CN111711961B - Service end-to-end performance analysis method introducing random probability parameters - Google Patents

Service end-to-end performance analysis method introducing random probability parameters Download PDF

Info

Publication number
CN111711961B
CN111711961B CN202010360719.1A CN202010360719A CN111711961B CN 111711961 B CN111711961 B CN 111711961B CN 202010360719 A CN202010360719 A CN 202010360719A CN 111711961 B CN111711961 B CN 111711961B
Authority
CN
China
Prior art keywords
service
priority
node
services
video
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
Application number
CN202010360719.1A
Other languages
Chinese (zh)
Other versions
CN111711961A (en
Inventor
朱晓荣
施金豆
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.)
Nanjing University of Posts and Telecommunications
Original Assignee
Nanjing University of Posts and Telecommunications
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 Nanjing University of Posts and Telecommunications filed Critical Nanjing University of Posts and Telecommunications
Priority to CN202010360719.1A priority Critical patent/CN111711961B/en
Publication of CN111711961A publication Critical patent/CN111711961A/en
Application granted granted Critical
Publication of CN111711961B publication Critical patent/CN111711961B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Abstract

The patent discloses a service end-to-end performance analysis method introducing random probability parameters, which introduces random probability parameters according to the characteristic that a wireless network introduces a software defined network and the selection of the route has randomness; adopting a preemptive priority scheduling method to divide the service priority in the network into a high priority, a medium priority and a low priority; by utilizing a stochastic network operation method based on a moment mother function, according to the Cherenov inequality, a series theorem, a residual service theorem, a convolution and a theorem in the stochastic network operation are respectively obtained to obtain a closed expression of the relationship between the time delay and backlog upper bound boundary and the default probability when three priority services are used as research objects.

Description

Service end-to-end performance analysis method introducing random probability parameter
Technical Field
The invention relates to the technical field of communication networks, in particular to a service end-to-end performance analysis method introducing random probability parameters.
Background
In a wireless network, if the gateway service near a user is saturated and cannot meet the user requirement, a task is forwarded to other gateways with service capability for task processing, or when the user near the gateway and the users of other gateways share data and interact information, multi-hop implementation is required. In a wireless network, a control plane and a data plane of the network are separated by a software defined network technology, various resources such as calculation, transmission and storage in the network are integrated, centralized management and distribution are carried out, and the forwarding of network flow is flexibly controlled. The routing of the wireless network introduced into the software defined network has randomness, wiMAX is adopted in the network architecture, different types of QoS have different priorities, and the different types of QoS are suitable for the characteristics of different services, and the services are divided into high priorities, such as network voice telephone services; medium priority, such as video traffic, and low priority, such as file transfer traffic.
The random network operation method is used as a tool for analyzing problems, has the advantage of converting complex nonlinear problems into linear problems convenient to analyze, is only suitable for certain specific distribution compared with a queuing theory, has no limitation on arrival distribution of service data by random network operation, and can be applied to analysis of various scenes. For example, the analysis of time delay, backlog and throughput of a wireless sensor network, the multi-hop performance analysis of a narrowband internet of things, the performance analysis in a network function virtualization network, the performance analysis of video services and the like are all researched based on random network calculus. Random network calculus has its own disadvantages, because scaling may result in too loose a default probability boundary, and some researches have proposed related methods for improvement aiming at its defects.
The invention provides a service end-to-end performance analysis method introducing random probability parameters, which is used for analyzing the service performance in a wireless network multi-hop scene.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the problem of end-to-end performance analysis of the upper-layer service of the wireless network gateway, the invention solves the problem of end-to-end performance analysis of the wireless network service by introducing random probability parameters.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the technical scheme that:
a service end-to-end performance analysis method introducing random probability parameters comprises the following steps:
s1, introducing a random probability parameter to indicate that a wireless network adopts software to define a network planning route so that the route selection has randomness;
s2, in a wireless network with random probability parameters, dividing services into high-priority services, medium-priority services and low-priority services according to different types of QoS in WiMAX and different priorities; the high priority service comprises a network voice telephone service, the medium priority service comprises a video service, and the low priority service comprises a file transmission service;
s3, analyzing the wireless network with random probability parameters introduced by a random network operation method based on a intalox function to obtain intalox function forms of the three priority services in the arrival process, and respectively obtaining intalox function forms of service curves of the three priority services according to a residual service theorem;
and S4, obtaining a closed expression of the relation between the time delay and the backlog upper bound boundary and the default probability according to the convolution and deconvolution theorem.
Further, the specific steps of introducing the random probability parameter in step S1 are as follows:
for the service [.]Is provided withThree probability parameters, constituting a set of probability parameters (P) [.].a ,P [.].b ,P [.].c ) (ii) a Wherein P is [.].a Express service [.]Probability of reaching an agent on a given service chain and needing processing or forwarding; p [.].b Is shown at P [.].a Service under conditions.]The same probability as the path of the next hop of the study on the service chain; p [.].c Is shown at P [.].b On condition, the probability that an agent is required to process or forward after coming to the next agent node of the service chain.
Further, the form of the intalox function of the arrival process of the three priority services in step S3 is as follows:
(1) The arrival process of the high-priority network voice telephone service obeys Poisson distribution, so the moment mother function form of the accumulated arrival data volume in the time interval (s, t) is as follows:
Figure BDA0002474909440000021
wherein A is VoIP (s, t) represents the accumulated data volume of the network voice telephone service in (s, t) of the non-local service chain nodes adjacent to each intelligent agent node on the service chain;
(2) The arrival rate of the medium priority video service is a constant r, and the moment mother function form of the accumulated arrival data volume in the time interval is as follows:
Figure BDA0002474909440000022
wherein A is Video (s, t) represents the video traffic accumulated data volume in (s, t) of non-local service chain nodes adjacent to each agent node on the service chain;
(3) The arrival process of the low-priority file transmission service obeys Poisson distribution, and the moment mother function form of the accumulated arrival data volume in the time interval (s, t) is as follows:
Figure BDA0002474909440000031
wherein A is FTP And (s, t) represents the accumulated arriving data volume of the file transmission service in (s, t) of the service chain nodes which are not adjacent to each agent node on the service chain.
Further, the specific step of obtaining the intalox forms of the three priority service curves in step S3 includes:
the method comprises the following steps that when three types of priority services are acquired as research objects penetrating through a service chain, interference from other services is received, and the method comprises the following steps:
(1) High priority voice over internet service: the priority is highest and is not interfered by other services;
(2) Medium priority video services: the received service is interfered by network voice telephone service, and at each node of a service chain, the interference is as follows:
Figure BDA0002474909440000032
wherein
Figure BDA0002474909440000033
Representing the amount of data occupied at each node during the time interval (s, t) when voice over internet telephony service is acting as an interfering service,
Figure BDA0002474909440000034
represents the data quantity of the network voice telephone service in the time interval (s, t) as interference service from the non-local service chain to each node of the local service chain,
Figure BDA0002474909440000035
representing the amount of data arriving at node j from node j-1 for network voice telephony traffic on the service link during the time interval (s, t), the specific expression is as follows:
Figure BDA0002474909440000036
Figure BDA0002474909440000037
(3) Low priority file transfer service: the service receiving is interfered by network voice telephone service and video service; wherein the interference of the network voice telephone service is as shown in the derivation of (2):
Figure BDA0002474909440000038
the video traffic interference is as follows:
Figure BDA0002474909440000041
wherein
Figure BDA0002474909440000042
Representing the amount of data occupied at each node of the service chain during the time interval (s, t) when video traffic is acting as interference traffic,
Figure BDA0002474909440000043
representing the data quantity of video traffic arriving at each node of the service chain from non-local service chain as interference traffic in a time interval (s, t),
Figure BDA0002474909440000044
the data amount of the video service arriving at the node j from the node j-1 on the service chain in the time interval (s, t) is represented by the following specific expression:
Figure BDA0002474909440000045
Figure BDA0002474909440000046
to sum up, the amount of interference suffered by the low-priority file transmission service is as follows:
Figure BDA0002474909440000047
deducing a service curve when each priority service is used as a research object penetrating a service chain;
(1) High priority voice over internet service: when the flow is through, the flow is not interfered by other types of services, and the service curve is as follows:
Figure BDA0002474909440000048
(2) Medium priority video services: as a through stream, is subject to interference from voice over internet telephony services. By the remaining service theorem, the service curve is:
Figure BDA0002474909440000049
(3) Low priority file transfer service: when the service is a through flow, the service is interfered by network voice telephone service and video service, and the service curve is as follows through the rest service theorem:
Figure BDA00024749094400000410
the service received by the wireless network service is divided into two types, including data processing service provided by an intelligent agent node and data transmission service provided by a wireless channel, and the two types of service nodes are distributed at intervals; the intelligent agent node provides data processing service, the data transmission service selects a Nakagami-M channel to provide a channel, and a moment mother function form of a service curve is solved:
(1) The service rate of the agent node is constant C, so the intalox function form of the agent service node in (s, t) is:
Figure BDA0002474909440000051
(2) The moment mother function form of the Nakagami-M channel node service curve is as follows:
Figure BDA0002474909440000052
wherein
Figure BDA0002474909440000053
B denotes the bandwidth of the channel, M is a Nakagami parameter, γ denotes the signal-to-noise ratio, l denotes the distance of the neighboring agent, α denotes the path fading factor,
Figure BDA0002474909440000054
(3) Combining (1) and (2), and obtaining a general formula of a moment mother function of a node service curve of the service chain, wherein the general formula is as follows:
Figure BDA0002474909440000055
(4) Thereby obtaining the service curve intalox forms of three services:
(a) High priority voice over internet service:
Figure BDA0002474909440000056
(b) Medium priority video services:
Figure BDA0002474909440000057
(c) Low priority file transfer service:
Figure BDA0002474909440000058
further, the step of obtaining the closed expression of the relationship between the time delay and the backlog upper bound and the default probability in step S4 is specifically as follows:
s4.1, deducing a general closed expression between the time delay upper bound boundary and the default probability:
Figure BDA0002474909440000059
where N represents the number of nodes on the service chain,
Figure BDA00024749094400000510
D [.] (t) represents traffic [.]Time delay at time t;
s4.2, deducing each priority service as a closed expression of the relationship between the upper bound of the time delay boundary and the default probability when the traffic passes through the flow:
(1) High-priority network voice call service:
Figure BDA0002474909440000061
wherein
Figure BDA0002474909440000062
(2) Medium priority video services:
Figure BDA0002474909440000063
wherein
Figure BDA0002474909440000064
y VoIP (j) The probability of the network voice telephone service occupying the service volume on each node is represented as follows:
Figure BDA0002474909440000065
(3) Low priority file transfer service:
Figure BDA0002474909440000066
wherein
Figure BDA0002474909440000067
y Video (j) The probability of the video traffic occupying the service volume on each node is expressed as follows:
Figure BDA0002474909440000068
s4.3, deducing a general closed expression between the backlog upper bound boundary and the default probability:
Figure BDA0002474909440000069
wherein B is [.] (t) represents traffic [.]Backlog at time t;
s4.4, deducing each priority service as a closed expression of the relationship between the upper bound of the time delay boundary and the default probability when the traffic passes through the flow:
(1) High priority voice over internet service:
Figure BDA0002474909440000071
(2) Medium priority video services:
Figure BDA0002474909440000072
(3) Low priority file transfer service:
Figure BDA0002474909440000073
has the advantages that:
the random probability parameter is introduced to analyze the end-to-end performance of the wireless network service, because the wireless network introduces software to define the network planning route, the route selection of the service has randomness, the performance analysis method of the invention considers the influence factors more comprehensively, and the analysis result is more in line with the characteristics of the wireless network.
Drawings
Fig. 1 is a schematic diagram of an upper-layer multi-hop structure of a wireless network gateway provided by the present invention;
FIG. 2 is a diagram of a mathematical model provided by the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings.
The present invention takes the upper multi-hop diagram of the wireless gateway shown in fig. 1 as an example. In this scenario, the service volume of the gateway near the user is saturated, and the user task needs to be transmitted to a distant idle gateway for task processing, or the user near the gateway and the distant gateway user need to perform information interaction and sharing, and need to perform multi-hop. In a multi-hop scene, a software-defined network is introduced, a plurality of paths exist between source and destination hosts, such as a flow path a and a flow path b on the graph, the source and destination pairs are the same, but the paths are completely different, and the routing selection has randomness, so that a random probability parameter (P) is introduced in the invention [.].a ,P [.].b ,P [.].c ) To express the randomness, abstracting the channel between the agent and the agent on the path to be a service node, selecting a path as a service chain, using the through flow on the service chain as a research object, and obtaining a mathematical model diagram as shown in fig. 2, where the three services are all the interfering flows on the service chain.
Specifically, for traffic [.]Setting three probability parameters to form a probability parameter set (P) [.].a ,P [.].b ,P [.].c ) (ii) a Wherein P is [.].a Express service [.]Probability of reaching an agent on a given service chain and needing processing or forwarding; p [.].b Is shown at P [.].a Service under conditions.]The probability of being the same as the path of the next hop of the study on the service chain; p [.].c Is shown at P [.].b On condition, the probability that an agent is required to process or forward after coming to the next agent node of the service chain.
In a wireless network introducing random probability parameters, dividing services into high-priority services, medium-priority services and low-priority services according to different types of QoS in WiMAX with different priorities; the high priority service comprises a network voice telephone service, the medium priority service comprises a video service, and the low priority service comprises a file transfer service. Determining that preemptive priority scheduling is adopted among different services, and first-come first-serve scheduling is adopted among the same services; and determining the end-to-end time delay and backlog performance of the analysis service.
And analyzing the wireless network introduced with the random probability parameters by a random network operation method based on a intalox function to obtain intalox function forms of the three priority services in the arrival process, and respectively obtaining intalox function forms of service curves of the three priority services according to a residual service theorem.
Specifically, the intalox forms of the arrival processes of the three priority services are as follows:
(1) The arrival process of the high-priority network voice telephone service obeys Poisson distribution, so the moment mother function form of the accumulated arrival data volume in the time interval (s, t) is as follows:
Figure BDA0002474909440000081
wherein A is VoIP (s, t) represents the accumulated data volume of the network voice telephone service in (s, t) of the non-local service chain nodes adjacent to each intelligent agent node on the service chain;
(2) The arrival rate of the medium priority video service is constant r, and the moment mother function form of the accumulated arrival data volume in the time interval is as follows:
Figure BDA0002474909440000082
wherein A is Video (s, t) represents the video traffic accumulated data volume in (s, t) of non-local service chain nodes adjacent to each agent node on the service chain;
(3) The arrival process of the low-priority file transmission service obeys Poisson distribution, and the moment mother function form of the accumulated arrival data volume in the time interval (s, t) is as follows:
Figure BDA0002474909440000091
wherein A is FTP And (s, t) represents the accumulated arriving data volume of the file transmission service in (s, t) of the service chain nodes which are not adjacent to each agent node on the service chain.
The concrete steps of obtaining the intalox form of the service curves of the three priorities comprise:
the method comprises the following steps that when three types of priority services are acquired as research objects penetrating through a service chain, interference from other services is received, and the method comprises the following steps:
(1) High priority voice over internet service: the priority is highest and is not interfered by other services;
(2) Medium priority video services: the received service is interfered by the network voice telephone service, and at each node of the service chain, the interference is as follows:
Figure BDA0002474909440000092
wherein
Figure BDA0002474909440000093
Representing the amount of data occupied at each node during the time interval (s, t) when voice over internet telephony service is acting as an interfering service,
Figure BDA0002474909440000094
representing the data volume of the network voice telephone service as interference service from the non-local service chain to each node of the local service chain in the time interval (s, t),
Figure BDA0002474909440000095
indicating that the network voice telephone traffic is linked from node j-1 to node t during the time interval (s, t)The data amount of the destination node j is shown as follows:
Figure BDA0002474909440000096
Figure BDA0002474909440000097
(3) Low priority file transfer service: the service receiving is interfered by network voice telephone service and video service; wherein the interference of the network voice telephone service is as shown in the derivation of (2):
Figure BDA0002474909440000098
the video traffic interference is as follows:
Figure BDA0002474909440000099
wherein
Figure BDA00024749094400000910
Representing the amount of data occupied at each node of the service chain during the time interval (s, t) when video traffic is acting as interference traffic,
Figure BDA00024749094400000911
representing the data quantity of video traffic arriving at each node of the service chain from non-local service chain as interference traffic in a time interval (s, t),
Figure BDA0002474909440000101
the data amount of the video service arriving at the node j from the node j-1 on the service chain in the time interval (s, t) is represented by the following specific expression:
Figure BDA0002474909440000102
Figure BDA0002474909440000103
to sum up, the amount of interference suffered by the low-priority file transmission service is as follows:
Figure BDA0002474909440000104
deducing a service curve when each priority service is used as a research object penetrating a service chain;
(1) High priority voice over internet service: when the cross flow is not interfered by other types of services, the service curve is as follows:
Figure BDA0002474909440000105
(2) Medium priority video services: as a through stream, is subject to interference from voice over internet telephony services. By the remaining service theorem, the service curve is:
Figure BDA0002474909440000106
(3) Low priority file transfer service: when the streaming is interfered by network voice telephone service and video service, the service curve is as follows through the rest service theorem:
Figure BDA0002474909440000107
the service received by the wireless network service is divided into two types, including data processing service provided by an intelligent agent node and data transmission service provided by a wireless channel, and the two types of service nodes are distributed at intervals; the intelligent agent node provides data processing service, the data transmission service selects a Nakagami-M channel to provide a channel, and a moment mother function form of a service curve is solved:
(1) The service rate of the agent node is constant C, so the intalox function form of the agent service node in (s, t) is:
Figure BDA0002474909440000108
(2) The rectangular mother function form of the Nakagami-M channel node service curve is as follows:
Figure BDA0002474909440000111
wherein
Figure BDA0002474909440000112
B denotes the bandwidth of the channel, M is a Nakagami parameter, γ denotes the signal-to-noise ratio, l denotes the distance of the neighboring agent, α denotes the path fading factor,
Figure BDA0002474909440000113
(3) Combining (1) and (2), and obtaining a general formula of a moment mother function of a node service curve of the service chain, wherein the general formula is as follows:
Figure BDA0002474909440000114
(4) Thereby obtaining the service curve intalox forms of three services:
(a) High priority voice over internet service:
Figure BDA0002474909440000115
(b) Medium priority video services:
Figure BDA0002474909440000116
(c) Low priority file transfer service:
Figure BDA0002474909440000117
and S4, obtaining a closed expression of the relation between the time delay and the backlog upper bound boundary and the default probability according to the convolution and deconvolution theorem. In particular, the amount of the solvent to be used,
s4.1, deducing a general closed expression between the time delay upper bound boundary and the default probability:
Figure BDA0002474909440000118
where N represents the number of nodes on the service chain,
Figure BDA0002474909440000119
D [.] (t) represents traffic [.]Time delay at time t;
s4.2, deducing each priority service as a closed expression of the relationship between the upper bound of the time delay boundary and the default probability when the traffic passes through the flow:
(1) High-priority network voice call service:
Figure BDA0002474909440000121
wherein
Figure BDA0002474909440000122
(2) Medium priority video services:
Figure BDA0002474909440000123
wherein
Figure BDA0002474909440000124
y VoIP (j) The probability of the network voice telephone service occupying the service volume on each node is represented as follows:
Figure BDA0002474909440000125
(3) Low priority file transfer service:
Figure BDA0002474909440000126
wherein
Figure BDA0002474909440000127
y Video (j) The probability of the video traffic occupying the service volume on each node is expressed as follows:
Figure BDA0002474909440000128
s4.3, deducing a general closed expression between the backlog upper bound boundary and the default probability:
Figure BDA0002474909440000129
s4.4, deducing each priority service as a closed expression of the relationship between the upper bound of the time delay boundary and the default probability when the traffic passes through the flow:
(1) High priority voice over internet service:
Figure BDA00024749094400001210
(2) Medium priority video services:
Figure BDA0002474909440000131
(3) Low priority file transfer service:
Figure BDA0002474909440000132
the above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.

Claims (3)

1. A business end-to-end performance analysis method introducing random probability parameters is characterized by comprising the following steps:
s1, introducing a random probability parameter to indicate that a wireless network adopts software to define a network planning route so that the route selection has randomness;
step S2, in a wireless network with random probability parameters introduced, dividing services into high-priority services, medium-priority services and low-priority services according to different types of QoS in WiMAX, wherein the different types of QoS have different priorities; the high priority service comprises a network voice telephone service, the medium priority service comprises a video service, and the low priority service comprises a file transmission service;
s3, analyzing the wireless network with random probability parameters by a random network operation method based on a intalox function to obtain intalox function forms of the three priority service arrival processes; the method comprises the following specific steps:
(1) High priority voice over internet telephony, the arrival process obeys a poisson distribution, where λ VoIP Representing the average arrival rate of telephone traffic, θ is a free variable, so its moment parent function form of the cumulative arrival data amount over the time interval (s, t) is:
Figure FDA0003952230250000011
wherein A is VoIP (s, t) represents the accumulated data volume of the network voice telephone service in (s, t) of the non-local service chain nodes adjacent to each intelligent agent node on the service chain;
(2) The arrival rate of the medium priority video service is constant r, and the moment mother function of the accumulated arrival data amount in the time interval (s, t) is as follows:
Figure FDA0003952230250000012
wherein A is Video (s, t) represents the video traffic accumulated data volume in (s, t) of non-local service chain nodes adjacent to each agent node on the service chain;
(3) The arrival process of the low-priority file transmission service obeys Poisson distribution, wherein lambda FTP The moment mother function representing the average arrival rate of file transfer traffic and the cumulative arrival data amount in the time interval (s, t) is in the form of:
Figure FDA0003952230250000013
wherein A is FTP (s, t) represents the accumulated arriving data volume of the file transmission service of the service chain nodes adjacent to each agent node on the service chain in (s, t);
according to the rest service theorem, the intalox function forms of the service curves of the three types of priority services are respectively obtained as follows:
(a) High priority voice over internet service:
Figure FDA0003952230250000021
(b) Medium priority video services:
Figure FDA0003952230250000022
(c) Low priority file transfer service:
Figure FDA0003952230250000023
s4, obtaining a closed expression of the relation between the service time delay and the backlog upper bound boundary and the default probability according to the convolution and deconvolution theorem; in particular, the amount of the solvent to be used,
step S4.1, a general closed expression between the time delay upper bound boundary and the default probability is deduced:
Figure FDA0003952230250000024
where N represents the number of nodes on the service chain,
Figure FDA0003952230250000025
D [.] (t) represents traffic [.]Time delay at time t;
step S4.2, deducing each priority service as a closed expression of the relationship between the time delay boundary upper bound and the default probability when the service passes through the flow:
(1) High-priority network voice call service:
Figure FDA0003952230250000026
wherein
Figure FDA0003952230250000027
(2) Medium priority video services:
Figure FDA0003952230250000028
wherein
Figure FDA0003952230250000029
y VoIP (j) The probability of the network voice telephone service occupying the service volume on each node is represented as follows:
Figure FDA0003952230250000031
(3) Low priority file transfer service:
Figure FDA0003952230250000032
wherein
Figure FDA0003952230250000033
y Video (j) The probability of the video traffic occupying the service volume on each node is expressed as follows:
Figure FDA0003952230250000034
s4.3, deducing a general closed expression between the backlog upper bound boundary and the default probability:
Figure FDA0003952230250000035
wherein B is [.] (t) represents traffic [.]Backlog at time t;
s4.4, deducing each priority service as a closed expression of the relationship between the upper bound of the time delay boundary and the default probability when the traffic passes through the flow:
(1) High priority voice over internet service:
Figure FDA0003952230250000036
(2) Medium priority video services:
Figure FDA0003952230250000037
(3) Low priority file transfer service:
Figure FDA0003952230250000038
2. the method for analyzing end-to-end performance of service by introducing random probability parameter according to claim 1, wherein the specific steps of introducing random probability parameter in step S1 are as follows:
for the service [.]Setting three probability parameters to form a probability parameter set (P) [.].a ,P [.].b ,P [.].c ) (ii) a Wherein P is [.].a Express service [.]Probability of reaching an agent on a given service chain and needing processing or forwarding; p [.].b Is shown at P [.].a Service under conditions.]The probability of being the same as the path of the next hop of the study on the service chain; p [.].c Is shown at P [.].b On condition, the probability that an agent is required to process or forward after coming to the next agent node of the service chain.
3. The method for analyzing end-to-end performance of services by introducing random probability parameters according to claim 1, wherein the specific step of obtaining the intalox function form of the service curves of three priorities in step S3 comprises:
the method comprises the following steps that when three types of priority services are acquired as research objects penetrating through a service chain, interference from other services is received, and the method comprises the following steps:
(1) High priority voice over internet service: the priority is highest, and the interference of other services is avoided;
(2) Medium priority video services: the received service is interfered by the network voice telephone service, and at each node of the service chain, the interference is as follows:
Figure FDA0003952230250000041
wherein
Figure FDA0003952230250000042
Representing the amount of data occupied at each node during the time interval (s, t) when voice over internet telephony service is acting as an interfering service,
Figure FDA0003952230250000043
to representThe data volume of the network voice telephone service as interference service from the non-local service chain to each node of the local service chain in the time interval (s, t),
Figure FDA0003952230250000044
the data amount of the network voice telephone service on the service chain from the node j-1 to the node j in the time interval (s, t) is represented by the following specific expression:
Figure FDA0003952230250000045
Figure FDA0003952230250000046
(3) Low priority file transfer service: the service receiving is interfered by network voice telephone service and video service; the interference of the network voice telephone service is as follows:
Figure FDA0003952230250000047
the video traffic interference is as follows:
Figure FDA0003952230250000048
wherein
Figure FDA0003952230250000049
Representing the amount of data occupied at each node of the service chain during the time interval (s, t) when video traffic is acting as interference traffic,
Figure FDA00039522302500000410
representing the number of video traffic arriving at each node of the serving chain as interference traffic from a non-serving chain during a time interval (s, t)According to the amount of the data,
Figure FDA00039522302500000411
the data amount of the video service arriving at the node j from the node j-1 on the service chain in the time interval (s, t) is represented by the following specific expression:
Figure FDA0003952230250000051
Figure FDA0003952230250000052
to sum up, the amount of interference suffered by the low-priority file transmission service is as follows:
Figure FDA0003952230250000053
deducing a service curve when each priority service is used as a research object penetrating a service chain;
(1) High priority voice over internet service: when the flow is through, the flow is not interfered by other types of services, and the service curve is as follows:
Figure FDA0003952230250000054
(2) Medium priority video service: as a through flow, is interfered by the voice over internet telephony service; by the remaining service theorem, the service curve is:
Figure FDA0003952230250000055
(3) Low priority file transfer service: when the streaming is interfered by network voice telephone service and video service, the service curve is as follows through the rest service theorem:
Figure FDA0003952230250000056
the service received by the wireless network service is divided into two types, including data processing service provided by an intelligent agent node and data transmission service provided by a wireless channel, and the two types of service nodes are distributed at intervals; the intelligent agent node provides data processing service, the data transmission service selects a Nakagami-M channel to provide a channel, and a moment mother function form of a service curve is solved:
(1) The service rate of the agent node is constant C, so the intalox function form of the agent service node in (s, t) is:
Figure FDA0003952230250000057
(2) The rectangular mother function form of the Nakagami-M channel node service curve is as follows:
Figure FDA0003952230250000058
wherein
Figure FDA0003952230250000059
B denotes the bandwidth of the channel, M is a Nakagami parameter, γ denotes the signal-to-noise ratio, l denotes the distance of the neighboring agent, α denotes the path fading factor,
Figure FDA0003952230250000061
(3) Combining (1) and (2), and obtaining a general formula of a moment mother function of a node service curve of the service chain, wherein the general formula is as follows:
Figure FDA0003952230250000062
(4) Thereby obtaining the service curve intalox forms of three services:
(a) High priority voice over internet service:
Figure FDA0003952230250000063
(b) Medium priority video services:
Figure FDA0003952230250000064
(c) Low priority file transfer service:
Figure FDA0003952230250000065
CN202010360719.1A 2020-04-30 2020-04-30 Service end-to-end performance analysis method introducing random probability parameters Active CN111711961B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010360719.1A CN111711961B (en) 2020-04-30 2020-04-30 Service end-to-end performance analysis method introducing random probability parameters

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010360719.1A CN111711961B (en) 2020-04-30 2020-04-30 Service end-to-end performance analysis method introducing random probability parameters

Publications (2)

Publication Number Publication Date
CN111711961A CN111711961A (en) 2020-09-25
CN111711961B true CN111711961B (en) 2023-03-21

Family

ID=72536732

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010360719.1A Active CN111711961B (en) 2020-04-30 2020-04-30 Service end-to-end performance analysis method introducing random probability parameters

Country Status (1)

Country Link
CN (1) CN111711961B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220100922A1 (en) * 2020-09-29 2022-03-31 Rockwell Automation Technologies, Inc. Predicting industrial automation network performance
CN112616157B (en) * 2020-12-11 2024-03-08 大连大学 Wireless multi-hop Mesh network end-to-end time delay upper bound acquisition method based on network algorithm
CN113328879B (en) * 2021-05-21 2022-08-23 西北工业大学 Cloud data center network QoS (quality of service) guaranteeing method based on network calculus

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102075444B (en) * 2011-02-28 2013-10-02 北京邮电大学 Network system and method for guaranteeing multi-type service quality
CN102647760B (en) * 2012-03-02 2014-10-15 黄东 Multi-service-network-based efficient service resource management method
CN107896192B (en) * 2017-11-20 2020-09-25 电子科技大学 QoS control method for differentiating service priority in SDN network
CN109219071B (en) * 2018-11-05 2021-09-10 重庆邮电大学 Vertical switching method based on service classification in heterogeneous wireless network

Also Published As

Publication number Publication date
CN111711961A (en) 2020-09-25

Similar Documents

Publication Publication Date Title
CN111711961B (en) Service end-to-end performance analysis method introducing random probability parameters
Sariowan et al. SCED: A generalized scheduling policy for guaranteeing quality-of-service
US7620010B2 (en) Wireless communications apparatus, and routing control and packet transmission technique in wireless network
JP5133876B2 (en) Method and apparatus for improving scheduling in packet data networks
US20070076693A1 (en) Scheduling variable bit rate multimedia traffic over a multi-hop wireless network
US8023423B2 (en) Automated policy generation for mobile communication networks
CN104301933B (en) A kind of method for being used for computation bandwidth and distribution bandwidth in wireless self-networking
Głąbowski et al. Modelling overflow systems with distributed secondary resources
KR20000035662A (en) Link capacity computation methods and apparatus for designing ip networks with performance guarantees
KR20000035663A (en) Network topology optimization methods and apparatus for designing ip networks with performance guarantees
KR20000035664A (en) Router placement methods and apparatus for designing ip networks with performance guarantees
CN107332766B (en) Method for improving network throughput based on software defined network flow scheduling
CN114884557B (en) Satellite time sensitive network path selection method based on network algorithm
Lou et al. Boosting or hindering: AoI and throughput interrelation in routing-aware multi-hop wireless networks
Amuthan et al. Hyper-Erlang channel allocation factor-based QoS enhancement mechanism for mobile ad hoc networks
CN115604193A (en) Deterministic resource scheduling method and system in hot rolling control system
CN117118911A (en) Data transmission method and device
Sllame et al. Performance comparison of VoIP over wireless ad hoc networks using different routing protocols and queuing techniques
KR100818303B1 (en) Method for predicting traffic characteristics and traffic estimation devices for the wired and wireless networks
Martinez et al. A cross-layer design for ad hoc wireless networks with smart antennas and QoS support
Paschos et al. Multirate multicast: Optimal algorithms and implementation
Bouillard et al. Optimal routing for end-to-end guarantees: the price of multiplexing
Paschos et al. In-Network Congestion Control<? Pub _newline=""?> for Multirate Multicast
Pourmohammad et al. An analytical QoS model for IEEE 802.11-based single and multihop wireless networks
Sinha et al. Peak Age of Information under Tandem of Queues

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