CN116232978A - Method for recommending optimal path for service opening - Google Patents
Method for recommending optimal path for service opening Download PDFInfo
- Publication number
- CN116232978A CN116232978A CN202310207317.1A CN202310207317A CN116232978A CN 116232978 A CN116232978 A CN 116232978A CN 202310207317 A CN202310207317 A CN 202310207317A CN 116232978 A CN116232978 A CN 116232978A
- Authority
- CN
- China
- Prior art keywords
- topological
- path
- nodes
- optimal path
- service
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000010586 diagram Methods 0.000 claims abstract description 12
- 230000003287 optical effect Effects 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 7
- 239000000758 substrate Substances 0.000 claims 2
- 239000000523 sample Substances 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 abstract description 5
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 235000008694 Humulus lupulus Nutrition 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- DWSYCUKCNSVBRA-UHFFFAOYSA-N 4-(5-methylsulfonyltetrazol-1-yl)phenol Chemical compound CS(=O)(=O)C1=NN=NN1C1=CC=C(C=C1)O DWSYCUKCNSVBRA-UHFFFAOYSA-N 0.000 description 1
- NIZKGBJVCMRDKO-KWQFWETISA-N Ala-Gly-Tyr Chemical compound C[C@H](N)C(=O)NCC(=O)N[C@H](C(O)=O)CC1=CC=C(O)C=C1 NIZKGBJVCMRDKO-KWQFWETISA-N 0.000 description 1
- 101710167643 Serine/threonine protein phosphatase PstP Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000036314 physical performance Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
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
- H04L45/02—Topology update or discovery
-
- 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
- H04L41/145—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
- H04L41/16—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
- H04L45/12—Shortest path evaluation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Optical Communication System (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a method for recommending a service opening optimal path, which belongs to the technical field of data transmission and comprises the following steps: acquiring service requirements of opening special line service and a topology structure diagram of the existing optical cable; acquiring all topological nodes between stations based on the acquired station information and a topological structure diagram; building a topological path selection model, inputting newly acquired attribute characteristics of topological nodes between sites into the built model, and obtaining an optimal path for opening the special line service through the model. The invention can rapidly release new service based on the existing private network topology, and improves the opening efficiency of the private service.
Description
Technical Field
The invention relates to the technical field of data transmission, in particular to a method for recommending a service opening optimal path.
Background
Currently, government and enterprise private lines mainly include internet private lines, data private lines, and Virtual Private Network (VPN) private lines. The internet private line is generally oriented to small and medium-sized micro clients, mainly provides internet access and access, adopts devices such as a Passive Optical Network (PON), a Packet Transport Network (PTN), a multi-service access platform (MSAP) or protocol conversion, and is basically consistent with the architecture of a common home broadband network. The data private line is usually oriented to large enterprise clients, and mainly provides a data transmission channel between the enterprises, and mainly comprises PTN, a multi-service transmission platform/synchronous digital hierarchy (MSTP/SDH) and other devices. VPN dedicated lines are usually large enterprise clients, implement VPN interconnection between different office areas, and mainly use multiprotocol label switching-virtual private network (MPLS-VPN) devices.
With the development of globalization, informatization and cloud services, private line demands will be increasing, and the private line service market will become a competitive focus in the 2B market in addition to the carrier 2C service (mobile service, broadband service).
When the government and enterprise private line service is opened, the most core link is to design and plan a proper optical path based on the selected starting point and the selected end point.
The private line network topology includes nodes formed by network element devices and pipes connecting the nodes. Dedicated line on refers to allocating a pipeline resource capable of realizing network data transmission between a given starting point and a given ending point (for example, a-Z).
Typically, when making a pipe route recommendation, the main recommendation rules can be categorized as: the idle communication path is optimal, the distance is short, the number of hops is small, the routing cannot be realized, the time delay is low, and the like. In these existing recommendation rules, the determination of the optimal route is implemented from a single direction or dimension, which results in a low overall performance of the recommended route path.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method for recommending a service opening optimal path. When the problem that the special line service in the OSS field is opened, when the service opening between the starting point and the end point is required to be carried out after the starting point and the end point are determined is solved, service staff is helped to quickly and accurately determine the optimal special line opening path based on the existing special line network topology
The technical scheme of the invention is as follows:
a method for recommending a service opening optimal path comprises the following steps:
acquiring site information in special line service opening requirements and a topology structure diagram of an existing optical cable, wherein the site information comprises initial site information and termination site information;
acquiring all topological nodes between stations based on the acquired station information and a topological structure diagram;
building a topological path selection model, inputting newly acquired attribute characteristics of topological nodes between sites into the built model, and obtaining an optimal path for opening the special line service through the model.
Further, the method comprises the steps of,
dividing a plurality of sites in site information into a plurality of site intervals according to a position adjacent relation, traversing a topological structure diagram according to the intervals to obtain a sub-node set, combining the sub-nodes to obtain the topological node set, and obtaining all the topological nodes between the sites.
The topological path selection model comprises an optimal path generation module and more than one constraint module.
The training steps of the path selection model are as follows:
1) Inputting the acquired multidimensional attribute characteristics of m topological nodes (which can be called transfer points) X= { x_1, x_2, … …, x_m } between the starting station and the ending station into an optimal path generation module;
2) Grouping all the service opening demands to obtain a plurality of service opening demand groups;
3) Inputting the opening attribute characteristics and a plurality of service opening requirement groups into a constraint module to obtain a plurality of groups of topological path sets corresponding to the requirement groups;
4) And adding the parameter adjustment coefficient to the model parameter in the optimal path generation model until the path distance between the optimal path generated by the optimal path generation model after parameter adjustment and the path distance in the multi-group topological path set obtained by constraint model is kept in a relatively constant range, and completing model training.
Still further, the method comprises the steps of,
the multidimensional attribute features comprise distribution bandwidth of nodes on topological links, topological relation of the nodes and QOT value of the topological links where the nodes are located, and QOT value can reflect physical properties of the links.
The grouping all the service opening requirements to obtain a plurality of service opening requirement groups comprises the following steps: clustering all the service opening requirements to obtain a plurality of service opening requirement groups.
And respectively calculating path distances between more than one group of topological paths and the optimal paths generated by the optimal path generation model, and then taking a set distance threshold value (average value of path distances obtained each time) as a parameter adjustment coefficient of the optimal path generation model. The parameter adjustment coefficient may be converted into an appropriate value range by conversion.
Still further, the method comprises the steps of,
the newly acquired attribute characteristics of m topological nodes X= { x_1, x_2, … … and x_m } between sites are input into a constructed optimal path generation module, and an optimal path for opening the special line service is obtained through the model.
The invention has the beneficial effects that
The method and the device can rapidly and accurately determine the optimal private line opening path based on the existing private line network topology by distributing bandwidth of the nodes on the topology links, topological relation of the nodes and QOT values of the topology links where the nodes are located and fitting path recommended values of different service demands in a path selection model, and compared with the scheme of realizing optimal route determination from a single direction or dimension in the prior art, the route path recommended by the scheme of the invention can determine the private line service opening path with high comprehensive performance on the whole and improve the operation and maintenance efficiency of the private line service opening.
Drawings
Fig. 1 is a schematic diagram of the operation of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
According to the technical scheme, the recommended method for opening the optimal optical path of the special line service is designed, so that the recommended route path can be guaranteed to achieve minimum overall time delay and less jumper connection.
According to the optimal path recommendation method, the optimal path recommendation is achieved through combining a machine learning algorithm. The detailed implementation scheme is as follows:
s1, acquiring a service requirement for opening a special line service and a topology structure diagram of an existing optical cable, wherein the service requirement comprises site information of the opening special line, such as A-G-Y.
S2, acquiring all topological nodes between stations based on the acquired station information and a topological structure diagram;
specifically, a plurality of sites in site information can be segmented into a plurality of site intervals according to a position adjacent relation, then a topology structure diagram is traversed according to the intervals, so that a plurality of groups of sub-node sets can be obtained, the sub-nodes are combined and combined to obtain a topology node set, and all topology nodes among the sites are obtained.
S3, constructing a topological path selection model, wherein the path selection model comprises an optimal path generation module and a plurality of constraint modules;
specifically, the plurality of constraint modules function to constrain training of the optimal path generation module. The training logic of the path selection model is as follows:
s3-1, m topological nodes (which can be called transfer points) X= { X between stations to be acquired 1 ，x 2 ，......，x m The attribute characteristics of the second step are input to an optimal path generation module;
the attribute features include the distribution bandwidth of the nodes on the topological links, the topological relation of the nodes and the QOT value of the topological links where the nodes are located, and QOT value can reflect the physical performance of the links, and currently existing QOT performance prediction methods are implemented by using a Gaussian Noise (GN) model, networkKriging (NK) algorithm and machine learning method (decision tree, support vector machine, random forest, neural network, etc.).
S3-2, clustering all the service demands to obtain a plurality of service demand groups;
clustering the acquired business demand sample data can realize grouping the business demands, and the clustered demand classification can comprise: the idle communication path is optimal, the distance is short, the number of hops is small, the routing cannot be realized, the time delay is low, and the like.
S3-3, inputting the attribute characteristics and the clustered multiple demand groups into multiple constraint modules to obtain multiple groups of topological path sets corresponding to the demand groups;
the constraint module is not actually based on a prediction model constructed by the neural network, and the topological paths corresponding to different topological recommendation rules can be obtained through the model.
S3-4, respectively calculating path distances between a plurality of groups of topological paths and the optimal paths generated by the optimal path generation model, and then taking a set distance threshold value (average value of path distances obtained each time) as a parameter adjustment coefficient (a value range of the parameter adjustment coefficient in a conversion way) of the optimal path generation model.
And S3-5, adding the parameter adjustment coefficient to the model parameter in the optimal path generation model until the path distance between the optimal path generated by the optimal path generation model after parameter adjustment and the path distance in the multi-group topological path set obtained by the constraint model is kept in a relatively constant range, and completing model training.
S4, inputting newly acquired attribute characteristics of m topological nodes (which can be called transfer points) X= { x_1, x_2, … … and x_m } between sites into a constructed optimal path generation module, and obtaining an optimal path for opening the special line service through the model.
The foregoing description is only illustrative of the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (8)
1. A method for recommending a service opening optimal path is characterized by comprising the following steps of
Acquiring site information in special line service opening requirements and a topology structure diagram of an existing optical cable, wherein the site information comprises initial site information and termination site information;
acquiring all topological nodes between stations based on the acquired station information and a topological structure diagram;
constructing a topological path selection model, and inputting multidimensional attribute characteristics of topological nodes into the constructed model to obtain an optimal path opened by the private line service.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises,
dividing a plurality of sites in site information into a plurality of site intervals according to a position adjacent relation, traversing a topological structure diagram according to the intervals to obtain a sub-node set, combining the sub-nodes to obtain the topological node set, and obtaining all the topological nodes between the sites.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises,
the topological path selection model comprises an optimal path generation module and more than one constraint module.
4. The method of claim 3, wherein the step of,
the training steps of the path selection model are as follows:
1) Inputting the acquired multidimensional attribute characteristics of m (> =0) topological nodes or switching points X= { x_1, x_2, … …, x_m } between the starting station and the ending station to an optimal path generation module;
2) Grouping all the service opening demands to obtain a plurality of service opening demand groups;
3) Inputting the opening attribute characteristics and a plurality of service opening demand groups into a constraint module to obtain a topology path set corresponding to the demand groups;
4) And adding the parameter adjustment coefficient to the model parameter in the optimal path generation module until the path distance between the optimal path generated by the optimal path generation module after parameter adjustment and the topological path set obtained by the constraint module is kept in a relatively constant range, and completing model training.
5. The method of claim 4, wherein the step of determining the position of the first electrode is performed,
the multidimensional attribute features comprise distribution bandwidth of the nodes on the topological links, topological relation of the nodes and QOT values of the topological links where the nodes are located.
6. The method of claim 4, wherein the step of determining the position of the first electrode is performed,
the grouping all the service opening requirements to obtain a plurality of service opening requirement groups comprises the following steps: clustering all the service opening requirements to obtain a plurality of service opening requirement groups.
7. The method of claim 4, wherein the step of determining the position of the first electrode is performed,
and respectively calculating path distances between more than one group of topological paths and the optimal paths generated by the optimal path generation module, and then taking a set distance threshold value (average value of path distances obtained each time) as a parameter adjustment coefficient of the optimal path generation module.
8. The method of claim 7, wherein the step of determining the position of the probe is performed,
the parameter adjustment coefficient can be converted into a value range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310207317.1A CN116232978A (en) | 2023-03-01 | 2023-03-01 | Method for recommending optimal path for service opening |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310207317.1A CN116232978A (en) | 2023-03-01 | 2023-03-01 | Method for recommending optimal path for service opening |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116232978A true CN116232978A (en) | 2023-06-06 |
Family
ID=86574711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310207317.1A Pending CN116232978A (en) | 2023-03-01 | 2023-03-01 | Method for recommending optimal path for service opening |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116232978A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110932976A (en) * | 2019-12-12 | 2020-03-27 | 国家电网有限公司大数据中心 | Meteorological disaster-based power grid fault service recovery method, device and equipment |
| US20220004307A1 (en) * | 2016-09-15 | 2022-01-06 | Simpsx Technologies Llc | Virtual Power Plant Optimization Method and System |
| CN114726778A (en) * | 2020-12-18 | 2022-07-08 | 中国联合网络通信集团有限公司 | Service special line opening method and server |
-
2023
- 2023-03-01 CN CN202310207317.1A patent/CN116232978A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220004307A1 (en) * | 2016-09-15 | 2022-01-06 | Simpsx Technologies Llc | Virtual Power Plant Optimization Method and System |
| CN110932976A (en) * | 2019-12-12 | 2020-03-27 | 国家电网有限公司大数据中心 | Meteorological disaster-based power grid fault service recovery method, device and equipment |
| CN114726778A (en) * | 2020-12-18 | 2022-07-08 | 中国联合网络通信集团有限公司 | Service special line opening method and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gong et al. | Novel location-constrained virtual network embedding LC-VNE algorithms towards integrated node and link mapping | |
| Garrett et al. | A study of slot reuse in dual bus multiple access networks | |
| Soltan et al. | A learning-based method for generating synthetic power grids | |
| CN105024853A (en) | SDN resource matching and service path discovering method based on rumor spreading mechanism | |
| CN107465966B (en) | Topology reconstruction control method for optical network | |
| CN110996196B (en) | Optimal route optimizing method for optical transmission network optical path fiber core utilization | |
| CN102546220A (en) | Key quality indicator (KQI) composition method based on service characteristics | |
| CN108900350A (en) | Photosphere business hierarchical mode configuration method and system in a kind of network management system | |
| CN109327401A (en) | A kind of traffic scheduling method and system of SDN network | |
| CN105472484A (en) | Wave channel balancing route wavelength allocation method of power backbone optical transport network | |
| Nace et al. | Computing optimal max-min fair resource allocation for elastic flows | |
| CN108512765B (en) | Network content diffusion method based on network node distributed Pagerank | |
| CN116232978A (en) | Method for recommending optimal path for service opening | |
| Yoon et al. | Design of a distributed fiber transport network with hubbing topology | |
| CN108111991B (en) | D2D network building method based on scalable video streaming user experience quality | |
| CN114745227B (en) | Electric power business network slicing time delay calculation method and device based on FlexE and SPN technologies | |
| CN116133082A (en) | Multi-hop clustering method for improving topology duration of aviation ad hoc network | |
| CN106612207B (en) | The management-control method and device of ethernet device RSTP information | |
| Sun et al. | A load-balancing-based fault-tolerant mapping method in smart grid virtual networks | |
| CN114390489B (en) | End-to-end network slice servitization deployment method | |
| CN116683981B (en) | Low-orbit satellite path planning method based on multidimensional time-varying resource diagram | |
| Zhao et al. | Service Function Chain Deployment for 5G Delay-Sensitive Network Slicing | |
| Herrera et al. | Bipartite networks to enable management of internet core and metro infrastructure | |
| CN110971450B (en) | Information point location ordering method and device for operation and maintenance | |
| CN116436730B (en) | Virtual network mapping method and mapping system based on cloud computing service |
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 |