Asymmetric flow processing method and system based on multi-core optical fiber data center network

By constructing the topological relationship diagram of multi-core fiber network and path slicing processing, and calculating the signal coupling coefficient, the problem of inefficient asymmetric traffic processing in the multi-core fiber data center network is solved, and efficient traffic transmission and signal stability are achieved.

CN118944755AInactive Publication Date: 2024-11-12SHENZHEN POLYTECHNIC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410909439.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-08
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In multi-core fiber optic data center networks, signal damage caused by core crosstalk and complex traffic processing algorithms lead to inefficient asymmetric traffic processing and increased transmission delay.

Method used

By building a multi-core fiber network topology diagram between the data center node and the client node, the bidirectional traffic requirements are determined, the traffic bytes of the same-direction and reverse signal channels are counted, the path segmentation is performed, and the calculation is based on the same-direction signal characteristics are calculated based on the same-direction signal characteristics. Coupling coefficient, if the conditions are not met, a bidirectional optical core is built in the slicing reverse link for traffic transmission.

Benefits of technology

It improves the asymmetric traffic processing efficiency of the central network, reduces crosstalk between the cores, and ensures efficient data transmission.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118944755A_ABST
    Figure CN118944755A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of network flow transmission, and provides an asymmetric flow processing method and system based on a multi-core optical fiber data center network, and the method comprises the steps: constructing a multi-core optical fiber network topological relation graph between a data center node and a client node; determining a fiber channel of a bidirectional flow demand between the central node and the client node; when the bytes of the bidirectional traffic between the central node and the client node are inconsistent, selecting to perform bidirectional segmentation on the optical core in the multi-core optical fiber according to the actual demand of the bidirectional traffic; and executing traffic transmission between the data center node and the client node in the bidirectional optical core to obtain a traffic transmission result. According to the invention, the asymmetrical flow processing efficiency of the central network can be improved, and crosstalk between fiber cores can be reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of network traffic transmission technology, and in particular to an asymmetric traffic processing method and system based on a multi-core optical fiber data center network. Background Art

[0002] Data generation has increased significantly with the rapid expansion of cloud services such as artificial intelligence, data analytics, and machine learning, which rely on computing resources in remote data centers to process large amounts of data. In multi-core fiber (MCF)-based spatial division multiplexing (SDM) data center networks, core crosstalk can cause severe impairments between optical signals in adjacent cores on the same wavelength.

[0003] At present, asymmetric traffic processing in central networks is carried out according to the load of the network and the resource limitations of the system. By dynamically scheduling and adjusting the traffic, some traffic may be restricted in bandwidth or given a lower priority to ensure the stable transmission of critical traffic. However, due to the complex traffic processing algorithms and routing selection decisions, asymmetric traffic processing in central networks may introduce additional transmission delays, which in turn leads to inefficient asymmetric traffic processing in central networks. Summary of the invention

[0004] In order to solve the above problems, the present invention provides an asymmetric traffic processing method and system based on a multi-core optical fiber data center network, which can improve the asymmetric traffic processing efficiency of the central network while reducing crosstalk between fiber cores.

[0005] In a first aspect, the present invention provides an asymmetric traffic processing method based on a multi-core optical fiber data center network, comprising:

[0006] Acquire data center nodes and client nodes applied to a multi-core optical fiber data center network, and construct a multi-core optical fiber network topology relationship diagram between the data center nodes and the client nodes;

[0007] In response to the bidirectional traffic demand sent by the client node to the data center node, determine the optical fiber channel of the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram, wherein the optical fiber channel includes a codirectional signal channel and a reverse signal channel;

[0008] According to the bidirectional traffic demand, the traffic bytes in the codirectional signal channel and the reverse signal channel are counted respectively to obtain bidirectional traffic bytes, and when the bidirectional traffic bytes between the central node and the client node are inconsistent, the codirectional signal channel and the reverse signal channel are path-splitting based on the bidirectional traffic demand to obtain a split codirectional link and a split reverse link;

[0009] Extracting the co-directional signal characteristics in the split co-directional link, and calculating the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics;

[0010] When the codirectional signal coupling coefficient does not meet the preset conditions, a bidirectional optical core corresponding to the split codirectional link is constructed in the split reverse link, and traffic transmission between the data center node and the client node is performed in the bidirectional optical core to obtain a traffic transmission result.

[0011] In a possible implementation manner of the first aspect, constructing a multi-core optical fiber network topology relationship diagram between the data center node and the client node includes:

[0012] Query the node function corresponding to the data center node;

[0013] Determine the topological relationship between the nodes in the data center according to the node function to obtain a first topological relationship;

[0014] Obtaining node description information corresponding to the client node;

[0015] Analyzing the topological relationship between the client nodes according to the node description information to obtain a second topological relationship;

[0016] Scan the port information corresponding to the data center node;

[0017] Analyze the topological relationship between the data center node and the client node according to the port information and the node description information to obtain a third topological relationship;

[0018] In combination with the first topological relationship, the second topological relationship and the third topological relationship, a multi-core optical fiber network topological relationship diagram between the data center node and the client node is constructed.

[0019] In a possible implementation manner of the first aspect, analyzing the topological relationship between the data center node and the client node according to the port information and the node description information to obtain the third topological relationship includes:

[0020] Identify the protocol information in the node description information, and extract the protocol association information in the port information;

[0021] Performing vectorization processing on the protocol information and the protocol association information respectively to obtain a first protocol vector and a second protocol vector;

[0022] calculating a vector similarity between the first protocol vector and the second protocol vector;

[0023] According to the vector similarity, the data center node and the client node are divided into nodes to obtain classification nodes;

[0024] Determining a node logical relationship in the classification node according to the protocol information and the protocol association information;

[0025] The node logical relationship is used as the topological relationship between the data center node and the client node to obtain a third topological relationship.

[0026] In a possible implementation of the first aspect, in response to the bidirectional traffic demand sent by the client node to the data center node, determining the optical fiber channel of the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram includes:

[0027] Analyze the transmission data volume corresponding to the bidirectional traffic demand, and calculate the node distance between the client node and the data center node;

[0028] Querying the node bandwidth corresponding to the data center node, and calculating the transmission delay corresponding to the bidirectional traffic demand according to the transmission data volume and the node bandwidth;

[0029] Setting the node priority corresponding to the data center node, and filtering the interaction center node corresponding to the client node from the data center node in combination with the node priority and the transmission delay;

[0030] According to the interactive central node and the client node, a fiber channel for bidirectional traffic demand between the central node and the client node is determined from the multi-core optical fiber network topology relationship diagram.

[0031] In a possible implementation manner of the first aspect, setting the node priority corresponding to the data center node includes:

[0032] Reading a node log corresponding to the data center node, and determining a node task volume and abnormal statistical data corresponding to the data center node according to the node log;

[0033] Calculate the node utilization rate of the data center node according to the node task volume;

[0034] Calculate the node health corresponding to the data center node according to the abnormal statistical data;

[0035] The node priority corresponding to the data center node is set in combination with the node utilization and the node health.

[0036] In a possible implementation manner of the first aspect, the counting of traffic bytes in the same-direction signal channel and the reverse signal channel respectively according to the bidirectional traffic demand to obtain the bidirectional traffic bytes includes:

[0037] Collecting the same-direction traffic data corresponding to the two-way traffic demand, and obtaining the data task corresponding to the same-direction traffic data;

[0038] Counting the data packets corresponding to the same-direction traffic data to obtain the same-direction data packets;

[0039] Counting bytes of the same-direction data packets to obtain the same-direction flow bytes of the same-direction signal channel;

[0040] According to the data task, data exchange processing is performed on the same-direction flow data to obtain exchange flow data;

[0041] Counting the data packets corresponding to the exchange traffic data to obtain reverse data packets, and counting the bytes of the reverse data packets to obtain reverse traffic bytes;

[0042] The same-direction traffic byte and the reverse-direction traffic byte are combined to obtain a bidirectional traffic byte.

[0043] In a possible implementation manner of the first aspect, the path splitting of the co-directional signal channel and the reverse signal channel based on the bidirectional traffic demand to obtain a split co-directional link and a split reverse link includes:

[0044] Performing byte cleaning processing on the bidirectional traffic bytes to obtain target traffic bytes;

[0045] Calculate the byte standard deviation corresponding to the target traffic byte, and analyze the byte stability corresponding to the target traffic byte according to the byte standard deviation;

[0046] In combination with the byte stability, the same-direction signal channel and the reverse signal channel are path-segmented to obtain a segmented same-direction link and a segmented reverse link.

[0047] In a possible implementation manner of the first aspect, combining the byte stability and performing path splitting processing on the co-directional signal channel to obtain a split co-directional link and a split reverse link includes:

[0048] Extracting link nodes of the same-direction signal channel and the reverse signal channel, and searching for associated nodes corresponding to the link nodes;

[0049] Detecting the node states corresponding to the link node and the associated node in real time to obtain the link node state and the associated node state;

[0050] According to the associated node state and the byte stability, path tracing is performed on the associated node to obtain an associated path;

[0051] According to the associated path, path splitting processing is performed on the in-direction signal channel and the reverse signal channel to obtain a split in-direction link and a split reverse link.

[0052] In a possible implementation manner of the first aspect, the calculating, based on the co-directional signal feature, the co-directional signal coupling coefficient in the split co-directional link includes:

[0053] Calculating the characteristic entropy value corresponding to the same-direction signal feature;

[0054] Normalizing the characteristic entropy value to obtain a target characteristic entropy value;

[0055] According to the target feature, assigning a feature weight corresponding to the same-direction signal feature;

[0056] Calculating the feature correlation between the same-direction signal features;

[0057] The co-directional signal coupling coefficient in the split co-directional link is calculated according to the feature association degree and the feature weight.

[0058] In a second aspect, the present invention provides an asymmetric traffic processing system based on a multi-core optical fiber data center network, the system comprising:

[0059] A relationship graph construction module, used to obtain data center nodes and client nodes applied to a multi-core optical fiber data center network, and to construct a multi-core optical fiber network topology relationship graph between the data center nodes and the client nodes;

[0060] A link determination module, configured to determine, in response to a bidirectional traffic demand sent by the client node to the data center node, a fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram, wherein the fiber channel includes a codirectional signal channel and a reverse signal channel;

[0061] A path splitting module is used to count the traffic bytes in the same direction signal channel and the reverse signal channel respectively according to the bidirectional traffic demand to obtain the bidirectional traffic bytes, and when the bidirectional traffic bytes between the central node and the client node are inconsistent, the same direction signal channel is path split based on the same direction traffic bytes to obtain a split same direction link, and the reverse signal channel is path split based on the reverse traffic bytes to obtain a split reverse link;

[0062] A coupling coefficient calculation module, used for extracting the co-directional signal characteristics in the split co-directional link, and calculating the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics;

[0063] A traffic transmission module is used to construct a bidirectional optical core corresponding to the split codirectional link in the split reverse link when the codirectional signal coupling coefficient does not meet the preset conditions, and to perform traffic transmission between the data center node and the client node in the bidirectional optical core to obtain a traffic transmission result.

[0064] Compared with the prior art, the technical principle and beneficial effects of this solution are:

[0065] The embodiment of the present invention constructs a multi-core optical fiber network topology relationship diagram between the data center node and the client node to facilitate visualization of the network structure, thereby increasing the understanding of the central network and providing a basis for the subsequent determination of the optical fiber channel. Furthermore, the embodiment of the present invention determines the optical fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram to ensure that data can be efficiently transmitted from the client node to the data center node, thereby facilitating the subsequent asymmetric traffic processing of the multi-core optical fiber data center network. Furthermore, the embodiment of the present invention respectively counts the traffic bytes in the same-direction signal channel and the reverse signal channel, which can be used to calculate the data transmitted in both directions. The data quantity is quantified and recorded, which is convenient for subsequent path splitting processing, thereby reducing the mutual crosstalk between signal transmissions in the link. The embodiment of the present invention calculates the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics, so as to understand the degree of correlation between co-directional signals, so as to evaluate the stability and quality of signal transmission. It should be understood that when the co-directional signal coupling coefficient does not meet the preset conditions, it means that the split co-directional link can no longer complete normal signal transmission. The present invention constructs a bidirectional optical core corresponding to the split co-directional link in the split reverse link to execute the traffic transmission between the data center node and the client node, thereby improving the asymmetric traffic processing efficiency of the central network. The asymmetric traffic processing method and system based on a multi-core optical fiber data center network proposed in the embodiment of the present invention can improve the asymmetric traffic processing efficiency of the central network while reducing the crosstalk between the fiber cores. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0067] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0068] Figure 1 A schematic diagram of a flow chart of an asymmetric traffic processing method based on a multi-core optical fiber data center network provided by one embodiment of the present invention;

[0069] Figure 2 A schematic diagram of a module of an asymmetric traffic processing system based on a multi-core optical fiber data center network provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0070] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0071] The embodiment of the present invention provides an asymmetric traffic processing method based on a multi-core fiber data center network, and the execution subject of the asymmetric traffic processing method based on the multi-core fiber data center network includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the asymmetric traffic processing method based on a multi-core fiber data center network can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0072] See also Figure 1 FIG. 1 is a flow chart of an asymmetric traffic processing method based on a multi-core optical fiber data center network provided by an embodiment of the present invention. Figure 1 The asymmetric traffic processing method based on a multi-core optical fiber data center network described in the specification includes:

[0073] S1. Acquire data center nodes and client nodes applied to a multi-core optical fiber data center network, and construct a multi-core optical fiber network topology relationship diagram between the data center nodes and the client nodes.

[0074] The embodiment of the present invention constructs a multi-core fiber network topology relationship diagram between the data center node and the client node to facilitate visualization of the network structure, thereby increasing the understanding of the data center and providing a basis for the subsequent determination of the fiber channel. The multi-core fiber data center network is a high-performance data center network architecture that combines fiber optic transmission technology with multi-core processor technology. The data center node generally refers to the core node or centralized management node of the network, which has higher processing power, greater bandwidth and more complex functions, and is used to process the routing, forwarding, management and control of network traffic. The client node refers to a terminal device or user device that is connected to the network and requests or receives services from the data center node. These nodes can be computers, smart phones, tablets or other network terminal devices.

[0075] As an embodiment of the present invention, the construction of a multi-core optical fiber network topology relationship diagram between the data center node and the client node includes: querying the node function corresponding to the data center node, determining the topology relationship between the data center nodes according to the node function, obtaining a first topology relationship, obtaining the node description information corresponding to the client node, analyzing the topology relationship between the client nodes according to the node description information, obtaining a second topology relationship, scanning the port information corresponding to the data center node, analyzing the topology relationship between the data center node and the client node according to the port information and the node description information, obtaining a third topology relationship, and combining the first topology relationship, the second topology relationship and the third topology relationship to construct a multi-core optical fiber network topology relationship diagram between the data center node and the client node.

[0076] Among them, the node function is the service provided by the data center node, such as transmitting data and storing information; the first topological relationship represents the physical connection relationship and logical relationship between the data center nodes; the node description information is the self-description information about the client node, such as the node's characteristics or identifier information; the port information is the physical interface or logical interface of the data center node, which is used to connect other devices or nodes.

[0077] Optionally, the node function corresponding to the data center node can be queried through a network monitoring tool, such as a Nagios tool; the topological relationship between the data center nodes can be determined based on the node function, and based on the node tasks, services or responsibilities in the node function, the interaction mode, communication path and data flow between the nodes can be identified, thereby obtaining a first topological relationship; the node description information corresponding to the client node can be obtained through a SolarWinds tool; the topological relationship between the client nodes can be obtained by analyzing the node description information, and by identifying the input and output information in the node description information, the logical relationship between the client nodes, such as sequence or no direct relationship, can be determined, thereby obtaining a second topological relationship; scanning of the port information corresponding to the data center node can be achieved through a port scanning tool, such as an Nmap tool; construction of a multi-core fiber optic network topology relationship diagram between the data center node and the client node can be achieved through a drawing tool, such as a Visio tool.

[0078] Further, as an optional embodiment of the present invention, the topological relationship between the data center node and the client node is analyzed according to the port information and the node description information to obtain a third topological relationship, including: identifying the protocol information in the node description information, extracting the protocol association information in the port information, vectorizing the protocol information and the protocol association information respectively to obtain a first protocol vector and a second protocol vector, calculating the vector similarity between the first protocol vector and the second protocol vector, dividing the data center node and the client node according to the vector similarity to obtain classification nodes, determining the node logical relationship in the classification node according to the protocol information and the protocol association information, using the node logical relationship as the topological relationship between the data center node and the client node to obtain a third topological relationship.

[0079] Among them, the protocol association information is the information related to the protocol in the port information. Optionally, the identification of the protocol information in the node description information can be achieved through OCR recognition technology; the extraction of the protocol association information in the port information can be achieved by combining a port mapping table, wherein the port mapping table is a table of mapping relationships between different port numbers and various protocols; the vectorization processing of the protocol information and the protocol association information can be achieved through a word2vec algorithm; the calculation of the vector similarity between the first protocol vector and the second protocol vector can be achieved through a cosine similarity algorithm; the node division of the data center node and the client node can be achieved when the vector similarity is greater than a preset similarity, and the preset similarity can be 0.8, or it can be set according to the actual application scenario; the node logical relationship in the classification node can be determined by analyzing the content in the protocol information and the protocol association information.

[0080] S2. In response to the bidirectional traffic demand sent by the client node to the data center node, determine the optical fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram, wherein the optical fiber channel includes a unidirectional signal channel and a reverse signal channel.

[0081] An embodiment of the present invention determines the optical fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology diagram, so as to ensure that the client node can efficiently transmit data to the data center node, thereby facilitating the subsequent asymmetric traffic processing of the multi-core optical fiber data center network, wherein the bidirectional traffic demand is the data transmission volume corresponding to the sending and receiving feedback of the client node to the data center node, the optical fiber channel is the link of the request sent by the client node to the data center node, the unidirectional signal channel refers to the link from the source address to the destination address, and the reverse signal channel refers to the link from the destination address to the source address.

[0082] As an embodiment of the present invention, in response to the bidirectional traffic demand sent by the client node to the data center node, determining the optical fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram, includes: analyzing the transmission data volume corresponding to the bidirectional traffic demand, calculating the node distance between the client node and the data center node, querying the node bandwidth corresponding to the data center node, calculating the transmission delay corresponding to the bidirectional traffic demand based on the transmission data volume and the node bandwidth, and setting the node priority corresponding to the data center node, combining the node priority and the transmission delay, screening out the interactive central node corresponding to the client node from the data center node, and determining the optical fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram based on the interactive central node and the client node.

[0083] Among them, the node bandwidth is the processing data transmission rate corresponding to the data center node, the transmission delay indicates the time for the data center node to transmit data, the node priority indicates the corresponding priority of the data center node when processing data, and the interactive center node is the best node for data interaction among the data center nodes.

[0084] Optionally, the amount of transmission data corresponding to the bidirectional traffic demand can be obtained by analyzing the label content corresponding to the bidirectional traffic demand, such as information on data type, service level, priority requirements, etc.; the calculation of the node distance between the client node and the data center node can be implemented by the Dijkstra algorithm; the node bandwidth corresponding to the data center node can be obtained by querying SNMP (Simple Network Management Protocol), and by querying the data center node through SNMP, its current bandwidth utilization can be obtained; the transmission delay corresponding to the bidirectional traffic demand can be obtained by calculating the ratio of the transmission data volume and the node bandwidth; the interactive center node corresponding to the client node can be obtained by screening from the data center nodes by combining the node priority and the corresponding performance of the transmission delay; the interactive center node and the client node are marked in the multi-core optical fiber network topology relationship diagram to determine the optical fiber channel for the bidirectional traffic demand between the center node and the client node.

[0085] Further, as an optional embodiment of the present invention, setting the node priority corresponding to the data center node includes: reading the node log corresponding to the data center node, determining the node task volume and abnormal statistical data corresponding to the data center node based on the node log, calculating the node utilization corresponding to the data center node based on the node task volume, calculating the node health corresponding to the data center node based on the abnormal statistical data, and setting the node priority corresponding to the data center node in combination with the node utilization and the node health.

[0086] Among them, the node log is the information of activities and events recorded by the nodes in the network, the node task volume is the current processing tasks and remaining unprocessed tasks corresponding to the data center node, and optionally, the reading of the node log corresponding to the data center node can be achieved through a log server; the node utilization corresponding to the data center node can be obtained by calculating the total working time required for the unprocessed tasks and the processing tasks in the node task volume, and calculating the ratio of the total working time to the total available time corresponding to the data center node to obtain the node utilization, wherein the total available time can be obtained by the system administrator recording the running time of the system; the node health corresponding to the data center node can be obtained by dividing the total duration of the fault in the abnormal statistical data by the total available time of the node; according to the network requirements of the central network, the importance of the node utilization and the node health of each node to the network performance and stability are analyzed respectively, and appropriate weights are assigned to the node utilization and the node health, and the node utilization and the node health are multiplied by the corresponding weights and summed to obtain the node score value, and the node priority is set according to the node score value.

[0087] S3. According to the bidirectional traffic demand, the traffic bytes in the codirectional signal channel and the reverse signal channel are respectively counted to obtain bidirectional traffic bytes, and when the bidirectional traffic bytes between the central node and the client node are inconsistent, the codirectional signal channel is path-splitting based on the codirectional traffic bytes to obtain a split codirectional link, and the reverse signal channel is path-splitting based on the reverse traffic bytes to obtain a split reverse link.

[0088] The embodiment of the present invention counts the traffic bytes in the same-direction signal channel and the reverse signal channel respectively, and can quantify and record the amount of data transmitted in two directions, thereby facilitating subsequent path segmentation processing, thereby reducing mutual crosstalk between signal transmissions in the link.

[0089] As an embodiment of the present invention, according to the bidirectional traffic demand, the traffic bytes in the unidirectional signal channel and the reverse signal channel are respectively counted to obtain bidirectional traffic bytes, including: collecting the unidirectional traffic data corresponding to the bidirectional traffic demand, and obtaining the data task corresponding to the unidirectional traffic data, counting the data packets corresponding to the unidirectional traffic data to obtain unidirectional data packets, counting the bytes of the unidirectional data packets to obtain the unidirectional traffic bytes of the unidirectional signal channel, performing data exchange processing on the unidirectional traffic data according to the data task to obtain exchange traffic data, and counting the data packets corresponding to the exchange traffic data to obtain reverse data packets, counting the bytes of the reverse data packets to obtain reverse traffic bytes, and combining the unidirectional traffic bytes and the reverse traffic bytes to obtain bidirectional traffic bytes.

[0090] Among them, the unidirectional traffic data is the data that the bidirectional traffic demand needs to be sent to the data center node for processing, the data task is the processing target corresponding to the unidirectional traffic data, and the unidirectional data packet is the basic data unit in the unidirectional traffic data.

[0091] Furthermore, the same-direction traffic data corresponding to the two-way traffic demand can be collected by a traffic analyzer; the data tasks corresponding to the same-direction traffic data can be obtained by a network traffic analysis tool, such as Wireshark; the statistics of the data packets corresponding to the same-direction traffic data can be processed by writing custom scripts or programs, and these scripts can parse the data packets and count the relevant information, such as the number of data packets, size, protocol distribution, etc. Using Python, Perl, or other programming languages ​​can help achieve this purpose; the byte count of the same-direction data packets can be achieved by a network packet capture tool, such as the tcpdump tool; the same-direction traffic data can be processed according to the data tasks to obtain the exchange traffic data.

[0092] The present invention divides the co-directional signal channel into different parts by performing path segmentation on the co-directional signal channel based on the co-directional traffic bytes to obtain segmented co-directional links, so as to accurately analyze problems occurring during the transmission process later.

[0093] As an embodiment of the present invention, based on the bidirectional traffic demand, the co-directional signal channel and the reverse signal channel are path-segmented to obtain a segmented co-directional link and a segmented reverse link, including: performing byte cleaning processing on the bidirectional traffic bytes to obtain target traffic bytes, calculating the byte standard deviation corresponding to the target traffic bytes, analyzing the byte stability corresponding to the target traffic bytes based on the byte standard deviation, and performing path segmentation on the co-directional signal channel and the reverse signal channel in combination with the byte stability to obtain a segmented co-directional link and a segmented reverse link.

[0094] Optionally, the calculation of the byte standard deviation corresponding to the target traffic byte can be achieved by a standard deviation calculator; the byte stability corresponding to the target traffic byte can be analyzed according to the numerical size of the byte standard deviation, and the larger the byte standard deviation, the lower the byte stability.

[0095] As an optional embodiment of the present invention, the method combines the byte stability to perform path splitting processing on the same-direction signal channel to obtain a split same-direction path, including: extracting link nodes of the same-direction signal channel and the reverse signal channel, searching for associated nodes corresponding to the link nodes, detecting the node states corresponding to the link nodes and the associated nodes in real time to obtain link node states and associated node states, performing path tracing on the associated nodes according to the associated node states and the byte stability to obtain an associated path, and performing path splitting processing on the same-direction signal channel and the reverse signal channel according to the associated path to obtain a split same-direction link and a split reverse link.

[0096] Among them, the associated node is a node with the same function as the link node, and can replace the adjacent node of the link node. The associated path is the unidirectional link path formed by the associated node. Optionally, the path tracking of the associated node can be achieved by using a network path tracking tool based on the associated node status, such as a traceroute tool, wherein a node with an idle state and high stability of the associated node is selected during the path tracking process; according to the associated node, the split point corresponding to the associated path is determined, and according to the split point, the associated path is split into the unidirectional signal channel to obtain a split unidirectional path.

[0097] S4. Extracting the co-directional signal characteristics in the split co-directional link, and calculating the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics.

[0098] The embodiment of the present invention calculates the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal feature, so as to understand the correlation between the co-directional signals, so as to evaluate the stability and quality of signal transmission. The co-directional signal coupling coefficient represents the correlation between the co-directional signals in the split co-directional link, and optionally, the extraction of the co-directional signal feature in the split co-directional link can be achieved by a time domain feature extraction method.

[0099] As an embodiment of the present invention, the calculation of the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal feature includes: calculating a characteristic entropy value corresponding to the co-directional signal feature, normalizing the characteristic entropy value to obtain a target characteristic entropy value, allocating a characteristic weight corresponding to the co-directional signal feature according to the target feature, calculating a characteristic correlation between the co-directional signal features, and calculating the co-directional signal coupling coefficient in the split co-directional link according to the characteristic correlation and the characteristic weight.

[0100] Among them, the characteristic entropy value represents the uncertainty corresponding to the co-directional signal feature, the target characteristic entropy value is the value obtained by mapping the characteristic entropy value to the same scale, the characteristic correlation degree represents the characteristic correlation between the co-directional signal features, and optionally, the characteristic entropy value corresponding to the co-directional signal feature can be calculated by the Shannon entropy formula; the normalization processing of the characteristic entropy value can be achieved by the minimum-maximum normalization method; the characteristic correlation degree between the co-directional signal features can be calculated by the Pearson correlation coefficient formula; the co-directional signal coupling coefficient in the split co-directional link can be obtained by calculating the product of the characteristic correlation degree and the corresponding characteristic weight and summing them.

[0101] S5. When the co-directional signal coupling coefficient does not meet the preset conditions, a bidirectional optical core corresponding to the split co-directional link is constructed in the split reverse link, and traffic transmission between the data center node and the client node is performed in the bidirectional optical core to obtain a traffic transmission result.

[0102] It should be understood that when the co-directional signal coupling coefficient does not meet the preset conditions, it means that the split co-directional link can no longer complete normal signal transmission. The present invention constructs a bidirectional optical core corresponding to the split co-directional link in the split reverse link to execute traffic transmission between the data center node and the client node, thereby improving the asymmetric traffic processing efficiency of the central network. The bidirectional optical core is a core program for optimizing or adjusting the characteristics of optical signal transmission. The construction of the bidirectional optical core corresponding to the split co-directional link in the split reverse link can be achieved through a programming program. According to communication requirements and network planning, a suitable optical fiber type, such as single-mode optical fiber or multi-mode optical fiber, is selected. Then, the internal composition of the bidirectional optical core is designed according to the communication system requirements and transmission characteristics to meet signal transmission or refraction and other processing.

[0103] The embodiment of the present invention constructs a multi-core optical fiber network topology relationship diagram between the data center node and the client node to facilitate visualization of the network structure, thereby increasing the understanding of the central network and providing a basis for the subsequent determination of the optical fiber channel. Furthermore, the embodiment of the present invention determines the optical fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram to ensure that data can be efficiently transmitted from the client node to the data center node, thereby facilitating the subsequent asymmetric traffic processing of the multi-core optical fiber data center network. Furthermore, the embodiment of the present invention respectively counts the traffic bytes in the same-direction signal channel and the reverse signal channel, which can be used to calculate the data transmitted in both directions. The data quantity is quantified and recorded, which is convenient for subsequent path splitting processing, thereby reducing the mutual crosstalk between signal transmissions in the link. The embodiment of the present invention calculates the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics, so as to understand the degree of correlation between co-directional signals, so as to evaluate the stability and quality of signal transmission. It should be understood that when the co-directional signal coupling coefficient does not meet the preset conditions, it means that the split co-directional link can no longer complete normal signal transmission. The present invention constructs a bidirectional optical core corresponding to the split co-directional link in the split reverse link to execute the traffic transmission between the data center node and the client node, thereby improving the asymmetric traffic processing efficiency of the central network. The asymmetric traffic processing method based on a multi-core optical fiber data center network proposed in the embodiment of the present invention can improve the asymmetric traffic processing efficiency of the central network while reducing the crosstalk between the fiber cores.

[0104] like Figure 2 Shown is an asymmetric traffic processing method and system functional module diagram based on a multi-core optical fiber data center network of the present invention.

[0105] The asymmetric traffic processing system 200 based on the multi-core optical fiber data center network of the present invention can be installed in an electronic device. According to the functions to be implemented, the equipment safety control system under bridge construction implemented by the Internet of Things can include the relationship graph construction module 201, the link determination module 202, the path segmentation module 203, the coupling coefficient calculation module 204 and the traffic transmission module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0106] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0107] The relationship graph construction module 201 is used to obtain data center nodes and client nodes applied to a multi-core optical fiber data center network, and to construct a multi-core optical fiber network topology relationship graph between the data center nodes and the client nodes;

[0108] The link determination module 202 is used to determine the optical fiber channel of the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram in response to the bidirectional traffic demand sent by the client node to the data center node, wherein the optical fiber channel includes a codirectional signal channel and a reverse signal channel;

[0109] The path splitting module 203 is used to count the traffic bytes in the same direction signal channel and the reverse signal channel respectively according to the bidirectional traffic demand to obtain the bidirectional traffic bytes, and when the bidirectional traffic bytes between the central node and the client node are inconsistent, the same direction signal channel and the reverse signal channel are path split based on the bidirectional traffic demand to obtain the split same direction link and the split reverse link;

[0110] The coupling coefficient calculation module 204 is used to extract the co-directional signal characteristics in the split co-directional link, and calculate the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics;

[0111] The traffic transmission module 205 is used to construct a bidirectional optical core corresponding to the split codirectional link in the split reverse link when the codirectional signal coupling coefficient does not meet the preset conditions, and to perform traffic transmission between the data center node and the client node in the bidirectional optical core to obtain a traffic transmission result.

[0112] In detail, the modules in the equipment safety control system 200 for bridge construction implemented by the Internet of Things in the embodiment of the present invention are used in the same manner as described above. Figure 1 to Figure 2The asymmetric traffic processing method based on the multi-core optical fiber data center network described in the invention has the same technical means and can produce the same technical effects, so it will not be repeated here.

[0113] The present invention further provides a storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0114] Acquire data center nodes and client nodes applied to a multi-core optical fiber data center network, and construct a multi-core optical fiber network topology relationship diagram between the data center nodes and the client nodes;

[0115] In response to the bidirectional traffic demand sent by the client node to the data center node, determine the optical fiber channel of the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram, wherein the optical fiber channel includes a codirectional signal channel and a reverse signal channel;

[0116] According to the bidirectional traffic demand, the traffic bytes in the codirectional signal channel and the reverse signal channel are counted respectively to obtain bidirectional traffic bytes, and when the bidirectional traffic bytes between the central node and the client node are inconsistent, the codirectional signal channel and the reverse signal channel are path-splitting based on the bidirectional traffic demand to obtain a split codirectional link and a split reverse link;

[0117] Extracting the co-directional signal characteristics in the split co-directional link, and calculating the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics;

[0118] When the codirectional signal coupling coefficient does not meet the preset conditions, a bidirectional optical core corresponding to the split codirectional link is constructed in the split reverse link, and traffic transmission between the data center node and the client node is performed in the bidirectional optical core to obtain a traffic transmission result.

[0119] In the several embodiments provided by the present invention, it should be understood that the provided devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0120] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0122] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0123] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0124] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0125] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An asymmetric traffic processing method based on a multi-core optical fiber data center network, characterized in that: The method comprises: Acquire data center nodes and client nodes applied to a multi-core optical fiber data center network, and construct a multi-core optical fiber network topology relationship diagram between the data center nodes and the client nodes; In response to the bidirectional traffic demand sent by the client node to the data center node, determine the optical fiber channel of the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram, wherein the optical fiber channel includes a codirectional signal channel and a reverse signal channel; According to the bidirectional traffic demand, the traffic bytes in the codirectional signal channel and the reverse signal channel are counted respectively to obtain bidirectional traffic bytes, and when the bidirectional traffic bytes between the central node and the client node are inconsistent, the codirectional signal channel and the reverse signal channel are path-splitting based on the bidirectional traffic demand to obtain a split codirectional link and a split reverse link; Extracting the co-directional signal characteristics in the split co-directional link, and calculating the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics; When the codirectional signal coupling coefficient does not meet the preset conditions, a bidirectional optical core corresponding to the split codirectional link is constructed in the split reverse link, and traffic transmission between the data center node and the client node is performed in the bidirectional optical core to obtain a traffic transmission result.

2. The method according to claim 1, characterized in that The constructing of a multi-core optical fiber network topology relationship diagram between the data center node and the client node includes: Query the node function corresponding to the data center node; Determine the topological relationship between the nodes in the data center according to the node function to obtain a first topological relationship; Obtaining node description information corresponding to the client node; Analyzing the topological relationship between the client nodes according to the node description information to obtain a second topological relationship; Scan the port information corresponding to the data center node; Analyze the topological relationship between the data center node and the client node according to the port information and the node description information to obtain a third topological relationship; In combination with the first topological relationship, the second topological relationship and the third topological relationship, a multi-core optical fiber network topological relationship diagram between the data center node and the client node is constructed.

3. The method according to claim 2, characterized in that The step of analyzing the topological relationship between the data center node and the client node according to the port information and the node description information to obtain a third topological relationship includes: Identify the protocol information in the node description information, and extract the protocol association information in the port information; Performing vectorization processing on the protocol information and the protocol association information respectively to obtain a first protocol vector and a second protocol vector; calculating a vector similarity between the first protocol vector and the second protocol vector; According to the vector similarity, the data center node and the client node are divided into nodes to obtain classification nodes; Determining a node logical relationship in the classification node according to the protocol information and the protocol association information; The node logical relationship is used as the topological relationship between the data center node and the client node to obtain a third topological relationship.

4. The method according to claim 1, characterized in that: The step of determining, in response to the bidirectional traffic demand sent by the client node to the data center node, a fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram comprises: Analyze the transmission data volume corresponding to the bidirectional traffic demand, and calculate the node distance between the client node and the data center node; Querying the node bandwidth corresponding to the data center node, and calculating the transmission delay corresponding to the bidirectional traffic demand according to the transmission data volume and the node bandwidth; Setting the node priority corresponding to the data center node, and filtering the interaction center node corresponding to the client node from the data center node in combination with the node priority and the transmission delay; According to the interactive central node and the client node, a fiber channel for bidirectional traffic demand between the central node and the client node is determined from the multi-core optical fiber network topology relationship diagram.

5. The method according to claim 4, characterized in that The setting of the node priority corresponding to the data center node includes: Reading a node log corresponding to the data center node, and determining a node task volume and abnormal statistical data corresponding to the data center node according to the node log; Calculate the node utilization rate of the data center node according to the node task volume; Calculate the node health corresponding to the data center node according to the abnormal statistical data; The node priority corresponding to the data center node is set in combination with the node utilization and the node health.

6. The method according to claim 1, characterized in that The step of respectively counting the traffic bytes in the same-direction signal channel and the reverse signal channel according to the bidirectional traffic demand to obtain the bidirectional traffic bytes includes: Collecting the same-direction traffic data corresponding to the two-way traffic demand, and obtaining the data task corresponding to the same-direction traffic data; Counting the data packets corresponding to the same-direction traffic data to obtain the same-direction data packets; Counting bytes of the same-direction data packets to obtain the same-direction flow bytes of the same-direction signal channel; According to the data task, data exchange processing is performed on the same-direction flow data to obtain exchange flow data; Counting the data packets corresponding to the exchange traffic data to obtain reverse data packets, and counting the bytes of the reverse data packets to obtain reverse traffic bytes; The same-direction traffic byte and the reverse-direction traffic byte are combined to obtain a bidirectional traffic byte.

7. The method according to claim 1, characterized in that The method of performing path segmentation on the co-directional signal channel and the reverse signal channel based on the bidirectional traffic demand to obtain segmented co-directional links and segmented reverse links includes: Performing byte cleaning processing on the bidirectional traffic bytes to obtain target traffic bytes; Calculate the byte standard deviation corresponding to the target traffic byte, and analyze the byte stability corresponding to the target traffic byte according to the byte standard deviation; In combination with the byte stability, the same-direction signal channel and the reverse signal channel are path-segmented to obtain a segmented same-direction link and a segmented reverse link.

8. The method according to claim 7, characterized in that The method of combining the byte stability and performing path segmentation processing on the co-directional signal channel to obtain segmented co-directional links and segmented reverse links includes: Extracting link nodes of the same-direction signal channel and the reverse signal channel, and searching for associated nodes corresponding to the link nodes; Detecting the node states corresponding to the link node and the associated node in real time to obtain the link node state and the associated node state; According to the associated node state and the byte stability, path tracing is performed on the associated node to obtain an associated path; According to the associated path, path splitting processing is performed on the in-direction signal channel and the reverse signal channel to obtain a split in-direction link and a split reverse link.

9. The method according to claim 1, characterized in that: The calculating, based on the co-directional signal characteristics, the co-directional signal coupling coefficient in the split co-directional link comprises: Calculating the characteristic entropy value corresponding to the same-direction signal feature; Normalizing the characteristic entropy value to obtain a target characteristic entropy value; According to the target feature, assigning a feature weight corresponding to the same-direction signal feature; Calculating the feature correlation between the same-direction signal features; The co-directional signal coupling coefficient in the split co-directional link is calculated according to the feature association degree and the feature weight.

10. An asymmetric traffic processing system based on a multi-core optical fiber data center network, characterized in that: The system comprises: A relationship graph construction module, used to obtain data center nodes and client nodes applied to a multi-core optical fiber data center network, and to construct a multi-core optical fiber network topology relationship graph between the data center nodes and the client nodes; A link determination module, configured to determine, in response to a bidirectional traffic demand sent by the client node to the data center node, a fiber channel for the bidirectional traffic demand between the central node and the client node from the multi-core optical fiber network topology relationship diagram, wherein the fiber channel includes a codirectional signal channel and a reverse signal channel; A path splitting module is used to count the traffic bytes in the same direction signal channel and the reverse signal channel respectively according to the bidirectional traffic demand to obtain the bidirectional traffic bytes, and when the bidirectional traffic bytes between the central node and the client node are inconsistent, the same direction signal channel is path split based on the same direction traffic bytes to obtain a split same direction link, and the reverse signal channel is path split based on the reverse traffic bytes to obtain a split reverse link; A coupling coefficient calculation module, used for extracting the co-directional signal characteristics in the split co-directional link, and calculating the co-directional signal coupling coefficient in the split co-directional link based on the co-directional signal characteristics; A traffic transmission module is used to construct a bidirectional optical core corresponding to the split codirectional link in the split reverse link when the codirectional signal coupling coefficient does not meet the preset conditions, and to perform traffic transmission between the data center node and the client node in the bidirectional optical core to obtain a traffic transmission result.