CN116663856A - 5G virtual private network communication terminal management system facing electric power - Google Patents
5G virtual private network communication terminal management system facing electric power Download PDFInfo
- Publication number
- CN116663856A CN116663856A CN202310911991.8A CN202310911991A CN116663856A CN 116663856 A CN116663856 A CN 116663856A CN 202310911991 A CN202310911991 A CN 202310911991A CN 116663856 A CN116663856 A CN 116663856A
- Authority
- CN
- China
- Prior art keywords
- entity
- vertex
- hidden layer
- representing
- information
- 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.)
- Granted
Links
- 238000004891 communication Methods 0.000 title claims abstract description 49
- 239000013598 vector Substances 0.000 claims description 46
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000004913 activation Effects 0.000 claims description 5
- 210000001503 joint Anatomy 0.000 abstract description 5
- 238000000034 method Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Biodiversity & Conservation Biology (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Primary Health Care (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of communication management, and discloses a 5G virtual private network communication terminal management system facing electric power, which comprises the following components: the original information acquisition module is used for acquiring factory scheduling information; a map generation module that generates a factory scheduling knowledge map based on factory scheduling information; a first graph model generation module that generates a first graph model based on engineering dispatch information; a second graph model generation module; the slice matching module distributes corresponding network slice templates for the first entity through a slice matching model, wherein the slice matching model comprises a first hidden layer, a second hidden layer and a classifier; according to the invention, the network slice template is automatically adapted to the terminal in the network directly through the collected scheduling information, so that the dependence on the butt joint communication of factory personnel and 5G communication industry personnel is relieved.
Description
Technical Field
The invention relates to the technical field of communication management, in particular to a 5G virtual private network communication terminal management system facing power.
Background
The factory is a wired communication network based on a bus generally, the communication knowledge graph generated by the structure of the communication network has very large difference with the communication relationship between the terminal and the terminal when the 5G virtual special network is constructed, the communication knowledge graph cannot be applied to the reference when the 5G virtual special network is constructed to the 5G network slice, more needs to consider the connection between terminal equipment and service, although the communication can be configured in a mode of matching 5G slice templates, the quantity of the fine customized selectable 5G slice templates is large, how to select the 5G slice templates and how to adapt the 5G slice templates are realized by the butt joint communication between factory personnel and 5G communication industry personnel, but professional barriers exist between the factory personnel and the 5G communication industry personnel, and the butt joint communication efficiency is low.
Disclosure of Invention
The invention provides a 5G virtual private network communication terminal management system oriented to electric power, which solves the technical problem that in the related art, the adaptation of a 5G slice template depends on the butt joint communication between factory personnel and 5G communication industry personnel.
The invention provides a 5G virtual private network communication terminal management system facing electric power, which comprises:
the original information acquisition module is used for acquiring factory scheduling information;
the map generation module is used for generating a factory scheduling knowledge map based on factory scheduling information, wherein entities in the factory scheduling knowledge map comprise an acquisition terminal entity, a communication node entity, a scheduling content entity, an equipment entity and a scheduling personnel entity;
the first graph model generation module is used for generating a first graph model based on engineering dispatching information, the first graph model comprises first vertexes and edges connected with the first vertexes, each first vertex corresponds to one first entity, the first entity is one of a device entity, a communication node entity, an acquisition terminal entity and a dispatcher entity in a factory dispatching knowledge graph, and the first entities corresponding to the first vertexes connected with the two edges are connected; initializing a first vertex vector for each first vertex of the first graph model;
the second graph model generation module is used for generating a second graph model based on engineering dispatching information, the second graph model comprises second vertexes and edges connected with the second vertexes, each second vertex corresponds to an entity in a factory dispatching knowledge graph, and two entities corresponding to the second vertexes connected by the edges are connected;
the slice matching module distributes a corresponding network slice template for the first entity through a slice matching model, wherein the slice matching model comprises a first hidden layer, a second hidden layer and a classifier, the first hidden layer inputs the first graph model, updates a first vertex vector of a first vertex, the second hidden layer inputs the updated first vertex vector of the first hidden layer and the second graph model, outputs an updated second vertex vector to the classifier, and the classifier outputs an ID (identity) of the network slice template to which the entity corresponding to the second vertex belongs;
and the slice generation module is used for adding the equipment, the communication node, the acquisition terminal and the dispatcher corresponding to the first entity into the corresponding network slice template to generate the network slice.
Further, the factory scheduling information includes scheduling content information, equipment information, communication node information, acquisition terminal information, and scheduling personnel information.
Further, each component of the initialized first vertex vector has a value of 1.
Further, the network slice template ID refers to an ID corresponding to a network slice template stored in the database, and a unique network slice template ID in the database can be indexed by a network slice template ID.
Further, the calculation formula of the first hidden layer is as follows:
wherein the method comprises the steps ofAnd->Output of the first hidden layer of the first layer and the first-1 layer, respectively, when l=1 +.>Representing an input feature matrix, each row of the input feature matrix representing an initialized first vertex vector,/a>Representing the sum of the adjacency matrix and the identity matrix between the first vertex vectors, < >>Representation->Degree matrix of->Weight matrix representing first hidden layer of first layer,/->Representing an activation function.
Further, the calculation formula of the second hidden layer is as follows:
wherein the method comprises the steps ofAnd->Second vertex vector update results of the ith second vertex of the t-th and t-1 th second hidden layers, respectively,/->Weight parameter representing the t-th hidden layer, < >>Representing the update result of the second vertex vector of the jth second vertex of the t-1 th hidden layer,/for the second vertex>Representing a second vertex set directly connected to the ith second vertex,/and>representation->Second vertex count in>Tan represents the hyperbolic tangent function, +.>Representation ofAn adjustable parameter, defaulting to the inverse of the dimension of the second vertex vector, < >>Representing an activation function;
when t=1, the number of the groups,and->Representing the initial second vertex vectors of the ith and jth second vertices, respectively.
Further, during initialization, the scheduling content entity is encoded as an initial second vertex vector of a corresponding second vertex; the initial second vertex vector of the second vertex corresponding to the first entity is the same as the first vertex vector corresponding to the same first entity updated by the first hidden layer.
Further, the classifier inputs only the result that the second vertex vector corresponding to the first entity is updated by the second hidden layer.
Further, the loss function of the slice matching model is:
where L represents the loss value, G is the total number of first entities, F is the total number of network slice templates,a probability value representing that the g first entity belongs to the f-th network slice template, when the g first entity actually belongs to the f-th network slice template +.>Otherwise->。
The invention has the beneficial effects that: according to the invention, the network slice template is automatically adapted to the terminal in the network directly through the collected scheduling information, so that the dependence on the butt joint communication of factory personnel and 5G communication industry personnel is relieved, and the construction speed of the vertical application of the 5G network is improved.
Drawings
Fig. 1 is a schematic block diagram of a power-oriented 5G virtual private network communication terminal management system according to the present invention.
In the figure: the system comprises an original information acquisition module 101, a map generation module 102, a first map model generation module 103, a second map model generation module 104, a slice matching module 105 and a slice generation module 106.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It is to be understood that these embodiments are merely discussed so that those skilled in the art may better understand and implement the subject matter described herein and that changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
As shown in fig. 1, a system for managing a 5G virtual private network communication terminal for electric power includes:
an original information acquisition module 101 for acquiring factory scheduling information;
the factory scheduling information comprises scheduling content information, equipment information, communication node information, acquisition terminal information and scheduling personnel information, and the acquisition terminal is a terminal for acquiring equipment or environment or other production related information inside the factory.
The schedule content may be a production schedule content or a device control schedule content, etc.
A communication node refers to an entity device used only for transmitting data in a factory scheduling system, and in one embodiment of the present invention, it further includes a virtual node.
A map generation module 102 that generates a plant scheduling knowledge map based on the plant scheduling information
The entities in the factory scheduling knowledge graph comprise an acquisition terminal entity, a communication node entity, a scheduling content entity, an equipment entity and a scheduling personnel entity;
the first graph model generating module 103 generates a first graph model based on engineering scheduling information, wherein the first graph model comprises first vertexes and edges connected with the first vertexes, each first vertex corresponds to a first entity, the first entity is one of a device entity, a communication node entity, an acquisition terminal entity and a dispatcher entity in a factory scheduling knowledge graph, and a connection exists between the first entities corresponding to the first vertexes connected with the two edges; a first vertex vector is initialized for each first vertex of the first graph model, each component of the first vertex vector having a value of 1.
For example, a first vertex corresponds to a device number 006.
The second graph model generating module 104 generates a second graph model based on engineering scheduling information, wherein the second graph model comprises second vertexes and edges connected with the second vertexes, each second vertex corresponds to an entity in a factory scheduling knowledge graph, and two entities corresponding to the second vertexes connected by the edges are connected;
the slice matching module 105 distributes a corresponding network slice template for the first entity through a slice matching model, wherein the slice matching model comprises a first hidden layer, a second hidden layer and a classifier, the first hidden layer inputs the first graph model, updates a first vertex vector of a first vertex, the second hidden layer inputs the updated first vertex vector of the first hidden layer and the second graph model, outputs an updated second vertex vector to the classifier, and the classifier outputs an ID of the network slice template to which the entity corresponding to the second vertex belongs;
the network slice template ID refers to an ID corresponding to a network slice template stored in the database, and a unique network slice template ID in the database can be indexed by a network slice template ID.
The calculation formula of the first hidden layer is as follows:
wherein the method comprises the steps ofAnd->Output of the first hidden layer of the first layer and the first-1 layer, respectively, when l=1 +.>Representing an input feature matrix, each row of the input feature matrix representing an initialized first vertex vector,/a>Representing the sum of the adjacency matrix and the identity matrix between the first vertex vectors, < >>Representation->Degree matrix of->A weight matrix representing a first hidden layer of the first layer;
the calculation formula of the second hidden layer is as follows:
wherein the method comprises the steps ofAnd->Second vertex vector update results of the ith second vertex of the t-th and t-1 th second hidden layers, respectively,/->Weight parameter representing the t-th hidden layer, < >>Representing the update result of the second vertex vector of the jth second vertex of the t-1 th hidden layer,/for the second vertex>Representing a second vertex set directly connected to the ith second vertex,/and>representation->Second vertex count in>Tan represents the hyperbolic tangent function, +.>Representing the adjustable parameter, defaulting to the inverse of the dimension of the second vertex vector.
When t=1, the number of the groups,and->Representing the initial second vertex vectors of the ith and jth second vertices, respectively.
When initializing, encoding the scheduling content entity as an initial second vertex vector of the corresponding second vertex; the initial second vertex vector of the second vertex corresponding to the first entity is the same as the first vertex vector corresponding to the same first entity updated by the first hidden layer.
The classifier inputs only the result of the second vertex vector corresponding to the first entity being updated by the second hidden layer.
In one embodiment of the invention, the loss function of the slice matching model is:
wherein L represents a loss value, G isThe total number of first entities, F is the total number of network slice templates,a probability value representing that the g first entity belongs to the f-th network slice template, when the g first entity actually belongs to the f-th network slice template +.>Otherwise->。
The above-mentioned schedule information flow path lacks vector representation, and the slice matching model performs feature extraction on the existing schedule information flow path information and schedule content information of the factory, and generates the relationship between the user terminal and the network slice by using the existing schedule information of the factory to the maximum extent.
In one embodiment of the invention, the scheduling content entity is data in text form, and the encoding method can be used for encoding by using word frequency-inverse document frequency (TF-IDF), N-Gram, and document-vector model (Doc 2 vec).
In the above-described embodiments of the present invention,representing the activation function, a ReLU function is employed.
In one embodiment of the present invention, the first hidden layer performs independent training, and is connected to a first full-connection layer during training, where a classification label output by the first full-connection layer is a type of a first entity (four types are an equipment entity, a communication node entity, an acquisition terminal entity, and a dispatcher entity) corresponding to the first vertex.
The first hidden layer is independently trained, then the first full-connection layer is deleted, and then the slice matching model is added.
And the slice generation module 106 is used for adding the equipment, the communication node, the acquisition terminal and the dispatcher corresponding to the first entity into the corresponding network slice template to generate the network slice. The dispatcher actually represents the user terminal it holds.
Because the formatted content exists in the network slice template, network layers and topological relations of an access network, a core network and the like belong to the formatted content, and the rest parameter adjustment can be carried out by network technicians according to user terminals in the network slice.
The embodiment has been described above with reference to the embodiment, but the embodiment is not limited to the above-described specific implementation, which is only illustrative and not restrictive, and many forms can be made by those of ordinary skill in the art, given the benefit of this disclosure, are within the scope of this embodiment.
Claims (10)
1. The utility model provides a 5G virtual private network communication terminal management system towards electric power which characterized in that includes:
the original information acquisition module is used for acquiring factory scheduling information;
the map generation module is used for generating a factory scheduling knowledge map based on factory scheduling information, wherein entities in the factory scheduling knowledge map comprise an acquisition terminal entity, a communication node entity, a scheduling content entity, an equipment entity and a scheduling personnel entity;
the first graph model generation module is used for generating a first graph model based on engineering dispatching information, the first graph model comprises first vertexes and edges connected with the first vertexes, each first vertex corresponds to one first entity, the first entity is one of a device entity, a communication node entity, an acquisition terminal entity and a dispatcher entity in a factory dispatching knowledge graph, and the first entities corresponding to the first vertexes connected with the two edges are connected; initializing a first vertex vector for each first vertex of the first graph model;
the second graph model generation module is used for generating a second graph model based on engineering dispatching information, the second graph model comprises second vertexes and edges connected with the second vertexes, each second vertex corresponds to an entity in a factory dispatching knowledge graph, and two entities corresponding to the second vertexes connected by the edges are connected;
the slice matching module distributes a corresponding network slice template for the first entity through a slice matching model, wherein the slice matching model comprises a first hidden layer, a second hidden layer and a classifier, the first hidden layer inputs the first graph model, updates a first vertex vector of a first vertex, the second hidden layer inputs the updated first vertex vector of the first hidden layer and the second graph model, outputs an updated second vertex vector to the classifier, and the classifier outputs an ID (identity) of the network slice template to which the entity corresponding to the second vertex belongs;
and the slice generation module is used for adding the equipment, the communication node, the acquisition terminal and the dispatcher corresponding to the first entity into the corresponding network slice template to generate the network slice.
2. The power-oriented 5G virtual private network communication terminal management system of claim 1, wherein the factory scheduling information includes scheduling content information, device information, communication node information, acquisition terminal information, and scheduler information.
3. The power-oriented 5G virtual private network communication terminal management system of claim 1, wherein each component of the initialized first vertex vector has a value of 1.
4. The system according to claim 1, wherein the network slice template ID is an ID corresponding to a network slice template stored in the database, and a unique network slice template ID in the database can be indexed by a network slice template ID.
5. The power-oriented 5G virtual private network communication terminal management system of claim 1, wherein the calculation formula of the first hidden layer is as follows:
wherein->And->Output of the first hidden layer of the first layer and the first-1 layer, respectively, when l=1 +.>Representing an input feature matrix, each row of the input feature matrix representing an initialized first vertex vector,/a>Representing the sum of the adjacency matrix and the identity matrix between the first vertex vectors, < >>Representation->Is used for the degree matrix of the (c),weight matrix representing first hidden layer of first layer,/->Representing an activation function.
6. The power-oriented 5G virtual private network communication terminal management system according to claim 1, wherein the calculation formula of the second hidden layer is as follows:
wherein->And->Second vertex vector update results of the ith second vertex of the t-th and t-1 th second hidden layers, respectively,/->Weight parameter representing the t-th hidden layer, < >>Representing the update result of the second vertex vector of the jth second vertex of the t-1 th hidden layer,/for the second vertex>Representing a second vertex set directly connected to the ith second vertex,/and>representation->Is selected from the group consisting of the total number of second vertices,tan represents the hyperbolic tangent function, +.>Representing adjustable parameters->Representing an activation function;
when t=1, the number of the groups,and->Representing the initial second vertex vectors of the ith and jth second vertices, respectively.
7. The power-oriented 5G virtual private network communication terminal management system of claim 6, wherein upon initialization, the schedule content entity is encoded as an initial second vertex vector for its corresponding second vertex; the initial second vertex vector of the second vertex corresponding to the first entity is the same as the first vertex vector corresponding to the same first entity updated by the first hidden layer.
8. The system of claim 1, wherein the classifier inputs only the result of the second vertex vector corresponding to the first entity being updated by the second hidden layer.
9. The power-oriented 5G virtual private network communication terminal management system of claim 1, wherein the loss function of the slice matching model is:
wherein L represents a loss value, G is the total number of first entities, F is the total number of network slice templates, +.>A probability value representing that the g first entity belongs to the f-th network slice template, when the g first entity actually belongs to the f-th network slice template +.>Otherwise->。
10. The power-oriented 5G virtual private network communication terminal management system of claim 1, further comprising a slice generation module, wherein the slice generation module is configured to add the device, the communication node, the acquisition terminal, and the dispatcher corresponding to the first entity to the corresponding network slice template to generate the network slice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310911991.8A CN116663856B (en) | 2023-07-25 | 2023-07-25 | 5G virtual private network communication terminal management system facing electric power |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310911991.8A CN116663856B (en) | 2023-07-25 | 2023-07-25 | 5G virtual private network communication terminal management system facing electric power |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116663856A true CN116663856A (en) | 2023-08-29 |
| CN116663856B CN116663856B (en) | 2023-10-13 |
Family
ID=87719321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310911991.8A Active CN116663856B (en) | 2023-07-25 | 2023-07-25 | 5G virtual private network communication terminal management system facing electric power |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116663856B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112804287A (en) * | 2020-12-04 | 2021-05-14 | 广东电力通信科技有限公司 | Intelligent network slice template generation method and system for power Internet of things |
| CN114531662A (en) * | 2022-04-20 | 2022-05-24 | 国网浙江省电力有限公司信息通信分公司 | Terminal intelligent access authentication management method based on electric power 5G virtual private network |
| CN115460613A (en) * | 2022-04-14 | 2022-12-09 | 国网福建省电力有限公司 | Safe application and management method for power 5G slice |
| US20230040079A1 (en) * | 2020-04-14 | 2023-02-09 | Huawei Technologies Co., Ltd. | Data transmission method and apparatus |
-
2023
- 2023-07-25 CN CN202310911991.8A patent/CN116663856B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230040079A1 (en) * | 2020-04-14 | 2023-02-09 | Huawei Technologies Co., Ltd. | Data transmission method and apparatus |
| CN112804287A (en) * | 2020-12-04 | 2021-05-14 | 广东电力通信科技有限公司 | Intelligent network slice template generation method and system for power Internet of things |
| CN115460613A (en) * | 2022-04-14 | 2022-12-09 | 国网福建省电力有限公司 | Safe application and management method for power 5G slice |
| CN114531662A (en) * | 2022-04-20 | 2022-05-24 | 国网浙江省电力有限公司信息通信分公司 | Terminal intelligent access authentication management method based on electric power 5G virtual private network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116663856B (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Razali et al. | Backward reduction application for minimizing wind power scenarios in stochastic programming | |
| Sonmez et al. | Symbiotic organisms search algorithm for dynamic economic dispatch with valve-point effects | |
| CN110162390B (en) | Task allocation method and system for fog computing system | |
| CN107705213B (en) | Overlapped community discovery method of static social network | |
| Zhang et al. | Coded computation over heterogeneous workers with random task arrivals | |
| CN116663856B (en) | 5G virtual private network communication terminal management system facing electric power | |
| CN110516849A (en) | A kind of load classification evaluation of result method based on typical day load curve | |
| CN108829846B (en) | Service recommendation platform data clustering optimization system and method based on user characteristics | |
| Rathnayaka et al. | GM (1, 1) analysis and forecasting for efficient energy production and consumption | |
| Jeong et al. | Lossless data compression with bit-back coding on massive smart meter data | |
| CN116957304B (en) | Unmanned aerial vehicle group collaborative task allocation method and system | |
| Jin et al. | Joint scheduling of deferrable demand and storage with random supply and processing rate limits | |
| CN111881115A (en) | Database coordination optimization method based on big data dynamic planning | |
| KR102542058B1 (en) | Method and system of predicting and managing of probabilistic solar power generation | |
| CN114726870B (en) | Mixed cloud resource arrangement method and system based on visual drag and electronic equipment | |
| CN116307111A (en) | Reactive load prediction method based on K-means clustering and random forest algorithm | |
| CN103336865B (en) | A kind of dynamic communication network construction method and device | |
| CN115409170A (en) | Sample data generation and trip demand prediction model training and prediction method and device | |
| CN111680337B (en) | PDM system product design requirement information acquisition method and system | |
| CN110457650B (en) | Method, device, medium and electronic equipment for generating livability design | |
| CN114329127A (en) | Characteristic box dividing method, device and storage medium | |
| CN113962716A (en) | Electric power customer subdivision method based on hybrid neural network | |
| CN112738225A (en) | Edge calculation method based on artificial intelligence | |
| CN112559854A (en) | Classification method and device | |
| CN116521852B (en) | Deep learning-based intelligent mapping device and mapping method for power equipment |
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 |