CN105162612B - A kind of overstocked method of data in calculating AFDX networks - Google Patents
A kind of overstocked method of data in calculating AFDX networks Download PDFInfo
- Publication number
- CN105162612B CN105162612B CN201510336533.1A CN201510336533A CN105162612B CN 105162612 B CN105162612 B CN 105162612B CN 201510336533 A CN201510336533 A CN 201510336533A CN 105162612 B CN105162612 B CN 105162612B
- Authority
- CN
- China
- Prior art keywords
- data
- node
- delay
- upper bound
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
Landscapes
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses the method that data in a kind of calculating AFDX networks overstock, comprise the steps of:Step 1: AFDX networks are divided into different subnets according to priority, network analysis is independently carried out for each subnet, calculates the arrival curve and service curves of each virtual link.Step 2: calculate inside each interchanger due to data delay D caused by queuingi;Step 3: according to data delay DiThe data for calculating each node overstock.Data lower in AFDX networks are obtained by the present invention and overstock the upper bound, more reliable theoretical foundation is provided for Internet resources distribution and bigger configuration data optimizes space, more effectively ensure the certainty of AFDX networks.
Description
Technical field
The present invention relates to AFDX (Avionic Full-Duplex Switched Ethernet) switch network to analyze skill
A kind of overstocked method of data in calculating AFDX networks during art, the more particularly to deterministic parsing of AFDX networks.
Background technology
AFDX applies to the certainty airplane data networking bus system of avionics system information transfer.AFDX is in ether
Certainty timing mechanism and reliable information transmission mechanisms are added on the basis of net to adapt to avionics application, certainty timing mechanism
Realized by the virtual link technology with finite bandwidth and frame transmission interval, reliable information transfer then passes through frame administrative mechanism
Realize, include the redundant transmission and integrity checking of information.Really the state of qualitative representation system is to predict to avionics system
, that is, know the current state of system and the behavior of transition criterion can Estimation System.Certainty is always with safety analysis
Related.For the safety of aircraft, the deterministic each system level required suitable for aircraft.For data communication system,
Data communication must require to ensure certainty by network analysis.
Network calculus are a network certainty queuing theorys, are the theoretical foundation of AFDX network deterministic parsings.AFDX
Network deterministic parsing needs delay, shake and product based on information transfer in network calculus theoretical calculation worst case lower network
Pressure etc..Network calculus were proposed by L.Cruz in 1991, by the development of twenties years, especially Agrawal, Le Boudec
Et al. proposition to service curves, Min-plus algebra and class convolution concept so that it is complete that network calculus have become a basis
It is standby, be widely used, the theory that system is huge.
The basic theories of network calculus is applied to AFDX networks by C.Fraboul and J.Grieu et al. earliest, it is proposed that ratio
More complete model and algorithm.Two parameters of most important of which are exactly that data delay and data overstock.In engineering in practice, net
The maximum data that network allows overstocks to be configured in units of frame number, therefore needs to calculate network transmission process in network analysis
The upper bound of the frame number of each priority backlog inside middle interchanger.Existing mathematical modeling and its algorithm are calculating the overstocked frame of data
The number upper bounds when, in units of byte, and assume the overstocked all frames in data buffer zone for virtual chains all in the priority
The maximum of the maximum frame length (Max Frame Size) on road (VL, Virtual Link).This computational methods are excessively coarse,
Comparison of computational results is pessimistic, often overstocks the upper bound far beyond real data.
The content of the invention
In order to realize the overstocked frame number computational methods of the data of more excellent AFDX network analysis modeling, the invention provides one
Kind calculates the method that data are overstocked in AFDX networks, obtains data lower in AFDX networks and overstocks the upper bound, for Internet resources point
With more reliable theoretical foundation and bigger configuration data optimization space is provided, more effectively ensure the certainty of AFDX networks.
The goal of the invention of the present invention is achieved through the following technical solutions:
The overstocked method of data, is comprised the steps of in a kind of calculating AFDX networks:
Step 1: AFDX networks are divided into different subnets according to priority, network analysis is independently carried out for each subnet,
Calculate arrival curve and service curves of each virtual link in each interchanger internal damping outlet port:
A the arrival curve of network in each subnet) is calculated:
α (t)=σ+ρ t,
Wherein, it is σ burstiness, ρ is transmission rate;
B the service curves of network in each subnet) are calculated:
βR,T(t)=R [t-T]+,
Wherein R is service speed, and T is service delay, symbol [x]+Represent:The value is equal to x if x >=0, otherwise the value
For 0.
Step 2: the data delay upper bound D as caused by calculating due to queuing arrival curve and service curvesi, calculation formula
For:
Di=supt≥0{infτ≥0{α(t)≤β(t+τ)}}
Step 3: do not have to maximum transversal distance in the present invention overstocks the upper bound to calculate data, but it is upper with data delay
Boundary calculates the overstocked frame number upper bound of data.According to data delay upper bound DiThe data for calculating each node overstock the upper bound:
Wherein:TTachnical delayFor the tachnical delay upper bound of each node, general TTachnical delay=50 μ s, TShapingFor from being shaped into from hair
The tachnical delay of dynamic terminal output.
Brief description of the drawings
Fig. 1 is embodiment neutron network topology structure;
Fig. 2 is arrival curve schematic diagram in embodiment;
Fig. 3 is service curves schematic diagram in embodiment;
Fig. 4 is data delay schematic diagram under worst case in embodiment;
Fig. 5 is the schematic flow sheet of the present invention.
Embodiment
In conventional method, it is after arrival curve and service curves is obtained that data delay and data, which overstock, takes transverse direction
The computation of maximal distance data delay upper bound, longitudinal computation of maximal distance data are taken to overstock the upper bound, data delay and data, which overstock, is
Separate parallel computation.Do not have to maximum transversal distance in the present invention and overstock the upper bound to calculate data, but it is upper with data delay
Boundary calculates the overstocked frame number upper bound of data.
Due to the periodicity that data are sent in AFDX networks, within cycle regular hour, sent out from transmission terminal
Frame number is bounded above, and the residence time of the data of the invention according to every VL in a network comes calculating network or some node
Data overstock.
As shown in figure 5, the implementing procedure of the present invention is as follows:
Step 1: arrival curve and service curves are asked after subregion.
Network partition:
It is divided into different subnets according to priority firstly the need of by network, network analysis meter is independently carried out for each subnet
Calculate.I.e. for multipriority AFDX networks, AFDX networks need to be divided into multiple subnets according to priority, each subnet only includes
The VL of same priority.Fig. 1 is the network topology structure figure of certain priority subnet.Wherein i represent network node (interchanger it is each
There is a buffering area individual outlet, and each buffering area is a network node).
For example, having high (H), the VL of low (L) two priority in the AFDX networks of A, B net redundancy, then it can be divided into four
Individual subnet:
N(H,A):Include all high priority VL netted by A;
N(H,B):Include all high priority VL netted by B;
N(L,A):Include all low priority VL netted by A;
N(L,B):Include all low priority VL netted by A;
It is overstocked preceding, it is necessary to first calculate the arrival curve of network, service curves and data in the subnet to calculate data in subnet
Delay.
Arrival curve:
VL is as the basic data transmission channel in AFDX networks, and terminal is by controlling the maximum of data frame in every VL
Frame length SmaxCarry out the transmission of control information with transmission interval BAG, according to the leakage prediction of shaping, can obtain VL arrival curve:
α (t)=σ+ρ t
It is wherein σ burstiness, ρ is transmission rate.Arrival curve schematic diagram is as shown in Figure 2.
Service curves:
One basic service curves model is referred to as rate delay service curves, as follows:
βR,T(t)=R [t-T]+
Wherein R is service speed, and T is service delay, symbol [x]+Represent:The value is equal to x if x >=0, otherwise the value
For 0.
Service curves schematic diagram is as shown in Figure 3.
Step 2: go out the data delay of each virtual link based on network calculus theoretical calculation.
By the way that based on the theoretical network analysis of network calculus, each VL can be calculated inside each interchanger due to row
Data delay caused by team, this parameter is designated as D by wei。
It is assumed that a data stream enters some buffer joint, the arrival curve of the data flow is α (t), service curves β
(t).The then maximum data delay D of the buffer jointi(unit:Ms) the maximum transversal distance between α (t) and β (t), such as Fig. 4
It is shown.Then there is equation below:
Di=supt≥0{infτ≥0{α(t)≤β(t+τ)}}。
Overstock Step 3: calculating data on the basis of data delay.
1st, since every VL be to follow it sending terminal reshaper to send cycle, therefore the timing since the point, false
The fixed tachnical delay that terminal exports from being shaped into from starting is TShaping, then every VLkFrom terminal reshaper is sent to some node
Delay Bound before m transmissionsFor:
Explanation:
(a) since set A is included sending terminal, VLkAll node structures passed through along its sub-path arrival node m
Into set (include node m).
(b) frame of the time more than this time is sent not in node m buffering area.
(c)TTachnical delay=50 μ s, it is the tachnical delay upper bound of each node.
2nd, data frame is periodically sent according to minimum bandwidth interval (BAG) in AFDX networks, then every VLk When
The frame number upper bound of interior transmission is:
And node m data overstock, and belong to VLkThe frame number upper bound, the result can further optimize.
Represented with set B since being sent terminal, VLkThe previous node that node m is reached along its sub-path is passed through
All nodes form set (do not include node m).
Then there is following fundamental formular:
(a) data of m points overstock=set A data are overstocked-set B data overstock;
(b) data of m points overstock the upper bound=set A overstocked upper bound-set B of the data data overstocked next time
And not all data frame all overstocks at node i, in VLkAll nodes on path can all overstock, and count below
Calculate minimum at node before this overstock.
It is assumed that entering ingress NmNode before is not lined up, and only exists tachnical delay.Due to
Total tachnical delay within the time is less than VLkOne transmission the cycle, the minimum frame number that can be overstock be 0.This says
It is brightIn time interval, on the path before node m, lower bound overstocked set B is 0.
Therefore,Just it is node NmOverstocked belongs to VLkFrame the frame number upper bound.
3rd, calculated more than both for a VLkFor, if having by node m VL multiple, then what node m overstock
The upper bound of all frame numbersFor:
Wherein, K is the virtual link VL that node m is passed through in pathkSet
4th, in summary 1,2,3 formula, you can obtain calculating the overstocked computational methods of AFDX network switch data:
It is understood that for those of ordinary skills, can be with technique according to the invention scheme and its hair
Bright design is subject to equivalent substitution or change, and all these changes or replacement should all belong to the guarantor of appended claims of the invention
Protect scope.
Claims (1)
1. the overstocked method of data, is comprised the steps of in a kind of calculating AFDX networks:
Step 1: AFDX networks are divided into different subnets according to priority, network analysis is independently carried out for each subnet, for
Each subnet, the arrival curve and service curves of each virtual link are calculated according to the method for network calculus;
Step 2: and then each virtual link is calculated inside each interchanger due to data delay upper bound D caused by queuingi;
Step 3: according to data delay upper bound DiThe data for calculating each node overstock the upper bound:
Wherein, K is the virtual link VL that node m is passed through in pathkSet;M is a certain node serial number;Set A is from transmission terminal
Start, virtual link VLkThe set for all nodes composition that node m is passed through is reached along sub-path;I is the member in set A
Element;TTachnical delayFor the tachnical delay upper bound of node;TShapingFor the tachnical delay of the output of the terminal from being shaped into from starting;For void
Intend link VLkTransmission interval.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510336533.1A CN105162612B (en) | 2015-06-17 | 2015-06-17 | A kind of overstocked method of data in calculating AFDX networks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510336533.1A CN105162612B (en) | 2015-06-17 | 2015-06-17 | A kind of overstocked method of data in calculating AFDX networks |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105162612A CN105162612A (en) | 2015-12-16 |
CN105162612B true CN105162612B (en) | 2018-01-26 |
Family
ID=54803376
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510336533.1A Active CN105162612B (en) | 2015-06-17 | 2015-06-17 | A kind of overstocked method of data in calculating AFDX networks |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105162612B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108540323B (en) * | 2017-12-29 | 2020-02-21 | 西安电子科技大学 | Method for predicting processing rate of router based on minimum additive deconvolution |
CN112733303B (en) * | 2019-10-11 | 2024-03-12 | 中国科学院沈阳自动化研究所 | Multi-strategy industrial TSN shaper modeling method based on deterministic network algorithm |
CN112821937B (en) * | 2020-12-31 | 2021-12-07 | 广州大学 | Data transmission method through satellite network, satellite network system, apparatus and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101894192A (en) * | 2010-07-19 | 2010-11-24 | 北京航空航天大学 | Simulation and demonstration system for design and validation of AFDX (Avionics Full Duplex Switched Ethernet) network and simulation and demonstration method thereof |
CN102780581A (en) * | 2012-07-20 | 2012-11-14 | 北京航空航天大学 | AFDX (Avionics Full Duplex Switched Ethernet) end-to-end delay bound claculation method based on random network calculus |
CN102970156A (en) * | 2012-10-11 | 2013-03-13 | 上海交通大学 | Optimal modeling method for end-to-end delay in avionics full duplex switched Ethernet (AFDX) data networks |
US8958297B1 (en) * | 2012-06-26 | 2015-02-17 | Rockwell Collins, Inc. | Data network with “per flow” flow monitoring |
-
2015
- 2015-06-17 CN CN201510336533.1A patent/CN105162612B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101894192A (en) * | 2010-07-19 | 2010-11-24 | 北京航空航天大学 | Simulation and demonstration system for design and validation of AFDX (Avionics Full Duplex Switched Ethernet) network and simulation and demonstration method thereof |
US8958297B1 (en) * | 2012-06-26 | 2015-02-17 | Rockwell Collins, Inc. | Data network with “per flow” flow monitoring |
CN102780581A (en) * | 2012-07-20 | 2012-11-14 | 北京航空航天大学 | AFDX (Avionics Full Duplex Switched Ethernet) end-to-end delay bound claculation method based on random network calculus |
CN102970156A (en) * | 2012-10-11 | 2013-03-13 | 上海交通大学 | Optimal modeling method for end-to-end delay in avionics full duplex switched Ethernet (AFDX) data networks |
Non-Patent Citations (2)
Title |
---|
《Worst-case backlog evaluation of Avionics switched Ethernet networks with the Trajectory approach》;Henri Bauer;《IEEE 2012 24th Euromicro Conference on Real-Time Systems》;20120806;全文 * |
《基于AFDX网络演算的性能分析技术研究》;邱征;《电子世界》;20130731;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN105162612A (en) | 2015-12-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bauer et al. | Applying and optimizing trajectory approach for performance evaluation of AFDX avionics network | |
Charara et al. | Methods for bounding end-to-end delays on an AFDX network | |
CN106357537B (en) | A kind of link monitoring method based on SDN multi-path transmission | |
US9363184B2 (en) | Token bucket-based traffic limiting method and apparatus | |
Ray | Performance evaluation of medium access control protocols for distributed digital avionics | |
Li et al. | Improving end-to-end delay upper bounds on an AFDX network by integrating offsets in worst-case analysis | |
CN102780581B (en) | AFDX (Avionics Full Duplex Switched Ethernet) end-to-end delay bound claculation method based on random network calculus | |
Bauer et al. | Worst-case end-to-end delay analysis of an avionics AFDX network | |
CN105162612B (en) | A kind of overstocked method of data in calculating AFDX networks | |
CN104601375A (en) | Intelligent substation communication network monitoring system, setting method and monitoring method | |
CN107070808A (en) | A kind of the worst queueing delay processing method of the pre- constant current of AVB network multiclass based on credit shaping | |
CN107689919A (en) | The dynamic adjustment weight fuzzy routing method of SDN | |
CN102104537A (en) | Time triggered method for fiber channel terminal system | |
CN107682235A (en) | A kind of propagation delay time prediction data dispatching method based on Kalman filtering | |
Li et al. | A SDN-based traffic bandwidth allocation method for time sensitive networking in avionics | |
CN114448899A (en) | Method for balancing network load of data center | |
CN113438182B (en) | Credit-based flow control system and flow control method | |
Finzi et al. | Performance enhancement of extended AFDX via bandwidth reservation for TSN/BLS shapers | |
CN102970156A (en) | Optimal modeling method for end-to-end delay in avionics full duplex switched Ethernet (AFDX) data networks | |
CN105119843A (en) | A method for setting a message buffer queue length | |
Liu et al. | Modeling and simulation of avionics full duplex switched Ethernet (AFDX network) based on OPNET | |
Jiang et al. | Modelling delay propagation within a train communication network | |
Zimmermann et al. | Towards reliability evaluation of AFDX avionic communication systems with rare-event simulation | |
CN106788863A (en) | A kind of aviation electronics WDM network management analogue systems for supporting subnet time triggered to communicate | |
CN110086680A (en) | AFDX network configuration generation method, apparatus and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |