481 results about "Service flow" patented technology

The invention provides a self-adaptive network topology dynamic reconstruction method and system based on deep reinforcement learning, and relates to the technical field of deep reinforcement learning, and the method comprises the steps: obtaining the topology state information, service flow distribution information and historical reconstruction records of a current network; extracting topological correlation characteristics among nodes through graph convolution operation, and generating fusion state representation in combination with service flow information; inputting the fusion state representation into a deep reinforcement learning model to identify bottleneck nodes and redundant links, and outputting a reconstruction action candidate set; searching and evaluating the long-term cumulative income of the candidate actions through a Monte Carlo tree, and screening an optimal reconstruction action sequence; a graph coloring algorithm is utilized to allocate time slots and process resource conflicts, and a resource-feasible topology adjustment scheme is generated; and extracting a network evolution rule through tensor decomposition, and constructing a topological optimization association mapping graph. According to the method, the network bottleneck can be intelligently identified, the network topology structure is dynamically optimized, and the network performance and the resource utilization rate are effectively improved.

A routing method for supporting differential service requirements in a satellite internet comprises the following steps: step 1, constructing multi-dimensional network state perception as a base layer which is responsible for collecting and quantifying physical states and logic states of a satellite network in real time, and obtaining objective network states and subjective QoS (Quality of Service) requirements of services; 2, generating a nonlinear adaptive weight driven by a service as a strategy layer, mapping an objective network state and a subjective QoS (Quality of Service) demand of the service, dynamically adjusting the value orientation of routing judgment, and generating a dynamic weight; and step 3, taking the dynamic cost routing decision as an execution layer, calculating the comprehensive cost based on the dynamic weight, and executing next hop selection and path maintenance, and through cooperative work of the dynamic cost routing decision, the comprehensive cost and the next hop selection and path maintenance, realizing intelligent path selection and high-reliability transmission for different service flows in a high-dynamic and resource-limited environment of the low-orbit satellite. According to the invention, while the routing computation overhead is effectively reduced, multiple requirements of differentiated services on low time delay and high reliability can be considered.

The invention relates to the technical field of power system network and information security, and discloses a power system transverse isolation and secure data transmission method and system.The method comprises the steps that a production control security domain and a management information security domain are determined, and cross-domain service flow information is configured; when transmission between a production control security domain and a management information security domain is needed, cross-domain service flow information to which service data belongs is collected and packaged into a security self-description data unit; on the transverse isolation path, acquiring header information to generate a session token; when the secure self-description data unit is forwarded, feature data are obtained and compared with the associated session token, and forwarding is carried out when limiting conditions are met; and maintaining a sliding time window, carrying out statistics on the forwarded security self-description data unit, and identifying an abnormal behavior. According to the invention, semantic-level access control and dynamic protection of cross-domain services between a production control security domain and a management information security domain are realized.

The invention provides a cross-equipment circulation and collaborative operation and maintenance method for a gap atomization service, relates to the technical field of computer system operation and maintenance, is applied to complex scenes such as a smart park, and aims to solve the problems that services among different gap terminals cannot be seamlessly coordinated and the operation and maintenance efficiency is low. According to the method, granularity self-adaptive splitting and standardized packaging are carried out on atomization services by constructing a swan gap terminal cluster; a cross-device circulation scheduling center is established based on the Gawan distributed soft bus, and dynamic migration of the service sub-modules among the terminals is realized through a circulation decision algorithm; meanwhile, a collaborative operation and maintenance system is constructed, operation and maintenance data are integrated, and intelligent early warning and batch operation and maintenance are achieved through a fault prediction model; and the data consistency before and after service circulation is guaranteed by combining a distributed incremental synchronization mechanism. According to the method, through deep fusion of seamless circulation of atomization services and collaborative operation and maintenance, the multi-terminal service collaborative efficiency in a complex scene is improved, the resource utilization rate is optimized, and the operation and maintenance cost is reduced.

The disclosure relates to a communication method and device for an extended reality (XR) service in a wireless communication system. A method performed by an application server for the XR service in the wireless communication system includes allocating, to at least one UE, identification information for identifying the at least one UE using a same XR service or identifying at least one service flow for transferring XR data to each of the at least one UE and providing XR service-related information including the identification information and information about a delay time allowable for the XR service to the wireless communication system accessed by the at least one UE.

The invention discloses an AI large model-oriented financial private network optimization method and system, and relates to the technical field of communication networks. According to the method, an exclusive path strategy is generated for AI training, reasoning and sensitive data traffic by collecting AI service requirements and network states and utilizing the SID programming capability of SRv6; the load of the computing power node is monitored in real time, the computing power state is linked with network scheduling, and network-computing power collaborative optimization is realized; a hop-by-hop path authentication mechanism based on a dynamic authentication segment identifier Auth-SID is introduced, so that the security of a data transmission path is enhanced; and end-to-end visual operation and maintenance and closed-loop feedback of the service flow are realized by adopting a flow-following detection technology. According to the invention, the problems of mismatching of flow scheduling and AI service requirements, insufficient network and computing power collaboration, lack of path security guarantee and weak operation and maintenance visualization capability in the prior art are solved, deep adaptation of network resources and the AI service requirements is realized, and the computing power collaboration efficiency, the path security and the operation and maintenance intelligence level are improved.

The invention relates to the technical field of computers, in particular to a flow limiting method and system based on an AI gateway and a micro-service gateway, a medium and equipment, and the method comprises the steps: receiving service flow data corresponding to the micro-service gateway, AI flow data corresponding to the AI gateway, and a system resource utilization rate, building a quota negotiation channel between the micro-service gateway and the AI gateway, and transmitting the quota negotiation channel to the micro-service gateway; constructing a data set; calculating the flow quota of the micro-service gateway and the AI gateway through a dynamic quota algorithm based on the data set; receiving and identifying a service scene priority corresponding to the target request, and reserving an elastic burst quota for the target request based on the service scene priority; and judging the relationship between the total number of the current effective requests and the traffic quota of the corresponding gateway, and triggering a corresponding process. By establishing a dynamic quota mechanism and constructing a double-gateway cooperation mode of an AI gateway and a micro-service gateway, insufficient overall resource utilization efficiency caused by local current limiting is avoided, optimal global resource allocation is realized, and system stability is improved through cascade backoff.

The invention relates to the technical field of communication network maintenance, and discloses a communication network operation quality monitoring and closed-loop operation and maintenance scheduling management system, which comprises an acquisition unit for acquiring network element telemetry data; the observation module extracts a flow fingerprint, converts a link into a transfer function model, and generates a consistency gradient vector according to singular point offset; the echo prediction module converts the scheduling instruction into an expected gradient offset vector; the module calculates the scheduling residual error of the actually measured offset and the expected offset; the decision-making unit generates a path reconstruction instruction, and the scheduling residual error is utilized to check the execution efficiency and update the operation reference; according to the invention, the flow conduction consistency constraint is anchored, the link degradation characteristic and random fluctuation decoupling is realized, and the transient interference generated by the scheduling action is eliminated.

A message processing method for in-situ flow detection and network device relate to the field of communication technology. The method includes: receiving a first service message; sending a second service message to a second network device, wherein the second service message includes a first in-situ flow detection option and the first service message, wherein the first in-situ flow detection option includes first additional information, the first additional information includes first reverse service flow characteristics, and the first reverse service flow characteristics are used by a head node of a first reverse path for generating a first service flow identification rule for in-situ flow detection; wherein, the head node is a tail node of a first forward path, and the first network device and the second network device are both on the first forward path and the first reverse path. The configuration workload can be reduced.

The invention discloses a cable television network multi-mode fault root cause positioning method and system, and mainly relates to the technical field of cable television networks. Comprising the steps of collecting multi-source operation and maintenance data and triggering a diagnosis event; screening topological nodes based on a service flow path, and constructing a multi-modal data unit; cross-modal features are extracted, a topological weight matrix is introduced, and a joint causal feature vector is constructed; initial root cause inference is carried out in combination with topology level constraints; correcting the root cause probability based on the fault propagation consistency; and outputting a diagnosis result and updating the model based on feedback. The method has the beneficial effects that structural fusion of multi-modal data is realized, topological constraint and propagation consistency verification are introduced, the positioning accuracy and interpretability of a complex chain fault are remarkably improved, and the method has a self-evolution capability.

The invention discloses a high-concurrency virtual service transfer scheduling method and system based on a cloud edge collaborative architecture, and relates to the technical field of cloud computing and edge computing collaboration, and the method comprises the steps: constructing a service gene analysis model at an edge node, responding to a virtual service access request, extracting the resource consumption characteristics of a service flow in real time, and calculating a service separation potential energy index. The virtual business is dynamically decoupled into a connection anchoring phase and a computing power free phase based on the index; establishing a load inertia monitoring mechanism, modeling resource consumption of edge nodes into a kinematics system, collecting speed and acceleration of load change in real time, calculating system pressure momentum, and generating a graded unloading instruction when the momentum exceeds a preset critical collapse threshold value; starting a convergent differential injection mechanism, pre-constructing a logic shadow at a cloud end, and calculating a convergence ratio of a memory dirty page generation rate to a network transmission rate in real time; the method has the advantages of being high in practicability, having the pre-judgment capacity and being capable of achieving lossless switching.

A user equipment (UE) route selection policy (URSP) detection method including obtaining first policy section identifier (PSI) information corresponding to a first URSP rule corresponding to a target user equipment, the first URSP rule being matched with a target service flow corresponding to the target user equipment, generating a first packet detection rule based on the first URSP rule that corresponds to the first PSI information, configuring the first packet detection rule to a user plane function (UPF) network element of a first protocol data unit (PDU) session, the first PDU session corresponding to the first URSP rule, and receiving, from the UPF network elements, a first detection result based on the first packet detection rule and indicating whether the target service flow associated with the first PDU session matches the first packet detection rule.

A novel dynamic bandwidth allocation system integrates an intelligent traffic prediction module and an on-demand token replenishment module in a quality-of-service (QoS)-based media access control (MAC) layer controller, which is able to dynamically allocate data transmission capacity (i.e., bandwidth) to multiple incoming service flows of data packets for multiple subscribers more efficiently with less network congestions and service inconsistencies than conventional MAC layer management methods. The novel dynamic bandwidth allocation system utilizes network traffic predictions to identify potentially sudden or rapid changes in near-term network traffic, and if necessary, adjusts bandwidth allocations preemptively to service flows to minimize service quality degradations while also improving network resource usage efficiencies, compared to conventional static bandwidth allocation methods. The novel dynamic bandwidth allocation system also minimizes unnecessary packet droppages, network congestions, and / or speed degradations during bursty and oscillating network traffic, and improves QoS satisfaction rates for network subscribers.

The invention discloses a dynamic self-verification method based on service flow-test flow homologous heterogeneous execution. The method comprises the following steps: uniformly describing service logic and a corresponding interface test contract through a strong type of domain specific language (DSL); the method comprises the following steps: simultaneously compiling homologous DSL descriptions into stateful business workflows executed by a process engine and stateless and combinable atomic test contract sets called by a test executor by utilizing a double-path compiling engine; during operation, loose coupling synchronous triggering and execution of a service flow and a test flow are realized based on a high-throughput event bus, and real-time and high-fidelity contract verification, performance monitoring and chaos probe testing are performed on cross-system interface calling in a production environment. According to the invention, the traditional post-event and off-line integration test is converted into the in-event, on-line and continuous system endogenous capability, and the industrial problems that the complex enterprise system group integration test is difficult and the operation and maintenance monitoring is passive are effectively solved.

The invention discloses a multi-target flow dynamic allocation method based on deep learning, which comprises the following steps: collecting network topology data, link operation data and service flow request data to form a network state sequence; a multi-target constraint set is obtained and written into a target constraint description table; constructing a state vector, and dividing the state vector into multiple groups of input sub-vectors; carrying out conjoint analysis on the service flow, and constructing a candidate allocation action set; constructing an improved CMAC network model, and outputting an action value vector; constructing an anti-multi-arm bandit decision-making module, and outputting action selection distribution; and executing multi-target feasible region projection processing to generate a feasible traffic distribution decision. According to the method, the improved CMAC network model is introduced, and the anti-multi-arm bandit decision-making method is combined, so that stable and self-adaptive dynamic distribution of the network traffic under the multi-target constraint and complex network state is realized.

The invention discloses a service flow scheduling method, equipment and a medium. The method comprises the following steps: acquiring business flow scheduling instruction information; analyzing the service flow scheduling instruction information to obtain a service flow scheduling constraint condition corresponding to the scheduling target and an effective condition of the service flow scheduling constraint condition; obtaining queue state information of a service flow queue of each service flow scheduling level; constructing a service flow scheduling optimization model based on the service flow scheduling constraint condition and the queue state information under the condition that the effective condition is met, and solving the service flow scheduling optimization model to obtain a scheduling strategy of the first service flow; wherein the service flow scheduling hierarchy comprises a flow hierarchy, a queue hierarchy and a port hierarchy. According to the technical scheme, the problem that the multi-layer queue business flow scheduling effect needs to be improved at present is solved, the stability of business flow scheduling can be improved through collaborative scheduling management of the multi-layer business flow queues and an intelligent decision-making mechanism for dynamically adjusting parameters, and the business transmission service effect is guaranteed.

The invention discloses a discrete service flow predictive digital triggering method and system under time delay constraint, and relates to the field of network service quality assurance, and the method comprises the steps: collecting an arrival time sequence, a packet length sequence, network state data and service level protocol parameters of a plurality of discrete service flows; performing multi-scale dependency decomposition on the arrival time sequence, and predicting an arrival amount and a queuing length in a future time window; calculating and predicting a residual time delay budget in combination with the maximum tolerant time delay, and mapping the residual time delay budget into a digital triggering probability representing the scheduling urgency degree; and further fusing the stream importance index to determine the scheduling weight, and dynamically adjusting the service sequence and resource allocation of the edge nodes according to the scheduling weight. Therefore, advanced scheduling triggering of multiple paths of service flows is realized, and the time delay guarantee capability and the resource scheduling efficiency are improved.

A novel dynamic bandwidth allocation system and a method of its operation incorporate a quality-of-service (QOS)-based media access control (MAC) layer controller, which is able to dynamically allocate data transmission capacity (i.e. bandwidth) to multiple incoming service flows of data packets for multiple subscribers more efficiently with less network congestions and service inconsistencies than conventional MAC layer management methods. The QoS-based MAC layer controller is able to determine and place incoming service flows into two separate states of token buckets (i.e. conforming or non-conforming), wherein the conforming token bucket utilizes a longer filtering interval (e.g. 1 second) and the non-conforming token bucket utilizes a shorter filtering interval (e.g. 1 ms) for detecting token bucket violations. The QoS-based MAC layer controller is able to utilize either conforming or non-conforming states flexibly and intelligently to minimize unnecessary packet droppages, network congestions, or speed degradations during bursty and oscillating network traffic.

The invention discloses a data center dynamic energy-saving scheduling method and system based on AI prediction, electronic equipment and a storage medium, and the method comprises the steps: collecting load data of a data center server and external service flow data in real time to construct an original data set, and processing the original data set through employing a long short-term memory network to obtain a load change trend; according to the load change trend, determining distribution characteristics of the thermal load trend in a future time window, extracting idle computing resource data from the server group based on the distribution characteristics, and computing a computing resource distribution proportion needing to be adjusted; carrying out iterative optimization on the calculation resource distribution proportion by adopting a genetic algorithm to obtain an optimized server load distribution scheme; through a server load distribution scheme, obtaining associated refrigeration system parameter data, determining an adjustment vector of a refrigeration strategy, fusing real-time energy consumption data of a power supply module, and judging a correction demand of power supply scheduling; and obtaining the operation configuration of the overall energy efficiency optimization according to the correction demand.

The invention discloses a heterogeneous deterministic network cross-domain periodic mapping method, a heterogeneous deterministic network cross-domain periodic mapping system and a related device, and belongs to the technical field of power system communication, and the method comprises the following steps: for a power service end-to-end deterministic network formed by a plurality of different sub-network domains, monitoring a buffer queue state through an edge gateway node of the heterogeneous deterministic network; performing queue management on the data packets of the service flow through the edge gateway node according to the queue state monitoring result of the buffer area, and obtaining queuing and queue offset distribution results of the data packets in the buffer area; the edge gateway node calculates and distributes a mapping period of the cross-domain network; and in combination with queuing and queue offset allocation results of the data packets in the buffer area, the edge gateway node feeds back and optimizes the time delay determinacy guarantee condition of the service flow, and the allocation of network resources and the routing strategy of the service flow are adjusted. According to the method, dynamic mapping of different network periods in a heterogeneous deterministic network scene can be realized, and scene requirements of dynamic changes of services and networks can be better met.

The present disclosure provides a configuration method, including: determining, according to OAN service types, information of at least one OAN slice for transmitting an OAN service flow of each OAN service type; determining, according to OTN service types, information of at least one OTN slice for transmitting an OTN service flow of each OTN service type; and establishing, according to a correspondence relationship of the OAN service types and the OTN service types, a mapping relationship between the at least one OAN slice and the at least one OTN slice to obtain information of at least one end-to-end slice, where each end-to-end slice includes a set of OAN slice and OTN slice having a mapping relationship. The present disclosure further provides a data transmission method, a controller, an optical line terminal, and a computer-readable storage medium.

The invention discloses a cache resource management method and device, equipment and a storage medium, and relates to the field of communication. A pre-occupied cache needing to be occupied by the to-be-processed data can be determined based on the time delay and the packet rate of the service flow of the first port, and a cache threshold value of the first port is determined according to unused caches except the pre-occupied caches of all ports in the queue caches and the pre-occupied cache of the first port. The cache threshold of the first port is determined not only based on the unused cache, but also based on the pre-occupied cache required by the time delay and the packet rate of the service traffic of the first port, so that the pre-occupied cache of the first port is different when different degrees of time delay jitter and / or traffic burst occur; therefore, the cache threshold of the first port can be improved according to the cache demand of the first port, and packet loss caused by traffic burst and / or delay jitter is reduced.

The present document relates to a handover support method for an important communication service, and an apparatus therefor. To this end, the method by which a target network device allowing a user equipment (UE) to perform handover supports handover of the UE in a mobile communication system comprises: receiving, by the target network device, a handover request message of the UE, the handover request message including bearer information configured such that the UE receives a source network device and one communication service flow through two or more bearers; and transmitting a handover request response message on the basis of the bearer information.

The embodiment of the invention provides a service flow configuration method and device, a storage medium and a program product, relates to the technical field of communication, and can improve the transmission efficiency of a service flow. The method comprises: sending a first message, the first message being used for a negotiation request of an extended service flow, the extended service flow being a service flow carrying an extended flow identifier; and receiving a second message, wherein the second message is used for indicating a negotiation response of the extended service flow.

Provided in the embodiments of the present disclosure are a route selection method, a storage medium, an electronic apparatus, and a computer program product. The method comprises: a controller determining a timeslot cross entry of each sub-burst of a target service flow, and sending a first announcement message to an ingress node of a timeslot queuing and forwarding domain, such that the ingress node constructs a first forwarding entry on the basis of the first announcement message. The first announcement message comprises timeslot cross entries, wherein each timeslot cross entry comprises an ideal inbound timeslot and an outbound timeslot stack, the ideal inbound timeslot is an ideal inbound timeslot of each sub-burst at the ingress node of the timeslot queuing and forwarding domain, and the outbound timeslot stack comprises an outbound timeslot of each node of a traffic engineering path corresponding to each sub-burst.

The invention discloses a test system, method and device of a priority mapping function, a storage medium and a program product, and relates to the technical field of network communication. A test management platform of the test system of the priority mapping function is in communication connection with a management port of a tested device through network ports in a first network port group; the test equipment is in communication connection with the service port of the tested equipment through the network ports in the second network port group; due to the fact that the priority mapping configuration instruction and the service flow data are sent in the connection mode that different network ports are separated from each other, transmission of the control flow data and transmission of the service flow data are not interfered with each other, and the testing accuracy is improved. Meanwhile, full-process automation from test case generation, test execution to result verification is achieved, and the manual participation range in the test process is reduced.

The embodiment of the invention relates to the technical field of computers, in particular to an inter-service flow anomaly detection and treatment method, device and equipment. The anomaly detection and treatment method for the traffic between the services comprises the steps of receiving original traffic data between the services; transmitting the original traffic data to a kernel space of the CPU, reading the original traffic data in the kernel space through a kernel resident program, and extracting specified field information of traffic from the original traffic data; extracting multi-dimensional traffic features from the specified field information, and performing traffic anomaly detection based on the multi-dimensional traffic features; and if the abnormal event is detected, generating a corresponding exception handling scheme, and executing the exception handling scheme. The method has microsecond-level anomaly detection capability, and can realize accurate anomaly identification and disposal.

This application relates to a link switching method based on traffic pattern recognition. The method includes: performing traffic behavior fingerprint analysis on the traffic data of the service flow to be transmitted on the current link to obtain the traffic behavior fingerprint of the service flow to be transmitted; predicting the service intent of the service flow to be transmitted within a future time window based on the traffic behavior fingerprint and the historical traffic behavior fingerprint of the service flow to be transmitted, to obtain a traffic intent vector; projecting the traffic intent onto each candidate link based on the traffic intent vector and the link capability profile of each candidate link of the service flow to be transmitted, to obtain a target twin link; and performing bi-state link convergence migration on the service flow to be transmitted based on the virtual bearer result of the target twin link, to obtain the service flow to be transmitted via the target twin link. This method can effectively improve the foresight, accuracy, and continuity of link switching.

Embodiments of the present disclosure relate to implementing dynamic service flows in a cable convergence network. An access gateway function (AGF) device receives quality of service (QoS) information associated with a packet data unit (PDU) session of a cable modem device from an access and mobility management function (AMF) device of a core network. The AGF device determines QoS matching criterion information based on the QoS information. The AGF device sends a service flow creation message to a cable modem termination system (CMTS) associated with the cable modem device over an interface between the AGF device and the CMTS, such as a General Open Policy Service (COPS) interface, the service flow creation message including QoS matching criterion information. Sending a service flow creation message enables the CMTS to create a first service flow between the CMTS and the cable modem device, and enables the cable modem device to create a second service flow between the cable modem device and the CMTS.

A user equipment may receive a payload notification configuration from a network node, the payload notification configuration including a baseline notification priority level and a notification priority delta value associated with an identifier of a traffic flow. A user equipment may generate a status message to be transmitted according to an uplink control channel opportunity resource, the status message including a status indication corresponding to a payload corresponding to a traffic flow received by the user equipment. The user equipment may prioritize the status indication in the status message according to a baseline notification priority indicated in the payload notification configuration and based on the capacity of the opportunity resource for accommodating the status indication. A baseline notification priority corresponding to a status indication not included in the status message may be increased by a notification priority increment such that the status indication is prioritized in the next status message higher than another status indication corresponding to a higher baseline notification priority in the payload notification configuration.