CN115174435A - Comprehensive evaluation method for performance of power communication transmission network - Google Patents
Comprehensive evaluation method for performance of power communication transmission network Download PDFInfo
- Publication number
- CN115174435A CN115174435A CN202210964576.4A CN202210964576A CN115174435A CN 115174435 A CN115174435 A CN 115174435A CN 202210964576 A CN202210964576 A CN 202210964576A CN 115174435 A CN115174435 A CN 115174435A
- Authority
- CN
- China
- Prior art keywords
- network
- power communication
- module
- communication network
- transmission
- 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.)
- Withdrawn
Links
- 230000006854 communication Effects 0.000 title claims abstract description 287
- 238000004891 communication Methods 0.000 title claims abstract description 281
- 230000005540 biological transmission Effects 0.000 title claims abstract description 149
- 238000011156 evaluation Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000005457 optimization Methods 0.000 claims abstract description 24
- 230000006855 networking Effects 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 43
- 230000003287 optical effect Effects 0.000 claims description 33
- 230000007547 defect Effects 0.000 claims description 25
- 238000000605 extraction Methods 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000011176 pooling Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 14
- 239000013307 optical fiber Substances 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 239000000835 fiber Substances 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 150000001875 compounds Chemical class 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 235000008694 Humulus lupulus Nutrition 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 36
- 238000013527 convolutional neural network Methods 0.000 description 8
- 238000002474 experimental method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000005693 optoelectronics Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241001071861 Lethrinus genivittatus Species 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000010453 quartz Substances 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/079—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using measurements of the data signal
- H04B10/0795—Performance monitoring; Measurement of transmission parameters
-
- 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
- H04L45/50—Routing or path finding of packets in data switching networks using label swapping, e.g. multi-protocol label switch [MPLS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Environmental & Geological Engineering (AREA)
- Electromagnetism (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a comprehensive evaluation method for the performance of a power communication transmission network, which relates to the technical field of power communication transmission and solves the technical problem of comprehensive evaluation for the performance of the power communication transmission network; the method comprises the steps of constructing an improved OTN + PTN networking mode to form a power communication transmission network frame, transmitting input data information, realizing data information transmission through a packet transmission network, realizing data packet transmission facing network data information connection through expanding an MPLS-TP module in the packet transmission network, increasing label forwarding capacity, and evaluating the performance of the power communication transmission network in the communication network through an optimization model.
Description
Technical Field
The invention relates to the technical field of communication transmission, in particular to a comprehensive evaluation method for performance of a power communication transmission network.
Background
The transmission and transformation communication network construction process faces the following challenges: the power business is in high demand, and the safety and reliability requirements are high; the traditional TDM service and the newly added IP service need to be simultaneously loaded; the communication interface in the transformer substation is complex and difficult to maintain; the demand of extra-high voltage and extra-long distance power transmission for extra-long distance communication and the like. For example, in the solution of power transmission and transformation communication, MS-OTN devices are used to construct a power communication transmission network, to carry services such as dispatch telephone, differential relay protection, SCADA service, and office automation, and to build a network with high security, high reliability, low time delay and facing the future for customers.
In the above method, although the evaluation during the operation of the power communication transmission network can be performed during the power communication transmission application, the efficiency of the network performance is low and the transmission information evaluation capability is poor when data information evaluation is performed.
Disclosure of Invention
Aiming at the technical defects, the invention discloses a comprehensive evaluation method for the performance of an electric power communication transmission network, which can effectively improve the comprehensive evaluation of the performance of the electric power communication transmission network and improve the operation efficiency of the electric power communication transmission network.
The invention adopts the following technical scheme:
a comprehensive evaluation method for the performance of a power communication transmission network comprises the following steps:
step one, sensing communication information characteristics of a power communication transmission network through a sensing unit, and transmitting sensed data information to an application terminal through a wireless communication module;
constructing an improved OTN + PTN networking mode to form a power communication transmission network frame, transmitting input data information, wherein the communication network comprises a power terminal, an optical network node, a relay node, an optical fiber link and a photoelectric mapping interface, realizing data information transmission through a packet transmission network, and realizing data packet transmission facing network data information connection by expanding an MPLS-TP module in the packet transmission network, so that the label forwarding capability is increased, and the hop-by-hop routing forwarding function based on IP addresses is improved;
the extended MPLS-TP module comprises a coding module and an identification module; the encoding module is used for encoding different data nodes in the power communication transmission network architecture, and the identification module is used for identifying the encoded data nodes;
evaluating the performance of the power communication transmission network in the communication network through an optimization model, wherein the optimization model realizes data information evaluation through the following method;
the optimization model function construction method comprises the following steps:
(S31) constructing a time delay constraint model, wherein the time delay constraint model function is expressed as:
in the formula (1), the first and second groups,indicating the optical transmission delay of the OTN layer,indicating the transmission speed of the data in the fiber link,indicates the length of the optical fiber link of the communication network,representing the processing delay of the optical network node equipment,representing the number of communication network routing hops,representing the total routing time delay, and calculating the time delay constraint of the power communication transmission network performance evaluation through an optimization model of a formula (1);
(S32) constructing a reliability constraint function model of the data communication;
reliability constraint of the performance of the power communication network is related to reliability factors of a power terminal path, an OTN layer photoelectric interface path and an optical fiber path, the probability of protecting fault-free transmission service of each module in the communication network is represented, and a reliability constraint function model is represented as follows:
in the formula (2), the first and second groups of the chemical reaction are represented by the following formula,a model of a fiber reliability constraint function is represented,representing the reliability of the main path of power communication,indicating the reliability of the power communication backup path,representing the total reliability of data transmission;
(S32) constructing a node importance function of the power communication network;
the node importance function of the power communication network is expressed as:
in the formula (3), the first and second groups,representing voltage level weights in the power communication transmission network,representing power node degree weights in a power communications transmission network,representing node voltage levels in the power communications transmission network,representing a number of degrees of a communications network power node in a power communications transmission network;
(S33) constructing node importance of an OTN layer in the power communication transmission network, node risk and node occupancy rate of an optical network layer, wherein the occupancy rate function is as follows:
in the formula (4), the first and second groups,representing the optical layer node risk degree weight,representing the optical layer node occupancy weight,the optical layer normalized risk is shown,normalized power node degrees are represented;
the node reliability performance standard deviation function of the communication network in the power communication transmission network is expressed as follows:
in the formula (5), whereinRepresents the average node occupancy rate of communication in the power communication transmission network,representing the total number of network nodes in the power communications transmission network,the network reliability in the power communication transmission network is represented, and the node fluctuation condition in the power communication transmission network is reflected through a formula (5);
(S34) calculating a network delay of the network data communication;
when the optimization model optimizes the reliable route in the communication network, the importance degree of the initial optical layer node and the communication network time delay are calculated, and all reachable paths are counted to form a main path set which is recorded asCalculating a separation path for each path in the set to obtain a backup path setThen, the average node importance in the main path and the backup path is calculated, and the average node importance function is as follows:
in formula (6), g and h represent OTN layer network nodes, x and y represent the total number of nodes of the primary path and the backup path,indicating the node importance of the network data node as g,the node importance degree of the network data node is represented as h, and the node importance degree is calculated through a formula (6)When the node importance is high, the main path and the backup path with the minimum importance are selected to transmit service data in the power communication system, and then the node importance in the communication network is updated to calculate a time node when a transmission data information service in the next power communication transmission network arrives;
the communication evaluation in the power communication transmission network is realized through an evaluation module, wherein the evaluation module comprises a feature extraction module, a convolution calculation module, a pooling calculation module, a feature prediction module, an information clustering analysis module and a loss calculation module, the output end of the feature extraction module is connected with the input end of the convolution calculation module, the output end of the convolution calculation module is connected with the input end of the pooling calculation module, the output end of the pooling calculation module is connected with the input end of the feature prediction module, the output end of the feature prediction module is connected with the input end of the information clustering analysis module, and the output end of the information clustering analysis module is connected with the input end of the loss calculation module;
the system comprises a feature extraction module, a convolution calculation module, a pooling calculation module and a probability value normalization module, wherein the feature extraction module is used for extracting data information in the power communication network, the convolution calculation module is used for calculating communication parameters in the data information in the power communication network, and the pooling calculation module is used for normalizing input information feature map values and randomly sampling and selecting the input information feature map values according to the probability value after the feature map is normalized;
the characteristic prediction module is used for predicting data information of the data information in the power communication network in the communication process according to the data information in the power communication network, the information clustering analysis module is used for carrying out clustering analysis and classification on the input data information in the power communication network so as to improve the data information classification capability in the power communication network, and the loss calculation module is used for calculating the loss of the data information in the power communication network in the communication process.
As a further technical scheme, a control chip adopted by a sensing unit is an STM32F429ZET6 single chip microcomputer, and communication data information transmission is realized through an ARM 32-bit Cortex TM-M4 processor core, wherein the sensing unit is provided with 12 channels of DMA and 112 rapid I/O ports, and the dominant frequency range is 1.4 to 1.6GHZ.
As a further technical scheme of the invention, the data information sensed by the sensing unit is a communication protocol, a network communication mode, a format of transmission data information, a communication transmission speed, a networking mode, a network node, a data stream protocol header, a data stream symbol, data stream characteristic information, sensing time delay and link bandwidth.
As a further technical scheme of the invention, the wireless communication module adopts a USR-G806 router.
As a further technical scheme of the invention, the MPLS-TP module collects data information in the power communication network through the analog quantity collecting circuit, and the data information is input into the input channel、Andtogether forming an input set of the acquisition circuit,andrespectively, a resistance value ofAndto realize the conversion of input current and voltage, wherein the diodeModel SS34, realizes reverse connection protection of input end, and makes maximum forward conduction voltage drop 0.5V, and simulates switchAnd operational amplifierThe middle stage of the acquisition circuit is formed, and the output end of the switch is connected with a voltage follower in a cascade mode.
As a further technical scheme of the invention, the power communication transmission network frame is a power communication network architecture in an improved OTN + PTN networking mode.
As a further technical scheme of the invention, the performance evaluation of the power communication transmission network is realized through a network evaluation algorithm model, wherein the method of the network evaluation algorithm comprises the following steps:
the convolution operation formula for the FDD network in the power communication network is as follows:
in the formula (7), x in the formula is input power communication network transmission line image data,a kernel function of the FDD network is represented,representing the output power communication network characteristic mapping result,a weighted average parameter representing the power communication network,a weight vector representing the image data,
the volume integral calculation function is:
in the formula (8), in the formula、Representing the length and width of the defect image input feature matrix,which represents an activation function of the network,expressing a defect feature vector, and completing the nonlinear activation of the vector in the feature extraction channel through a formula (8); after the feature extraction is completed, the power communication network performs feature fusion of different scales, and a fusion formula is expressed as follows:
in the formula (9), B represents the number of prior frames in the FPN network, C represents the number of categories of the network line defect characteristics of the power communication network,andthe offset representing the image grid coordinates is the horizontal and vertical coordinates,andand (3) representing the scale for predicting the transmission performance of the power communication network line, wherein the power communication network line defect characteristic normalization function is represented as follows:
in the case of the formula (10),representing the scale normalization processing of the data information of the network line defect of the power communication network,a real target frame of a data information detection model representing the network line defect characteristics of the power communication network,the clustering center represents the communication data information of the network line of the power communication network;
calculating the coordinate loss of the power communication network line detection model, wherein the loss function is as follows:
in the case of the formula (11),representing the size of the power communication network line extraction information image,actual values representing the target boxes of the power communication network line detection model,representing the line scaling parameters of the power communication network,representing a loss function in the transmission of network line data of the power communication network.
The invention has the beneficial and positive effects that:
the invention senses the communication information characteristics of the power communication transmission network through the sensing unit and transmits the sensed data information to the application terminal through the wireless communication module; the method comprises the steps that an improved OTN + PTN networking mode is constructed to form a power communication transmission network frame, input data information is transmitted, the communication network comprises a power terminal, an optical network node, a relay node, an optical fiber link and a photoelectric mapping interface, data information transmission is achieved through a packet transmission network, data packet transmission facing network data information connection is achieved through expanding an MPLS-TP module in the packet transmission network, the label forwarding capability is improved, and the hop-by-hop routing forwarding function based on IP addresses is improved; evaluating the performance of a power communication transmission network in a communication network through an optimization model, wherein the optimization model realizes data information evaluation through the following method; the communication evaluation in the power communication transmission network is realized through the evaluation module, wherein the evaluation module comprises a feature extraction module, a convolution calculation module, a pooling calculation module, a feature prediction module, an information clustering analysis module and a loss calculation module, and the comprehensive evaluation capability of the performance of the power communication transmission network is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive exercise, wherein:
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a convolution model of the present invention;
FIG. 3 is a schematic diagram of an analog acquisition circuit according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, and it should be understood that the embodiments described herein are merely for the purpose of illustrating and explaining the present invention and are not intended to limit the present invention.
As shown in fig. 1, a method for comprehensively evaluating the performance of a power communication transmission network includes the following steps:
step one, sensing communication information characteristics of a power communication transmission network through a sensing unit, and transmitting sensed data information to an application terminal through a wireless communication module;
constructing an improved OTN + PTN networking mode to form a power communication transmission network frame, transmitting input data information, wherein the communication network comprises a power terminal, an optical network node, a relay node, an optical fiber link and a photoelectric mapping interface, realizing data information transmission through a packet transmission network, and realizing data packet transmission facing network data information connection by expanding an MPLS-TP module in the packet transmission network, so that the label forwarding capability is increased, and the hop-by-hop routing forwarding function based on IP addresses is improved;
the extended MPLS-TP module comprises a coding module and an identification module; the encoding module is used for encoding different data nodes in the power communication transmission network architecture, and the identification module is used for identifying the encoded data nodes;
evaluating the performance of the power communication transmission network in the communication network through an optimization model, wherein the optimization model realizes data information evaluation through the following method;
the optimization model takes the time delay and the reliability of the power service in the communication network as constraint conditions, and takes the influence of cascading faults into consideration, and the optimization target is the minimum risk dispersion. The time delay constraint of the model consists of the communication path time delay of the electric power equipment, the time delay of an optical-electric interface and the optical transmission time delay;
the construction method of the optimization model function comprises the following steps:
(S31) constructing a time delay constraint model, wherein the time delay constraint model function is expressed as:
in the formula (1), the first and second groups of the compound,representing the optical transmission delay of the OTN layer,indicating the transmission speed of the data in the fiber link,indicating the length of the optical fiber link of the communication network,representing the processing delay of the optical network node equipment,representing the number of communication network routing hops,representing the total routing time delay, and calculating the time delay constraint of the power communication transmission network performance evaluation through an optimization model of a formula (1);
(S32) constructing a reliability constraint function model for data communication;
reliability constraint of the performance of the power communication network is related to factors such as reliability of a power terminal path, an OTN layer photoelectric interface path and an optical fiber path, the probability of protecting fault-free transmission service of each module in the communication network is represented, and a reliability constraint function model is represented as follows:
in the formula (2), the first and second groups,a model of a fiber reliability constraint function is represented,representing the reliability of the main path of power communication,indicating the reliability of the power communication backup path,representing the total reliability of data transmission;
(S32) constructing an importance function of the power communication network nodes;
when the model is optimized, the risk degree of the communication node and the occupation degree of the node are considered, and the node importance function of the power communication network is expressed as follows:
in the formula (3), the first and second groups of the compound,representing voltage level weights in the power communication transmission network,representing power node degree weights in a power communications transmission network,representing node voltage levels in the power communications transmission network,representing the number of communication network power nodes in the power communication transmission network.
(S33) constructing node importance of an OTN layer in the power communication transmission network, node risk and node occupancy rate of an optical network layer, wherein the occupancy rate function is as follows:
in the formula (4), the first and second groups of the chemical reaction are shown in the formula,representing the risk degree weight of the optical layer node,representing the optical layer node occupancy weight,the optical layer normalized risk is shown,normalized power node degrees are represented;
the node reliability performance standard deviation function of the communication network in the power communication transmission network is expressed as:
in the formula (5), whereinRepresents the average node occupancy rate of communication in the power communication transmission network,represents the total number of network nodes in the power communication transmission network,the network reliability in the power communication transmission network is represented, and the node fluctuation condition in the power communication transmission network is reflected through a formula (5).
(S34) calculating a network delay of the network data communication;
when the optimization model optimizes reliable routes in the communication network, the importance of the initial optical layer nodes and the communication network time delay are calculated, and all reachable paths are counted to form a main path set which is recorded asCalculating a separation path for each path in the set to obtain a backup path setThen go right againCalculating the average node importance in the main path and the backup path, wherein the average node importance function is as follows:
in formula (6), g and h represent OTN layer network nodes, x and y represent the total number of nodes of the primary path and the backup path,indicating the node importance of the network data node as g,and (3) representing the node importance when the network data node is h, selecting the main path and the backup path with the minimum importance to transmit service data in the power communication system when the node importance is calculated through a formula (6), and updating the node importance in the communication network to calculate the time node when the transmission data information service in the next power communication transmission network arrives.
The time delay and the reliability of the electric power service are constraint conditions, the influence of cascade faults is considered, the optimization target is that the risk dispersion is minimum, and the time delay constraint of the model is composed of the path time delay of the electric power equipment, the time delay of the photoelectric interface and the optical transmission time delay;
fourthly, communication evaluation in the power communication transmission network is realized through an evaluation module, wherein the evaluation module comprises a feature extraction module, a convolution calculation module, a pooling calculation module, a feature prediction module, an information clustering analysis module and a loss calculation module, the output end of the feature extraction module is connected with the input end of the convolution calculation module, the output end of the convolution calculation module is connected with the input end of the pooling calculation module, the output end of the pooling calculation module is connected with the input end of the feature prediction module, the output end of the feature prediction module is connected with the input end of the information clustering analysis module, and the output end of the information clustering analysis module is connected with the input end of the loss calculation module;
wherein the characteristic extraction module is used for extracting data information in the power communication network, the convolution calculation module is used for calculating communication parameters in the data information in the power communication network, the pooling calculation module is used for normalizing the input information characteristic diagram value,
randomly sampling and selecting according to the normalized probability value of the feature map;
the characteristic prediction module is used for predicting data information of the data information in the power communication network in the communication process according to the data information in the power communication network, the information clustering analysis module is used for clustering analysis and classification of the input data information in the power communication network so as to improve the data information classification capability in the power communication network, and the loss calculation module is used for calculating the loss of the data information in the power communication network in the communication process;
in a specific embodiment, the electric power communication Network designed by the invention integrates an Optical Transport Network (OTN) and a Packet Transport Network (PTN), the communication Network is composed of an electric power terminal, an Optical Network node, a relay node, an Optical fiber link, an optoelectronic mapping interface and the like, and distributed Network management and control are adopted, so that the communication Network can effectively manage and configure Network resources, and Packet transmission can effectively detect data loss and avoid data collision. In the hybrid networking of the power communication network, the optical transmission network can fully utilize the limited optical network resources in the power grid, and has a multi-layer transmission mechanism, and the hybrid networking mode can adjust the data rate and allocate the frequency spectrum, and can provide dynamic resource allocation according to different service requirements. By applying the network sensing technology, the power communication network has sensing capability on the network state, senses the network topology, time delay and faults in real time, and realizes network node sensing through the network topology and time delay.
In the embodiment, a control chip adopted by the sensing unit is an STM32F429ZET6 singlechip, and the transmission of communication data information is realized through an ARM 32-bit Cortex TM-M4 processor core, wherein the sensing unit is provided with 12-channel DMA and 112 fast I/O ports, and the dominant frequency range is 1.4 to 1.6GHZ.
In a specific embodiment, the embedded development board of the sensing unit uses Exynos4412, the sensing unit has a plurality of analog parameter signal input interfaces, can be adapted to a plurality of types of network devices in a network, and uploads the data such as the sensed running state of the network devices and network parameters to the monitoring server in a wireless transmission mode after amplification, filtering and digitization processing.
In the above embodiment, the data information sensed by the sensing unit is a communication protocol, a network communication mode, a format of transmitting data information, a communication transmission speed, a networking mode, a network node, a data stream protocol header, a data stream symbol, data stream characteristic information, a sensing delay, and a link bandwidth.
In a particular embodiment, the wireless communication module employs a USR-G806 router.
As shown in fig. 3, in a specific embodiment, the WiFi signal may reach 100M, and a 3dbi high gain antenna is used to support multiple encrypted transmissions. The clock module uses a DS1337 chip, an X1 pin of the clock module is connected to a 32.7KHz quartz crystal oscillator to provide an external oscillation signal source, an SCL is a serial clock input and is used for synchronous bus data transmission, an SDA interface is connected with an LCD pin to output clock data, and the clock and signal output can be controlled by configuring a time register in the clock module.
In fig. 3, in the specific embodiment, the MPLS-TP module collects data information in the power communication network through the analog quantity collecting circuit, in the input channel, by、Andtogether forming an input set of the acquisition circuit,andrespectively have a resistance value ofAndto realize the conversion of input current and voltage, wherein the diodeModel SS34, realizes reverse connection protection of input end, makes maximum forward conduction voltage drop 0.5V, and simulates switchAnd operational amplifierThe middle stage of the acquisition circuit is formed, and the output end of the switch is connected with a voltage follower in a cascade mode.
The current of the conducting branch is reduced, and meanwhile, the output voltage error of the intermediate stage is reduced.
In a specific embodiment, the power communication transmission network rack is a power communication network architecture in an improved OTN + PTN networking mode.
The electric power communication Network designed by the invention integrates an Optical Transport Network (OTN) and a Packet Transport Network (PTN), the communication Network comprises an electric power terminal, an Optical Network node, a relay node, an Optical fiber link, an optoelectronic mapping interface and the like, and the distributed Network management and control are adopted, so that the communication Network can effectively manage and configure Network resources, and the Packet transmission can effectively detect the loss of data and avoid data collision.
In a specific embodiment, the performance evaluation of the power communication transmission network is realized through a network evaluation algorithm model, wherein the method of the network evaluation algorithm comprises the following steps:
the method is improved on a YOLO algorithm model, a backbone network (FFD) is added for extracting defect characteristics, a defect detection model is constructed on the basis of a YOLOV3 network, the characteristics of different branches are fused and then predicted, the final characteristic expression capability is enhanced, and the method can be better applied to the detection task of the system.
The FFD network finishes Feature extraction through a large amount of convolution and pooling operations, outputs corresponding image features, and is continuously fused with bottom-layer features, wherein the SPP module fuses local detail features with global features, and a Feature Prediction Network (FPN) combines high-level semantic features with low-level features, so that the predicted scale is more accurate. The convolution operation formula of the FDD network in the power communication network is as follows:
in the formula (7), x in the formula is input power communication network transmission line image data,a kernel function of the FDD network is represented,representing the output power communication network characteristic mapping result,a weighted average parameter representing the power communication network,and (4) representing the weight vector of the image data, and completing defect feature extraction on the power transmission line image through a formula (7). Because the convolution operation is focused on the local information of the image data, the operation between the average values of all elements in the feature extraction channel is adopted, and the convolution component calculation function is as follows:
in the formula (8), in the formula、Indicating the length and width of the defect image input feature matrix,which represents the activation function of the network and,expressing a defect feature vector, and completing the nonlinear activation of the vector in the feature extraction channel through a formula (8); after the feature extraction is completed, the power communication network performs feature fusion of different scales, and a fusion formula is expressed as follows:
in the formula (9), B represents the number of prior frames in the FPN network, C represents the number of categories of the defect characteristics of the power communication network line,andthe offset representing the image grid coordinates is the horizontal and vertical coordinates,andand (3) representing the scale for predicting the transmission performance of the power communication network line, wherein the power communication network line defect characteristic normalization function is represented as follows:
in the formula (10), the first and second groups,representing the scale normalization processing of the data information of the network line defect of the power communication network,a real target frame of a data information detection model representing the network line defect characteristics of the power communication network,the clustering center represents the communication data information of the network line of the power communication network;
calculating the coordinate loss of the power communication network line detection model, wherein the loss function is as follows:
in the formula (11), the first and second groups,representing the size of the extracted information image of the power communication network line,representing the actual values of the target boxes of the power communication network line detection model,representing the line scaling parameters of the power communication network,representing the loss function in the data transmission process of the network line of the power communication network.
In summary, the residual module and the bottom layer features are fused, the improved features between the backbone networks are used for extraction, the local detail features and the global features are fused with each other, and the improved multi-scale branches are used for prediction, so that the detection effect of the target with small defect features is improved.
Convolutional Neural Networks (CNNs) are a class of feed forward Neural Networks (fed Neural Networks) that include convolution computations and have a deep structure, and are one of the representative algorithms of deep learning (deep learning). Convolutional Neural Networks have a representation learning (representation learning) capability, and can perform Shift-Invariant classification (Shift-Invariant classification) on input information according to a hierarchical structure thereof, and are therefore also called Shift-Invariant Artificial Neural Networks (SIANN) "When the network line data information of the power communication network is evaluated, a backbone network (FFD) is added for extracting defect characteristics, in a specific embodiment, a defect detection model can be constructed on the basis of a YOLOV3 network, the characteristics of different branches are fused and then predicted, the final characteristic expression capability is enhanced, and the method can be better applied to a detection task of a system.
In order to verify the reliability of the power communication network, a simulation test platform is set up for experimental analysis, and functional verification is performed through testing. The experiment computer uses Intel core i9 12900K processor, carries LANCER 32GB DDR5 5200 memory, and the hard disk uses HOF EXTREME M.2 TB SSD. The experimental computer builds an experimental environment suitable for the power communication network by using a MININET simulation tool, and the number of ports of different topology types is kept consistent. The experimental environment configuration is shown in table 1.
Table 1 experimental environment configuration
The experimental data set transmitted in the power communication network comprises power scheduling data, safety control data, power terminal operation parameters, fault information, direct current protection data, power marketing data and the like, and the data set is subjected to preliminary screening and preprocessing operations. The experimental data set is shown in table 2.
TABLE 2 Experimental data set
When a node state analysis experiment of the power communication network is carried out, the method and the scheme 1 are used for carrying out optimization protection on the built power service with the same configuration, and the scheme 2 adopts a convolutional neural network method. The experimental time is set to 30 minutes, the node occupancy rates of the communication network after the power service is loaded are counted, and the counted node occupancy rate data are shown in table 3.
TABLE 3 node occupancy data
In the comparison table, the displayed network node occupation conditions show that in the communication network of the method, all nodes operate normally, the node occupancy rate is approximately within the range of 20% -35%, and the occupancy rate of partial nodes reaches 38% at most. When the method ensures the normal transmission of the power service data, the condition of high node occupancy rate of partial nodes is considered, the transmission path with high node occupancy rate can be replaced by the suboptimal path, and the data communication pressure of a communication network is relieved. In the comparison method, the node occupancy rate is up to 45% at most, the node occupancy rate range fluctuates between 10% and 40%, part of nodes are in a fault state, the excessive node occupancy rate may cause full-load operation of the nodes, and corresponding grounding cannot normally operate when a fault occurs. The average time delay of the communication link is tested during the experiment, the number of the power businesses in the communication network is set to be 100, the power businesses are distributed in a plurality of communication paths, and the flow passing through the communication link is simulated. The method of the invention carries out route optimization,
according to the analysis experiment result, the average time delay of the communication link optimized by the method is low and is less than 40ms as a whole, and the average time delay of the communication link optimized by the method of the scheme 2 is more than 50ms at most. In the method of the scheme 2, the loads of the No. 1, no. 5 and No. 8 communication links are large, the data transmission delay is more than 30ms, the balance degree is low, the average delay of the No. 4 link is 16.5ms, the load conditions of other links can be considered in optimization, the overall load balance degree of a communication network cannot be influenced, the average delay of the No. 1 link is 37.5ms at most, the average delays of the No. 5, no. 7, no. 9 and No. 10 communication links are less than 20ms, and the delay of the No. 7 link is 11.2ms at least.
The above tests show the specific and outstanding technical effects of the method of the present invention.
Although specific embodiments of the invention have been described herein, it will be understood by those skilled in the art that these embodiments are merely illustrative and that various omissions, substitutions and changes in the form and details of the methods and systems described may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the steps of the above-described methods to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is to be limited only by the following claims.
Claims (7)
1. A comprehensive evaluation method for the performance of a power communication transmission network is characterized by comprising the following steps: the method comprises the following steps:
step one, sensing the communication information characteristics of a power communication transmission network through a sensing unit, and transmitting sensed data information to an application terminal through a wireless communication module;
constructing an improved OTN + PTN networking mode to form a power communication transmission network frame, transmitting input data information, wherein the communication network comprises a power terminal, an optical network node, a relay node, an optical fiber link and a photoelectric mapping interface, realizing data information transmission through a packet transmission network, and realizing data packet transmission facing network data information connection by expanding an MPLS-TP module in the packet transmission network, so that the label forwarding capability is increased, and the hop-by-hop routing forwarding function based on IP addresses is improved;
the extended MPLS-TP module comprises an encoding module and an identification module; the encoding module is used for encoding different data nodes in the power communication transmission network architecture, and the identification module is used for identifying the encoded data nodes;
evaluating the performance of the power communication transmission network in the communication network through an optimization model, wherein the optimization model realizes data information evaluation through the following method;
the optimization model function construction method comprises the following steps:
(S31) constructing a time delay constraint model, wherein the time delay constraint model function is expressed as:
in the formula (1), the first and second groups of the compound,representing the optical transmission delay of the OTN layer,indicating the transmission speed of the data in the fiber link,indicates the length of the optical fiber link of the communication network,representing the processing delay of the optical network node equipment,representing the number of communication network routing hops,the total time delay of the route is represented, and the power communication transmission is calculated through an optimization model of formula (1)Delay constraint of network performance evaluation is input;
(S32) constructing a reliability constraint function model of the data communication;
reliability constraint of the performance of the power communication network is related to reliability factors of a power terminal path, an OTN layer photoelectric interface path and an optical fiber path, the probability of protecting fault-free transmission service of each module in the communication network is represented, and a reliability constraint function model is represented as follows:
in the formula (2), the first and second groups,a model of a fiber reliability constraint function is represented,representing the reliability of the main path of power communication,indicating the reliability of the power communication backup path,representing the total reliability of data transmission;
(S32) constructing an importance function of the power communication network nodes;
the node importance function of the power communication network is expressed as:
in the formula (3), the first and second groups of the compound,representing voltage level weights in the power communications transmission network,representing power node degree weights in a power communications transmission network,representing node voltage levels in the power communications transmission network,representing a number of power nodes of a communication network in a power communication transmission network;
(S33) constructing node importance of an OTN layer in the power communication transmission network, node risk and node occupancy rate of an optical network layer, wherein the occupancy rate function is as follows:
in the formula (4), the first and second groups,representing the risk degree weight of the optical layer node,representing the optical layer node occupancy weight,the optical layer normalized risk is represented,normalized power node degrees are represented;
the node reliability performance standard deviation function of the communication network in the power communication transmission network is expressed as:
in the formula (5), whereinRepresents the communication average node occupancy rate in the power communication transmission network,representing the total number of network nodes in the power communications transmission network,the network reliability in the power communication transmission network is represented, and the node fluctuation condition in the power communication transmission network is reflected through a formula (5);
(S34) calculating a network delay of the network data communication;
when the optimization model optimizes reliable routes in the communication network, the importance of the initial optical layer nodes and the communication network time delay are calculated, and all reachable paths are counted to form a main path set which is recorded asCalculating a separation path for each path in the set to obtain a backup path setThen, the average node importance in the main path and the backup path is calculated, and the average node importance function is:
in formula (6), g and h represent OTN layer network nodes, x and y represent the total number of nodes of the primary path and the backup path,indicating the node importance of the network data node as g,representing the node importance when the network data node is h, when the node importance is calculated through a formula (6), selecting a main path and a backup path with the minimum importance to transmit service data in the power communication system, and then updating the node importance in the communication network to calculate a time node when a transmission data information service arrives in the next power communication transmission network;
fourthly, communication evaluation in the power communication transmission network is realized through an evaluation module, wherein the evaluation module comprises a feature extraction module, a convolution calculation module, a pooling calculation module, a feature prediction module, an information clustering analysis module and a loss calculation module, the output end of the feature extraction module is connected with the input end of the convolution calculation module, the output end of the convolution calculation module is connected with the input end of the pooling calculation module, the output end of the pooling calculation module is connected with the input end of the feature prediction module, the output end of the feature prediction module is connected with the input end of the information clustering analysis module, and the output end of the information clustering analysis module is connected with the input end of the loss calculation module;
the system comprises a feature extraction module, a convolution calculation module, a pooling calculation module and a probability value normalization module, wherein the feature extraction module is used for extracting data information in the power communication network, the convolution calculation module is used for calculating communication parameters in the data information in the power communication network, and the pooling calculation module is used for normalizing input information feature map values and randomly sampling and selecting the input information feature map values according to the probability value after the feature map is normalized;
the characteristic prediction module is used for predicting data information of the data information in the power communication network in the communication process according to the data information in the power communication network, the information clustering analysis module is used for clustering analysis and classification of the input data information in the power communication network so as to improve the data information classification capability in the power communication network, and the loss calculation module is used for calculating the loss of the data information in the power communication network in the communication process.
2. The method according to claim 1, wherein the method comprises the following steps: a control chip adopted by the sensing unit is an STM32F429ZET6 single chip microcomputer, and communication data information transmission is realized through an ARM 32-bit Cortex TM-M4 processor core, wherein the sensing unit is provided with 12-channel DMA and 112 rapid I/O ports, and the main frequency range is 1.4-1.6 GHZ.
3. The method according to claim 2, wherein the method comprises the following steps: the data information sensed by the sensing unit is communication protocol, network communication mode, format of transmission data information, communication transmission speed, networking mode, network node, data stream protocol header, data stream symbol, data stream characteristic information, sensing time delay and link bandwidth.
4. The method according to claim 1, wherein the method comprises the following steps: the wireless communication module adopts a USR-G806 router.
5. The method according to claim 1, wherein the method comprises the following steps: the MPLS-TP module collects data information in the power communication network through an analog quantity collecting circuit, and the data information is transmitted to the MPLS-TP module through the analog quantity collecting circuit in an input channel、Andtogether forming an input set of the acquisition circuit,andrespectively have a resistance value ofAndto realize the conversion of input current and voltage, wherein the diodeModel SS34, realizes reverse connection protection of input end, makes maximum forward conduction voltage drop 0.5V, and simulates switchAnd operational amplifierThe middle stage of the acquisition circuit is formed, and the output end of the switch is connected with a voltage follower in a cascade mode.
6. The method according to claim 1, wherein the method comprises the following steps: the power communication transmission net rack is a power communication network framework in an improved OTN + PTN networking mode.
7. The method according to claim 1, wherein the method comprises the following steps: the performance evaluation of the power communication transmission network is realized through a network evaluation algorithm model, wherein the method of the network evaluation algorithm comprises the following steps:
the convolution operation formula for the FDD network in the power communication network is as follows:
in the formula (7), x in the formula is input power communication network transmission line image data,a kernel function of the FDD network is represented,representing the output power communication network characteristic mapping result,a weighted average parameter representing the power communication network,a weight vector representing the image data,
the volume integral calculation function is:
in the formula (8), in the formula、Representing the length and width of the defect image input feature matrix,which represents the activation function of the network and,expressing a defect feature vector, and completing the nonlinear activation of the vector in the feature extraction channel through a formula (8); after the feature extraction is completed, the power communication network performs feature fusion of different scales, and a fusion formula is expressed as follows:
in the formula (9), B represents the number of prior frames in the FPN network, C represents the number of categories of the defect characteristics of the power communication network line,andthe offset representing the image grid coordinates is the horizontal and vertical coordinates,andand (3) representing the scale for predicting the transmission performance of the power communication network line, wherein the power communication network line defect characteristic normalization function is represented as follows:
in the case of the formula (10),representing the scale normalization processing of the data information of the network line defect of the power communication network,a real target frame of a data information detection model representing the network line defect characteristics of the power communication network,the clustering center represents the communication data information of the network line of the power communication network;
calculating the coordinate loss of the power communication network line detection model, wherein the loss function is as follows:
in the formula (11), the first and second groups,representing the size of the extracted information image of the power communication network line,actual values representing the target boxes of the power communication network line detection model,representing the line scaling parameters of the power communication network,representing a loss function in the transmission of network line data of the power communication network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210964576.4A CN115174435A (en) | 2022-08-12 | 2022-08-12 | Comprehensive evaluation method for performance of power communication transmission network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210964576.4A CN115174435A (en) | 2022-08-12 | 2022-08-12 | Comprehensive evaluation method for performance of power communication transmission network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115174435A true CN115174435A (en) | 2022-10-11 |
Family
ID=83480263
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210964576.4A Withdrawn CN115174435A (en) | 2022-08-12 | 2022-08-12 | Comprehensive evaluation method for performance of power communication transmission network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115174435A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116599687A (en) * | 2023-03-15 | 2023-08-15 | 中国人民解放军61660部队 | Low-communication-delay cascade vulnerability scanning probe deployment method and system |
-
2022
- 2022-08-12 CN CN202210964576.4A patent/CN115174435A/en not_active Withdrawn
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116599687A (en) * | 2023-03-15 | 2023-08-15 | 中国人民解放军61660部队 | Low-communication-delay cascade vulnerability scanning probe deployment method and system |
CN116599687B (en) * | 2023-03-15 | 2023-11-24 | 中国人民解放军61660部队 | Low-communication-delay cascade vulnerability scanning probe deployment method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Nie et al. | Network traffic prediction based on deep belief network and spatiotemporal compressive sensing in wireless mesh backbone networks | |
CN102938742B (en) | Communication bandwidth forecasting method and device based on power business requirements | |
CN101997717B (en) | Analysing communication performance of IED | |
CN102549513A (en) | Reliability calculation for substation automation systems | |
CN110971525B (en) | Service routing and addressing method for service operation of power communication network | |
CN111431819A (en) | Network traffic classification method and device based on serialized protocol flow characteristics | |
CN113438010B (en) | Constellation system capability evaluation system and system for heaven-earth integrated network | |
TWI783229B (en) | Anomaly flow detection device and anomaly flow detection method | |
EP3923517A1 (en) | System and method for predicting and handling short-term overflow | |
CN105187255B (en) | Failure analysis methods, fail analysis device and server | |
CN116633835B (en) | Complex high-reliability network performance comprehensive evaluation method | |
US20210027167A1 (en) | Model structure extraction for analyzing unstructured text data | |
CN109299160B (en) | Power CPS security analysis method based on monitoring big data mining | |
CN115174435A (en) | Comprehensive evaluation method for performance of power communication transmission network | |
CN111355671B (en) | Network traffic classification method, medium and terminal equipment based on self-attention mechanism | |
CN111935767B (en) | Network simulation system | |
Bouwmeester et al. | Towards an innovative electrical interface standard for PocketQubes and CubeSats | |
CN111431872B (en) | Two-stage Internet of things equipment identification method based on TCP/IP protocol characteristics | |
Alsulami et al. | A real application enabled traffic generator for networking ai model development | |
Guo et al. | FullSight: A feasible intelligent and collaborative framework for service function chains failure detection | |
CN107688878B (en) | Air Quality Forecast method and device | |
US20220286263A1 (en) | Signaling analysis method and related apparatus | |
CN110191028A (en) | It can the test device of interconnection equipment of software definition, system and method | |
CN115981192A (en) | Industrial network based cooperative control and prejudgment method | |
CN115423041A (en) | Edge cloud fault prediction method and system based on deep learning |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221011 |
|
WW01 | Invention patent application withdrawn after publication |