12 results about "Link weight" patented technology

The invention relates to an application test method and device, electronic equipment and a storage medium, and relates to the technical field of computers, and the method comprises the steps: obtaining an application service relation graph and test range indication information under the condition that an application test instruction is received; determining a plurality of to-be-tested services and service link diagrams based on the application service relation diagram; performing link weight analysis on each to-be-tested sub-link based on the edge weight information or the node weight information in each to-be-tested sub-link to obtain sub-link weight information; based on the sub-link weight information and the service link diagram, performing a flow distribution test on the plurality of to-be-tested sub-links to obtain a link calling test result; obtaining service test codes corresponding to a plurality of to-be-tested services; based on the service test code, performing a service execution test on each service to be tested in the plurality of services to be tested to obtain a service execution test result; and generating an application test result based on the link call test result and the service execution test result.

The application provides a signaling communication network topology determination method and device, electronic equipment and a storage medium. The method comprises: obtaining an original optical network topology; determining the original carrying traffic, original security attribute value and original link weight of each link; deleting a first target link with the lowest original link weight to obtain a first updated network topology, and determining whether the first updated network topology meets the connectivity requirement; if the first updated network topology meets the connectivity requirement, determining the first updated carrying traffic and first updated security attribute value of each link; determining whether the first updated carrying traffic is not greater than the maximum carrying traffic of the link, and whether the first updated security attribute value reaches a preset security attribute value; if the first updated carrying traffic is greater than the maximum carrying traffic of the link, and / or the first updated security attribute value does not reach the preset security attribute value, adding the first target link to the first updated network topology to determine a target network topology.

This application discloses a transmission path determination method, comprising: determining the predicted performance value of each network node in a predetermined time period using a preset model based on a historical network graph of a historical time period, wherein the historical network graph includes: adjacency weight values ​​between network nodes and historical performance values ​​of each network node in the historical time period, wherein the historical time period corresponds to the predetermined time period; determining the link weight of each link between network nodes in the predetermined time period based at least on the predicted performance values ​​of each network node, wherein the link weight is used to characterize the transmission performance of the link; and determining the transmission path used for transmitting service data in the predetermined time period based on the link weights of each link, wherein the transmission path includes at least one link. This application also discloses a transmission path determination apparatus, an electronic device, and a storage medium.

The application provides a production management method based on artificial intelligence, comprising the following steps: constructing a space-time correlation traceability graph based on a production network topology and taking time sequence characteristic values of micro-variable mark sequences as node and link weights according to the micro-variable mark sequences, determining a congestion diffusion conduction direction and a network topology boundary coordinate; obtaining a real-time delay of a production task transmission path, performing space-time dimension feature correlation on the congestion diffusion conduction direction, the network topology boundary coordinate and the real-time delay of the corresponding production task transmission path, and determining a congestion risk; and monitoring a path utilization rate in real time, if the path utilization rate breaks through a preset critical buffer threshold, switching a new task to a next available path in order, and obtaining a final task bearing scheme that adapts to production load demand.

The application discloses a routing method, medium, equipment and product of a low-orbit satellite constellation, relates to the technical field of satellite routing, and comprises the following steps: according to a quality of service parameter, performing snapshot freezing on a current network topology to construct a static topology graph structure; constructing a basic quality of service parameter cost function for each link; performing an offline ant colony optimization algorithm to globally evaluate a satellite topology library constructed in advance, constructing a heuristic function according to a link basic quality of service parameter cost; initializing a pheromone value for each link, and updating the pheromone in an iteration process according to the heuristic function; adjusting the cost function based on the pheromone; taking the cost of the discounted pheromone as the final link weight of the satellite network, constructing a weighted graph structure, and adopting a shortest path search algorithm to calculate a routing path between a source node and a target node, so that an optimal routing path is obtained. The application solves the problems of high-speed time-varying satellite link state adaptability and poor quality of service.

This invention discloses a method, medium, device, and product for dynamic OSPF link weight optimization, relating to the field of OSPF link weight optimization technology. The method includes: acquiring OSPF link bandwidth, link latency, maximum utilization, and link error rate in real time via the SNMP protocol to construct a state vector; using the state vector as input and the weight adjustment values ​​of each link as output to construct a deep reinforcement learning model; calculating new link weights based on the weight adjustment values ​​output by the model; writing the new weight values ​​into the interface configuration of the OSPF router to trigger OSPF to recalculate routes. This invention directly applies deep reinforcement learning technology to OSPF link weight optimization, achieving intelligent and automated dynamic OSPF link weight optimization.

The invention provides an industrial wireless sensor network topology control method for data collection, which comprises the following steps of: uniformly dividing a task period into a plurality of continuous time periods, and calculating an initial network topology sequence according to whether each industrial sensor node is active or not in each time period and dynamic position information, constructing a space-time diagram according to the initial network topology sequence; calculating an energy consumption index and a reliability index of each link in the space-time diagram, and fusing the energy consumption index and the reliability index into a comprehensive link weight; and searching an optimal space-time path from each industrial sensor node to a control node by using an improved shortest path algorithm according to the space-time diagram and the comprehensive link weight, and combining link sets of all the shortest space-time paths to form a final network topology of the IWSNs. According to the method, the energy consumption and reliability of data transmission in a dynamic network are balanced while the influence of node mobility on industrial wireless communication is considered.

The invention belongs to the field of network management and traffic engineering, and discloses a routing optimization method based on traffic matrix completion prediction, which comprises the following steps: step 1, constructing a routing matrix A and collecting a link load vector at the current moment, and step 2, constructing a traffic matrix completion model and outputting a complete traffic matrix. 3, constructing a space-time traffic prediction model, and outputting a predicted traffic matrix at the next moment; 4, connecting the traffic matrix completion model and the space-time traffic prediction model in series, and defining a joint loss function to perform parameter updating on the whole end-to-end network; and step 5, pre-evaluating a pre-estimated load state, dynamically adjusting a link weight and generating an optimal routing strategy by utilizing the output predicted traffic matrix at the next moment and combining network topology information, and finally issuing configuration to a data level to realize routing optimization of traffic transmission. According to the method, the integrity of the traffic matrix is ensured, adaptive attention to the key link is realized, and the complemented data highly conforms to future trend prediction.

The invention discloses a computing power network routing and online data processing joint optimization method and system based on deep reinforcement learning, and the method comprises the steps: S1, collecting the state information of a whole network, and constructing network state representation; s2, inputting the network state representation into a pre-configured decision model, wherein the decision model is used for extracting network features and outputting strategy distribution parameters; s3, based on the strategy distribution parameters, sampling from the strategy distribution to generate a joint action vector; s4, calculating a transmission path for the data stream based on the link weight parameter; s5, screening on the transmission path based on the processing probability parameter and determining a computing node for executing the on-network data processing task; and S6, issuing a routing table item and a calculation instruction, and executing data stream forwarding and online data processing operation. According to the method, a unified decision framework is created, and whether more computing resources are consumed to save communication resources or the communication resources are directly used for transmission can be determined according to the real-time network state.

The invention provides a portal frame quality detection method and system, and relates to the technical field of portal frame production, and the method comprises the steps: obtaining the process link data of each key part in the production process of a forklift portal frame, and the process link data comprises the welding link data and the assembly link data; performing anomaly detection on the link data of each process to obtain a link anomaly degree value; according to the link abnormal degree value and the link weight corresponding to the link abnormal degree value, stability analysis of different use modes is carried out to obtain a stability index; and according to the stability index, determining the qualification of the door frame quality so as to complete door frame quality detection. According to the detection method and system provided by the invention, the quality evaluation efficiency of the door frame after production can be effectively improved, and the reliability of a door frame quality qualification detection result is ensured.

The application belongs to the field of network management and traffic engineering, and discloses a routing optimization method based on traffic matrix completion prediction, which comprises the following steps: step 1, constructing a routing matrix A , collecting a link load vector at the current moment, step 2, constructing a traffic matrix completion model to output a complete traffic matrix; step 3, constructing a space-time traffic prediction model to output a predicted traffic matrix at the next moment, step 4, connecting the traffic matrix completion model and the space-time traffic prediction model in series, defining a joint loss function to update parameters of the entire end-to-end network; step 5, using the output predicted traffic matrix at the next moment, combining network topology information, pre-evaluating an estimated load state, dynamically adjusting link weights and generating an optimal routing strategy, and finally configuring and issuing to the data layer to realize routing optimization of traffic transmission. The application guarantees the integrity of the traffic matrix, realizes adaptive attention to key links, and makes the completed data highly consistent with future trend prediction.

The invention provides a network data transmission method for route optimization based on deep reinforcement learning and related equipment. The method comprises the following steps: acquiring environment state information of a network environment; joint optimization of a routing strategy and a caching strategy is carried out based on the environment state information, and joint strategy information about routing and caching is obtained; the joint strategy information comprises a link weight, a key cache node and a cache data flow type; acquiring transmission associated information of the to-be-transmitted data; based on the transmission association information, determining data transmission information with minimum transmission duration when a preset constraint is met; and executing a routing action based on the joint policy information, executing a data scheduling action based on the data transmission information, and transmitting the to-be-transmitted data.