CN107094115B - Ant colony optimization load balancing routing algorithm based on SDN - Google Patents

Ant colony optimization load balancing routing algorithm based on SDN Download PDF

Info

Publication number
CN107094115B
CN107094115B CN201710358160.7A CN201710358160A CN107094115B CN 107094115 B CN107094115 B CN 107094115B CN 201710358160 A CN201710358160 A CN 201710358160A CN 107094115 B CN107094115 B CN 107094115B
Authority
CN
China
Prior art keywords
link
node
network
switch
load balancing
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
CN201710358160.7A
Other languages
Chinese (zh)
Other versions
CN107094115A (en
Inventor
樊自甫
张丹
杨先辉
万晓榆
王正强
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.)
Chongqing University of Post and Telecommunications
Original Assignee
Chongqing University of Post 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 Chongqing University of Post and Telecommunications filed Critical Chongqing University of Post and Telecommunications
Priority to CN201710358160.7A priority Critical patent/CN107094115B/en
Publication of CN107094115A publication Critical patent/CN107094115A/en
Application granted granted Critical
Publication of CN107094115B publication Critical patent/CN107094115B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H04L45/125—Shortest path evaluation based on throughput or bandwidth
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/02—Topology update or discovery
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/12—Avoiding congestion; Recovering from congestion
    • H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1025—Dynamic adaptation of the criteria on which the server selection is based
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Landscapes

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

Abstract

The invention requests to protect an ant colony optimization load balancing routing algorithm based on an SDN, which comprises the following steps: firstly, acquiring state information of each link in an SDN network, and establishing a load balancing model, wherein the load balancing model not only limits the bandwidth capacity of the link, but also considers the limit of the flow table capacity of a switch; and then, providing an ant colony optimization algorithm for solving a load balancing model, wherein the ant colony optimization algorithm is mainly used for selecting a next node according to a probability formula and judging whether the next node is a target node, updating and setting pheromone updating rules on corresponding links when a cycle is finished, and solving a current optimal path set and outputting the current optimal path set until an iteration termination condition is met. The invention not only enables the flow in the network to be evenly distributed on each link, but also effectively avoids the insufficient space of the switch flow table caused by generating excessive flow table rules.

Description

Ant colony optimization load balancing routing algorithm based on SDN
Technical Field
The invention belongs to a load balancing routing technology in an SDN network, and provides an ant colony optimization load balancing routing algorithm based on an SDN.
Background
Under the SDN architecture, a logically centralized controller may obtain basic information of switches and paths, calculate an appropriate data flow path according to an operator intention and the basic information of a network, and then issue a corresponding forwarding rule to a corresponding switch. Forwarding rules in an SDN switch are stored in a Ternary Content Addressable Memory (TCAM) of limited size, which supports fast parallel queries for wildcard patterns, which can hold only a few thousand rules because it is very expensive and power consuming. The practical importance of limiting the size of the flow table has been recognized by the ASCII industry. Existing commercial OpenFlow switches have the size of a TCAM that can only store about 1500 OpenFlow forwarding rules because they forward flow entries longer than standard switches. Thus, SDN applications become more challenging in large networks. To avoid congestion, we need to ensure that the bandwidth of the data flow transmission path meets the data flow requirements. The size of the flow table is another constraint from the perspective of the switch. Once the limit of the switch flow table is reached, the switch will refuse to install more forwarding rules, which can lead to network forwarding errors. Therefore, bandwidth utilization and flow table usage are closely related. Selecting a forwarding packet path requires consideration of not only load balancing of links but also restriction of flow table capacity in switches on the path.
Lan Y L et al published an article entitled "Dynamic load-based path optimization in SDN-based centers networks" on 2016International Symposium on Communication Systems,2013: 25-28. The article proposes to propose a dynamic load balancing path optimization (DLPO) algorithm. The proposed DLPO algorithm can change the path of the stream during stream transmission, achieving load balancing between different links. In addition, a priority-based flow table update policy is also proposed to ensure that when all flow tables of associated switches in the light path are successfully updated, the data flow of the congested path is successfully redirected to the light path to avoid packet loss due to a path change of the flow. This scheme only takes into account the load of the link.
Li et al, 2014IEEE Networking IEEE/ACM Transactions on,2014:2787 + 2805, published a paper entitled "Load Balancing in IP Networks Using Generalized determination-Based Multi Routing". The generalized destination multi-path routing (GDMR) of the article realizes path load balancing, and divides data flow according to the residual bandwidth of the path in a certain proportion to realize uniform load distribution of a network. This scheme can also be implemented in a central controller with a global view of the entire network, while SDN is a platform well suited for real-time their schemes. But this scheme only takes into account the load of the link.
Zhang H et al published an article entitled "On the effect of forwarding table size On SDN networking", in 2014Conference On Computer communications, IEEE, 2014:13-18. The article proposes a pathlength maximum flow algorithm (PDMF). Modeling by limiting the maximum number of paths per node in the network aims to maximize the number of feasible flows in the network while satisfying the link limited bandwidth capacity and node path classes. The scheme ensures that the flow table with priority in the network does not exceed the capacity of the node by limiting the maximum path number of the node, but cannot ensure the link load balance in the network, so that the generation of network congestion is difficult to avoid.
It can be known from related researches that the current load balancing scheme mainly considers the load condition of a link, and may cause the occurrence of unsuccessful transmission of a data flow in a network due to the limitation of a switch flow table. The invention provides an ant colony optimization algorithm for modeling the complex balance problem in the SDN network and solving the load balance problem according to the link load condition in the network and the limited flow table of the switch.
Disclosure of Invention
The present invention is directed to solving the above problems of the prior art. An SDN-based ant colony optimized load balancing routing algorithm is proposed that avoids the generation of network congestion. The technical scheme of the invention is as follows:
an ant colony optimization load balancing routing algorithm based on an SDN (software defined network), comprising the following steps of:
the method comprises the steps of firstly obtaining state information of each link in the SDN network, and establishing a load balancing model, wherein the optimization aim is to minimize the maximum link utilization rate in the network, namely, traffic passing through the network is approximately and uniformly distributed on each link in time. In the load balancing model, the limitation on the bandwidth capacity of a link is considered, and the limitation on the capacity of a flow table of a switch is also considered;
then, an ant colony optimization algorithm is provided to solve the load balancing model, and the ant colony optimization algorithm is mainly to select the next node according to a probability formula until the next node reaches a target node; when all ants complete a search process, a loop iteration is completed; and when one cycle is finished, updating and setting the pheromone updating rule on the corresponding link until the iteration termination condition is met, solving the current optimal path set and outputting the optimal path set.
Further, the ant colony optimization algorithm for solving the load balancing model specifically comprises the following steps:
101. initializing network nodes, setting constraint conditions for links among all switch nodes and the switch nodes, and initializing parameters required in a network;
102. starting from the ant nest, namely the data sending source node, M ants judge the flow table capacity phi of the switch node uuIf the requirement of the flow table item of the data flow is met, deleting the switch nodes which do not meet the limiting conditions, deleting the links connected with the switch nodes, and selecting the next node by the kth ant according to a probability formula;
103. judging whether the next node is a destination node, if not, turning to 102, and continuing to search for the next node; if the next node is a destination node, observing whether the current ant track is in the path list, and if not, adding the path into the path list;
104. judging whether the ants finish an iterative process, if not, continuing 102; otherwise, carrying out global updating on the pheromone in the network, and continuing the next round of cyclic iteration process;
105. judging whether algorithm termination conditions are met, if so, continuing 106, otherwise, executing 102;
106. and (5) finishing the algorithm, and selecting and outputting the current optimal path set.
Further, in 101, for the links and switches between each switch nodeThe method for setting the constraint conditions by the machine nodes specifically comprises the following steps: link load constraints, i.e. limits on maximum load on a link
Figure BDA0001299652630000061
Where K denotes a request for a service flow in the network, λkRepresenting the bandwidth request for stream k,
Figure BDA0001299652630000032
representing that a service flow k passes through a link uv, c (u, v) representing the bandwidth of the link uv, theta representing the maximum link utilization in the network, and a switch node constraint, i.e. a node traffic conservation constraint
Figure BDA0001299652630000041
And node flow table capacity limits
Figure BDA0001299652630000042
Wherein phiuThe capacity of the switch node u is expressed, and an optimal path solution set that minimizes the maximum link utilization in the network is found according to the constraint conditions.
Further, the ant of step 102 selects the next node to satisfy:
Figure BDA0001299652630000043
wherein v ∈ allowedkα, gamma, kappa, three heuristic factors for adjusting the weight of the heuristic information, duv(t) is distance heuristic information, and
Figure BDA0001299652630000044
χu(t) representing the remaining space of the node u forwarding table at time t, taking
Figure BDA0001299652630000045
Wherein
Figure BDA0001299652630000046
Indicating the number of forwarding rules for node u at time t.
Further, in 104, when all ants complete one iteration, the final path set P ═ is determined (P ═ P)1，…pk，…p|k|)，pk∈Q|k|，k∈K,QkRepresenting feasible route set satisfying condition limitation and calculating link utilization rate
Figure BDA0001299652630000047
Where l represents the link (u, v), γp(l) Indicates the load of the link, order
Figure BDA0001299652630000048
After the first cycle is finished, obtaining the maximum link utilization rate according to the calculated link utilization rate and recording as α1Similarly, when ants perform the second cycle, the maximum link utilization α of the network can be obtained2If α2＜α1Then pair α2And updating the global pheromone by the corresponding link.
Further, the update rule of the global pheromone is as follows: tau isuv(t+n)＝(1-ρ)·τuv(t)+Δτuv(t) wherein the pheromone increment is represented as
Figure BDA0001299652630000049
Representing the cost of the path, Q representing the controller parameters, which the user can customize, and ρ representing the pheromone volatilization parameters.
The invention has the following advantages and beneficial effects:
on the basis of researching the topological architecture and the flow characteristics of the data center network, the invention fully utilizes the advantage of centralized control of the SDN architecture and provides a dynamic load balancing scheduling algorithm based on the link real-time load. The invention mainly has two modes for load balancing processing of the link: firstly, the controller sets a weight for a path according to the acquired state information of each link, and when the flow arrives in the network, an optimal transmission path is selected for the flow according to the weight; secondly, when the system detects that the load distribution of the links in the network is not uniform, the system schedules part of the flows on the link with the highest load onto other links so as to reduce the load on the link.
The invention provides an ant colony optimization load balancing algorithm based on an SDN. The invention firstly proposes a load balancing model, in which not only the link bandwidth capacity is limited, but also the limit of the switch flow table capacity is taken into account. Then, an ant colony optimization algorithm is provided to solve the model. The ant colony optimization algorithm is mainly used for calculating the probability of the corresponding node when the next node is selected and setting the pheromone updating rule on the corresponding link when one cycle is finished.
Drawings
Fig. 1 is a flow chart of an SDN-based ant colony optimization load balancing routing algorithm provided by a preferred embodiment of the present invention;
FIG. 2 is a comparison graph of transmission success rates of the ACLB algorithm, the PDMF algorithm and the GDMR algorithm provided by the present invention;
FIG. 3 is a comparison graph of the maximum link utilization of the ACLB algorithm, the PDMF algorithm and the GDMR algorithm provided by the present invention;
fig. 4 is a diagram comparing the number of entries of the switch flow table of the ACLB algorithm, PDMF algorithm and GDMR algorithm according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail and clearly with reference to the accompanying drawings. The described embodiments are only some of the embodiments of the present invention.
The technical scheme for solving the technical problems is as follows:
fig. 1 is a flowchart of an ant colony optimization load balancing routing algorithm based on SDN according to the present invention, which specifically includes:
the first step is as follows: initializing network nodes, setting constraint conditions for links among all switch nodes and the switch nodes, and initializing parameters required in a network;
the constraint conditions are a link load constraint and a switch node constraint. Limitation of maximum load on a link
Figure BDA0001299652630000061
Where K denotes a request for a service flow in the network, λkRepresenting the bandwidth request for stream k,
Figure BDA0001299652630000062
representing that the traffic flow k passes through the link uv, c (u, v) representing the bandwidth of the link uv, and θ representing the maximum link utilization in the network. Switch node constraints, i.e. node traffic conservation constraints
Figure BDA0001299652630000063
And node flow table capacity limits
Figure BDA0001299652630000064
Wherein phiuRepresenting the capacity of switch node u. According to the constraint conditions, an optimal path solution set is solved which minimizes the maximum link utilization in the network.
The second step is that: starting from an ant nest (a data sending source node), M ants judge the flow table capacity phi of a switch node uuIf the requirement of the flow table item of the data flow is met, deleting the switch nodes which do not meet the limiting conditions, deleting the links connected with the switch nodes, and selecting the next node by the kth ant according to a probability formula;
the ant selects the next node to meet the following requirements:
Figure BDA0001299652630000066
wherein v ∈ allowedkα, gamma, kappa, three heuristic factors for adjusting the weight of the heuristic information, duv(t) is distance heuristic information, and
Figure BDA0001299652630000067
χu(t) representing the remaining space of the node u forwarding table at time t, taking
Figure BDA0001299652630000068
Wherein
Figure BDA0001299652630000069
Indicating the number of forwarding rules for node u at time t.
The third step: judging whether the next node is a destination node, if not, turning to the second step, and continuously searching the next node; if the next node is a destination node, observing whether the current ant track is in the path list, and if not, adding the path into the path list;
the fourth step: judging whether the ants finish the iteration process once or not, if not, continuing the second step; otherwise, carrying out global updating on the pheromone in the network, and continuing the next round of cyclic iteration process;
when all ants complete one iteration, find the final path set p ═ p (p)1，…pk，…p|k|)，pk∈Q|k|， k∈K,QkRepresenting feasible route set satisfying condition limitation and calculating link utilization rate
Figure BDA0001299652630000071
Where l represents the link (u, v), γp(l) Indicates the load of the link, order
Figure BDA0001299652630000072
After the first cycle is finished, obtaining the maximum link utilization rate according to the calculated link utilization rate and recording as α1Similarly, when ants perform the second cycle, the maximum link utilization α of the network can be obtained2If α2＜α1Then pair α2And updating the global pheromone by the corresponding link, wherein the updating rule is as follows: tau isuv(t+n)＝(1-ρ)·τuv(t)+Δτuv(t) wherein the pheromone increment is represented as
Figure BDA0001299652630000073
costuvRepresents the overhead of path uv, and Q is 1 and ρ is 0.3.
The fifth step: judging whether the algorithm termination conditions are met, if so, continuing the sixth step, otherwise, executing the second step;
the termination condition is recorded as the maximum number of iterations set by the invention.
And a sixth step: and (5) finishing the algorithm, and selecting and outputting the current optimal path set.
The performance of the ACLB algorithm provided by the invention is compared and analyzed, and three network performance indexes of average transmission delay, link bandwidth utilization rate and load distribution are used for comparing with PDMF and GDMR algorithms.
In this embodiment, fig. 2 is a graph comparing the transmission success rates of the ACLB algorithm, the PDMF algorithm and the GDMR algorithm according to the present invention. As can be seen from fig. 2: compared with the average time delay obtained by the PDMF algorithm and the GDMR algorithm, the ACLB algorithm of the implementation method is more stable and smaller. Because the ACLB algorithm not only considers the link load when transmitting the data flow, the possibility of congestion of the network is effectively reduced, but also considers the limitation of the flow table capacity of the switch when finding the next switch by adopting the probability from the source node to the destination node, thereby improving the throughput of the network. The transmission success rate of the GDMR is lower than that of the PDMR because the GDMR uses the split data stream to realize load balance of the network, and the split data stream will generate a large amount of packet loss, so that the received data stream is far smaller than the size of the data stream during transmission, thereby greatly reducing the network transmission success rate.
In this embodiment, fig. 3 shows a maximum link utilization ratio comparison graph of the ACLB algorithm, the PDMF algorithm and the GDMR algorithm according to the present invention. As can be seen from fig. 3: the maximum link utilization rate of the ACLB algorithm of the implementation method is lower than that of the PDMF algorithm and the GDMR algorithm. When the PDMR transmits data flow, the limitation of the memory of the flow table of the switch is emphatically considered, so that the possibility of congestion in the network is increased; the ACLB algorithm is that under the same load condition, the maximum link utilization rate is the minimum, i.e. the probability of network congestion is the lowest (when the maximum link utilization rate in the network reaches 100%, the network congestion can be considered to occur), and the performance of the network is also the optimal compared with the GDMP and the PDMF.
In this embodiment, fig. 4 is a diagram comparing the number of flow table entries of the ACLB algorithm and the PDMF and GDMR algorithms proposed by the present invention. As can be seen from fig. 4: compared with the PDMF algorithm and the GDMR algorithm, the ACLB algorithm of the implementation method is more uniform in distribution of the number of switch flow table items. The GDMR algorithm does not consider the limitation of the flow table capacity, so that the switch flow table resource is unevenly used, the flow tables of the switches 2, 3, 6 and 8 are used by about 93 percent of the capacity of the flow table, even the switch 6 has the flow table rule exceeding the maximum capacity of the flow table, and the flow table rule in the switches 9 and 10 occupies about 15 percent of the capacity of the flow table; when the ACLB algorithm selects the next switch according to the probability, the surplus capacity of the switch flow table is taken as one heuristic factor, the more the surplus capacity of the switch flow table is, the greater the probability of the next hop selected to transmit the data flow is, thereby effectively avoiding the flow table rule generated in the switch from exceeding the maximum capacity of the flow table, and being capable of uniformly using the flow table resources in each switch.
The above examples are to be construed as merely illustrative and not limitative of the remainder of the disclosure. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.

Claims (1)

1. An ant colony optimization load balancing routing algorithm based on an SDN (software defined network), which is characterized by comprising the following steps:
firstly, acquiring state information of each link in an SDN network, and establishing a load balancing model, wherein the optimization aim is to minimize the maximum link utilization rate in the network, namely, the flow passing through the network is approximately and uniformly distributed on each link in time;
then, an ant colony optimization algorithm is provided to solve the load balancing model, and the ant colony optimization algorithm is mainly to select the next node according to a probability formula until the next node reaches a target node; when all ants complete a search process, a loop iteration is completed; when one cycle is finished, updating and setting the pheromone updating rule on the corresponding link, and solving and outputting the current optimal path set until the iteration termination condition is met;
the method for solving the load balancing model by the ant colony optimization algorithm specifically comprises the following steps:
101. initializing network nodes, setting constraint conditions for links among all switch nodes and the switch nodes, and initializing parameters required in a network;
102. starting from the ant nest, namely the data sending source node, M ants judge the flow table capacity phi of the switch node uuIf the requirement of the flow table item of the data flow is met, deleting the switch nodes which do not meet the limiting conditions, deleting the links connected with the switch nodes, and selecting the next node by the kth ant according to a probability formula;
103. judging whether the next node is a destination node, if not, turning to 102, and continuing to search for the next node; if the next node is a destination node, observing whether the current ant track is in the path list, and if not, adding the path into the path list;
104. judging whether the ants finish an iterative process, if not, continuing 102; otherwise, carrying out global updating on the pheromone in the network, and continuing the next round of cyclic iteration process;
105. judging whether algorithm termination conditions are met, if so, continuing 106, otherwise, executing 102;
106. after the algorithm is finished, selecting and outputting the current optimal path set;
in 101, setting constraint conditions for links between each switch node and each switch node specifically includes: link load constraints, i.e. limits on maximum load on a link
Figure FDA0002438528330000021
Where K denotes a request for a service flow in the network, λkRepresenting the bandwidth request for stream k,
Figure FDA0002438528330000022
representing a traffic flow k via a link uv, c (u, v) representingThe bandwidth of the link uv, θ represents the maximum link utilization in the network, the switch node constraint, i.e., the node traffic conservation constraint
Figure FDA0002438528330000023
And node flow table capacity limits
Figure FDA0002438528330000024
Wherein phiuRepresenting the capacity of a switch node u, and solving an optimal path solution set which minimizes the maximum link utilization rate in the network according to constraint conditions;
the ant selects the next node to satisfy in step 102:
Figure FDA0002438528330000025
Figure FDA0002438528330000026
wherein v ∈ allowedkα, gamma, kappa, three heuristic factors for adjusting the weight of the heuristic information, duv(t) is distance heuristic information, and
Figure FDA0002438528330000027
χu(t) representing the remaining space of the node u forwarding table at time t, taking
Figure FDA0002438528330000028
Wherein
Figure FDA0002438528330000029
The number of forwarding rules of the node u at the time t is represented;
in 104, when all ants complete one iteration, the final path set P ═ is determined (P)1,…pk,…p|k|),pk∈Q|k|，k∈K,QkRepresenting feasible route set satisfying condition limitation and calculating link utilization rate
Figure FDA00024385283300000210
Where l represents the link (u, v), γp(l) Indicates the load of the link, order
Figure FDA00024385283300000211
After the first cycle is finished, obtaining the maximum link utilization rate according to the calculated link utilization rate and recording as α1Similarly, when ants perform the second cycle, the maximum link utilization α of the network can be obtained2If α2＜α1Then pair α2Updating global pheromone by the corresponding link;
the update rule of the global pheromone is as follows: tau isuv(t+n)＝(1-ρ)·τuv(t)+Δτuv(t) wherein the pheromone increment is represented as
Figure FDA0002438528330000031
Representing the cost of the path, Q representing the controller parameters, which the user can customize, and ρ representing the pheromone volatilization parameters.
CN201710358160.7A 2017-05-19 2017-05-19 Ant colony optimization load balancing routing algorithm based on SDN Active CN107094115B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710358160.7A CN107094115B (en) 2017-05-19 2017-05-19 Ant colony optimization load balancing routing algorithm based on SDN

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710358160.7A CN107094115B (en) 2017-05-19 2017-05-19 Ant colony optimization load balancing routing algorithm based on SDN

Publications (2)

Publication Number Publication Date
CN107094115A CN107094115A (en) 2017-08-25
CN107094115B true CN107094115B (en) 2020-06-16

Family

ID=59638867

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710358160.7A Active CN107094115B (en) 2017-05-19 2017-05-19 Ant colony optimization load balancing routing algorithm based on SDN

Country Status (1)

Country Link
CN (1) CN107094115B (en)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107579923B (en) * 2017-09-18 2019-12-10 迈普通信技术股份有限公司 Link load balancing method of SDN and SDN controller
CN107454630B (en) * 2017-09-25 2021-02-02 中国联合网络通信集团有限公司 Load balancing method and load balancing router
CN113098773B (en) * 2018-03-05 2022-12-30 华为技术有限公司 Data processing method, device and system
CN108512772B (en) * 2018-03-09 2021-07-16 重庆邮电大学 Data center flow scheduling method based on service quality
CN109039897B (en) * 2018-07-20 2020-12-01 南京邮电大学 Software defined backhaul network routing method based on service awareness
CN110730131B (en) * 2019-10-22 2020-07-17 电子科技大学 SDN satellite network multi-QoS constraint routing method based on improved ant colony
CN112311670B (en) * 2019-12-04 2024-01-26 重庆邮电大学 Software defined network machine learning route optimization method
EP3869752B1 (en) * 2020-02-24 2024-02-14 Moxa Inc. Device for handling routing paths for streams in a time-sensitive networking network
CN112149788B (en) * 2020-09-28 2023-04-07 复旦大学 Minimum overhead route generation method based on ant colony algorithm
CN113068224B (en) * 2021-03-29 2022-10-21 烽火通信科技股份有限公司 Ant colony algorithm implementation method and device for constructing mesh transmission system
CN113542121B (en) * 2021-07-05 2022-07-15 浙江大学 Tree-shaped data center link layer load balancing routing method based on annealing method
CN115499306B (en) * 2022-07-29 2024-03-12 天翼云科技有限公司 Method and device for constructing flow scheduling model, electronic equipment and storage medium
CN115499376B (en) * 2022-07-29 2024-01-02 天翼云科技有限公司 Load balancing method, system, electronic equipment and storage medium
CN115426360B (en) * 2022-08-09 2023-09-19 徐州医科大学 Hierarchical self-adaptive load balancing method and system based on graph theory

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6687222B1 (en) * 1999-07-02 2004-02-03 Cisco Technology, Inc. Backup service managers for providing reliable network services in a distributed environment
CN105791117A (en) * 2016-03-21 2016-07-20 广东科学技术职业学院 QoSR fast solving method based on ant colony algorithm
CN105847151A (en) * 2016-05-25 2016-08-10 安徽大学 Multi-constrained QoS (Quality of Service) routing strategy designing method for software defined network
CN106230716A (en) * 2016-07-22 2016-12-14 江苏省电力公司信息通信分公司 A kind of ant group algorithm and power telecom network communication service intelligent allocation method
CN106572513A (en) * 2016-10-17 2017-04-19 宁波深路信息科技有限公司 Wireless sensor routing algorithm based on fuzzy multi-attribute decision

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10097372B2 (en) * 2014-01-09 2018-10-09 Ciena Corporation Method for resource optimized network virtualization overlay transport in virtualized data center environments

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6687222B1 (en) * 1999-07-02 2004-02-03 Cisco Technology, Inc. Backup service managers for providing reliable network services in a distributed environment
CN105791117A (en) * 2016-03-21 2016-07-20 广东科学技术职业学院 QoSR fast solving method based on ant colony algorithm
CN105847151A (en) * 2016-05-25 2016-08-10 安徽大学 Multi-constrained QoS (Quality of Service) routing strategy designing method for software defined network
CN106230716A (en) * 2016-07-22 2016-12-14 江苏省电力公司信息通信分公司 A kind of ant group algorithm and power telecom network communication service intelligent allocation method
CN106572513A (en) * 2016-10-17 2017-04-19 宁波深路信息科技有限公司 Wireless sensor routing algorithm based on fuzzy multi-attribute decision

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
An ACO-based Link Load-Balancing Algorithm in SDN;Chunzhi Wang;Gang Zhang;Hui Xu;Hongwei Chen;《 2016 7th International Conference on Cloud Computing and Big Data (CCBD)》;20161108;214-218 *
Maximizing Network Utilization for SDN Based on WiseAnt Colony Optimization;Shanwen Yi;Hua Wang;Xibo Yao;Chuangen Gao;Linbo Zhai;《 2016 IEEE 18th International Conference on High Performance Computing and Communications》;20170126;959-966 *
基于蚁群算法SDN负载均衡的研究;魏凯;《中国优秀硕士学位论文全文数据库（电子期刊）》;20150831;全文 *

Also Published As

Publication number Publication date
CN107094115A (en) 2017-08-25

Similar Documents

Publication Publication Date Title
CN107094115B (en) Ant colony optimization load balancing routing algorithm based on SDN
Jimenez et al. On the controller placement for designing a distributed SDN control layer
CN109257287B (en) Shortest path determining method and controller
KR101809779B1 (en) Automated traffic engineering for 802.1aq based upon the use of link utilization as feedback into the tie-breaking mechanism
US9401868B2 (en) Method of traffic engineering for provisioning routing and storage in content-oriented networks
Zhang et al. Delay-optimized multicast tree packing in software-defined networks
CN105357124B (en) A kind of MapReduce bandwidth optimization methods
US10237194B2 (en) Maximize network capacity policy with heavy-tailed traffic
Liu Intelligent routing based on deep reinforcement learning in software-defined data-center networks
CN109379230B (en) Service function chain deployment method based on breadth-first search
CN109151077B (en) Calculation unloading method based on target guidance
Xiaolong et al. MTSS: multi-path traffic scheduling mechanism based on SDN
CN114071582A (en) Service chain deployment method and device for cloud-edge collaborative Internet of things
Li et al. Content popularity and node level matched based probability caching for content centric networks
Maity et al. DART: Data plane load reduction for traffic flow migration in SDN
CN110621052B (en) Multipath routing optimization method
Iosifidis et al. The impact of storage capacity on end-to-end delay in time varying networks
CN112637061B (en) Dynamic multi-factor path calculation method based on heuristic algorithm
Pu ProNDN: MCDM‐Based Interest Forwarding and Cooperative Data Caching for Named Data Networking
Wu et al. Routing policy for balanced management of slices using flexible Ethernet
Yao et al. A novel joint adaptive forwarding and resource allocation strategy for named data networking based on SMDP
Hayamizu et al. On-demand routing for chaining multiple functions in ICN-based in-network processing
CN115037399A (en) Message forwarding method, electronic device and storage medium
Jingwen et al. A traffic scheduling scheme for data center networks based on sdn
Wang et al. Resource allocation for data-parallel computing in networks with data locality

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