33 results about "Network performance optimization" patented technology

The invention relates to the technical field of electric power communication and information, in particular to a substation wireless network performance optimization method based on the Internet of Things, which comprises a data acquisition module, a data transmission and preprocessing module, an intelligent analysis module, a strategy generation module, a strategy execution and feedback module and an effect evaluation and abnormity alarm module. The data acquisition module is used for acquiring operation data and environment parameters of a wireless network of the transformer substation in real time; and the data transmission and preprocessing module is used for performing low-power-consumption transmission, cleaning, normalization and feature extraction processing on the operation data and the environment parameters. According to the application, wireless signal quality (signal intensity, signal-to-noise ratio and the like), equipment operation states (CPU / memory utilization rate and connection number), service load characteristics (flow peak value and protocol type) and environmental parameters (electromagnetic interference intensity, temperature and humidity) are synchronously acquired through the data acquisition module, multi-dimensional data fusion is realized, and a more complete information basis is provided for subsequent analysis.

The invention discloses a network flow prediction method based on a decoupling dynamic space-time diagram neural network D2STGNN. The method comprises the following steps: constructing a network flow data processing and representing module, and collecting and preprocessing flow data; then, a prediction model is constructed based on D2STGNN, a space-time framework is decoupled to decompose a network traffic space-time signal into a node-traffic association signal and a network-traffic time trend signal, and by means of a space-time local convolution layer, a gating circulation unit and a multi-head self-attention layer, an inter-node association process and a capture time sequence dependency relationship are respectively modeled; and meanwhile, a time attenuation mechanism is introduced, and the real-time dynamic capturing capability of the model on the network flow is enhanced in combination with adaptive attenuation parameter adjustment and a layered attenuation mechanism. And finally, predicting real-time network flow data by using the trained model, and evaluating a prediction effect through related evaluation indexes. According to the method, the change trend of the network flow can be efficiently and accurately predicted, and powerful support is provided for reasonable distribution of network resources, network performance optimization and the like.

The embodiment of the invention provides a measurement report processing method, a terminal and a network element, and the method comprises the steps that the terminal reports a measurement report to a target network element according to pre-configured target network element information, and other network elements obtain the measurement report from the target network element. According to the embodiment of the invention, the problem that the network node cannot obtain the required terminal measurement report to optimize the network performance in the related technology can be solved, the centralized collection of the terminal measurement report is realized, and the unnecessary forwarding process in the reporting process of the measurement report is avoided.

The invention discloses a power grid hybrid network performance optimization model considering construction cost, and belongs to the technical field of intelligent power grid communication. According to the model, a parameter system including communication equipment, terrain and a global system is defined, a function with the purpose of minimizing the total cost of a life cycle and multivariate constraint conditions of transmission distance, retransmission times, delay, reliability and flow velocity are constructed, and optimal equipment and transfer device configuration is solved by adopting a node traversal and iterative optimization algorithm. Cost and performance collaborative optimization of a honeycomb, Wi-Fi and ZigBee heterogeneous hybrid communication network under a complex terrain is realized, planning accuracy and reliability are remarkably improved, and construction, operation and maintenance cost is reduced.

The application belongs to the technical field of communication, and particularly relates to a network performance testing method, a network performance testing device, a computer readable medium, an electronic device and a computer program product. The method comprises the following steps: establishing a network performance testing channel for communication connection with a specified network element, wherein the specified network element is a functional network element specified in a core network of a communication system; and performing data communication with the specified network element based on the network performance testing channel, so as to obtain network performance parameters of communication traffic. The application can improve the accuracy of network performance optimization.

The application discloses a network management method based on 5G embedded network management software, and solves the technical problem of insufficient intelligent level of some existing 5G embedded network management software. The method comprises the following steps: collecting data by using a Scrapy framework and a Selenium tool; storing data by using an HDFS system; pre-processing data by using a Spark SQL module; analyzing and processing data by using a reinforcement learning algorithm; learning and predicting network states according to data by using a supervised learning algorithm; verifying and detecting fault points based on the prediction of network states by using the supervised learning algorithm; and issuing an alarm notification and recovering from a fault based on the verification and detection result of the fault points. In the aspects of network fault prediction and network performance optimization management, the application introduces a supervised learning algorithm in a machine learning algorithm to predict network faults, and introduces a reinforcement learning algorithm to adjust network configuration, so as to optimize network performance. Compared with the prior art, the application improves the intelligent level of network management.

The invention particularly relates to a machine room network performance optimization system based on big data, and relates to the technical field of network performance optimization. A phase difference module which reflects and controls the path difference; a total phase in-phase implementation module; a reflection amplitude control module; and a dynamic monitoring and optimizing module. According to the invention, a full-link optimization system from signal characteristic analysis to phase and amplitude fine control is constructed, a reflection and control path difference module is combined with a machine room space to flexibly adjust a path difference, an active compensation phase is introduced by a total phase in-phase implementation module, and phase deviation of metal reflection and dielectric loss is accurately counteracted; the incident wave and the reflected wave are strictly superposed in the same phase at the receiving end, a phase foundation is built for signal gain, the superposition enhancement effect is theoretically developed into stable engineering practice, the problems that the signal enhancement effect is unstable and is easily counteracted by interference in traditional optimization are solved, and high reliability of data transmission is guaranteed.

The invention discloses a pulse time-driven network performance optimization system and method, and the system comprises a sparse scrambling coding module which is used for carrying out the sparse scrambling coding of input data, so as to convert the input data into a pulse sequence with the determined time distribution in the coding time, and obtain a coded pulse sequence; the decoding module is used for inputting the coded pulse sequence into the pulse neural network for reasoning, and continuously monitoring pulse activity of each category of channel of an output layer of the pulse neural network in the reasoning process; when the first pulse of any category of channel is detected, generating category prediction based on the pulse time, the pulse count or the combination thereof of the first pulse; and the coding and decoding driving training module is used for carrying out combined optimization of weights and thresholds on the network or carrying out conversion from an artificial neural network and carrying out threshold calibration on the network based on category prediction. Therefore, by adopting the embodiment of the invention, the recognition robustness of the network on the data set can be obviously improved.

The embodiment of the invention discloses a network performance optimization method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an optimization request; if the optimization request is a network optimization request, determining an initial optimization scheme through a large model; analyzing the network optimization request through a large model to obtain N sub-requests; the N sub-requests are sent to a second server, so that the second server calls M small models corresponding to the N sub-requests through a wireless intelligent management and arrangement function layer; receiving a first optimization scheme determined by the first small model according to the corresponding first sub-request and the current network state data; the first sub-request is any one of N sub-requests, comparing the initial optimization scheme with N first optimization schemes, and determining a target optimization scheme; and sending the target optimization scheme to the wireless network equipment, so that the wireless network equipment performs network optimization according to the target optimization scheme. An optimization scheme is provided through fusion of the large model and the small model, and the network optimization effect is improved.

This invention discloses a group-connected BD-RIS-assisted uplink communication system and a method for maximizing transmission rate, relating to the field of wireless communication technology. The method first establishes a channel model between the user, base station, and BD-RIS, derives the decoded signal expression for the user at the base station, and calculates the user's signal-to-interference-plus-noise ratio (SNR) and achievable rate. Then, it constructs an optimization problem with the goal of maximizing the system's sum and rate, with the optimization variables being the equalizer, user transmit power, and BD-RIS phase shift matrix. Finally, it employs an alternating optimization strategy, sequentially optimizing the equalizer based on the minimum mean square error criterion, transforming the non-convex problem into a convex problem to solve for the transmit power, and optimizing the phase shift matrix using the BFGS quasi-Newton method, iterating until the system performance converges. This invention overcomes the design limitations of traditional reconfigurable smart reflectors, fully leverages the control advantages of BD-RIS, effectively improves the sum and rate of the uplink communication system, and provides a new solution for future wireless network performance optimization.

Disclosed is data processing system having at least one server communicably couplable to at least one display apparatus, wherein at least one server has at least one processor configured to obtain quality of service information from network traffic regulator of communication network, wherein communication network is between at least one server and at least one display apparatus, obtain media processing latency information from at least one rendering application executing at the at least one server, and obtain client device operational information from at least one display apparatus; process quality of service information, media processing latency information, and client device operational information together to generate streaming configuration parameters; and control at least one rendering application to generate images for displaying at the at least one display apparatus and send images via communication network to at least one display apparatus, according to generated streaming configuration parameters.

The invention discloses a parameter adjustment method and device, a storage medium and electronic equipment, and relates to the technical field of communication, and the method comprises the steps: obtaining an operation parameter of target access network equipment in an area where network performance optimization needs to be carried out; determining network parameters and state information of at least one cell covered by the target access network equipment; performing global optimal analysis on the target access network equipment according to the network parameters and the state information to obtain target operation parameters corresponding to the target access network equipment; and adjusting the operation parameter of the target access network equipment to the target operation parameter so as to optimize the network performance of a target area where at least one cell in the area is located. According to the invention, the global optimal analysis is carried out on the target access network equipment according to the network parameters and the state information to obtain the corresponding target operation parameters, so that the accuracy of parameter adjustment is improved; by adjusting the operation parameter of the target access network device to the target operation parameter, the network performance optimization effect of the target area is improved.

The invention provides a lossless network performance guarantee method and system for real service flow simulation enabling, and belongs to the technical field of network communication, and the method comprises the steps: deploying a flow probe to collect service flow data, mapping the service flow data to a feature space of a preset dimension, carrying out the clustering of sample points in the feature space, outputting a flow mode label of each type, and carrying out the clustering of the sample points in the feature space; calculating statistical characteristics of the service flow data of each label; extracting a time sequence feature of the service flow data under each label, and splicing the statistical feature and the time sequence feature to obtain a feature vector; a special traffic simulation model is pre-trained for each label, and a traffic simulation framework is constructed in combination with model selection logic; and inputting the feature vector of each flow mode into a flow simulation framework, outputting simulation flow, evaluating the simulation flow, and quantifying an evaluation result. According to the invention, through real service flow simulation, the lossless network performance is accurately evaluated, the resource configuration is optimized, and the QoS guarantee capability of the key service is improved.

The invention provides an HTTP request performance diagnosis method and system based on a dynamic Agent mechanism and a storage medium, and relates to the technical field of computer network performance optimizing.The diagnosis method comprises the steps that S1, a dynamic Agent program is accessed to a target server through an Attach mechanism of a JVM tool script; s2, an Agent program acts as a service method of javax.servlet.http.HttpServlet, a specific HTTP request is intercepted, and a background monitoring thread is started to execute the following operations: setting an execution time threshold value, and marking the HTTP request exceeding the time threshold value as an STUCK state; performing thread stack sampling on the STUCK state request at a set frequency; collecting a method execution completion event, and constructing flame map data; s3, generating two result files: head.txt, and recording the total consumed time of the request and a unique identifier UUID; and uurid.txt, storing the flame image data obtained by sampling; s4, calling a flame graph generation tool to generate a flame graph in an SVG format; s5, positioning the performance bottleneck by analyzing the stack width and the sample number of the flame pattern; the width of the flame map is positively correlated with execution time consumption, and the widest stack is optimized preferentially.

The invention discloses a directed ring causal structure discrimination and estimation method for network intelligent operation and maintenance, relates to the technical field of network intelligent operation and maintenance, and provides a solution based on high-order cumulant matrix analysis for causal discovery and effect estimation requirements of a feedback loop in a network system. A unified cumulant matrix construction principle is established, so that cumulant total orders of main diagonal elements and auxiliary diagonal elements of the matrix are the same; on the basis, the system firstly utilizes rank conditions of a forward three-order cumulant matrix and a reverse three-order cumulant matrix to realize loop detection; and after the existence of the feedback loop is confirmed, constructing a mixed third-order cumulant matrix, constructing a solvable equation about a causal coefficient by utilizing determinant properties, directly completing loop effect estimation, and realizing integration of loop discrimination and effect estimation. According to the method, a complex intra-ring causal effect estimation problem is converted into an algebraic problem which can be solved directly, and accurate causal support is provided for network performance optimization, resource scheduling and safety protection.

The invention relates to a model training method and device and a processor readable storage medium, and a center node carries out model training in cooperation with a first distributed node according to node data of the first distributed node, so that the first distributed node can complete a model training task under the cooperative help of other nodes. The effects of improving the network performance of the whole distributed network and optimizing the network and application service experience are achieved.

The application discloses a kind of time synchronization network performance optimization method, device, equipment and medium, the method is applied to synchronous network probe monitoring system, comprising the following steps: when time synchronization network performance appears deterioration fault, probe equipment reports time synchronization network performance deterioration fault information to probe network management equipment;Probe network management equipment prompts operation and maintenance personnel to carry out fault maintenance to fault position, and issues first switching instruction to probe equipment, and probe equipment is switched from measurement mode to time source mode according to first switching instruction;Probe network management equipment receives fault solution receipt, then issues second switching instruction to probe equipment, and probe equipment is switched from time source mode to measurement mode according to second switching instruction;Probe equipment continues to measure and obtains the time synchronization network performance of access equipment, to complete the optimization of time synchronization network performance.The method can realize the automation and reliability of synchronous network fault root location process.

The invention discloses an image recognition method for handwritten digits and a terminal, and the method comprises the steps: setting algorithm parameters, such as momentum and learning rate, for a digit recognition model according to an obtained sample data set of the handwritten digits, calculating an adaptive learning rate and related parameters on a model training data set through gradient second-order information parameters, and carrying out network weight training; in the training process, a verification data set is used for evaluating a loss function value to judge whether training is completed or not, whether the adaptive learning rate is adjusted or not is judged in the verification stage, and if the adaptive learning rate is adjusted, adaptive learning rate parameters are updated through operations such as calculation of a negative gradient of the loss function value and normalization according to network performance optimization requirements; and finally, selecting a test data set for network prediction, and taking the weight corresponding to the minimum loss function value as the final weight of the model. Therefore, the advantages of the stochastic gradient descent optimization algorithm fusing the adaptive learning rate and the second-order information in improving the training efficiency and prediction accuracy of the digital recognition model are fully displayed.

A method for wireless communications comprising: transmitting, by a network node to a wireless device, a handover configuration information to facilitate reporting of successful handovers associated with the wireless device; receiving, at the network node, information reporting a successful handover associated with the wireless device, wherein the information reporting the successful handover is in accordance with the handover configuration information; and performing network optimization based on the information reporting the successful handover.

The invention discloses a performance optimization method based on a supporting cache millimeter wave cellular network, which relates to the technical field of wireless communication, and comprises the following steps: (1) constructing a hybrid millimeter wave small cellular network; (2) modeling the network, and establishing a path loss model containing a line-of-sight (LoS) link and a non-line-of-sight (NLoS) link; (3) designing an optimal caching strategy, and storing the most popular content MPC under Zipf request distribution to maximize the regional spectrum efficiency; (4) establishing a user dynamic association mechanism, and preferentially accessing a base station in which the requested content is cached; (5) deriving a closed solution expression of the regional spectral efficiency ASE under the condition that the backhaul capacity is limited, quantifying the network throughput performance, and reducing the calculation complexity by adopting a Gauss-Laguerre integral method; and (6) network performance optimization is carried out based on Zipf request distribution, and cache coverage gain and content reuse efficiency are balanced through joint optimization of cache node density and single-point cache capacity. The method effectively reduces backhaul resource consumption, and is suitable for 5G / 6G millimeter wave high-density small cellular network deployment.

The application discloses a kind of based on conditional risk value and whale optimization's unmanned plane computing unloading method, comprising: constructing air-ground link channel state information estimation error uncertainty set, constructs opportunity constraint model;Joint optimization unmanned plane position deployment, unloading decision and resource allocation, establish air edge computing unloading model;Determine the association scheme of user and unmanned plane;Construct the distributed robust opportunity constraint of worst condition task delay, and based on the conservative estimation of conditional risk value theory to distributed robust opportunity constraint, it is converted into second order cone constraint problem;Second order cone constraint problem is decoupled into computing resource allocation problem and unloading decision problem;Solving obtains the resource allocation and unloading decision scheme that unmanned plane minimizes under satisfying multidimensional constraint in hierarchical air edge computing network.This application effectively solves the network performance optimization problem under the condition that air-ground communication link exists channel state information estimation error.

The invention provides a communication method and device, and the method comprises the steps: receiving first data which comprises the traffic statistic data of one or more cells within the range of a base station; acquiring a first model based on the first data; reasoning the network performance of one or more cells within the range of the base station based on a first model to obtain communication parameters; and sending the communication parameters. Through the method provided by the invention, the transmission delay of the network performance optimization command can be reduced.

The application provides a method for improving controllability of a symmetric network by time segmentation, and relates to the technical field of network performance optimization. The method adopts a time segmentation method to divide a symmetric network into a symmetric time-varying network composed of multiple snapshots, and realizes the structural controllability of the whole network through the control of each snapshot. Given a symmetric network, the black and white coloring is performed through a breadth-first search algorithm for classification; the maximum matching of edges in the symmetric network is found; the undirected cactus is constructed according to the unmatched nodes and the matched edges; the network graph composed of each undirected cactus is used to construct a snapshot, and the number of snapshots is the same as the number of undirected cacti. When a symmetric network is divided into a symmetric time-varying network composed of multiple snapshots, the time segmentation method can effectively reduce the number of drive nodes in the symmetric network and improve the network controllability.

The application provides a HTTP request performance diagnosis method and system based on a dynamic Agent mechanism and a storage medium, relates to the technical field of computer network performance optimization, and the diagnosis method comprises the following steps: S1, a dynamic Agent program is connected to a target server through the Attach mechanism of a JVM tool script; S2, the Agent program proxies the service method of javax.servlet.http.HttpServlet, intercepts specific HTTP requests, and starts a background monitoring thread to perform the following operations: setting an execution time threshold, marking HTTP requests exceeding the time threshold as STUCK states; performing thread stack sampling on the STUCK state requests at a set frequency; collecting method execution completion events and constructing flame graph data; S3, two result files are generated: head.txt, which records the total time consumption of the request and a unique identifier UUID; and uuid.txt, which stores the flame graph data obtained by sampling; S4, a flame graph generation tool is called to generate an SVG format flame graph; and S5, the performance bottleneck is located by analyzing the stack width and the number of samples of the flame graph; the flame graph width is positively correlated with the execution time consumption, and the widest stack is preferentially optimized.

Embodiments of the present invention provide a network performance optimization method, a network performance optimization device, and a storage medium, belonging to the field of communication technology. The method includes: determining whether there are potential abnormal terminals in the cell based on the performance indicators of the cell; if there are potential abnormal terminals in the cell, performing power control screening on the terminals in the cell to determine the target abnormal terminal; releasing the target abnormal terminal and notifying the target abnormal terminal to reconnect to the cell network. The technical solution of the embodiment of the present invention achieves the purpose of improving network performance and optimizing network performance by screening out target abnormal terminals from the network and processing the screened out target abnormal terminals.

Embodiments of the present disclosure relate to network performance optimization, and more particularly to gNB performance optimization based on reinforcement learning (RL) operations. The method includes obtaining current state information of a network environment and a reward, the reward being associated with a reinforcement learning operation and pertaining to performance of the network environment; determining a predicted future state of the network environment based on the current state information; and generating a target set of configuration parameters of the network environment based on at least the predicted future state of the network environment by using the reinforcement learning operation; and configuring the network environment using the target set of configuration parameters.

The invention relates to the technical field of wireless communication, and particularly discloses a network performance optimization method suitable for wireless communication, which comprises a network performance optimization architecture module, a dynamic resource allocation module and a strategy iteration evolution module, and is characterized in that the network performance optimization architecture module is composed of a cross-layer collaborative block chain module and a scene feature adaptive module; and the cross-layer collaborative block chain module adopts a distributed block chain architecture. Real-time synchronization of data of each module within 10ms is realized through a cross-layer collaborative block chain module, decisions such as resource allocation and interference coordination are ensured to be based on a current real network state, the data authenticity is ensured through the non-tampering characteristic of a block chain, and strategy failure caused by malicious equipment counterfeiting interference data is avoided; meanwhile, the scene feature adaptive module can dynamically respond to user density sudden change and service type sudden change, so that a network optimization strategy is matched with actual requirements in real time, and the problems of module data synchronization delay and insufficient scene change adaptation in an existing wireless communication network are effectively solved.

The present disclosure provides a system for optimizing network performance based on correlated multi-source experiential feedback. The system includes a data pipeline comprising a telemetry ingestion module configured to collect structured system data and a natural language parser configured to extract sentiment-weighted indicators from unstructured user feedback data. An analytical artificial intelligence (AI) module identifies patterns and anomalies in the data. A correlation AI engine generates time-aligned embeddings and computes relationships between network events and user dissatisfaction. A generative AI module produces system modification recommendations based on correlation engine outputs. An action operator automatically deploys configuration changes to infrastructure nodes, monitors outcomes, and triggers rollback operations in response to performance regressions, without human intervention.

The invention discloses a thermal power generating unit main steam pressure multi-objective optimization method and system considering network-related performance, and the method comprises the steps: building a thermal power generating unit main steam pressure multi-objective optimization model which takes the minimum throttling loss as an economical efficiency optimization objective and takes the maximum AGC comprehensive performance index as a network-related performance optimization objective; and solving the multi-objective optimization model under a given load to obtain a main steam pressure optimization scheme. According to the method, dynamic optimization of the main steam pressure is achieved through the multi-objective optimization model, and collaborative optimization of economical efficiency and adjusting performance is effectively achieved.

The invention discloses a network performance optimization system and method based on data analysis, and the system comprises the steps: integrating multi-modal network data collection, multi-modal network knowledge graph construction, adaptive business intention analysis, an intention-driven graph attention time sequence prediction model (IGATP) and a multi-target intelligent arrangement and feedback module; the deep understanding of the network service intention, the accurate prediction of the network performance, the anticipation of the intention violation risk and the intelligent active arrangement of the network resources are realized. According to the system, the business intention, the knowledge graph, deep learning and reinforcement learning are creatively combined, the problems of insufficient intention perception, lack of association analysis, prediction lag and passive optimization decision in an existing network optimization scheme are solved, the reliability, efficiency and user experience of network services are remarkably improved, and the network is promoted to advance towards high-level autonomy.