a priority experience playback mechanism, according to a time sequence difference error and a reward value, an experience sampling probability is calculated, samples are extracted, Critic and Actor networks are updated in sequence, a decision model is deployed to an unmanned aerial vehicle cluster after training is completed, and each unmanned aerial vehicle executes an area coverage task in a distributed manner, so that efficient and low-risk communication coverage can be realized in a complex threat environment. The communication quality is improved; and the detected probability is reduced.

This invention provides an AI-based method and system for collaborative protection of routers, gateways, and cameras in the field of network security technology. The method includes: Step S1, deploying localized AI anomaly detection models in network devices and cameras respectively; Step S2, the server generates and distributes a unified security protection policy to the network devices, and the network devices distribute the security protection policy to at least one camera within the local area network; Step S3, the AI ​​anomaly detection model in the network devices monitors global network traffic in real time, and the AI ​​anomaly detection model in the cameras monitors its own device behavior in real time; when any AI anomaly detection model identifies an anomaly, it generates an alarm message and reports it to the network devices; Step S4, the network devices determine the attack risk level based on the alarm message and perform interception operations based on the attack risk level. The advantages of this invention are: achieving accurate and real-time perception and collaborative handling of unknown threats, while taking into account both privacy protection and deployment efficiency.

This invention discloses a security threat perception and detection method for global network devices. It simultaneously collects three types of data: network traffic, behavior logs, and attack characteristics, forming multi-dimensional factual evidence. The method utilizes a firework algorithm to optimize the deployment of logical monitoring points (feature nodes) in the virtual network and calculates the dynamic intensity of threat propagation at each point, thereby constructing a node-level threat field that quantifies the spatial distribution of threats. Subsequently, peak, mean, and dispersion indicators are extracted, and behavioral load, threat polarization, and cumulative threat indicators are calculated from the raw data, forming a six-dimensional vector. This vector is input into a pre-trained global threat level classification model, outputting a discrete threat level. Finally, based on this level, firewall rules, intrusion detection feature libraries, and other protection strategies are dynamically adjusted to achieve automatic matching of security configuration and threat posture.

In a data transmission control method, one or more pieces of identification information are added to determine an interface resource object for forwarding a data packet on an interface of a network device. The added one or more pieces of identification information include one piece of global identification information. The global identification information may correspond to a network slice, and different network slices correspond to different values of global identification information. A global network identifier corresponds to one or more interface resource objects. One interface resource object may be occupied by one network slice alone, or one interface resource object may be jointly shared by a plurality of network slices.

The application discloses a network slice arrangement method and device, equipment and a computer readable storage medium, the network slice arrangement method comprises: obtaining a preset scheme database and a cost database, determining a sub-domain network scheme combination in the scheme database according to input SLA demand; according to the preset optimization dimension and the cost database, the sub-domain network scheme combination is optimized, and a global network scheme is obtained; extract the sub-domain network capability parameter group in the global network scheme, construct a global SLO parameter group according to the sub-domain network capability parameter group, detect whether the global SLO parameter group matches the SLA demand; if matching, output the global network slice configuration template corresponding to the global SLO parameter group, and / or the sub-domain network slice configuration template corresponding to the sub-domain network capability parameter group. The application realizes automatic slice arrangement of network slice.

The invention relates to the technical field of wireless communication, and discloses a network-free video transmission scheme implementation method, which comprises the following steps of: firstly, calculating a fitness score according to comprehensive performance parameters such as residual electric quantity and computing resources of nodes through a distributed election algorithm, and electing a unique main control device; then, the main control equipment collects neighbor list information of nodes of the whole network, constructs a weighted global network topological graph, and calculates an optimal relay path with the lowest link cost for a video transmission task based on the topological graph; and finally, the main control equipment generates and broadcasts a global unified time division multiple access time slot allocation table, and accurately allocates conflict-free sending and relay time slots for each node on the optimal path. According to the method, the flexibility of distributed election and the certainty of centralized scheduling are combined, network data collision is effectively avoided, and the reliability and the real-time performance of video transmission in a dynamic and network-free environment are remarkably improved.

The invention provides a fog computing unloading method and system, and relates to the technical field of communication, and the method comprises the steps: based on a received computing task, an access point determines a computing task view according to the resource state information of a fog node; on the basis of service quality evaluation of the fog node in the view of the calculation task, it is determined that the target node is unloaded to execute the calculation task, and service quality evaluation comprises a reputation evaluation angle; after completion, generating a task completion record and broadcasting the task completion record to the whole network transaction pool; on the basis of the released proof-of-work calculation target, after the fog node collects transaction assembly candidate blocks from the whole-network transaction pool, proof-of-work calculation is carried out; the fog node which is fastest in completion broadcasts the candidate block containing the calculation result to the whole network; when all the nodes pass verification, adding the candidate blocks to a local block chain account book; and the access point updates an evaluation result of the fog node in the aspect of reputation evaluation based on the reputation evaluation data in the local block chain account book. The task allocation and execution efficiency and the allocation accuracy are improved.

The application provides a multi-value chain evolution training prediction method and system and a storage medium, comprising: generating a feature vector of a node based on local original data of a client and adjacent clients of the client, and the feature vector and node information of each node of the client forming distributed time sequence diagram data; calculating local network parameters of a distributed federal time sequence diagram neural network model at a current time, and sending the local network parameters to a server, the client having a distributed federal time sequence diagram neural network model established in advance; the server obtaining global network parameters according to the local network parameters and broadcasting the global network parameters to all clients; the client updating network parameters of the distributed federal time sequence diagram neural network model by using the global network parameters, the distributed federal time sequence diagram neural network model receiving distributed time sequence diagram data at a next time for learning, and outputting a predicted value of an edge at the next time. Therefore, future relationships among companies in a multi-value chain and whether a company is going to extinction can be predicted.

The present application relates to a kind of high-efficiency screening methods for risk substances in animal-derived food, comprising the following steps: 1) after the pretreatment of the animal-derived food sample to be tested, non-target detection and analysis are carried out using chromatography-mass spectrometry platform, and original chromatography-mass spectrometry data are obtained;2) by global network optimization, filter food endogenous components, while using quartile range method to remove various background interference, extract suspicious risk substances;Suspected risk substances that meet the conditions of global network optimization and quartile range method filtering at the same time are retained;3) by database search and standard comparison, the structure of suspicious risk substances is annotated and qualified.The present application effectively removes the interference of food endogenous components on risk substance screening, improves the efficiency of non-target screening.On the other hand, it has significant advantages in the screening analysis and efficient locking of unknown risk substances in animal-derived food.The present application has the advantages of high screening accuracy and low false positive rate.

The present application relates to the technical field of communication, and provides a 5G network health monitoring method, device, equipment and medium, which can construct a 5G network health monitoring model including a 5G private network layer model, a sub-domain layer model and a network element device layer model based on a pre-constructed basic index library, a 5G network health monitoring model framework and an application scenario, and perform health monitoring on the 5G network based on the 5G network health monitoring model, so as to refine, layer, classify and evaluate the network health degree from the whole to the part, layer by layer, which can not only evaluate the global network health degree of the 5G private network, but also evaluate the network health degree of each sub-domain and each device in a more fine-grained manner, and provide comprehensive network health degree real-time evaluation capability for 5G private network operation and maintenance.

The invention discloses a multi-agent-based resource scheduling method, system and device and a medium, and belongs to the field of resource scheduling, and the method comprises the steps: receiving local scheduling actions reported by a plurality of agents in a network and corresponding network state information; constructing a global network state view based on each local scheduling action and each piece of network state information, determining a scheduling conflict result among a plurality of agents based on the global network state view, and grading the network influence degree of each agent based on the scheduling conflict result to obtain a conflict grading result, determining an optimization priority and a global constraint condition according to a conflict grading result; and issuing the optimization priority and the global constraint condition to each agent to enable each agent to generate a global scheduling action, and performing resource scheduling based on the global scheduling action. Therefore, by implementing the method and the device, uniform distribution of resources in a multi-agent distributed network environment can be realized.

The application discloses a double-reliability RVFL bat optimization wind power interval prediction method and system, specifically for: preprocessing wind farm historical power data, constructing a data set; establishing a basic RVFL, a cascaded enhanced RVFL and a direct connection enhanced RVFL candidate model, expressing the upper and lower bounds of the prediction interval as a linear combination of enhanced features and output weights; in the first stage, the hidden layer parameters are fixed, the output weights are solved by using an opportunity constraint optimization model containing a training set and a validation set coverage constraint, and the optimal basic model is selected according to the validation set SCORE index; in the second stage, the model parameters are used as elite prior solutions, a mixed initialization bat population is constructed by combining random exploration individuals, and the global network parameters are optimized; and the prediction interval is output on the test set and evaluated. The application improves the generalization coverage ability by double-reliability constraint, enhances the scene adaptability, and optimizes the network parameters by using a mixed initialization bat algorithm.

The present disclosure provides a deep reinforcement learning (DRL) based dynamic network traffic management system including a LAN router, a plurality of WAN routers, a network switch, and a GNAT controller configured to measure one or more traffic states of a plurality of data flows, obtain an expected reward at the current time point, obtain the one or more traffic states to input to a DRL model to provide an expected reward of each data flow estimated for a next time point, obtain a target reward at the current time point, adjust parameters of the DRL model, predict a plurality of long-term rewards using the trained DRL model, select one of the plurality of long-term rewards, and adjust the bandwidth assigned to each data flow based on the selected long-term reward.

The invention provides a node identification method and device based on graph classification and a related product, and relates to the technical field of data processing. The method comprises the following steps: calling a preset connected sub-graph recognition algorithm to recognize one or more connected sub-graphs of which the node number is greater than a set threshold value in a social network to obtain a connected sub-graph set; extracting a user node in the connected sub-graph, and extracting a local structure of the user node in the global network, namely a user case sub-graph taking the user node as a center; then classifying the user case sub-graphs by using a pre-trained graph convolutional network dichotomy model; in this way, user node recognition is converted into recognition of the local network where the user node is located, the user case sub-graphs with the user node as the center are classified through the pre-trained graph convolutional network dichotomy model, and therefore the classification result of the user node is obtained, the calculation amount is greatly reduced, and the recognition accuracy and efficiency are improved.

The application relates to the technical field of data processing, and discloses a parking behavior analysis method and system based on data mining and a storage medium. The method comprises the following steps: collecting data through a parking sensor network to construct a parking behavior basic data structure, a local interest point database and a global network configuration database; adopting a local-global feature interaction matrix algorithm to perform fusion processing to obtain a fusion feature matrix and a dynamic weight vector; performing clustering through a fusion density clustering algorithm to obtain a fusion clustering result matrix; and performing pattern recognition based on double-layer space-time mode mining to obtain a parking behavior space-time fusion mode library and a demand prediction result. The application solves the technical problem that an existing parking behavior analysis method based on data mining cannot effectively fuse local interest point features and global network configuration features, leading to a lack of significant correlation between analysis results and actual parking use modes.

This application discloses a trusted access and network orchestration method, device, medium, and product for computing power nodes, including: acquiring information of nodes to be accessed and generating raw access data; performing pre-access trusted verification on nodes to be accessed and generating trusted verification records; generating an access profile containing node capabilities and trusted status based on the raw access data and trusted verification records; constructing a dynamic constraint model based on business intent, policy constraints, resource constraints, and network status, and performing joint scoring on candidate access domains and candidate paths based on the dynamic constraint model to screen candidate schemes; evaluating candidate schemes in conjunction with the impact of the nodes to be accessed on the global network topology and generating access orchestration results; sending the access orchestration results to the execution side to execute access and continuously monitoring; and updating the dynamic constraint model based on the drift state when a state drift event is detected, triggering re-verification, re-decision, and re-orchestration.

The embodiment of the invention relates to a frequency hopping interference resource allocation method under a reconnaissance error condition. The method comprises the following steps: constructing a frequency hopping interference resource allocation problem under the reconnaissance error condition according to a communication confrontation scene; solving a frequency hopping interference resource allocation problem by using an asynchronous deep reinforcement learning algorithm; constructing a policy network, wherein the policy network comprises a global network and a plurality of threads connected with the global network; training the strategy network by using the plurality of interference tasks to obtain a plurality of strategy gradients of the plurality of interference tasks corresponding to each thread; performing projection decomposition processing on the plurality of strategy gradients of each thread by using a gradient conflict resolution mechanism to obtain a corrected gradient of each thread; and updating the network parameters of the global network by using the plurality of correction gradients corresponding to the plurality of threads to obtain an optimized distribution strategy network. The distribution strategy network obtained by the embodiment of the invention can be directly generalized to an interference task for a real frequency hopping target within a certain reconnaissance error range.