CN108847969A - Network business reliability analysis method based on information flow - Google Patents

Network business reliability analysis method based on information flow Download PDF

Info

Publication number
CN108847969A
CN108847969A CN201810567208.XA CN201810567208A CN108847969A CN 108847969 A CN108847969 A CN 108847969A CN 201810567208 A CN201810567208 A CN 201810567208A CN 108847969 A CN108847969 A CN 108847969A
Authority
CN
China
Prior art keywords
business
node
data packet
queue
loss
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201810567208.XA
Other languages
Chinese (zh)
Other versions
CN108847969B (en
Inventor
黄宁
王春霖
孙利娜
李碧薇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beihang University
Original Assignee
Beihang University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beihang University filed Critical Beihang University
Priority to CN201810567208.XA priority Critical patent/CN108847969B/en
Publication of CN108847969A publication Critical patent/CN108847969A/en
Application granted granted Critical
Publication of CN108847969B publication Critical patent/CN108847969B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/145Network analysis or design involving simulating, designing, planning or modelling of a network

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention discloses a kind of the network business reliability analysis method based on information flow, step 1:According to engineer application and user demand, the weight and failure criterion of each business are determined;Step 2:Modeling and dynamic simulation are carried out to the business of the network operation, including data generate, transmission, are lined up and remove;Step 3:Business Reliability assessment.The invention has the advantages that:(1) the method for the present invention synthetically can carry out fail-safe analysis to the whole multiple services different performance index of net.Modeling and dynamic simulation are carried out based on business of the information flow model to the network operation, the specific performance index value of each business under multi-service operation can be obtained, targeted assessment can be realized according to the specific requirement to service reliability.(2) present invention carries out multi-service Reliability assessment according to each business weight shared in whole network service, and the significance level for embodying different business and user are to the desirability of different business.

Description

Network business reliability analysis method based on information flow
Technical field
The invention belongs to reliability and safety (safety system engineering) technical fields, and in particular to a kind of based on information flow Network business reliability analysis method.
Background technique
Network business reliability refers to that under prescribed conditions and in the stipulated time, the energy of predetermined function is completed to business for network Power.Wherein rated condition refers in the case where component (including hardware and software) can work normally, it is specified that the time refers to net Business in network is within the specified working time, it is specified that function refers to the service quality meet demand of business.Existing business can By property analysis model, difference is primarily directed to different failure criterions, such as the congestion metric of the lagger of business, business Deng.And the multiple business run in network would generally stress different performance requirements, such as mail service can stress packet loss requirement, Video call service can stress delay requirement.Existing service reliability analysis method is difficult to synthetically multiple services not to whole net Fail-safe analysis is carried out with performance indicator.Therefore the present invention proposes a kind of network business reliability analysis side based on information flow Method, particular content are to realize multiple services dynamic simulation based on information flow model, main includes generation, the transmission, row of data flow Team and remove process, thus obtain multi-service operation under each business different performance index value, and then synthetically to network not Service reliability analysis is carried out with performance indicator.Time delay and packet loss are as two performance indicators most important in network, in network It is concerned in fail-safe analysis, therefore the present invention chooses time delay and packet loss and carries out specifically to method proposed by the invention It is bright.Service reliability analysis method proposed by the present invention can synthetically carry out the whole multiple services different performance index of net reliable Property analysis, multiple services dynamic simulation can also be realized based on information flow model according to the specific requirement to service reliability, into And realize targetedly assessment.
Summary of the invention
The network business reliability analysis method based on information flow that the purpose of the present invention is to provide a kind of, it is existing to solve The problem of fail-safe analysis synthetically is carried out to whole net multiple services different performance index is difficult in technology.
The present invention proposes a kind of network business reliability analysis method based on information flow, can be synthetically to the whole more industry of net The different performance index of business carries out fail-safe analysis, such as the time sent from source node according to business data packet and arrival purpose The time calculation delay of node, packet loss number caused by having been expired in business data packet transmission process as buffer area, business datum It wraps with certain probability is transferred to the node of mistake and generates error code at each node, network signal is caused along service path transmission Signal decaying.For the different performance index analyzed, in the service dynamic simulation process realized based on information flow model, The performance data of acquisition is adjusted accordingly, and then carries out fail-safe analysis.The present invention chooses time delay and packet loss to the present invention The method proposed is described in detail, while a kind of method for providing procedure, applies in practice convenient for engineering.
The network business reliability analysis method based on information flow, detailed process are as follows:
Step 1:According to engineer application and user demand, the weight and failure criterion of each business are determined.
To each business i (i=1, L, M), the performance indicator to be investigated is time delay and packet loss.According to practical implementation and Demand of the user to different business determines business i weights omega shared in whole network servicei, for important business, weight is assigned Value is high;Determine that delay threshold is Ti, packet loss threshold value is Ki, M is the total business volume to be assessed.
Step 2:Modeling and dynamic simulation are carried out to the business of the network operation, including data generate, transmission, are lined up and move It removes.It is specific as follows:
(1) data generating procedure:All business in network are generated according to service generation algorithm, the source section including business Point, destination node and service path;
(2) data transmission procedure:All nodes are traversed according to node transfer capability come the data packet of forward node queue, it is right The each data packet transmitted determines next address between the data packet present node and destination node according to routing.Often The processing capacity of a node is Cj, i.e., each moment each node at most handles CjA data packet, according to section next in service path The number of point is forwarded.
(3) data queue process:According to the queue of node store dispatching algorithm, in each time step, each node into Row sends and receives data packet.In each time step, each node will be undergone to be operated twice, sends and receives data packet; Firstly, traversing all queues, if there is data packet in queue, dispatching algorithm is stored the C of queue according to queuejA data packet It forwards, is not operated if without data packet;Secondly by the data packet from other node received according to queue Store dispatching algorithm storage in the queue, the buffer queue size of each node is Qj, i.e., Q can be at most stored in each nodejIt is a Data packet is lined up according to the queue of node storage scheduling rule after reaching node, successively waits and be forwarded processing, if be not free Then node can not receive new data packet to not busy caching, and data packet is dropped at this time.
(4) data remove process:If data packet reaches destination node according to service path, by this data packet from network Otherwise middle removal continues to be forwarded to next node.For reaching the data packet of destination node, when writing down the calculating of its arrival time Prolong, if its time delay is in the transmission time of permission, then it is assumed that the data packet transmission success.
Step 3:Business Reliability assessment.
For the business reliability of single business, i.e., for business i (i=1, L, M), business reliability expression is as follows:
Ri=P (Delayi≤Ti,Lossi≤Ki)
Wherein, to business i, DelayiThe time delay that expression business i operational process generates, LossiFor the number of packet loss.According to Weight shared by each business, multiple services business reliability expression are as follows:
Wherein, ωiFor business i weight shared in whole network service.
Step 3 proposes the calculation method of business reliability, wherein total business volume, business weight and failure criterion according to Step 1 determines that time delay and packet loss value are calculated by step 2.Specifically, the present invention by the dynamic simulation to business come To the performance index value of business, and then the approximation of business reliability is obtained, process is as shown in Figure 1, specific as follows:
(1) determine network topology structure, the total business volume M to be assessed, weight shared by each business, each business when Prolong threshold value and packet loss threshold value, the processing capacity and caching queue size of each node, input emulation total time T;
(2) to each time step, the discrete events simulation of business, the simulation process are carried out according to the Four processes of step 2 It is specific as follows:
(2.1) simulation time t=1 is enabled, successful business sum success=0 is run, business i runs successful number successiThe packet loss number of=0, business i are Lossi=0;
(2.2) M business, the data packet number including each business, the source node of business, destination node and business are generated Path;
(2.3) data packet is added in the queue of source node, the time t of data packet generation is write down, if the queue of node It has been expired that, then by data packet discarding, the packet loss number Loss of corresponding businessi=Lossi+1;
(2.4) dispatching algorithm is stored according to the queue of node, each node is according to its processing capacity and forwards respective numbers Data packet;
(2.5) judge whether the data packet of each business not abandoned reaches destination node, if arrived destination node, Data packet is removed, and records data packet arrival time t to get propagation delay time Delay is arrivedi.If time delay is less than the business Delay threshold and packet loss number be less than the packet loss threshold value of the business, then it is assumed that the business transmission success, correspondingly successi=successi+ 1, success=success+1;Next node is forwarded to if not reaching destination node;
(2.6) judge whether nodal cache queue has expired, storing dispatching algorithm according to the queue of node if less than will be new To queues packets in nodal cache area;By extra data packet discarding if having expired, it is believed that these data packets are not transmitted Success, the packet loss number Loss of corresponding businessi=Lossi+1;
(2.7) simulation time t=t+1;
(2.8) judge whether to meet t≤T, if it is satisfied, then into (2.2);If conditions are not met, then reach emulation duration, Into (3).
(3) business reliability is calculated.In (2), each time step generates M business at random, i.e., each time step is suitable In the random sampling once emulated, time delay and the number of dropped packets of each business are recorded to get into business reliability expression DelayiAnd lossi, and then judge each business whether transmission success.Therefore for the business reliability of business i (i=1, L, M) Calculation formula is:
Wherein, successiSuccessful number, all are run for business iiFor the total number of run of business i.Multiple services industry Business formula of reliability be:
Wherein, ωiFor business i weight shared in whole network service.
The present invention proposes that a kind of network business reliability analysis method based on information flow, advantage are:
(1) the network business reliability analysis method provided by the invention based on information flow, can be synthetically more to whole net The different performance index of business carries out fail-safe analysis.Modeling and dynamic are carried out based on business of the information flow model to the network operation Emulation can obtain the specific performance index value of each business under multi-service operation, can be according to the specific of service reliability It is required that realize targeted assessment.
(2) present invention carries out multi-service Reliability assessment, body according to each business weight shared in whole network service The significance level for having showed different business and user are to the desirability of different business.
Detailed description of the invention
Fig. 1 is the method for the present invention business Reliability assessment flow chart.
Fig. 2 is network topology structure figure.
Fig. 3 is multi-service reliability curves figure.
Fig. 4 is single business reliability curves figure.
Specific embodiment
The present invention is described in further details below in conjunction with attached drawing and example.
The present invention is a kind of network business reliability analysis method based on information flow, can be synthetically to whole net multi-service Different performance index carry out fail-safe analysis.The present invention chooses time delay and packet loss and carries out in detail to method proposed by the invention Explanation, the following are network business reliabilities to analyze case, and specific step is as follows:
Step 1:According to engineer application and user demand, the weight and failure criterion of each business are determined.
To each business i (i=1, L, M), the performance indicator to be investigated is time delay and packet loss, in the present embodiment, is taken each Weight shared by business is all 1, i.e. ωi=1;The delay threshold for taking all business is Ti=10, packet loss threshold value is Ki=0;Respectively Taking total business volume is that M=100,200, L, 1500 carry out business reliability analysis.
Step 2:Modeling and dynamic simulation are carried out to the business of the network operation, including data generate, transmission, are lined up and move It removes.It is specific as follows:
(1) data generating procedure:All business in network are generated according to service generation algorithm, the source section including business Point, destination node and service path.In the present embodiment, network service includes three classes, i.e. stochastic pattern business, Custom Prosthesis business and journey Sequence business, the ratio of three classes business are 3:3:4, definition and generating mode are as follows:
1. stochastic pattern business:According to certain routing algorithm, the business road between source node and destination node is randomly choosed Diameter sends data.In the present embodiment, the generating mode to stochastic pattern business is:Business road between source node O to destination node D Diameter is generated according to shortest path, when there are a plurality of shortest path, randomly chooses one as service path.
2. Custom Prosthesis business:It provides that certain node is the node that must be accessed, while selecting industry according to certain routing algorithm Business path.In the present embodiment, the generating mode to Custom Prosthesis business is:Since the distribution of nodes degree determines to a certain extent The maximum node of nodes degree is set to Dominator S by the significance level of network node, the present embodiment, then Custom Prosthesis industry The service path of business can be segmented the sum of the shortest path of the shortest path Yu S to D of regarding O to S as.
3. sequencing business:Provide that certain link is the link having to pass through in operation flow, while according to certain routing Algorithms selection service path.In the present embodiment, the generating mode to sequencing business is:By second largest section of nodes degree The link of point node composition adjacent thereto is set to necessary link:P1→P2, then the service path of sequencing business can divide Section regards source node O to P as1Shortest path, necessary link:P1→P2And P2To the sum of the shortest path of destination node D.
In addition, present embodiment assumes that each business generates a data packet in each time step.
(2) data transmission procedure:All nodes are traversed according to node transfer capability come the data packet of forward node queue, it is right The each data packet transmitted determines next address between the data packet present node and destination node according to routing.This In embodiment, the processing capacity of each node is
CjFor the processing capacity of node j, BEjFor the betweenness of node j, C is throughput, and N is number of network node, this example Middle C=10000, N=38.Then each node of each moment at most handles CjA data packet, according to next node in service path Number be forwarded.
(3) data queue process:According to the queue of node store dispatching algorithm, in each time step, each node into Row sends and receives data packet.In the present embodiment, it is assumed that the queue storage dispatching algorithm of node is first in first out (first- In-first-out, FIFO) strategy.In each time step, each node will be undergone to be operated twice, sends and receives data Packet;Firstly, all queues are traversed, if there is data packet in queue, the C of queue frontjA data packet forwards, if There is no data packet not operate then;Secondly the data packet from other node received is stored in the tail of the queue of queue, each The buffer queue size of node is
Wherein, QjFor the buffer queue size of node j, BEjFor the betweenness of node j, Q is total queue resource, and N is network section It counts, in this example, Q=10000, N=38.Then Q can be at most stored in each nodejA data packet, after data packet reaches node It is lined up using the queue discipline of first in first out, successively waits and be forwarded processing, node can not connect if not idle caching By new data packet, data packet is dropped at this time.
(4) data remove process:If data packet reaches destination node according to service path, by this data packet from network Otherwise middle removal continues to be forwarded to next node.For reaching the data packet of destination node, when writing down the calculating of its arrival time Prolong, if its time delay is in the transmission time of permission, then it is assumed that the data packet transmission success.
Step 3:Business Reliability assessment.
For the business reliability of single business, i.e., for business i (i=1, L, M), business reliability expression is as follows:
Ri=P (Delayi≤Ti,Lossi≤Ki)
Wherein, to business i, DelayiThe time delay that expression business i operational process generates, LossiFor the number of packet loss.This reality It applies in example, weight shared by each business is 1, then multiple services business reliability expression is as follows:
The present invention obtains the performance index value of business by the dynamic simulation to business, and then obtains business reliability Approximation, process is as shown in Figure 1, specific as follows:
(1) network topology structure (the present embodiment is network topology as shown in Figure 2), the total business volume to be assessed point are determined Not Wei M=100,200, L, 1500, the delay thresholds of all business is Ti=10, packet loss threshold value is Ki=0, weight ωi=1; The processing capacity C of each nodejWith caching queue size QjAs described in step 2, total time T=100 is emulated;
(2) to each time step, the discrete events simulation of business, the simulation process are carried out according to the Four processes of step 2 It is specific as follows:
(2.1) simulation time t=1 is enabled, successful business sum success=0 is run, business i runs successful number successiThe packet loss number of=0, business i are Lossi=0;
(2.2) M business, the source node including business, destination node and service path, stochastic pattern business, customization are generated The ratio of type business and sequencing business three classes business is 3:3:4.Each business is raw in each time step in the present embodiment At a data packet, then data packet whether transmission success represent a corresponding business whether transmission success;
(2.3) data packet is added in the queue of source node, the time t of data packet generation is write down, if the queue of node It has been expired that, then by data packet discarding, the packet loss number Loss of corresponding businessi=Lossi+ 1 namely the non-transmission success of the business;
(2.4) dispatching algorithm is stored according to the queue of node, each node is according to its processing capacity and forwards respective numbers Data packet;
(2.5) judge whether data packet reaches destination node, if arrived destination node, data packet is removed, and remembers T of lower data packet arrival time is recorded to get propagation delay time Delay is arrivedi.If time delay is less than the delay threshold of the business, then it is assumed that The business transmission success, correspondingly successi=successi+ 1, success=success+1;If not reaching destination node Then it is forwarded to next node;
(2.6) judge whether nodal cache queue has expired, storing dispatching algorithm according to the queue of node if less than will be new To queues packets in nodal cache area;By extra data packet discarding if having expired, it is believed that these data packets are not transmitted Success, the packet loss number Loss of corresponding businessi=Lossi+ 1 namely the non-transmission success of the business;
(2.7) simulation time t=t+1;
(2.8) judge whether to meet t≤100, if it is satisfied, then into (2.2);If conditions are not met, when then reaching emulation It is long, into (3);
(3) business reliability is calculated.In (2), each time step generates M business at random, i.e., each time step is suitable In the random sampling once emulated, time delay and the number of dropped packets of each business are recorded to get into business reliability expression DelayiAnd lossi, and then judge each business whether transmission success.Therefore for the business reliability of business i (i=1, L, M) Calculation formula is:
Wherein, successiSuccessful number, all are run for business iiFor the total number of run of business i.In the present embodiment, Since each business generates a data packet, then all in each time stepiNamely for the total data of business i transmission Packet number, successiNamely it is directed to the data packet number of business i transmission success.Multiple services business formula of reliability For:
Wherein, success is that successful business number is run in network, and all is the business sum run in network.This reality It applies in example, success is the data packet number of transmission success in network, and all is the total data packet number of transmission.
It is hereby achieved that multi-service reliability (as shown in Figure 3) and single business reliability under different business total amount (the business reliability for being illustrated in figure 4 each business when total business volume is 900).

Claims (2)

1. a kind of network business reliability analysis method based on information flow, it is characterised in that:This method process is as follows:
Step 1:According to engineer application and user demand, the weight and failure criterion of each business are determined;
To each business i (i=1, L, M), the performance indicator to be investigated is time delay and packet loss;According to practical implementation and user Demand to different business determines business i weights omega shared in whole network servicei, for important business, weight assignment It is high;Determine that delay threshold is Ti, packet loss threshold value is Ki, M is the total business volume to be assessed;
Step 2:Modeling and dynamic simulation are carried out to the business of the network operation, including data generate, transmission, are lined up and remove;Tool Body is as follows:
(1) data generating procedure:All business in network, the source node including business, mesh are generated according to service generation algorithm Node and service path;
(2) data transmission procedure:All nodes are traversed according to node transfer capability come the data packet of forward node queue, to being passed Defeated each data packet determines next address between the data packet present node and destination node according to routing;Each section The processing capacity of point is Cj, i.e., each moment each node at most handles CjA data packet, according to next node in service path Number is forwarded;
(3) data queue process:Dispatching algorithm is stored according to the queue of node, in each time step, each node is sent out It send and received data packet;In each time step, each node will be undergone to be operated twice, sends and receives data packet;Firstly, All queues are traversed, if there is data packet in queue, dispatching algorithm is stored the C of queue according to queuejA data packet forwarding It goes out, is not operated if without data packet;Secondly the data packet from other node received is stored according to queue Dispatching algorithm stores in the queue, and the buffer queue size of each node is Qj, i.e., Q can be at most stored in each nodejA data Packet is lined up according to the queue of node storage scheduling rule after reaching node, successively waits and be forwarded processing, if not idle Then node can not receive new data packet to caching, and data packet is dropped at this time;
(4) data remove process:If data packet reaches destination node according to service path, this data packet is moved from network It removes, otherwise, continues to be forwarded to next node;For the data packet of arrival destination node, its arrival time calculation delay is write down, if Its time delay is in the transmission time of permission, then it is assumed that the data packet transmission success;
Step 3:Business Reliability assessment;
For the business reliability of single business, i.e., for business i (i=1, L, M), business reliability expression is as follows:
Ri=P (Delayi≤Ti,Lossi≤Ki)
Wherein, to business i, DelayiThe time delay that expression business i operational process generates, LossiFor the number of packet loss;According to each Weight shared by business, multiple services business reliability expression are as follows:
Wherein, ωiFor business i weight shared in whole network service.
2. the network business reliability analysis method according to claim 1 based on information flow, it is characterised in that:The step Rapid three obtain the performance index value of business by the dynamic simulation to business, and then obtain the approximation of business reliability, tool Body is as follows:
(1) network topology structure is determined, the total business volume M to be assessed, weight shared by each business, the time delay threshold of each business Value and packet loss threshold value, the processing capacity and caching queue size of each node, input emulation total time T;
(2) to each time step, the discrete events simulation of business is carried out according to the Four processes of step 2, the simulation process is specific It is as follows:
(2.1) simulation time t=1 is enabled, successful business sum success=0 is run, business i runs successful number successiThe packet loss number of=0, business i are Lossi=0;
(2.2) M business, the data packet number including each business, the source node of business, destination node and business road are generated Diameter;
(2.3) data packet is added in the queue of source node, writes down the time t of data packet generation, if the queue of node has been expired, Then by data packet discarding, the packet loss number Loss of corresponding businessi=Lossi+1;
(2.4) dispatching algorithm is stored according to the queue of node, each node is according to its processing capacity and the data for forwarding respective numbers Packet;
(2.5) judge whether the data packet of each business not abandoned reaches destination node, if arrived destination node, will count It is removed according to packet, and records data packet arrival time t to get propagation delay time Delay is arrivedi;If time delay be less than the business when Prolong threshold value and packet loss number is less than the packet loss threshold value of the business, then it is assumed that the business transmission success, correspondingly successi= successi+ 1, success=success+1;Next node is forwarded to if not reaching destination node;
(2.6) judge whether nodal cache queue has expired, storing dispatching algorithm according to the queue of node if less than will newly arrive Queues packets are in nodal cache area;By extra data packet discarding if having expired, it is believed that the non-transmission success of these data packets, The packet loss number Loss of corresponding businessi=Lossi+1;
(2.7) simulation time t=t+1;
(2.8) judge whether to meet t≤T, if it is satisfied, then into (2.2);If conditions are not met, then reaching emulation duration, enter (3);
(3) business reliability is calculated;In (2), each time step generates M business at random, i.e., each time step is equivalent to one The random sampling of secondary emulation records time delay and the number of dropped packets of each business to get to the Delay in business reliability expressioni And lossi, and then judge each business whether transmission success;Therefore for the business reliability calculating of business i (i=1, L, M) Formula is:
Wherein, successiSuccessful number, all are run for business iiFor the total number of run of business i;Multiple services business can It is by degree calculation formula:
Wherein, ωiFor business i weight shared in whole network service.
CN201810567208.XA 2018-06-05 2018-06-05 Network service reliability analysis method based on information flow Active CN108847969B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810567208.XA CN108847969B (en) 2018-06-05 2018-06-05 Network service reliability analysis method based on information flow

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810567208.XA CN108847969B (en) 2018-06-05 2018-06-05 Network service reliability analysis method based on information flow

Publications (2)

Publication Number Publication Date
CN108847969A true CN108847969A (en) 2018-11-20
CN108847969B CN108847969B (en) 2020-08-04

Family

ID=64211420

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810567208.XA Active CN108847969B (en) 2018-06-05 2018-06-05 Network service reliability analysis method based on information flow

Country Status (1)

Country Link
CN (1) CN108847969B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109726092A (en) * 2018-12-29 2019-05-07 深圳市联影医疗数据服务有限公司 Bus treatment effeciency appraisal procedure, system and computer storage medium
CN110474806A (en) * 2019-08-19 2019-11-19 国网甘肃省电力公司经济技术研究院 A kind of power telecom network key node recognition methods
CN113759728A (en) * 2021-09-30 2021-12-07 中国船舶重工集团公司第七一九研究所 Modeling method for digital network control system
CN114268985A (en) * 2021-11-26 2022-04-01 中国联合网络通信集团有限公司 Quality evaluation method and device for 5G private network, electronic equipment and storage medium
CN115189908A (en) * 2022-05-24 2022-10-14 安世亚太科技股份有限公司 Random attack survivability evaluation method based on network digital twin
CN115190027A (en) * 2022-05-24 2022-10-14 安世亚太科技股份有限公司 Natural fault survivability evaluation method based on network digital twin body
CN117176618A (en) * 2023-11-03 2023-12-05 中国西安卫星测控中心 Performance evaluation method for network data exchange software system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101741641A (en) * 2009-11-30 2010-06-16 北京航空航天大学 Method for reliability test of communication network services based on link circuits
GB2477515A (en) * 2010-02-03 2011-08-10 Orbital Multi Media Holdings Corp Controlling transmission rate dependent upon block ack/nak bitmask signals and receiver buffer fill levels

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101741641A (en) * 2009-11-30 2010-06-16 北京航空航天大学 Method for reliability test of communication network services based on link circuits
GB2477515A (en) * 2010-02-03 2011-08-10 Orbital Multi Media Holdings Corp Controlling transmission rate dependent upon block ack/nak bitmask signals and receiver buffer fill levels

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
薛鹏: "基于网络链路性能测量的网络可靠性分析系统的设计与实现", 《工程硕士学位论文》 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109726092B (en) * 2018-12-29 2022-06-07 深圳市联影医疗数据服务有限公司 Bus processing efficiency evaluation method, system and computer storage medium
CN109726092A (en) * 2018-12-29 2019-05-07 深圳市联影医疗数据服务有限公司 Bus treatment effeciency appraisal procedure, system and computer storage medium
CN110474806A (en) * 2019-08-19 2019-11-19 国网甘肃省电力公司经济技术研究院 A kind of power telecom network key node recognition methods
CN110474806B (en) * 2019-08-19 2022-04-01 国网甘肃省电力公司经济技术研究院 Power communication network key node identification method
CN113759728B (en) * 2021-09-30 2023-08-25 中国船舶重工集团公司第七一九研究所 Modeling method for digital network control system
CN113759728A (en) * 2021-09-30 2021-12-07 中国船舶重工集团公司第七一九研究所 Modeling method for digital network control system
CN114268985A (en) * 2021-11-26 2022-04-01 中国联合网络通信集团有限公司 Quality evaluation method and device for 5G private network, electronic equipment and storage medium
CN114268985B (en) * 2021-11-26 2024-02-13 中国联合网络通信集团有限公司 Quality evaluation method and device for 5G private network, electronic equipment and storage medium
CN115189908A (en) * 2022-05-24 2022-10-14 安世亚太科技股份有限公司 Random attack survivability evaluation method based on network digital twin
CN115190027B (en) * 2022-05-24 2024-01-23 安世亚太科技股份有限公司 Natural fault survivability evaluation method based on network digital twin
CN115190027A (en) * 2022-05-24 2022-10-14 安世亚太科技股份有限公司 Natural fault survivability evaluation method based on network digital twin body
CN115189908B (en) * 2022-05-24 2024-05-14 安世亚太科技股份有限公司 Random attack survivability evaluation method based on network digital twin
CN117176618A (en) * 2023-11-03 2023-12-05 中国西安卫星测控中心 Performance evaluation method for network data exchange software system
CN117176618B (en) * 2023-11-03 2024-01-09 中国西安卫星测控中心 Performance evaluation method for network data exchange software system

Also Published As

Publication number Publication date
CN108847969B (en) 2020-08-04

Similar Documents

Publication Publication Date Title
CN108847969A (en) Network business reliability analysis method based on information flow
CN103348640B (en) Relay
Frank et al. Topological considerations in the design of the ARPA computer network
US9172656B2 (en) Method and device for managing priority during the transmission of a message
Javani et al. Age of information in multiple sensing
US20130070584A1 (en) Network impairment unit for concurrent delay and packet queue impairments
CN106936645B (en) The optimization method of tree network topology structure based on queueing theory
US20090257441A1 (en) Packet forwarding apparatus and method for discarding packets
Guan et al. An analytical model for wormhole routing in multicomputer interconnection networks
Fraire et al. Leveraging routing performance and congestion avoidance in predictable delay tolerant networks
Grunwald et al. Networks for parallel processors: Measurements and prognostications
CN114448899A (en) Method for balancing network load of data center
CN116232984B (en) Routing method and system aiming at minimizing network end-to-end delay
CN107682235A (en) A kind of propagation delay time prediction data dispatching method based on Kalman filtering
CN107733812A (en) A kind of data packet dispatching method, device and equipment
JP4648290B2 (en) Packet transfer apparatus, packet distribution method, group affiliation processor change method, and computer program
Alsebae et al. Performance of a network coding queuing model with deterministic service
Duato Improving the efficiency of virtual channels with time-dependent selection functions
Lin et al. Modeling ATM traffic using stochastic Petri net
CN115062771B (en) Distributed machine learning gradient convergence method and device and model training method
Bahn et al. Design of simulation and analytical models for a 2D-meshed asymmetric adaptive router
CN117135107B (en) Network communication topology system, routing method, device and medium
US20100195510A1 (en) Method for the Digital Evaluation of a Data Transmission Network
Razouqi et al. Performance analysis of fuzzy thresholding-based buffer management for a large-scale cell-switching network
KR101046597B1 (en) Data processing method, data transceiver and computer readable recording medium in network environment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant