CN114189902A - Customized power 5G/B5G communication access method based on power service QoS flow mapping - Google Patents
Customized power 5G/B5G communication access method based on power service QoS flow mapping Download PDFInfo
- Publication number
- CN114189902A CN114189902A CN202111241824.4A CN202111241824A CN114189902A CN 114189902 A CN114189902 A CN 114189902A CN 202111241824 A CN202111241824 A CN 202111241824A CN 114189902 A CN114189902 A CN 114189902A
- Authority
- CN
- China
- Prior art keywords
- power
- data
- service
- communication
- flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004891 communication Methods 0.000 title claims abstract description 80
- 238000013507 mapping Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000007246 mechanism Effects 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 15
- 230000006399 behavior Effects 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 238000013501 data transformation Methods 0.000 claims description 7
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000013468 resource allocation Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000004069 differentiation Effects 0.000 abstract description 2
- HRULVFRXEOZUMJ-UHFFFAOYSA-K potassium;disodium;2-(4-chloro-2-methylphenoxy)propanoate;methyl-dioxido-oxo-$l^{5}-arsane Chemical compound [Na+].[Na+].[K+].C[As]([O-])([O-])=O.[O-]C(=O)C(C)OC1=CC=C(Cl)C=C1C HRULVFRXEOZUMJ-UHFFFAOYSA-K 0.000 description 7
- 238000007726 management method Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- 241000700605 Viruses Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000004941 influx Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
- H04W28/24—Negotiating SLA [Service Level Agreement]; Negotiating QoS [Quality of Service]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/0231—Traffic management, e.g. flow control or congestion control based on communication conditions
- H04W28/0236—Traffic management, e.g. flow control or congestion control based on communication conditions radio quality, e.g. interference, losses or delay
Abstract
The invention relates to a customized power 5G/B5G communication access method based on power service QoS flow mapping, which is technically characterized in that: capturing original service data packets at each communication access point through a network packet capturing tool; pre-processing the unclassified power communication data in the service data packet to obtain data convenient for power service flow identification, and classifying the power communication data; carrying out port matching according to the registered port list, and identifying the coarse granularity of the power service flow; obtaining source and destination addresses, a communication protocol and data packet length information by a deep analysis data packet detection technology; and identifying the power service based on the port and flow behaviors and distributing different QFI values for the power QoS flow by combining the QoS delay index. The invention can avoid the influence caused by level differentiation, meets the clear communication rigid QoS requirement commonly possessed by the electric power system service, perfects the electric power QoS flow mapping mechanism based on B5G, and provides a basis for service division of electric power communication delay calculation.
Description
Technical Field
The invention belongs to the technical field of 5G/B5G communication, relates to a 5G/B5G communication access method, and particularly relates to a customized power 5G/B5G communication access method based on power service QoS flow mapping.
Background
The wireless communication technology represented by 5G has significant advantages in the research of the power multi-agent convergence network, and the power wireless communication system will also become a development trend of the power communication system. The communication network architecture system generally comprises an access network, a bearer network and a core network.
The power B5G communication convergence system is a complex network composed of power grid and communication grid which are interdependent, and the interdependence is embodied by coupling between power nodes and communication nodes, as shown in fig. 1. The power nodes formed by physical entity equipment such as a generator, a transformer, a circuit breaker, a controllable load and the like are electrically connected to form a power grid with a certain topological structure. Because the communication network is laid according to the physical structure of the power grid, the communication network and the power grid have high topological similarity. The information real-time interaction is a core link for realizing electric power Communication coupling, electric power data are transmitted to the AAU through an intelligent electric power Communication Terminal (CT) connected with the AAU, and then are uploaded to a B5G core network through convergence of a DU/CU so as to realize dispatching automation management. Because the core network of the B5G cancels the bearing concept and adapts the QoS requirements of each access service at the RAN side, the QoS flow granularity mapping under the radio bearing mode based on the terahertz (THz) frequency band can make the service data flow control under the B5G communication environment finer.
At present, the QoS mapping involves multi-layer mapping, and because the messages transmitted by different layers and the protocols used by communication are different, the QoS mapping mechanism at the bottom layer cannot be directly applied to the QoS configuration at the upper layer. Such as: GOOSE and SV messages on the second layer in the substation are generally based on the higher priority VLAN tag obtained by IEEE 802.1Q, but they cannot correspond to the DSCP value set in the IP message on the third layer. For a complex power system involving multi-layer cascading, QoS configuration considering priority may become complicated. And 5G proposes mapping based on QoS flow granularity, each network function module of a core network completes corresponding QoS configuration and rules, and then data flow completes DRB establishment and QoS flow mapping in RAN. However, the power system services usually have explicit rigid QoS requirements for communication, and although the QoS characteristic mapping tables calibrated according to the QoS requirements of the distribution high voltage/medium voltage power services do not include the critical services of power, such as distributed energy regulation and response on the demand side of the electrical load, in the 3GPP TS22.261 and the 3GPP TS 23.501, the power QoS flow mapping mechanism based on B5G needs to be perfected.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a customized power 5G/B5G communication access method based on power service QoS flow mapping, which can perfect a power QoS flow mapping mechanism based on B5G and meet the current power service communication requirement.
The invention solves the technical problems in the prior art by adopting the following technical scheme:
a customized power 5G/B5G communication access method based on power service QoS flow mapping comprises the following steps:
step 3, carrying out port matching according to the registered port list, and identifying the coarse granularity of the power service flow;
step 4, obtaining source and destination addresses, a communication protocol and data packet length information through a deep analysis data packet detection technology;
and 5, identifying the power service based on the port and flow behaviors and distributing different QFI values for the power QoS flow by combining the QoS delay index.
Moreover, the step 2 adopts the following technology for pretreatment: data cleaning, data integration, data transformation and data specification; the preprocessing content comprises the following steps: repairing incomplete data, correcting error data, removing redundant data, and detecting and eliminating errors and inconsistencies in data; the pretreatment method comprises the following steps: and integrating relevant attributes, specification inconsistent attributes and constructing new attributes according to the characteristics of the power communication data, and processing non-specification data and data which cannot be processed by a data mining model through smoothing, aggregation and standardization operations in data transformation to finally obtain data convenient for power service flow identification.
In addition, the step 2 of classifying the power communication data is based on a support vector machine, and the classification of the power communication data is divided by combining the characteristics exhibited by extracting the redundant data, and the specific method comprises the following steps:
let T ═ x be the sample set used to characterize the redundant datai,yi) Wherein x isi∈Rn，yiBelongs to (-1, +1), if the function formula is judged to be:
f(X)＝sgn(ω·x+b)
considering yiE (-1, +1), the function should satisfy the condition that the distance between the data point and the optimal classification line is not less than 1, namely:
yi(ωixi+b)-1≥0
ω, x + b is 0 belonging to the hyperplane, and is used to distinguish and partition the samples, and if the distinguishing and partitioning work of the samples is planned to be performed by means of classifying the hyperplane, Lagrange function is preferred, that is:
wherein alpha isiA representative function multiplier, the value of which is not less than 0; in conjunction with the hyperplane creation parameters, the function used to make the classification decision is determined as:
f(x)＝sgn(∑yiαixix+b)
the function is utilized to accurately judge the x category, and the optimization problem is converted into the following steps:
suppose that
Then, combining the above formula, the following judgment function is obtained:
wherein, K (x)i,xj) Representing a kernel function.
Moreover, the specific implementation method of step 3 is as follows: according to user requirements, it is ensured that quantifiable service quality parameters are controlled in an allowed range, according to a differentiated service model, a plurality of service flows with the same characteristics are aggregated by adopting an aggregation mechanism, service is provided for the whole aggregated flow, classification and flow control are carried out on the service at a network entrance according to service requirements, each type of communication is differentiated in a network according to a configured mechanism, and the service comprises resource allocation, queue scheduling and grouping discarding strategies.
Moreover, the specific implementation method of the step 4 is as follows: and matching the content of each data packet with a group of predefined features by adopting a feature matching algorithm to obtain the length information of the data packet, identifying a control flow by adopting an application layer gateway identification technology, analyzing the control flow through a specific application layer gateway according to a protocol of the control flow, identifying a corresponding service flow from the protocol content, and further acquiring source and destination addresses and communication protocol information.
Moreover, the feature matching algorithm is carried out in a regular expression matching mode of a finite automaton, and the specific method is as follows:
the finite automaton is a mathematical model, the input is a string to be matched, the output is accept or reject, and a receiver of the finite automaton has a quintuple formula:
FA＝(Q，∑，δ，q0，F)
wherein Q is a finite set, not empty, representing a set of states;
Σ is an alphabet representing the input character set;
q0e.Q is an initial state;
δ is the state transition function, which is expressed as follows:
Q×∑→Q
namely:
δ(q，x)＝q′
in the above formula, when the current state of the finite automaton is q, the state q' is reached after the character x is read; and scanning each character in the string by the automaton in sequence, and after all the characters in the string are scanned, if the current state of the automaton is any receiving state, the automaton is called to accept the string, otherwise, the automaton is called to reject the string, and the length, source address, destination address and communication protocol information of the data packet are obtained through the pattern matching algorithm.
The invention has the advantages and positive effects that:
the invention provides a QoS flow mapping mechanism aiming at the power service by analyzing the service requirement of a power wireless access scene and combining with a mechanism about QoS flow mapping of 3GPP Release16, captures an original service data packet at each communication access point and carries out port matching to realize coarse grain identification of the power service flow, obtains information identification flow behaviors such as source and destination addresses, communication protocols, data packet lengths and the like by deep analysis data packet detection technology, identifies the power service based on the port and flow behaviors and distributes different QFI values for the power QoS flow by combining with QoS delay indexes, can avoid the influence caused by level differentiation, meets the clear communication rigid QoS requirement commonly possessed by the power system service, perfects the power QoS flow mapping mechanism based on B5G and provides a basis for service division of power communication delay calculation.
Drawings
FIG. 1 is a diagram of a power communication coupling architecture based on B5G;
fig. 2 is a QoS flow mapping diagram;
fig. 3 is a diagram of a mapping structure of power QoS flow according to the present invention.
Detailed Description
The embodiments of the present invention will be described in detail with reference to the accompanying drawings.
To facilitate an understanding of the present invention, the following concepts are first described:
1. QoS flow mapping mechanism
Concept of QoS: the meaning is service quality, specifically, it is an index measurement for measuring the service level provided by a specific system for various services flowing into the system by using a series of network technologies such as traffic engineering mechanism, communication interface protocol, queue scheduling policy, etc. Common network QoS measurement indexes comprise bandwidth, time delay, jitter and packet loss rate, and the performance indexes evaluate the network characteristics of a system from two dimensions of effectiveness and reliability respectively, so that the concept of QoS becomes an important index for guaranteeing differentiated service requirements of different services, and the method is widely applied to the field of communication. For the QoS application requirements of diversified and complicated services of different subjects, the core network of the communication system nowadays gradually cancels the externalization performance of the bearer, adopts more refined QoS flow granularity management and control, and introduces a QoS flow mapping mechanism, so that the QoS flow becomes the finest differentiated granularity in a Protocol Data Unit (PDU) session.
Concept of QoS flow mapping: QoS Flow mapping refers to mapping a plurality of traffic data flows with the same QoS requirement into the same QoS Flow class, and allocating unique qfi (QoS Flow identifier) identifiers to distinguish them, which is intended to occupy additional underlying physical resources in order to avoid a large influx of traffic of the same class.
Under the 5G/B5G communication network architecture, a User Equipment (UE) at a User side first performs flow control of uplink Service Data according to a preconfigured explicit QoS rule or an implicit QoS rule through a reflection mechanism, and then the RAN maps Data packets of each QoS flow to a specific radio Bearer (DRB) according to QoS configuration information and a Service Data Adaptation Protocol (SDAP), and marks a unique QFI identifier for uplink and downlink Data packets, thereby completing a QoS flow mapping process, where a simplified process is shown in fig. 2.
The most important network function module in fig. 2 is the UPF, which represents the user plane function and is responsible for processing and forwarding uplink and downlink packet data. The network function module (SMF) having a session management function is responsible for performing binding of QoS flows and transmitting QoS control information of Service Data Flows (SDFs) and class identification information (QFI) of each QoS Flow to the UPF. The network function module (AMF) with access and mobility management is responsible for sending explicit or implicit QoS rules to the UE, and sending QoS configuration information and QFI of each traffic flow to the RAN.
2. Power QoS flow mapping model
For a power communication network, the emergency degree and the delay constraint of a service are very important considerations, for example, once a power system element fails, a power frequency electrical quantity is subjected to instantaneous jump, which is very easy to cause a power failure accident, so that the protection action time of sending a trip command to a controlled breaker needs to be strictly controlled within 10 ms. Considering the QoS delay requirement of each power service flow comprehensively, it is proposed to complete the identification and mapping of the QoS-based power service flow by using a five-tuple consisting of a source port, a destination port, a source address, a destination address and a transport layer protocol, as shown in fig. 3.
Firstly, capturing original service data packets at each communication access point through a network packet capturing tool, and preprocessing unclassified power communication data; then, carrying out port matching according to the registered port list, and identifying the coarse granularity of the power service flow; then, obtaining information identification flow behaviors such as a source address, a destination address, a communication protocol, a data Packet length and the like through a Deep Packet Inspection (DPI) technology; and finally, identifying the power service based on the port and flow behaviors and distributing different QFI values for the power QoS flow by combining the QoS delay index.
As known from the standardized QoS mapping result of 3GPP, the resource type is a key characteristic that needs to be considered for QoS mapping, and therefore, the DSCP label value of the IP header needs to be set according to QFI allocation, so as to divide the resource types of the B5G power communication network. The DSCP high three bits are used for distinguishing resource types of the power traffic in the B5G communication, including a Guaranteed Bit Rate (GBR) resource class, a Non-Guaranteed Bit Rate (Non-GBR) resource class, and a time-Critical Guaranteed Bit Rate (DCGBR) resource class. Wherein, the first position "1" in the upper three bits of the DSCP represents Non-GBR class, the second position "1" represents GBR class, and the third position "1" represents DCGBR class. And the lower three bits of the DSCP adopt a uniform quantization coding rule according to the QFI value, namely, the DSCP is divided into eight levels from small to large from 000 to 111.
When different service requests are initiated from different intelligent power equipment, the UE can execute corresponding QoS control on data packets of different service flows according to QoS rules, analyze message header configuration information on a B5G access network side, and complete power QoS flow mapping according to binary DSCP tag values.
Based on the above description, the present invention provides a customized power 5G/B5G communication access method based on power service QoS flow mapping, which includes the following steps:
And 2, preprocessing the unclassified power communication data in the service data packet to obtain data convenient for power service flow identification, and classifying the power communication data.
In this step, the data preprocessing technique includes: data Cleaning (Data Cleaning), Data Integration (Data Integration), Data Transformation (Data Transformation), and Data Reduction (Data Reduction), and the processing of Data including quality problems includes: repairing the incomplete data, correcting the error data, removing the redundant data, and detecting and eliminating the errors and the inconsistency of the data; secondly, according to the characteristics of the electric power communication data, relevant attributes are integrated, inconsistent attributes are normalized, new attributes are constructed, data which are not normalized and cannot be processed by a data mining model need to be processed through operations of smoothing, aggregation, normalization and the like in data transformation, data which are convenient for electric power service flow identification are finally obtained, and the electric power communication data are classified.
And classifying the categories of the redundant data based on a support vector machine in combination with the characteristics exhibited by extracting the redundant data. Regarding data characteristics, linear divisible/nonlinear divisible are selected as research entry points, and by means of classification models applicable to different sample sets, redundant data can be effectively eliminated.
Assume that the sample set that can be used to represent redundant data features is T ═ xi,yi) Wherein x isi∈Rn，yiBelongs to (-1, +1), if the function formula is judged to be:
f(X)＝sgn(ω·x+b) (1)
considering yiE (-1, +1), the function should satisfy the condition that the distance between the data point and the optimal classification line is not less than 1,namely:
yi(ωixi+b)-1≥0 (2)
ω, x + b ═ 0 belongs to the hyperplane, and is generally used to distinguish and classify samples, and if the distinguishing and classifying work of samples is planned to be performed by classifying the hyperplane, Lagrange function is preferred, that is:
wherein alpha isiRepresents a multiplier of the function, whose value is often not less than 0. In conjunction with the hyperplane creation parameters, a function is determined that can be used to make classification decisions, namely:
f(x)＝sgn(∑yiαixix+b) (4)
and accurately judging the x category by using the function. Research shows that the nonlinear condition is common in a sample set, if the sample set is to be scientifically classified, the key is to map the redundant data features to a high-dimensional space through a mapping function, and at the moment, the optimization problem is converted into:
suppose that
Then, the following decision function can be obtained by combining the above formulas:
wherein, K (x)i,xj) Representing a kernel function. For the SVM, the core factor that can determine the performance is the parameter, so the penalty parameter and the kernel function parameter should be determined in advance, and generally, the performance of the SVM will usually follow the value of the above parametersChanges occur.
And 3, carrying out port matching according to the registered port list, and identifying the coarse granularity of the power service flow.
In this step, the quantization parameters of the network QoS include data rate, delay jitter, packet loss rate, etc., and the "granularity" of the QoS represents the reference of various parameter metrics. The term "coarse-grained identification" in this sense means that quantifiable service quality parameters can be guaranteed to be controlled within an allowable range according to user requirements, a differentiated service model (Diffserv) is adopted, a plurality of service flows with the same characteristics are aggregated by adopting an aggregation mechanism to provide services for the whole aggregated flow, the services are classified and flow-controlled at a network entrance according to service requirements, each type of communication is distinguished in a network according to a configured mechanism, and the services comprise resource allocation, queue scheduling, packet discarding strategies and the like.
And 4, obtaining information identification flow behaviors such as a source, a destination address, a communication protocol, a data packet length and the like through a deep analysis data packet detection technology, matching the content of each data packet with a group of predefined features by adopting a feature matching algorithm to obtain length information of the data packet, identifying a control flow by adopting an application layer gateway identification technology, analyzing the control flow through a specific application layer gateway according to the protocol of the control flow, identifying a corresponding service flow from the protocol content, and further obtaining the information such as the source, the destination address, the communication protocol and the like.
And performing characteristic matching with the data to be matched by using a characteristic rule, wherein the header of the partial traffic data packet has a specific network protocol format, such as: for the SSH protocol, the format rule is arranged into the characteristic rule, so that the data packet is always in the form of "SSH- [12] \\ d + \\ r \" as the information transmitted in the process of starting interaction, so that the "SSH- [12] \\ d + \ - + \ r \" field can be used as the DPI identification module to load the configuration of the SSH protocol. Similarly, a plurality of flows are selected to extract the characteristic rules, and the characteristic rules are generally extracted into the expression form of a regular expression and loaded into a DPI rule set so as to identify the flows.
The pattern matching is used as a key part in the detection technology, and two matching modes are used, wherein one mode is precise character string matching, and the other mode is regular expression matching. The accurate character string matching is the basis of all detection technologies, but in view of disguise and complexity of various viruses, trojans and the like, the accurate character string matching is difficult to meet the requirements of people, and the importance of regular expression matching is gradually highlighted. Regular expression matching approaches are currently classified into three types: regular expression matching based on Deterministic Finite Automata (DFA), regular expression matching based on non-deterministic finite automata (NFA) and filter-based matching.
The finite automaton is a mathematical model, the input is a string to be matched, and the output is accept or reject. The receiver of the finite automaton is a quintuple:
FA＝(Q，∑，δ，q0f) (7) wherein Q is a finite set, not empty, representing a state set;
Σ is an alphabet representing the input character set;
q0e.Q is an initial state;
δ is the state transition function, which is expressed as follows:
Q×∑→Q (8)
namely:
δ(q，x)＝q′ (9)
the above formula represents that when the current state of the finite automaton is q, after reading the character x, the state q' is reached. And scanning each character in the string by the automaton in sequence, and when all the characters in the string are completely scanned, if the current state of the automaton is any receiving state, the automaton is called to be capable of accepting the string, otherwise, the automaton is called to reject the string. The information such as the length, the source and destination addresses, the communication protocol and the like of the data packet is obtained through the pattern matching algorithm.
And 5, identifying the power service based on the port and flow behaviors and distributing different QFI values for the power QoS flow by combining the QoS delay index.
It should be emphasized that the embodiments described herein are illustrative rather than restrictive, and thus the present invention is not limited to the embodiments described in the detailed description, but also includes other embodiments that can be derived from the technical solutions of the present invention by those skilled in the art.
Claims (6)
1. A customized power 5G/B5G communication access method based on power service QoS flow mapping is characterized in that: the method comprises the following steps:
step 1, capturing original service data packets at each communication access point through a network packet capturing tool;
step 2, pre-processing the unclassified power communication data in the service data packet to obtain data convenient for power service flow identification, and classifying the power communication data;
step 3, carrying out port matching according to the registered port list, and identifying the coarse granularity of the power service flow;
step 4, obtaining source and destination addresses, a communication protocol and data packet length information through a deep analysis data packet detection technology;
and 5, identifying the power service based on the port and flow behaviors and distributing different QFI values for the power QoS flow by combining the QoS delay index.
2. The customized power 5G/B5G communication access method based on power service QoS flow mapping according to claim 1, wherein: the step 2 adopts the following technology for pretreatment: data cleaning, data integration, data transformation and data specification; the preprocessing content comprises the following steps: repairing incomplete data, correcting error data, removing redundant data, and detecting and eliminating errors and inconsistencies in data; the pretreatment method comprises the following steps: and integrating relevant attributes, specification inconsistent attributes and constructing new attributes according to the characteristics of the power communication data, and processing non-specification data and data which cannot be processed by a data mining model through smoothing, aggregation and standardization operations in data transformation to finally obtain data convenient for power service flow identification.
3. The customized power 5G/B5G communication access method based on power service QoS flow mapping according to claim 1, wherein: the step 2 of classifying the power communication data is based on a support vector machine, and the classification of the power communication data is divided by combining the characteristics exhibited by extracting redundant data, and the specific method comprises the following steps:
let T ═ x be the sample set used to characterize the redundant datai,yi) Wherein x isi∈Rn，yiBelongs to (-1, +1), if the function formula is judged to be:
f(X)＝sgn(ω·x+b)
considering yiE (-1, +1), the function should satisfy the condition that the distance between the data point and the optimal classification line is not less than 1, namely:
yi(ωixi+b)-l≥0
ω, x + b is 0 belonging to the hyperplane, and is used to distinguish and partition the samples, and if the distinguishing and partitioning work of the samples is planned to be performed by means of classifying the hyperplane, Lagrange function is preferred, that is:
wherein alpha isiA representative function multiplier, the value of which is not less than 0; in conjunction with the hyperplane creation parameters, the function used to make the classification decision is determined as:
f(x)＝sgn(∑yiaixix+b)
the function is utilized to accurately judge the x category, and the optimization problem is converted into the following steps:
suppose that
Then, combining the above formula, the following judgment function is obtained:
wherein, K (x)i,xj) Representing a kernel function.
4. The customized power 5G/B5G communication access method based on power service QoS flow mapping according to claim 1, wherein: the specific implementation method of the step 3 is as follows: according to user requirements, it is ensured that quantifiable service quality parameters are controlled in an allowed range, according to a differentiated service model, a plurality of service flows with the same characteristics are aggregated by adopting an aggregation mechanism, service is provided for the whole aggregated flow, classification and flow control are carried out on the service at a network entrance according to service requirements, each type of communication is differentiated in a network according to a configured mechanism, and the service comprises resource allocation, queue scheduling and grouping discarding strategies.
5. The customized power 5G/B5G communication access method based on power service QoS flow mapping according to claim 1, wherein: the specific implementation method of the step 4 comprises the following steps: and matching the content of each data packet with a group of predefined features by adopting a feature matching algorithm to obtain the length information of the data packet, identifying a control flow by adopting an application layer gateway identification technology, analyzing the control flow through a specific application layer gateway according to a protocol of the control flow, identifying a corresponding service flow from the protocol content, and further acquiring source and destination addresses and communication protocol information.
6. The customized power 5G/B5G communication access method based on power service QoS flow mapping of claim 5, wherein: the feature matching algorithm is carried out in a regular expression matching mode of a finite automaton, and the specific method is as follows:
the finite automaton is a mathematical model, the input is a string to be matched, the output is accept or reject, and a receiver of the finite automaton has a quintuple formula:
FA＝(Q,∑,δ,q0，F)
wherein Q is a finite set, not empty, representing a set of states;
Σ is an alphabet representing the input character set;
q0e.Q is an initial state;
δ is the state transition function, which is expressed as follows:
Q×∑→Q
namely:
δ(q，x)＝q′
in the above formula, when the current state of the finite automaton is q, the state q' is reached after the character x is read; and scanning each character in the string by the automaton in sequence, and after all the characters in the string are scanned, if the current state of the automaton is any receiving state, the automaton is called to accept the string, otherwise, the automaton is called to reject the string, and the length, source address, destination address and communication protocol information of the data packet are obtained through the pattern matching algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111241824.4A CN114189902A (en) | 2021-10-25 | 2021-10-25 | Customized power 5G/B5G communication access method based on power service QoS flow mapping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111241824.4A CN114189902A (en) | 2021-10-25 | 2021-10-25 | Customized power 5G/B5G communication access method based on power service QoS flow mapping |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114189902A true CN114189902A (en) | 2022-03-15 |
Family
ID=80539870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111241824.4A Pending CN114189902A (en) | 2021-10-25 | 2021-10-25 | Customized power 5G/B5G communication access method based on power service QoS flow mapping |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114189902A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115460041A (en) * | 2022-09-15 | 2022-12-09 | 重庆大学 | QoS mapping method for 5G and TSN converged network |
| CN116527710A (en) * | 2023-04-27 | 2023-08-01 | 国网黑龙江省电力有限公司齐齐哈尔供电公司 | Electric power communication network system |
-
2021
- 2021-10-25 CN CN202111241824.4A patent/CN114189902A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115460041A (en) * | 2022-09-15 | 2022-12-09 | 重庆大学 | QoS mapping method for 5G and TSN converged network |
| CN115460041B (en) * | 2022-09-15 | 2023-08-29 | 重庆大学 | QoS mapping method for 5G and TSN fusion network |
| CN116527710A (en) * | 2023-04-27 | 2023-08-01 | 国网黑龙江省电力有限公司齐齐哈尔供电公司 | Electric power communication network system |
| CN116527710B (en) * | 2023-04-27 | 2023-10-24 | 国网黑龙江省电力有限公司齐齐哈尔供电公司 | Electric power communication network system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10958506B2 (en) | In-situ OAM (IOAM) network risk flow-based “topo-gram” for predictive flow positioning | |
| CN114189902A (en) | Customized power 5G/B5G communication access method based on power service QoS flow mapping | |
| EP3382960A2 (en) | Machine learning-based traffic classification using compressed network telemetry data | |
| KR101234326B1 (en) | Distributed traffic analysis | |
| US11025486B2 (en) | Cascade-based classification of network devices using multi-scale bags of network words | |
| CN112104469B (en) | Data processing method and device | |
| WO2011130957A1 (en) | Method and apparatus for online distinguishing transmission control protocol traffic by using data flow head characteristics | |
| US20220369153A1 (en) | Method and system for managing quality-of-service (qos) in communication networks | |
| CN102724123B (en) | Network traffic control method and network traffic control device | |
| CN109005126B (en) | Data stream processing method, device and computer readable storage medium | |
| US11395174B2 (en) | Systems and methods for optimized LTE private networks | |
| CN103036802A (en) | Traffic unloading method and system | |
| CN108353022A (en) | A kind of processing method of data message, apparatus and system | |
| Aureli et al. | Going beyond diffserv in ip traffic classification | |
| CN111611280A (en) | Encrypted traffic identification method based on CNN and SAE | |
| CN108156018B (en) | Power network device topology identification method, electronic device and computer storage medium | |
| US11558769B2 (en) | Estimating apparatus, system, method, and computer-readable medium, and learning apparatus, method, and computer-readable medium | |
| EP2618524A1 (en) | Method for providing QoS management in a packet-based transport network | |
| CN107659505A (en) | The route selecting method and SDN controllers of a kind of SDN | |
| US10826772B2 (en) | Removal of environment and local context from network traffic for device classification | |
| CN116471196A (en) | Operation and maintenance monitoring network maintenance method, system and equipment | |
| Schiavo et al. | Forecasting for network management with joint statistical modelling and machine learning | |
| Mahboob et al. | A novel deep-learning-enabled qos management scheme for encrypted traffic in software-defined cellular networks | |
| CN107995312A (en) | A kind of border networks flow of services separate system and dynamic shunt method | |
| CN114257526A (en) | In-band telemetry system, method and device |
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 |