CN117424848B - Node call optimization method, system, equipment and medium based on machine learning - Google Patents
Node call optimization method, system, equipment and medium based on machine learning Download PDFInfo
- Publication number
- CN117424848B CN117424848B CN202311744007.XA CN202311744007A CN117424848B CN 117424848 B CN117424848 B CN 117424848B CN 202311744007 A CN202311744007 A CN 202311744007A CN 117424848 B CN117424848 B CN 117424848B
- Authority
- CN
- China
- Prior art keywords
- node
- network
- network performance
- nodes
- interface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000010801 machine learning Methods 0.000 title claims abstract description 33
- 238000005457 optimization Methods 0.000 title claims abstract description 33
- 238000004891 communication Methods 0.000 claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 43
- 230000006870 function Effects 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000003062 neural network model Methods 0.000 claims abstract description 14
- 238000004088 simulation Methods 0.000 claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
- H04L45/08—Learning-based routing, e.g. using neural networks or artificial intelligence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a node call optimization method, a system, equipment and a medium based on machine learning, which comprise the following steps: determining a network topology structure and a service node set according to the received network communication demand; configuring function interfaces for different service nodes in the service node set, and determining calling relations among the different service nodes according to the function interfaces; performing node simulation communication based on the network topology structure and the calling relation, and collecting communication data and request processing time among nodes; extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm to serve as a training data set; training the training data set through a preset neural network model to obtain a trained network performance prediction model; and determining a routing path with optimal network performance according to the network performance prediction model. The invention can optimize the route path among the nodes and realize the high-efficiency communication among the nodes of the centerless network.
Description
Technical Field
The present invention relates to the field of cluster communication technologies, and in particular, to a method, a system, an apparatus, and a medium for optimizing node call based on machine learning.
Background
With the continued development of computer networks, the design of network structures has become more and more complex. Conventional centralized network architectures have not been able to meet the complex user needs. Thus, a centreless network structure has been created; a centerless network architecture refers to a network architecture that has no central nodes and all nodes communicate and communicate equally between each other. The method has high robustness and reliability, and can effectively cope with node faults and network attacks.
Although there are many advantages to the centerless network structure, there are some potential drawbacks in practical applications at present, for example, because all nodes in the centerless network can provide services to the outside, and the centerless network often needs to use a distributed algorithm to manage communication and data consistency between nodes, which increases the complexity of the network and results in low communication efficiency of the nodes.
Disclosure of Invention
The invention provides a node call optimization method, a system, equipment and a medium based on machine learning, which can optimize routing paths among nodes and realize efficient communication among nodes of a centerless network.
In order to solve the technical problems, an embodiment of the present invention provides a node call optimization method based on machine learning, the method including:
determining a network topology structure and a service node set according to the received network communication demand;
configuring function interfaces for different service nodes in the service node set, and determining calling relations among the different service nodes according to the function interfaces;
based on the network topology structure and the calling relation, carrying out inter-node analog communication, and collecting communication data and request processing time between nodes;
extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm to serve as a training data set;
training the training data set through a preset neural network model to obtain a trained network performance prediction model;
determining a routing path with optimal network performance according to the network performance prediction model;
the determining a routing path with optimal network performance according to the network performance prediction model includes:
predicting the network performance of the network topology structure through the network performance prediction model to obtain network performance prediction data; wherein the network performance prediction data comprises a network state and a network workload;
and selecting an optimal routing path among the service nodes through a preset dynamic adjustment routing algorithm according to the network performance data.
Preferably, the configuring the function interface for different service nodes in the service node set, and determining the call relationship between different service nodes according to the function interface, includes:
marking the node information of the service node to generate node information;
generating a node data set according to the node information;
configuring function interfaces for different service nodes in the service node set;
generating interface structure information according to the functional interface;
generating an interface data set according to the interface structure information;
and determining the calling relation between the service nodes according to the node data set and the interface data set.
Preferably, the method further comprises:
when the service node is added, updating the node data set according to the node information of the added service node;
when deleting the service node, updating the node data set according to the node information of the deleted service node;
when an interface is added, updating the interface data set according to the interface structure information of the added interface;
and when the interface is deleted, updating the interface data set according to the interface structure information of the deleted interface.
Preferably, the method further comprises:
the terminal sends a first access request to at least one service node;
the service node receives the first access request, performs access analysis on the first access request, and detects whether the target node accessed by the first access request is abnormal;
if yes, returning node access failure information;
if not, judging whether the target node is a current service node; when the target node is the current service node, directly returning an access result; when the target node is not the current service node, a second access request is established according to the target node, the current service node accesses according to the second access request, and an access result is returned to the terminal; and the service node accessed by the second access request is the target node.
Preferably, the node information includes a node unique code and an IP address;
the service nodes all store the node data sets;
the interface structure information at least comprises an interface unique code, an interface name, a call address, an input parameter, an output parameter, a function description, a parameter unique code, a parameter name and a parameter type.
Preferably, the network topology is a centerless star network topology.
Compared with the prior art, the invention discloses a node calling optimization method based on machine learning, which comprises the following steps: determining a network topology structure and a service node set according to the received network communication demand; configuring function interfaces for different service nodes in the service node set, and determining calling relations among the different service nodes according to the function interfaces; performing node simulation communication based on the network topology structure and the calling relation, and collecting communication data and request processing time among nodes; extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm to serve as a training data set; training the training data set through a preset neural network model to obtain a trained network performance prediction model; and determining a routing path with optimal network performance according to the network performance prediction model. The method comprises the steps that data and data related to network performance can be extracted through a preset feature extraction algorithm and used as a training set, a network performance prediction model is obtained through training of a neural network model, communication among network nodes is predicted through the network performance prediction model, a prediction result is obtained, an optimal route path is selected according to the prediction result, and calling relations among the nodes are adjusted according to the optimal route path; therefore, the invention can optimize the route path among the nodes and realize the high-efficiency communication among the nodes of the centerless network.
In order to solve the above technical problem, the embodiment of the present invention further provides a node call optimization system based on machine learning, where the system includes:
the network construction module is used for determining a network topological structure and a service node set according to the received network communication requirement, configuring function interfaces for different service nodes in the service node set, and determining calling relations among different service nodes according to the function interfaces;
the simulation communication module is used for carrying out the simulation communication between the nodes based on the network topological structure and the calling relation, and collecting the communication data and the request processing time between the nodes;
the data processing module is used for extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm and taking the data characteristics as a training data set;
the neural network training module is used for training the training data set through a preset neural network model to obtain a trained network performance prediction model;
the node call optimization module is used for determining a routing path with optimal network performance according to the network performance prediction model;
the determining a routing path with optimal network performance according to the network performance prediction model includes:
predicting the network performance of the network topology structure through the network performance prediction model to obtain network performance prediction data; wherein the network performance prediction data comprises a network state and a network workload;
and selecting an optimal routing path among the service nodes through a preset dynamic adjustment routing algorithm according to the network performance data.
Preferably, the configuring the function interface for different service nodes in the service node set, and determining the call relationship between different service nodes according to the function interface, includes:
marking the node information of the service node to generate node information;
generating a node data set according to the node information;
configuring function interfaces for different service nodes in the service node set;
generating interface structure information according to the functional interface;
generating an interface data set according to the interface structure information;
and determining the calling relation between the service nodes according to the node data set and the interface data set.
Preferably, the network construction module is further configured to:
when the service node is added, updating the node data set according to the node information of the added service node;
when deleting the service node, updating the node data set according to the node information of the deleted service node;
when an interface is added, updating the interface data set according to the interface structure information of the added interface;
and when the interface is deleted, updating the interface data set according to the interface structure information of the deleted interface.
Preferably, the system further comprises a terminal communication module for:
sending a first access request to at least one service node through a terminal;
the service node receives the first access request, performs access analysis on the first access request, and detects whether the target node accessed by the first access request is abnormal;
if yes, returning node access failure information;
if not, judging whether the target node is a current service node; when the target node is the current service node, directly returning an access result; when the target node is not the current service node, a second access request is established according to the target node, the current service node accesses according to the second access request, and an access result is returned to the terminal; and the service node accessed by the second access request is the target node.
Preferably, the node information includes a node unique code and an IP address;
the service nodes all store the node data sets;
the interface structure information at least comprises an interface unique code, an interface name, a call address, an input parameter, an output parameter, a function description, a parameter unique code, a parameter name and a parameter type.
Preferably, the network topology is a centerless star network topology.
The embodiment of the invention also provides a terminal device, which is characterized by comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor realizes a node call optimization method based on machine learning when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, which is characterized in that the computer readable storage medium comprises a stored computer program; wherein the computer program, when running, controls a device in which the computer readable storage medium is located to execute a node call optimization method based on machine learning as described in any one of the above.
The invention discloses a node call optimization method, a system, equipment and a medium based on machine learning, which comprise the following steps: determining a network topology structure and a service node set according to the received network communication demand; configuring function interfaces for different service nodes in the service node set, and determining calling relations among the different service nodes according to the function interfaces; performing node simulation communication based on the network topology structure and the calling relation, and collecting communication data and request processing time among nodes; extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm to serve as a training data set; training the training data set through a preset neural network model to obtain a trained network performance prediction model; and determining a routing path with optimal network performance according to the network performance prediction model. The invention can optimize the route path among the nodes and realize the high-efficiency communication among the nodes of the centerless network.
Drawings
Fig. 1 is a schematic flow diagram of a node call optimization method based on machine learning according to an embodiment of the present invention.
Fig. 2 is a block diagram of a node call optimization system based on machine learning according to an embodiment of the present invention.
Fig. 3 is a block diagram of a preferred embodiment of a terminal device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention provides a node calling optimization method based on machine learning, and referring to fig. 1, the method is a flow diagram of the node calling optimization method based on machine learning, and the method comprises steps S10-S15:
s10: determining a network topology structure and a service node set according to the received network communication demand;
s11: configuring function interfaces for different service nodes in the service node set, and determining calling relations among the different service nodes according to the function interfaces;
s12: based on the network topology structure and the calling relation, carrying out inter-node analog communication, and collecting communication data and request processing time between nodes;
s13: extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm to serve as a training data set;
s14: training the training data set through a preset neural network model to obtain a trained network performance prediction model;
s15: and determining a routing path with optimal network performance according to the network performance prediction model.
When the invention is embodied, a network topology structure and a service node set are determined according to the received network communication requirement, the determined network topology structure is a centerless star network topology structure, an access request can be started from any service node, and the service node is usually an entity responsible for providing specific service in a system or a network, and the requirements of users are met through cooperative work and the reliability and the performance of the system are ensured; after the network topology structure and the service nodes are determined, function interfaces are configured for different service nodes in a centralized manner for the service nodes, calling relations among the different service nodes are determined according to the function interfaces, the simulation communication of the whole network can be realized based on the network topology structure and the calling relations among the nodes, and access requests can be sent among the nodes and data transmission can be carried out according to the calling relations. Collecting communication data and request processing time among nodes, and extracting data features of the communication data and the request processing time through a preset feature extraction algorithm to serve as a training data set; extracting data features related to network performance by a feature extraction algorithm commonly used in deep learning to be used as a training data set; inputting a training data set into a preset neural network model to train the training data set, so as to obtain a trained network performance prediction model; and finally, testing the network performance among the network nodes again through a network performance prediction model, determining an optimal routing path, adjusting the nodes, and further optimizing the calling relationship among the nodes.
The invention discloses a node calling optimization method based on machine learning, which comprises the following steps: determining a network topology structure and a service node set according to the received network communication demand; configuring function interfaces for different service nodes in the service node set, and determining calling relations among the different service nodes according to the function interfaces; performing node simulation communication based on the network topology structure and the calling relation, and collecting communication data and request processing time among nodes; extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm to serve as a training data set; training the training data set through a preset neural network model to obtain a trained network performance prediction model; and determining a routing path with optimal network performance according to the network performance prediction model. The method comprises the steps that data and data related to network performance can be extracted through a preset feature extraction algorithm and used as a training set, a network performance prediction model is obtained through training of a neural network model, communication among network nodes is predicted through the network performance prediction model, a prediction result is obtained, an optimal route path is selected according to the prediction result, and calling relations among the nodes are adjusted according to the optimal route path; therefore, the invention can optimize the route path among the nodes and realize the high-efficiency communication among the nodes of the centerless network.
In yet another embodiment provided by the present invention, node information is marked on the service node to generate node information; generating a node data set according to the node information; configuring function interfaces for different service nodes in the service node set; generating interface structure information according to the functional interface; generating an interface data set according to the interface structure information; and determining the calling relation between the service nodes according to the node data set and the interface data set.
In the implementation of this embodiment, the service node is marked with node information, where the marked information includes a node unique code and an IP address, for example, mark service node a, and service node a: a unique code S001; IP address: 192.168.0.10; all service nodes in the network topology are marked according to the marking mode. Collecting node information of all nodes and manufacturing a node data set, wherein each node stores the node data set; then, a functional interface is configured for the service node, the functional interface is used as an information channel for data transmission between nodes, and the service node capable of communicating with the functional interface can be determined according to the interface of the service node, so that the interface data can be used as a basis for calling relation between the nodes; the interface data generally includes: the interface unique code, interface name, call address, input parameters, output parameters, and remarks, which are typically related to the function description and the keyword description. Generating an interface data set from the interface data, and determining the calling relation of the service node in the whole network topology structure through the interface data and the node data set; the node data set and the interface data set are generated, so that unified management of the nodes and the interfaces is facilitated, and the node calling relationship determined by the node data and the interface data is more definite and efficient.
In yet another embodiment provided by the present invention, the network performance prediction model predicts the network performance of the network topology structure to obtain network performance prediction data; wherein the network performance prediction data comprises a network state and a network workload;
and selecting an optimal routing path among the service nodes through a preset dynamic adjustment routing algorithm according to the network performance data.
When the embodiment is implemented, the network performance prediction is performed on the network topology structure through a network performance prediction model, so as to obtain network performance prediction data, wherein the network performance prediction data comprises a network state and a network workload, the network state and the network workload serve as evaluation indexes of routing paths, an optimal routing path is selected according to the evaluation indexes, and network nodes are optimized and adjusted according to the optimal routing path, so that overall communication efficiency is improved.
In yet another embodiment of the present invention, when a service node is added, the node dataset is updated according to node information of the added service node; when deleting the service node, updating the node data set according to the node information of the deleted service node; when an interface is added, updating the interface data set according to the interface structure information of the added interface; and when the interface is deleted, updating the interface data set according to the interface structure information of the deleted interface.
When the embodiment is implemented, each node stores a node data set, and the node data set stores all node information in the network; each node also stores an interface data set, and the interface data set stores all interface information, that is, when the node and the interface are increased or decreased, the update of the whole network topology structure can be indirectly realized only by updating the corresponding data set, so that the data update is more convenient, and the network topology is least influenced by the node or the interface change.
In yet another embodiment provided by the present invention, the terminal sends a first access request to at least one of the service nodes; the service node receives the first access request, performs access analysis on the first access request, and detects whether the target node accessed by the first access request is abnormal; if yes, returning node access failure information; if not, judging whether the target node is a current service node; when the target node is the current service node, directly returning an access result; when the target node is not the current service node, a second access request is established according to the target node, the current service node accesses according to the second access request, and an access result is returned to the terminal; and the service node accessed by the second access request is the target node.
When the terminal needs to access to the network, the service node receiving the access request can analyze the access, for example, whether the access is normal or not and whether the accessed node exists in the node data set; only the service node will be processed by the analyzed access request; judging whether the access request is the current node or not again, if yes, directly sending the access content to the terminal, if not, not needing the terminal to establish the access request again, wherein the current service node can directly generate a second access request according to the accessed target node to search the target node and acquire the access content needed by the terminal, and then forwarding the access content to the terminal; through the content, the terminal can flexibly access the network node without repeated access, so that the access efficiency and the communication efficiency of the node are further improved, and the node can directly establish the second access request according to the target node.
In yet another embodiment provided by the present invention, the node information includes a node unique code and an IP address; the service nodes all store the node data sets; the interface structure information at least comprises an interface unique code, an interface name, a call address, an input parameter, an output parameter, a function description, a parameter unique code, a parameter name and a parameter type.
When the embodiment is implemented, the corresponding nodes can be accurately searched through the marks of the information, so that the node addressing is clearer and clearer, and the guarantee is provided for efficient communication among the nodes.
In yet another embodiment provided by the present invention, the network topology is a centerless star network topology.
When the embodiment is implemented, the capacity of any service node to finish the access task can be realized through the centerless star network topology structure, so that the fault tolerance of the network topology structure can be improved.
The embodiment of the invention also provides a node call optimization system based on machine learning, and referring to fig. 2, the node call optimization system based on machine learning is a structural block diagram of the node call optimization system based on machine learning, and the system comprises:
the network construction module 20 is configured to determine a network topology structure and a service node set according to the received network communication requirement, configure functional interfaces for different service nodes in the service node set, and determine calling relationships between different service nodes according to the functional interfaces;
a simulation communication module 21, configured to perform a simulation communication between nodes based on the network topology and the call relationship, and collect communication data and request processing time between nodes;
a data processing module 22, configured to extract data features of the communication data and the request processing time through a preset feature extraction algorithm, as a training data set;
the neural network training module 23 is configured to train the training data set through a preset neural network model, so as to obtain a trained network performance prediction model;
the node invokes the optimizing module 24 for determining a routing path with optimal network performance according to the network performance prediction model.
The system and the module can implement all the processes of the node call optimization method based on machine learning described in any one of the above embodiments, and the functions and the implemented technical effects of each module and unit in the system are respectively the same as those of the node call optimization method based on machine learning described in the above embodiments, and are not repeated here.
The embodiment of the present invention further provides a terminal device, referring to fig. 3, which is a block diagram of a preferred embodiment of a terminal device provided by the embodiment of the present invention, where the terminal device includes a processor 30, a memory 31, and a computer program stored in the memory 31 and configured to be executed by the processor 30, where the processor 30 implements a node call optimization method based on machine learning according to any one of the foregoing embodiments when executing the computer program.
Preferably, the computer program may be partitioned into one or more modules/units (e.g., computer program 1, computer program 2, & gtthe & lt- & gt) that are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program in the terminal device.
The processor 30 may be a central processing unit (Central Processing Unit, CPU), it may be a microprocessor, it may be other general purpose processor, it may be a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc., or it may be any conventional processor, the processor 30 may be a control center of the terminal device, and various interfaces and lines may be used to connect the various parts of the terminal device.
The memory 31 mainly includes a program storage area, which can store an operating system, an application program required for at least one function, and the like, and a data storage area, which can store related data and the like. In addition, the memory 31 may be a high-speed random access memory, a nonvolatile memory such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), or the like, or the memory 31 may be other volatile solid-state memory devices.
The embodiment of the invention also provides a computer readable storage medium, which comprises a stored computer program; wherein the computer program, when executed, controls a device on which the computer readable storage medium resides to perform a machine learning based node call optimization method as described in any of the above embodiments.
It should be noted that the above-described apparatus embodiments are merely illustrative, and the units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of 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. In addition, in the drawings of the embodiment of the device provided by the invention, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
In summary, the invention discloses a node call optimization method, a system, equipment and a medium based on machine learning, comprising the following steps: determining a network topology structure and a service node set according to the received network communication demand; configuring function interfaces for different service nodes in the service node set, and determining calling relations among the different service nodes according to the function interfaces; performing node simulation communication based on the network topology structure and the calling relation, and collecting communication data and request processing time among nodes; extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm to serve as a training data set; training the training data set through a preset neural network model to obtain a trained network performance prediction model; and determining a routing path with optimal network performance according to the network performance prediction model. The invention can optimize the route path among the nodes and realize the high-efficiency communication among the nodes of the centerless network.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (9)
1. A machine learning based node call optimization method, the method comprising:
determining a network topology structure and a service node set according to the received network communication demand;
configuring function interfaces for different service nodes in the service node set, and determining calling relations among the different service nodes according to the function interfaces;
based on the network topology structure and the calling relation, carrying out inter-node analog communication, and collecting communication data and request processing time between nodes;
extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm to serve as a training data set;
training the training data set through a preset neural network model to obtain a trained network performance prediction model;
determining a routing path with optimal network performance according to the network performance prediction model;
the determining a routing path with optimal network performance according to the network performance prediction model includes:
predicting the network performance of the network topology structure through the network performance prediction model to obtain network performance prediction data; wherein the network performance prediction data comprises a network state and a network workload;
and selecting an optimal routing path among the service nodes through a preset dynamic adjustment routing algorithm according to the network performance data.
2. The method for optimizing node call based on machine learning according to claim 1, wherein said configuring function interfaces for different service nodes in said set of service nodes and determining call relationships between different service nodes according to said function interfaces comprises:
marking the node information of the service node to generate node information;
generating a node data set according to the node information;
configuring function interfaces for different service nodes in the service node set;
generating interface structure information according to the functional interface;
generating an interface data set according to the interface structure information;
and determining the calling relation between the service nodes according to the node data set and the interface data set.
3. The machine learning based node call optimization method of claim 2, wherein the method further comprises:
when the service node is added, updating the node data set according to the node information of the added service node;
when deleting the service node, updating the node data set according to the node information of the deleted service node;
when an interface is added, updating the interface data set according to the interface structure information of the added interface;
and when the interface is deleted, updating the interface data set according to the interface structure information of the deleted interface.
4. The machine learning based node call optimization method of claim 1, wherein the method further comprises:
the terminal sends a first access request to at least one service node;
the service node receives the first access request, performs access analysis on the first access request, and detects whether the target node accessed by the first access request is abnormal;
if yes, returning node access failure information;
if not, judging whether the target node is a current service node; when the target node is the current service node, directly returning an access result; when the target node is not the current service node, a second access request is established according to the target node, the current service node accesses according to the second access request, and an access result is returned to the terminal; and the service node accessed by the second access request is the target node.
5. A machine learning based node call optimization method as claimed in claim 2, wherein said node information includes a node unique code and an IP address;
the service nodes all store the node data sets;
the interface structure information at least comprises an interface unique code, an interface name, a call address, an input parameter, an output parameter, a function description, a parameter unique code, a parameter name and a parameter type.
6. A machine learning based node call optimization method according to claim 2, wherein the network topology is a centreless star network topology.
7. A machine learning based node call optimization system, the system comprising:
the network construction module is used for determining a network topological structure and a service node set according to the received network communication requirement, configuring function interfaces for different service nodes in the service node set, and determining calling relations among different service nodes according to the function interfaces;
the simulation communication module is used for carrying out the simulation communication between the nodes based on the network topological structure and the calling relation, and collecting the communication data and the request processing time between the nodes;
the data processing module is used for extracting the data characteristics of the communication data and the request processing time through a preset characteristic extraction algorithm and taking the data characteristics as a training data set;
the neural network training module is used for training the training data set through a preset neural network model to obtain a trained network performance prediction model;
the node call optimization module is used for determining a routing path with optimal network performance according to the network performance prediction model;
the determining a routing path with optimal network performance according to the network performance prediction model includes:
predicting the network performance of the network topology structure through the network performance prediction model to obtain network performance prediction data; wherein the network performance prediction data comprises a network state and a network workload;
and selecting an optimal routing path among the service nodes through a preset dynamic adjustment routing algorithm according to the network performance data.
8. A terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing a machine learning based node call optimization method according to any one of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, wherein the computer readable storage medium comprises a stored computer program; wherein the computer program, when running, controls a device in which the computer readable storage medium is located to execute a node call optimization method based on machine learning as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311744007.XA CN117424848B (en) | 2023-12-19 | 2023-12-19 | Node call optimization method, system, equipment and medium based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311744007.XA CN117424848B (en) | 2023-12-19 | 2023-12-19 | Node call optimization method, system, equipment and medium based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117424848A CN117424848A (en) | 2024-01-19 |
| CN117424848B true CN117424848B (en) | 2024-03-26 |
Family
ID=89528798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311744007.XA Active CN117424848B (en) | 2023-12-19 | 2023-12-19 | Node call optimization method, system, equipment and medium based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117424848B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115333958A (en) * | 2022-08-15 | 2022-11-11 | 中国电信股份有限公司 | Software defined network performance prediction method and device, electronic equipment and storage medium |
| CN115473838A (en) * | 2022-09-15 | 2022-12-13 | 中国电信股份有限公司 | Network request processing method and device, computer readable medium and electronic equipment |
| CN116527565A (en) * | 2023-05-11 | 2023-08-01 | 清华大学 | Internet route optimization method and device based on graph convolution neural network |
| CN116963182A (en) * | 2023-08-18 | 2023-10-27 | 网络通信与安全紫金山实验室 | Time delay optimal task unloading method and device, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10666547B2 (en) * | 2018-10-25 | 2020-05-26 | Ca, Inc. | Efficient machine learning for network optimization |
| US20200184494A1 (en) * | 2018-12-05 | 2020-06-11 | Legion Technologies, Inc. | Demand Forecasting Using Automatic Machine-Learning Model Selection |
-
2023
- 2023-12-19 CN CN202311744007.XA patent/CN117424848B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115333958A (en) * | 2022-08-15 | 2022-11-11 | 中国电信股份有限公司 | Software defined network performance prediction method and device, electronic equipment and storage medium |
| CN115473838A (en) * | 2022-09-15 | 2022-12-13 | 中国电信股份有限公司 | Network request processing method and device, computer readable medium and electronic equipment |
| CN116527565A (en) * | 2023-05-11 | 2023-08-01 | 清华大学 | Internet route optimization method and device based on graph convolution neural network |
| CN116963182A (en) * | 2023-08-18 | 2023-10-27 | 网络通信与安全紫金山实验室 | Time delay optimal task unloading method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117424848A (en) | 2024-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108924274B (en) | Domain name system DNS processing method and device, storage medium and electronic equipment | |
| CN112367211B (en) | Method, device and storage medium for generating configuration template by device command line | |
| CN108427619B (en) | Log management method and device, computing equipment and storage medium | |
| CN109151025B (en) | Load balancing method and device based on URL, computer storage medium and equipment | |
| CN114091610A (en) | Intelligent decision method and device | |
| CN114064206A (en) | Pod method, system, equipment and storage medium for accessing edge node | |
| CN115529232A (en) | Control method and device for convergence and distribution equipment and storage medium | |
| CN113868367A (en) | Method, device and system for constructing knowledge graph and computer storage medium | |
| CN116760834A (en) | Load balancing method, system, equipment and storage medium | |
| WO2019163912A1 (en) | Network system, topology management method, and program | |
| CN114025000A (en) | Method, device, equipment and storage medium for establishing network access relationship | |
| CN117424848B (en) | Node call optimization method, system, equipment and medium based on machine learning | |
| CN115314419B (en) | Cloud network-oriented self-adaptive connectivity analysis method, system, equipment and storage medium | |
| CN112688884B (en) | Encrypted flow custom application identification method, system, device and storage medium | |
| CN113946611A (en) | Information mining method based on AI network and intelligent operation server | |
| CN113934767A (en) | Data processing method and device, computer equipment and storage medium | |
| CN116192723B (en) | Network routing link generation method and device and electronic equipment | |
| CN117640363B (en) | Micro-service configuration and management and control method and system | |
| EP3767922B1 (en) | Method of channel mapping in an industrial process control system | |
| CN114615150B (en) | Simulation network generation method and device | |
| CN111132121B (en) | Information processing method and network warehouse function NRF network element | |
| CN114528266B (en) | Method, system, device and storage medium for realizing database and cache consistency | |
| CN117880227B (en) | Chip routing system, method and related device | |
| CN111464520B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN114157721A (en) | Route distribution method, device, equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |