19 results about "Hierarchical routing" patented technology

This invention discloses a domain-specific intelligent routing method for large-scale low-Earth orbit (LEO) satellite networks, belonging to the field of satellite communication technology. This method constructs a network model based on multi-dimensional resource characteristics and combines an improved Transformer architecture regional traffic prediction algorithm to provide resource constraints and spatiotemporal correlation characteristics for routing decisions. Based on geographical region division into virtual nodes and autonomous domains, the LEO satellite network routing process is decoupled into intra-domain and inter-domain parts. Intra-domain routing employs a multi-agent deep Q-network, while inter-domain routing uses a summation tree-based deep Q-network. Routing and resource scheduling algorithms are designed separately for each domain. Through hierarchical routing and decoupled resource scheduling, a domain-specific intelligent routing system with both flexibility and scalability is constructed. This invention significantly enhances the service capabilities of LEO satellite networks under extreme scenarios such as high-frequency topology changes, strictly limited resources, and sudden spatiotemporal changes in traffic, providing a highly reliable, low-latency routing solution for integrated space-ground communication, emergency disaster early warning, and global real-time data transmission.

The application discloses a large-scale constellation hierarchical routing planning method for concurrent tasks, and belongs to the technical field of mega constellation management and routing planning.The application is used for solving the problem of constellation routing planning under large-scale concurrent tasks and large-scale nodes.The application comprises the following steps: dividing a large-scale constellation into constellation management domains, determining the shortest domain-level path from a starting constellation management domain to a terminal constellation management domain for each task, determining the initial entry domain endpoint and the initial exit domain endpoint of each constellation management domain based on a global routing reference direction, adjusting the exit domain endpoint of a congested node to obtain a final exit domain endpoint and a corresponding final entry domain endpoint, and dividing the tasks in the constellation management domain into rounds according to the estimated time sequence of the tasks to arrive at the constellation management domain, and selecting a low-load next-hop satellite node for each round of task.The application reduces the complexity of constellation routing planning under large-scale concurrent tasks and large-scale nodes, and realizes the optimization of network load balancing performance.

The embodiment of the invention provides a page loading method and device based on dynamic routing, equipment, a medium and a product, and is applied to the technical field of front-end routing. The method comprises the following steps: acquiring a nested hierarchical routing structure of a target platform; the nested hierarchical routing structure represents a superior-subordinate relationship of a plurality of service hierarchies in the target platform; each business level comprises at least one function page; the nested hierarchical routing structure supports nested views and state type routing; based on a nested hierarchy routing structure, configuring a corresponding path dynamic parameter for each service hierarchy; receiving an access request of a target platform, and obtaining an access link based on the access request; analyzing the access link to obtain the value of the path dynamic parameter; and loading a template file and a controller corresponding to the access request based on the value of the path dynamic parameter, and rendering a target page corresponding to the access request based on the template file and the controller. The technical effect of improving the operation page access efficiency is achieved.

The invention discloses an efficient self-adaptive routing protocol system of an underwater sensor network based on Q-learning and Bayesian optimization. According to the efficient self-adaptive routing protocol system of the underwater sensor network based on Q-learning and Bayesian optimization, hierarchical routing composed of intra-cluster routing and inter-cluster routing is executed, so that Q-learning application is realized, an efficient data forwarding path is easily found, and data forwarding from an underwater node to an aggregation node is realized; by executing Bayesian optimization, key network control parameters such as hyper-parameters and the like can be automatically adjusted, so that the whole routing system can adapt to different network conditions and continuously converge to a global performance optimal state. The method is widely applied to the technical field of underwater sensor networks.

The invention discloses a transformer area theoretical line loss rate calculation and release method based on a hierarchical routing and freezing strategy. The method comprises the following steps: preprocessing preset time window power data to generate an input set; the performability of the candidate methods is judged, routing is carried out according to priorities, non-performability reasons are recorded, and a uniform aperture consistency record is established; when the target method is a physical method, directly outputting a calculation result as a to-be-published value, otherwise, performing steady-state processing on the original output, and if the method cannot be executed, outputting a bottom value; covering and writing original output by using a unique identification key, and storing a calculation result, a value to be published and metadata of an input set; when an increment recalculation condition is triggered, performing increment recalculation and coverage release on the influenced minimum time window set; the method can avoid the instability of the release reference, ensures the long-term consistency of the external release aperture, and has no weight drift and cross-method fusion aperture jump.

The invention discloses a mixed expert efficient fine-tuning routing method for a coal mine equipment operation and maintenance multi-mode large model. The method comprises the following steps: collecting coal mine equipment multi-source heterogeneous data; carrying out multi-modal data feature extraction and joint embedding; hierarchical routing and expert probability calculation; carrying out routing stability smoothing processing; carrying out adaptive Top-k sparse expert activation and load constraint; and mixing expert efficient fine tuning. According to the method, working condition state key factors can be fully fused, cross-domain distribution deviation and knowledge interference occurring when the scale of heterogeneous knowledge is large are reduced, meanwhile, the consistency and stability of generated content are improved, and better balance between reasoning precision and calculation overhead is considered.

A method for load balancing flows of a Network on Chip (NoC) having a plurality of routers and a plurality of bridges arranged into a plurality of clusters described herein includes receiving packets at the NoC, the packet being associated with a target destination as specified by a cluster identifier and a local identifier. For receipt of each packet, the method includes routing the packet to a destination in the NoC according to the local identifier for the NoC having a same cluster identifier as the cluster identifier associated with the packet, and routing the packet according to a route lookup from referencing the cluster identifier and a path identifier associated with the packet for the NoC having a different cluster identifier from the cluster identifier associated with the packet.

The invention discloses an electric power wireless communication private network service method with multiple communication modes fused, which relates to the technical field of electric power wireless communication networks and comprises the following steps: monitoring and extracting original behavior records of a terminal in multiple communication modes; clustering and separating a communication quality stationary stage and a communication quality fluctuation stage in a time dimension; screening an alternative communication mode set according to the aggregation characteristic difference of the transmission scale of each communication mode in the two stages; calculating a topology adaptive value based on a coupling relationship between behavior records in a stationary stage, and determining a topology root node level of the terminal in combination with a time sequence attribute and a behavior frequency in a fluctuation stage; screening network hub nodes and constructing a layered routing network structure; and generating a hierarchical control instruction according to the connection characteristics of different levels. According to the method, communication mode dynamic optimization and network topology autonomous construction based on environment stage perception and behavior data analysis are realized, and the adaptability of a private network to a complex fluctuation environment and the reliability of service transmission are improved.

This application discloses a lightweight, anti-blocking intelligent routing method, apparatus, device, medium, and product for satellite constellations based on Stackelberg game theory, relating to the field of satellite communication networks. The method includes: constructing a satellite constellation network simulation environment and establishing a Stackelberg game model, defining the blocker as the leader and satellites as followers; designing a hierarchical routing framework, including a routing selection module based on an Actor-Critic architecture and an anti-blocking module based on Q-Learning; updating routing network parameters using a near-end policy optimization algorithm and utilizing Q-Learning to quickly reselect paths after detecting blockage; and achieving algorithm lightweighting through artificial dimensionality reduction of the state space and knowledge distillation techniques. This application effectively improves the robustness and reliability of satellite constellation networks in intelligent blocking environments, realizes a lightweight design of the intelligent algorithm, proves the existence of Stackelberg equilibrium, and significantly improves routing success rate and reduces average latency.

The application discloses a power wireless communication private network service method based on multi-communication mode fusion and relates to the technical field of power wireless communication networks, which comprises the following steps: monitoring and extracting original behavior records of terminals under multiple communication modes; clustering and separating communication quality stable stages and fluctuation stages in the time dimension; screening a set of alternative communication modes according to the differences in the aggregation characteristics of the transmission scale of each communication mode in the two types of stages; calculating a topology adaptation value based on the coupling relationship between the behavior records in the stable stage, and determining the topology root node level of the terminal in combination with the time sequence attributes and behavior frequency of the fluctuation stage; screening network hub nodes and constructing a hierarchical routing network structure according to the topology adaptation value; and generating hierarchical control instructions according to the connection characteristics of different levels. The method realizes dynamic optimization of communication modes and autonomous construction of network topology based on environment stage perception and behavior data analysis, and improves the adaptability of the private network to complex fluctuation environments and the reliability of service transmission.

The invention relates to a pressure measurement method and device for a distributed system, electronic equipment and a storage medium. The method comprises the following steps: receiving a pressure measurement request initiated by a service end; in response to the pressure measurement request, judging whether a service application corresponding to the pressure measurement request is matched with a preset shadow resource rule or not based on the pressure measurement identifier; if the preset shadow resource rule is matched, routing the pressure test request to a corresponding shadow resource according to a preset hierarchical routing strategy in the shadow resource rule; and if the preset shadow resource rule is not matched, carrying the pressure measurement identifier to the request of the downstream service, so that the downstream service re-executes until the full-link pressure measurement process is completed. Physical isolation of pressure measurement data and production data is achieved from the source, the data pollution problem is thoroughly avoided, manual pressure measurement data cleaning is not needed, and the operation and maintenance cost is greatly reduced; and the pressure measurement identifier is extracted and transmitted in a non-intrusive manner by relying on the Java probe, so that a developer is prevented from manually modifying a service code, and the influence of a redundant code on a service system is eliminated.

The application discloses a wireless sensor network clustering routing based on an improved beluga whale optimization algorithm and relates to the field of Internet of Things.The technical scheme of the application improves the beluga whale optimization algorithm through student t distribution and cosine boundary strategy, which is called tCBWO.BWO algorithm is in the local development stage most of the time during the algorithm execution process; a DPR heuristic algorithm is proposed and applied to WSN; a new hierarchical routing scheme of WSN is proposed.The stability of the BWO algorithm is improved, and the Prim algorithm is improved in combination with a transmission energy consumption model of WSN, and is named as tCBWO-DPR algorithm.The algorithm can provide high-quality data transmission service in each round and can effectively improve the balance of the network.

This invention proposes a continuous learning method and evaluation method to mitigate the double forgetting of visual language models. The method includes: adding two parallel paths to the backbone network of a pre-trained visual language model—one a task-agnostic expert path and the other a task-related expert group path—to obtain a model based on heterogeneous expert hybridization; training the model using a two-stage training strategy, including: a first stage, freezing the task-related expert group path and training only the task-agnostic expert path, using contrastive learning to solidify the pre-trained general knowledge of the visual language model; a second stage, freezing the task-agnostic expert path and training only the task-related expert group path, using a cross-entropy loss function to learn task-specific knowledge; and an inference stage, dynamically fusing the outputs of the two parallel paths through a hierarchical routing mechanism to achieve collaborative learning of pre-trained knowledge and task-specific knowledge.

The application discloses the technical field of micro-service gateway and relates to a unified service scheduling method and device based on a micro-service gateway, a medium and equipment, which comprises the following steps: deploying a service gateway to each middle platform tenant; pulling corresponding service configurations from a gateway configuration center through the service gateway; acquiring full initialization data of the service gateway through a management tool; connecting the service gateway to a registration center in the corresponding middle platform tenant to realize automatic service registration and route construction; when the route is changed, sending a change notification to a message component through the management tool; and the service gateway receives the change notification and updates the memory route. The application solves the technical problems that the system based on the micro-service gateway cannot realize fault isolation and automatic service registration in the prior art, realizes hierarchical routing and multi-tenant isolation by setting multiple gateway components, ensures the isolation of the traffic of each middle platform, avoids single-node faults, realizes automatic service registration and route construction, and effectively unifies the service call management of each middle platform.

Multi-level hierarchical routing matrices for pattern-recognition processors are provided. One such routing matrix may include one or more programmable and / or non-programmable connections in and between levels of the matrix. The connections may couple routing lines to feature cells, groups, rows, blocks, or any other arrangement of components of the pattern-recognition processor.

The invention discloses an electric power wireless sensor network routing method considering link quality and communication load, which belongs to the technical field of electric power wireless sensor network routing, and comprises the following steps: firstly, establishing a network model and an energy consumption model which adopts an LEACH model; then link quality and communication load evaluation is carried out; secondly, in a cluster head election and clustering establishment stage, a sparrow search algorithm is adopted to optimize distribution of cluster heads, cluster head broadcasting is carried out after cluster head election is completed, and members enter a cluster based on the minimum cost; and finally, in a routing transmission stage, hierarchical routing is adopted and comprises intra-cluster transmission and inter-cluster transmission. According to the electric power wireless sensor network routing method considering the link quality and the communication load, the link quality and the communication load balance are considered, reliable routing is ensured, packet loss is avoided, meanwhile, network congestion can be controlled, and flow balance can be achieved.

This invention relates to a hierarchical adaptive federated learning method, apparatus, and medium. The method includes: a server initializing global model parameters and broadcasting them to a client; a client initializing local model parameters; the client extracting scaling factors for each batch normalization (BN) layer in the local model and calculating hierarchical channel importance scores to generate a personalized channel set and a shared channel set; performing hierarchical routing fusion of local and global parameters based on the personalized and shared channel sets to update the local model parameters; training the local model and applying adaptive constraint losses to the parameters corresponding to the personalized and shared channel sets during training; after training, the client pruning and differentially privacy-processing the updated amount of the shared parameters based on the BN layer scaling factors and uploading it to the server; the server updating the global shared parameters and distributing them to the client; repeating the aforementioned steps for a preset number of rounds to obtain the local model.

The application discloses a kind of multi-task data analysis systems based on hybrid expert model, comprising: data input module is standardized to multi-task original data;Task feature extraction module extracts the corresponding feature expression data in multi-task data set;Hierarchical gated routing module determines the expert path of task using hierarchical routing algorithm;Hierarchical expert network module executes feature fusion according to routing result;Multi-task prediction module executes task prediction to the fused features;Multi-task loss optimization module optimizes model parameters based on gradient normalization and uncertainty weighting algorithm;Model parameter update module realizes parameter synchronous update;Multi-task result output module carries out final correction of prediction result.The application effectively improves the stability and accuracy of multi-task data analysis.