CN112616157A - Method for acquiring end-to-end delay upper bound of wireless multi-hop Mesh network based on network calculation - Google Patents
Method for acquiring end-to-end delay upper bound of wireless multi-hop Mesh network based on network calculation Download PDFInfo
- Publication number
- CN112616157A CN112616157A CN202011452952.9A CN202011452952A CN112616157A CN 112616157 A CN112616157 A CN 112616157A CN 202011452952 A CN202011452952 A CN 202011452952A CN 112616157 A CN112616157 A CN 112616157A
- Authority
- CN
- China
- Prior art keywords
- delay
- node
- upper bound
- time delay
- path
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004364 calculation method Methods 0.000 title claims abstract description 19
- 230000005540 biological transmission Effects 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 15
- 230000002776 aggregation Effects 0.000 claims description 23
- 238000004220 aggregation Methods 0.000 claims description 23
- 238000004088 simulation Methods 0.000 abstract description 15
- 238000011160 research Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 description 8
- 230000007423 decrease Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a method for acquiring an end-to-end delay upper bound of a wireless multi-hop Mesh network based on network calculation, which is used for acquiring a single-node delay upper bound by solving queuing delay and processing delay of system nodes; setting an arrival curve and a service curve of the node and combining a wireless multi-hop mesh network research method to calculate the time delay upper bound of a single transmission system of the wireless multi-hop mesh network; and acquiring the delay upper bound of the multi-transmission system based on the delay upper bound of the single transmission system. Compared with a system simulation system, a single transmission system and a multi-transmission system through simulation experiments, the end-to-end delay upper bound of the wireless multi-hop mesh network obtained by the invention is close to the end-to-end delay simulation value of an actual network, and the QoS service of the network can be ensured.
Description
Technical Field
The invention relates to a group decision method, in particular to a wireless multi-hop Mesh network end-to-end delay upper bound acquisition method based on network calculation.
Background
As a broadband access technology, compared with the traditional wireless network, the wireless multi-hop Mesh network has the advantages of flexible node movement, various access modes and the like, and is paid attention by researchers in recent years. The network is mainly composed of three layers, namely an Internet access layer, a core network layer and an output access layer. The core network layer is arranged between the Internet access layer and the output access layer and is a key influencing the performance of the wireless multi-hop Mesh network, and the analysis of the performance of the core network brings references to the architecture design, network optimization and the like of the wireless Mesh network.
The end-to-end delay is an important index of network performance and is also an important parameter for measuring the quality of service (QoS) of the network and the user experience. The accuracy of the end-to-end delay upper bound analysis directly influences the network QoS guarantee level and is also an important basis for network admission control and route optimization.
The traditional research method mainly utilizes a network calculus theory to analyze the time delay upper bound in single-path transmission of the wireless multi-hop Mesh network and the time delay jitter upper bound between paths in multi-path transmission, however, the end-to-end time delay upper bound of a multi-path transmission system is not considered, and in addition, the network parameter modeling method mainly researches the approximate upper bound of the end-to-end time delay of the wireless multi-hop Mesh network.
Disclosure of Invention
In view of the problem that the traditional upper time delay research method cannot accurately obtain the upper end-to-end time delay of the wireless multi-hop Mesh network, the application provides an upper end-to-end time delay obtaining method based on network calculation so as to guarantee the QoS service of the network.
In order to achieve the purpose, the technical scheme of the application is as follows: an end-to-end delay upper bound acquisition method of a wireless multi-hop Mesh network based on network calculation comprises the following steps:
acquiring a single-node time delay upper bound;
obtaining an end-to-end delay upper bound of the wireless multi-hop Mesh network single-path transmission system by utilizing a network calculus theory according to the single-node delay upper bound;
and acquiring the end-to-end delay upper bound of the multi-path transmission system through the end-to-end delay upper bound of the single-path transmission system.
Further, before obtaining the upper bound of the single-node delay, it is assumed that a service flow a (t) is constrained by an arrival curve through a node p, where the arrival curve is:
where ρ is the average arrival rate of the data stream and σ is the maximum burst size of the data stream;
the service is provided by a service curve β (t) represented by a delay-Rate function LR (Latency-Rate), which is:
where R is the service rate, and T is the service delay of the data stream in the system, i.e. the packet processing delay, and is denoted as T ═ L/R + L/C.
Furthermore, the single-node time delay is composed of queuing time delay and processing time delay of system cache, wherein the processing time delay is a time delay parameter T, and the queuing time delay DqueueThe upper bound is regarded as the maximum busy interval, and the single-node queuing delay upper bound is as follows:
therefore, the delay upper bound of the single node i is expressed as:
further, the end-to-end delay upper bound of the wireless multi-hop Mesh network single-path transmission system obtained by utilizing a network calculus theory according to the single-node delay upper bound comprises two parts: one part is variable time delay and is used for queuing time delay of a system buffer area; the other part is fixed time delay which comprises processing time delay, forwarding time delay and link propagation time delay of a node system, and for the fixed time delay, the fixed time delay between two adjacent nodes in the n nodes is assumed to be d in sequence1,d2,…,dn-1;
For a path containing n nodes, the arrival curve of the ith node data stream is alphai(t)=σi+ρit, transport service system capability is betai=Ri[t-Ti]+The single-path end-to-end delay of nodes 1 to n is
1) When n is 1, the delay is bounded by a single nodeAnd equation (4) obtain the end-to-end delay upper bound; when n is 2, the upper bound of the time delay of the 1 st node is obtained by the horizontal deviation theoremThe output of the node 1 is limited to the arrival curve, the node 1 transmits the data stream to the link, and then reaches the 2 nd node through propagation, so that the 2 nd node arrival curve α (t) ═ α*(t); obtaining the upper time delay bound of the node 2 according to the calculation formula of the upper time delay bound of the single nodeCombining the fixed time delay between two adjacent nodes, the end-to-end time delay between the 1 st and 2 nd nodes is:
2) assuming that when n is k-1, the end-to-end delay bound is:
3) when n is k, the arrival curve of the k-th nodeDelay bound of single nodeIt is found that the delay upper bound of the kth node is:
the end-to-end delay upper bound of the single path containing k nodes is equal to the delay upper bound of the first k-1 nodesFixed time delay d between the kth node and the kth nodek-1And the upper bound of the delay of the kth nodeThe sum of the three, i.e.
Further, the method for acquiring the end-to-end delay upper bound of the multi-path transmission system through the end-to-end delay upper bound of the single-path transmission system specifically includes: assuming that m paths exist between a source end node g and an aggregation node a, a data stream R (t) entering a network system first passes through the source end node g and then is divided into m paths for transmission, which is denoted as Ri(t), i is 1,2, …, m, and hasLet beta be used for service curve of jth node on ith path(i,j)Wherein j is 1,2, …, ni,niThe number of the nodes on the ith path is represented, and the service capability of the aggregation node a is represented as betaa(ii) a For the aggregation node a, the cache queue area of the node is assumed to be large enough, so that data overflow is not caused;
there are m paths from node g to node a, and n on the ith pathiEach node has service capability represented as betaa=Ra[t-Ta]+,β(i,j)=R(i,j)[t-T(i,j)]+,βg=Rg[t-Tg]+,i=1,2,…,m;j=1,2,…,niBecause the maximum delay value in the multipath transmission before the data streams from g to a are not aggregated is the transmission delay of the path with the maximum transmission delay, it is expressed as:
the output data flow of the ith path is subjected to curve according to the end-to-end time delay of the single pathConstraint, assuming that the aggregation node a needs to process all data streams after they arrive, the flow entering the aggregation node a needs to be subjected to the curve:
the upper time delay bound of the aggregation node after the transmission through the m paths meets the following relational expression
Wherein, Ta=L/RaService delay, p, for aggregation node aa=ρ1+ρ2+…+ρm。
In summary, the upper bound of the end-to-end delay of the multipath transmission system is obtained as
Compared with the existing method, the method has the advantages that: the method comprises the steps of solving queuing time delay and processing time delay of system nodes to obtain a single-node time delay upper bound; setting an arrival curve and a service curve of the node and combining a wireless multi-hop mesh network research method to calculate the time delay upper bound of a single transmission system of the wireless multi-hop mesh network; and acquiring the delay upper bound of the multi-transmission system based on the delay upper bound of the single transmission system. Compared with a system simulation system, a single transmission system and a multi-transmission system through simulation experiments, the end-to-end delay upper bound of the wireless multi-hop mesh network obtained by the invention is close to the end-to-end delay simulation value of an actual network, and the QoS service of the network can be ensured.
Drawings
FIG. 1 arrives at a graph;
FIG. 2 is a single path transmission diagram;
FIG. 3 is a multi-path transmission diagram;
FIG. 4 is a single transmission system scene simulation diagram;
FIG. 5R is an end-to-end delay plot at 150 Mb/s;
FIG. 6 is an upper bound analysis graph of end-to-end delay;
FIG. 7 is a graph showing a relationship between single-path end-to-end delay and the number of link nodes;
FIG. 8 is a graph of end-to-end delay versus network service rate;
FIG. 9 is a diagram of end-to-end delay and three types of service weight assignment;
FIG. 10 is a graph of the relationship between the upper bound of the multi-path end-to-end delay and the network service rate;
fig. 11 is a graph of the relationship between the upper bound of the end-to-end delay of multiple paths and the number of multiple paths.
Detailed Description
The invention is described in further detail below with reference to the following figures and specific examples: the present application is further described by taking this as an example.
The embodiment provides a method for acquiring an end-to-end delay upper bound of a wireless multi-hop Mesh network based on network calculation, which comprises the following steps:
firstly, acquiring a single-node time delay upper bound;
specifically, the delay of a single node is formed by queuing delay and processing delay of a system cache, when a traffic flow a (t) arrives at the node, the traffic flow is limited by a token bucket with the node parameter (ρ, σ), that is, is constrained by an arrival curve α (t) of the node,
where ρ is the average arrival rate of the data stream and σ is the maximum burst size of the data stream. And provides services through a service curve β (t) represented by a delay-Rate function LR (Latency-Rate):
where R is the service rate and T is the service delay of the data flow in the system, i.e. the packet processing delay, denoted as T ═ L/R + L/C.
The single-node time delay is composed of queuing time delay and processing time delay of system cache, wherein the processing time delay is a delay parameter T, and the queuing time delay DqueueThe upper bound is considered as the maximum busy interval with a single-node queuing delay of the upper bound
Therefore, the upper bound of the single-node i delay is obtained as follows:
secondly, obtaining an end-to-end delay upper bound of the wireless multi-hop Mesh network single-path transmission system by utilizing a network calculus theory according to the single-node delay upper bound;
specifically, the end-to-end single-path transmission of the wireless multi-hop Mesh network is shown in fig. 2, and includes two parts: one part is variable time delay, mainly queuing time delay of a system buffer area; the other part is fixed time delay, which mainly comprises node system processing time delay, forwarding time delay and link propagation time delay. For the fixed time delay, the fixed time delay between two adjacent nodes in the n nodes is assumed to be d in sequence in the application1,d2,…,dn-1。
For a path containing n nodes, the arrival curve of the ith node data stream is alphai(t)=σi+ρit, transport service system capability is betai=Ri[t-Ti]+Then the single path end-to-end delay of nodes 1 to n is
1) When n is 1, the delay is bounded by a single nodeAnd equation (4) obtain the end-to-end delay upper bound; when n is 2, the upper delay bound of the 1 st node is obtained by the horizontal deviation theoremThe output of node 1 is limited to the curve, node 1 transmits the data stream onto the link, and then reaches the 2 nd node through propagation, so that the 2 nd node reaches the curve α (t) ═ α*(t) of (d). Obtaining the upper time delay bound of the node 2 according to the calculation formula of the upper time delay bound of the single nodeCombining the fixed time delay between two adjacent nodes, the end-to-end delay between the 1 st and 2 nd nodes is:
2) assuming that when n is k-1, the end-to-end delay bound is:
3) when n is k, the arrival curve of the k-th nodeDelay bound of single nodeIt is found that the delay upper bound of the kth node is
The end-to-end delay upper bound of the single path containing k nodes is equal to the delay upper bound of the first k-1 nodesFixed time delay d between the kth node and the kth nodek-1And the upper bound of the delay of the kth nodeThe sum of the three, i.e.
Thirdly, acquiring an end-to-end delay upper bound of a multi-path transmission system through the end-to-end delay upper bound of the single-path transmission system;
specifically, the multipath transmission is as shown in fig. 3, according to the network calculation and the end-to-end delay bound of the single-path transmission system, assuming that m paths exist between the source end node g of the multipath transmission and the aggregation node a, a data stream R (t) entering the network system will first pass through the source end node g and then be divided into m paths for transmission, which is denoted as Ri(t), i is 1,2, …, m, and hasLet beta be used for service curve of jth node on ith path(i,j)Wherein j is 1,2, …, ni,niThe number of the nodes on the ith path is represented, and the service capability of the aggregation node a is represented as betaa. For the aggregation node a, the present application assumes that the buffer queue area of the node is large enough not to cause data overflow。
The nodes g to a have m paths, and the ith path has niEach node has service capability represented as betaa=Ra[t-Ta]+,β(i,j)=R(i,j)[t-T(i,j)]+,βg=Rg[t-Tg]+,i=1,2,…,m;j=1,2,…,niBecause the maximum delay in the multipath transmission before the data streams from g to a are not aggregated is the transmission delay of the path with the maximum transmission delay, which is expressed as
According to the end-to-end delay of the single path, the output data flow of the ith path is subjected to the curveConstraint, assuming that the aggregation node a needs to process all data streams after arriving, the curve is needed to make the traffic enter the aggregation node a
The upper time delay bound of the aggregation node after the transmission through the m paths meets the following relational expression
Wherein, Ta=L/RaService delay, p, for aggregation node aa=ρ1+ρ2+…+ρm。
In summary, the end-to-end delay upper bound of the multipath transmission system is obtained as follows:
in order to verify the effectiveness and the correctness of the method for acquiring the end-to-end delay upper bound of the wireless multi-hop Mesh network based on network calculation, a single transmission system is simulated to carry out end-to-end delay statistics, and a single-path transmission system is set by using an OPNET simulation tool, as shown in FIG. 4. An experimental scene is as follows: 1000m, the client sending rate of the source node router1 is 120Mb/s, the initial value of the service rate of each router is set to 150Mb/s, the node cache size is set to 500MTU, and the distances from the router1 to the router7 are 250m in sequence. Other network parameters employ the setup parameters in table 1.
Table 1 network experiment parameter set-up
Table 1 Network Experiment Parameter Settings
Note: the maximum packet length is set according to MTU (maximum Transmission Unit) specified in computer network Ethernet
The method and the device perform end-to-end delay upper bound value simulation verification from two angles of a single-path transmission system and a multi-path transmission system respectively. For a single-path transmission system, the analysis is carried out from two aspects, namely, the analysis and the comparison of the end-to-end delay upper bound obtained by calculation based on the network calculus theory and the simulation end-to-end delay upper bound are carried out to verify the result, and the influence of the end-to-end delay upper bound calculated by the application under different conditions is described through the following three data streams with different characteristics. The long-term average rate and the burst size of X are respectively 120Mb/s and 200 kbits; the long-term average rate and the burst amount of Y are respectively 200Mb/s and 200 kbits; the long term average rate and burst size for Z are 120Mb/s, 300 kbits, respectively.
1. End-to-end delay upper bound of single-path transmission system
In order to maintain the consistency of simulation analysis of the present invention, service parameters in the stream X are uniformly adopted, and the network end-to-end delay upper bound value obtained by simulation according to fig. 5 is compared with the end-to-end delay upper bound obtained by calculation of the present application, as shown in fig. 6, it can be seen that the end-to-end delay upper bound calculated by the present application is increasingly close to the simulation delay upper bound analog value as the network service rate increases.
In addition, fig. 7, fig. 8, and fig. 9 are respectively the influence of the data streams with three different characteristics, X, Y, and Z, on the upper bound of the end-to-end delay from the three aspects of the number of link nodes, the network service rate, and the service weight assignment.
(1) Relation between link node number and end-to-end delay
Fig. 7 shows the influence of the number of link nodes on the end-to-end delay under the condition of a single path, and it can be seen that the delay is increased along with the increase of the number of the link nodes, and the result reflects the characteristics of network calculation and actual delay, that is, when the number of the link nodes is more, the convolution value of the network calculation can reflect the real network performance more.
(2) Relation between network service rate and end-to-end delay
Fig. 8 shows the relationship between the end-to-end delay and the network service rate, and it can be easily seen that the two are inversely related, i.e., the end-to-end delay decreases as the network service rate increases, which is consistent with the actual network situation. In addition, it can be seen that when the service rate is less than 350Mb/s, the amplitude of the decrease of the end-to-end delay with the increase of the network service rate is large, and when the service rate is more than 350Mb/s, the decrease amplitude tends to be stable. The curves between the end-to-end delay of data streams X and Z and the network service rate almost overlap because the two services have the same value, and the input-output relationship between the nodes changes with the convolution value of the network calculation, which is mainly influenced by the burst amount, but not greatly influenced, but the delay of Z is slightly larger. This is verified by the significant difference in the curves between the end-to-end delay of X and Y and the network service rate.
(3) Service rate weight versus end-to-end delay
Fig. 9 shows the relationship between the end-to-end delay and the service rate weight assignment in the case of a fixed number of link nodes. Assuming a total service rate of 800Mb/s, the service rate allocation weights for data flow X, Y, Z are 0.2, 0.5, and 0.3, respectively. The whole of the end-to-end time delay of the three parts is in an ascending trend, wherein the X end-to-end time delay is the highest, the Y time delay is the lowest, and the Z time delay is consistent with the analysis result. Under the condition of the same arrival rate, the service rate distributed by Z is greater than the rate distributed by X, although the burst quantity can also affect the delay, the impact is not great, and the naturally calculated end-to-end delay is smaller; while Y has a large impact on the arrival rate compared to X, the same impact is less pronounced for the highest service rate assigned to Y.
2. End-to-end delay bound for multi-path transmission system
Under the multipath condition, the influence on the upper bound of the end-to-end delay is mainly analyzed from the aspects of the number of paths and the network service rate. In the transmission process, data output by the source node g is set to reach the aggregation node a through three paths, and the service rates provided by all links are 90Mb/s, 100Mb/s and 110Mb/s respectively. Meanwhile, for the convenience and effectiveness of comparative analysis, only the corresponding change condition of the end-to-end delay upper bound of the data stream X under different conditions is analyzed under the multipath.
(1) Relation between traffic distribution mode and end-to-end delay
Fig. 10 reveals the influence of the network service rate and the traffic distribution manner on the upper end-to-end delay bound under the multipath condition, where the upper delay bounds of both the two traffic distribution manners gradually decrease with the increase of the service rate, and it can also be seen that the delay through the weight distribution manner is lower, which shows that the effect of distributing proper traffic according to the service requirements of different links is better, and the influence of network congestion caused by large load of local links on the overall upper end-to-end delay bound is reduced.
(2) Relation between traffic distribution mode and end-to-end delay
Fig. 11 shows the influence of the number of multipath and the traffic distribution mode on the upper bound of the end-to-end delay when the total service rate of the link is set to 300Mb/s and the service rates of the source node and the aggregation node are both 500Mb/s, and the change of the upper bound of the end-to-end delay of the data stream X under different conditions is simulated and analyzed. It can be seen that the end-to-end delay upper bounds of the two traffic distribution modes increase with the increase of the number of the multipath, and the end-to-end delay upper bound obtained by weight distribution is lower than the average distribution delay upper bound, which is also attributed to that the weight distribution mode avoids the influence of network congestion caused by large load on the local link, thereby influencing the total end-to-end delay upper bound.
Simulation analysis is carried out by using different indexes, and the upper bound of the end-to-end delay of the wireless multi-hop mesh network based on network calculation provided by the invention is close to the simulation value of the end-to-end delay of the actual network, so that the QoS service of the network can be ensured.
The above description is only for the purpose of creating a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution and the inventive concept of the present invention within the technical scope of the present invention.
Claims (5)
1. An end-to-end delay upper bound acquisition method of a wireless multi-hop Mesh network based on network calculation is characterized by comprising the following steps:
acquiring a single-node time delay upper bound;
obtaining an end-to-end delay upper bound of the wireless multi-hop Mesh network single-path transmission system by utilizing a network calculus theory according to the single-node delay upper bound;
and acquiring the end-to-end delay upper bound of the multi-path transmission system through the end-to-end delay upper bound of the single-path transmission system.
2. The method for acquiring the end-to-end delay upper bound of the wireless multi-hop Mesh network based on the network calculus as claimed in claim 1, wherein before acquiring the single-node delay upper bound, it is assumed that a service flow a (t) is constrained by an arrival curve through a node p, and the arrival curve is:
where ρ is the average arrival rate of the data stream and σ is the maximum burst size of the data stream;
the service is provided through a service curve β (t) represented by a delay-rate function LR, which is:
where R is the service rate, and T is the service delay of the data stream in the system, i.e. the packet processing delay, and is denoted as T ═ L/R + L/C.
3. The method for obtaining the end-to-end delay bound of the wireless multi-hop Mesh network based on the network calculus as claimed in claim 2, wherein the single-node delay is composed of the queuing delay and the processing delay of the system node, wherein the processing delay is the delay parameter T, and the queuing delay D is the delay parameter TqueueThe upper bound is regarded as the maximum busy interval, and the single-node queuing delay upper bound is as follows:
therefore, the delay upper bound of the single node i is expressed as:
4. the method for acquiring the end-to-end delay upper bound of the wireless multi-hop Mesh network based on the network calculus of claim 1, wherein the method for acquiring the end-to-end delay upper bound of the wireless multi-hop Mesh network single-path transmission system by using the network calculus theory according to the single-node delay upper bound comprises two parts: one part is variable time delay and is used for queuing time delay of a system buffer area; the other part is fixed time delay which comprises processing time delay, forwarding time delay and link propagation time delay of a node system, and for the fixed time delay, the fixed time delay between two adjacent nodes in the n nodes is assumed to be d in sequence1,d2,…,dn-1;
For a path containing n nodes, the arrival curve of the ith node data stream is alphai(t)=σi+ρit, transport service system capability is betai=Ri[t-Ti]+The single-path end-to-end delay of nodes 1 to n is
1) When n is 1, the delay is bounded by a single nodeAnd equation (4) obtain the end-to-end delay upper bound; when n is 2, the upper bound of the time delay of the 1 st node is obtained by the horizontal deviation theoremThe output of the node 1 is limited to the arrival curve, the node 1 transmits the data stream to the link, and then reaches the 2 nd node through propagation, so that the 2 nd node arrival curve α (t) ═ α*(t); obtaining the upper time delay bound of the node 2 according to the calculation formula of the upper time delay bound of the single nodeCombining the fixed time delay between two adjacent nodes, the end-to-end time delay between the 1 st and 2 nd nodes is:
2) assuming that when n is k-1, the end-to-end delay bound is:
3) when n is kArrival curve of the kth nodeDelay bound of single nodeIt is found that the delay upper bound of the kth node is:
the end-to-end delay upper bound of the single path containing k nodes is equal to the delay upper bound of the first k-1 nodesFixed time delay d between the kth node and the kth nodek-1And the upper bound of the delay of the kth nodeThe sum of the three, i.e.
5. The method for acquiring the end-to-end delay upper bound of the wireless multi-hop Mesh network based on the network calculus as claimed in claim 1, wherein the method for acquiring the end-to-end delay upper bound of the multi-path transmission system through the end-to-end delay upper bound of the single-path transmission system specifically comprises the following steps: assuming that m paths exist between a source end node g and an aggregation node a, a data stream R (t) entering a network system first passes through the source end node g and then is divided into m paths for transmission, which is denoted as Ri(t), i is 1,2, …, m, and hasLet beta be used for service curve of jth node on ith path(i,j)Wherein j is 1,2, …, ni,niThe number of the nodes on the ith path is represented, and the service capability of the aggregation node a is represented as betaa(ii) a For the aggregation node a, the cache queue area of the node is assumed to be large enough, so that data overflow is not caused;
there are m paths from node g to node a, and n on the ith pathiEach node has service capability represented as betaa=Ra[t-Ta]+,β(i,j)=R(i,j)[t-T(i,j)]+,βg=Rg[t-Tg]+,i=1,2,…,m;j=1,2,…,niBecause the maximum delay value in the multipath transmission before the data streams from g to a are not aggregated is the transmission delay of the path with the maximum transmission delay, it is expressed as:
the output data flow of the ith path is subjected to curve according to the end-to-end time delay of the single pathConstraint, assuming that the aggregation node a needs to process all data streams after they arrive, the flow entering the aggregation node a needs to be subjected to the curve:
the upper time delay bound of the aggregation node after the transmission through the m paths meets the following relational expression
Wherein, Ta=L/RaService delay, p, for aggregation node aa=ρ1+ρ2+…+ρm。
In summary, the upper bound of the end-to-end delay of the multipath transmission system is obtained as
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011452952.9A CN112616157B (en) | 2020-12-11 | 2020-12-11 | Wireless multi-hop Mesh network end-to-end time delay upper bound acquisition method based on network algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011452952.9A CN112616157B (en) | 2020-12-11 | 2020-12-11 | Wireless multi-hop Mesh network end-to-end time delay upper bound acquisition method based on network algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112616157A true CN112616157A (en) | 2021-04-06 |
CN112616157B CN112616157B (en) | 2024-03-08 |
Family
ID=75233640
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011452952.9A Active CN112616157B (en) | 2020-12-11 | 2020-12-11 | Wireless multi-hop Mesh network end-to-end time delay upper bound acquisition method based on network algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112616157B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113328879A (en) * | 2021-05-21 | 2021-08-31 | 西北工业大学 | Cloud data center network QoS (quality of service) guaranteeing method based on network calculus |
CN116566903A (en) * | 2023-07-05 | 2023-08-08 | 南京信息工程大学 | End-to-end time delay analysis method for converging flow of heterogeneous links of finger control network |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050111487A1 (en) * | 2002-06-28 | 2005-05-26 | Matta Johnny M. | Method and apparatus for quality of service determination |
CN1941737A (en) * | 2005-09-30 | 2007-04-04 | 富士通株式会社 | Method and device for pre-determining time delay in node, and method and device for guarantee of time delay |
US20110013644A1 (en) * | 2009-07-15 | 2011-01-20 | Qualcomm Incorporated | Systems and methods for providing resource allocation meeting communication constraints for multi-hop network data flows |
CN103312606A (en) * | 2013-05-23 | 2013-09-18 | 杭州卓沃电子商务有限公司 | Wireless Mesh network routing based on multi-path concurrence and method thereof |
CN103338471A (en) * | 2013-06-27 | 2013-10-02 | 南京邮电大学 | Service quality index evaluating method for wireless multi-hop network based on model |
CN106102084A (en) * | 2016-05-24 | 2016-11-09 | 重庆邮电大学 | Wireless sensor network end-to-end time delay upper bound appraisal procedure based on retransmission feedback |
CN107346988A (en) * | 2017-06-20 | 2017-11-14 | 大连大学 | A kind of appearance based on low-track satellite network late/hold circuit network route computing method |
CN110708716A (en) * | 2019-08-28 | 2020-01-17 | 华北电力大学(保定) | Short packet communication transmission performance analysis method based on multi-antenna energy capture |
CN111711961A (en) * | 2020-04-30 | 2020-09-25 | 南京邮电大学 | Service end-to-end performance analysis method introducing random probability parameter |
EP3809634A1 (en) * | 2019-10-16 | 2021-04-21 | Huawei Technologies Co., Ltd. | Network configuration method and device |
-
2020
- 2020-12-11 CN CN202011452952.9A patent/CN112616157B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050111487A1 (en) * | 2002-06-28 | 2005-05-26 | Matta Johnny M. | Method and apparatus for quality of service determination |
CN1941737A (en) * | 2005-09-30 | 2007-04-04 | 富士通株式会社 | Method and device for pre-determining time delay in node, and method and device for guarantee of time delay |
US20110013644A1 (en) * | 2009-07-15 | 2011-01-20 | Qualcomm Incorporated | Systems and methods for providing resource allocation meeting communication constraints for multi-hop network data flows |
CN103312606A (en) * | 2013-05-23 | 2013-09-18 | 杭州卓沃电子商务有限公司 | Wireless Mesh network routing based on multi-path concurrence and method thereof |
CN103338471A (en) * | 2013-06-27 | 2013-10-02 | 南京邮电大学 | Service quality index evaluating method for wireless multi-hop network based on model |
CN106102084A (en) * | 2016-05-24 | 2016-11-09 | 重庆邮电大学 | Wireless sensor network end-to-end time delay upper bound appraisal procedure based on retransmission feedback |
CN107346988A (en) * | 2017-06-20 | 2017-11-14 | 大连大学 | A kind of appearance based on low-track satellite network late/hold circuit network route computing method |
CN110708716A (en) * | 2019-08-28 | 2020-01-17 | 华北电力大学(保定) | Short packet communication transmission performance analysis method based on multi-antenna energy capture |
EP3809634A1 (en) * | 2019-10-16 | 2021-04-21 | Huawei Technologies Co., Ltd. | Network configuration method and device |
CN111711961A (en) * | 2020-04-30 | 2020-09-25 | 南京邮电大学 | Service end-to-end performance analysis method introducing random probability parameter |
Non-Patent Citations (8)
Title |
---|
FLAVIUS PANA等: "A Survey on Evolution of RSVP", 《IEEE》 * |
刘宴兵;吕娟;黄俊;熊姿;: "面向云服务的网络参数建模与定量分析", 数学的实践与认识, no. 04, 23 February 2014 (2014-02-23), pages 2 - 3 * |
刘宴兵;吕娟;黄俊;熊姿;: "面向云服务的网络参数建模与定量分析", 数学的实践与认识, no. 04, pages 2 - 3 * |
李庆华;陈志刚;张连明;曾锋;李翔;: "基于网络演算的无线自组网QoS性能确定上界研究", 通信学报, no. 09, 25 September 2008 (2008-09-25) * |
杨力;杨恒;魏德宾;潘成胜;: "SAGA:一种面向任务的卫星网络资源分配算法", 小型微型计算机系统, no. 01, 15 January 2020 (2020-01-15) * |
陈志刚: "无线mesh网中时延约束抖动优化的多路径流量分配算法", 《通信学报》, pages 2 * |
陈志刚;曾锋;李庆华;: "无线mesh网中时延约束抖动优化的多路径流量分配算法", 通信学报, no. 01, 25 January 2011 (2011-01-25), pages 2 - 4 * |
陈志刚;曾锋;李庆华;: "无线mesh网中时延约束抖动优化的多路径流量分配算法", 通信学报, no. 01, pages 2 - 4 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113328879A (en) * | 2021-05-21 | 2021-08-31 | 西北工业大学 | Cloud data center network QoS (quality of service) guaranteeing method based on network calculus |
CN116566903A (en) * | 2023-07-05 | 2023-08-08 | 南京信息工程大学 | End-to-end time delay analysis method for converging flow of heterogeneous links of finger control network |
CN116566903B (en) * | 2023-07-05 | 2023-09-26 | 南京信息工程大学 | End-to-end time delay analysis method for converging flow of heterogeneous links of finger control network |
Also Published As
Publication number | Publication date |
---|---|
CN112616157B (en) | 2024-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kurose | On computing per-session performance bounds in high-speed multi-hop computer networks | |
CN112616157B (en) | Wireless multi-hop Mesh network end-to-end time delay upper bound acquisition method based on network algorithm | |
US20030223428A1 (en) | Method and apparatus for scheduling aggregated resources | |
CN1643860A (en) | Method and arrangement for dinamic allocation of network resources | |
Yuan et al. | Fair round-robin: A low complexity packet schduler with proportional and worst-case fairness | |
CN108183828B (en) | Flow control method based on local wireless network topology | |
Wang et al. | Adaptive placement and routing for service function chains with service deadlines | |
CN104935524B (en) | The soft load-balancing method that a kind of multipath network is controlled based on chain-circuit time delay | |
CN114448899A (en) | Method for balancing network load of data center | |
CN112565014A (en) | Satellite network end-to-end delay upper bound acquisition method based on network calculus | |
Zheng et al. | An analysis of resequencing delay of reliable transmission protocols over multipath | |
Li et al. | Schedulability criterion and performance analysis of coordinated schedulers | |
Liu et al. | A stochastic network calculus | |
Varma | Performance and buffering requirements of TCP applications in asymmetric networks | |
Kanhere et al. | On the latency bound of pre-order deficit round robin | |
Thombre | Network jitter analysis with varying tcp for internet communications | |
Nikolova et al. | Evaluation of surplus round robin scheduling algorithm | |
Musa et al. | A Comparative Study of Different Queuing Scheduling Disciplines | |
Kim et al. | Feedback control for QoS of mixed traffic in communication networks | |
Czarkowski et al. | Traffic Type Influence on Performance of OSPF QoS Routing | |
WO2006067770A1 (en) | A network analysis tool | |
Goebbels | Traffic Theory Approach for Heterogeneous Mobile Communication Networks | |
Ruan et al. | S3: size-aware sequential scheduling to meet deadlines in data center networks | |
Shi et al. | Design of Buffer Queue in Low-Orbit Satellite Network Based on Average Route Hops | |
Diwan et al. | Routing and rate allocation to provide end-to-end delay guarantees under PGPS scheduling |
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 |