CN107094115A - A kind of ant group optimization Load Balance Routing Algorithms based on SDN - Google Patents
A kind of ant group optimization Load Balance Routing Algorithms based on SDN Download PDFInfo
- Publication number
- CN107094115A CN107094115A CN201710358160.7A CN201710358160A CN107094115A CN 107094115 A CN107094115 A CN 107094115A CN 201710358160 A CN201710358160 A CN 201710358160A CN 107094115 A CN107094115 A CN 107094115A
- Authority
- CN
- China
- Prior art keywords
- link
- node
- ant
- network
- sdn
- 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
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]
Abstract
A kind of ant group optimization Load Balance Routing Algorithms based on SDN are claimed in the present invention, including:Each link-state information in SDN is obtained first, a kind of Load Balancing Model is set up, and in the Load Balancing Model, not only link bandwidth capacity is limited, while being additionally contemplates that the limitation of interchanger flow table capacity;Then, propose that a kind of ant colony optimization algorithm solves Load Balancing Model, carried ant colony optimization algorithm mainly selects next node according to new probability formula and determines whether destination node, when terminating one cycle, setting is updated to the pheromone updating rule in respective link, until when meeting stopping criterion for iteration, solving current best path collection and merging output.The present invention is distributed on each link with not only making the uniform flow in network, while also efficiently avoid the excessive flow table rule of generation and cause interchanger flow table insufficient space.
Description
Technical field
The invention belongs to the load balancing route technology in SDN, it is proposed that a kind of ant group optimization load based on SDN
Proportional routing algorithm.
Background technology
Under SDN frameworks, the controller concentrated in logic can obtain the essential information in interchanger and path, according to operation
Business is intended to and the essential information of network calculates suitable data flow path, and corresponding forwarding rule then is issued into corresponding friendship
Change planes.Forwarding rule in SDN switch is stored in the limited Ternary Content Addressable Memory (Ternary of size
Content Addressable Memory, TCAM) in, it supports fast parallel inquiry to wildcard pattern, and it only can be with
Thousands of rules are preserved, because its very expensive and power consumption.The actual importance of limitation flow table size is recognized by ASCII industry
Can.There is existing business OpenFlow interchangers TCAM size can only store about 1500 OpenFlow forwarding rule
Then, because they are longer than standard switchboard forwarding stream entry.Therefore, SDN is applied becomes more challenging in catenet.
In order to avoid congestion, it would be desirable to ensure that the bandwidth of data flow transmission route meets data flow requirements.From the point of view of interchanger,
The size of flow table is another constraint.Once reaching the limitation of interchanger flow table, interchanger will be refused to install more forwarding rule
Then, this can cause forwarded mistake.Therefore, bandwidth usage and flow table are using being closely related.Selection forwarding packet path
The load balancing of consideration link is not only needed, also needs to consider the limitation of flow table capacity in interchanger on path.
Lan Y L et al. exist《2016International Symposium on Communication Systems,
2013:25-28》On deliver entitled " Dynamic load-balanced path optimization in SDN-based
Data center networks " article.This article proposes a kind of dynamic load leveling path optimization (DLPO) of proposition and calculated
Method.Carried DLPO algorithms can change the path of stream during streaming, realize the load balancing between different links.In addition,
Also propose the more new strategy of the flow table based on priority, with ensure in underloading path be associated interchanger all flow tables by into
When work(updates, the data flow of congestion path is successfully redirected underloading path to avoid dividing caused by the path of stream changes
Group is lost.This scheme only accounts for the load of link.
J.Li et al. exists《2014IEEE Networking IEEE/ACM Transactions on,2014:2787 -
2805》On deliver entitled " Load Balancing in IP Networks Using Generalized Destination-
Based Multipath Routing " article.This article broad sense destination Multi-path route (GDMR) realizing route is loaded
Equilibrium, realizes that a certain proportion of data flow segmentation realizes that the load distribution of network is equal by data flow according to the remaining bandwidth in path
It is even.This scheme can also be realized in the central controller of the global view with whole network, and SDN is one and is especially suitable for
The platform of their schemes in real time.But this scheme only considered the load of link.
Zhang H et al. exist《2014Conference on Computer Communications.IEEE, 2014:
13-18.》On deliver entitled " On the effect of forwarding table size on SDN network
Utilization " article.This article proposes path degree maximum-flow algorithm (PDMF).By limiting each node in network
Maximum path number model, maximum limit while target is to meet link limited bandwidth capability and node path grade
Improve the number of feasible flow in network in degree ground.This scheme is by limiting the maximum path number of node to ensure stream preferential in network
Table can not ensure link in network load balancing to be difficult to avoid that the generation of network congestion without departing from its capacity.
From related research, current load balancing scheme is mainly the loading condition of consideration link, may be due to
The finiteness of interchanger flow table causes the generation of the unsuccessful phenomenon of transmitting data stream in network.The present invention is negative according to link in network
Load situation and the limited flow table of interchanger, are that complicated equalization problem models and proposes a kind of ant colony optimization algorithm in SDN
Solve problem of load balancing.
The content of the invention
Present invention seek to address that above problem of the prior art.Propose a kind of generation for avoiding network congestion based on
SDN ant group optimization Load Balance Routing Algorithms.Technical scheme is as follows:
A kind of ant group optimization Load Balance Routing Algorithms based on SDN, it comprises the following steps:
Each link-state information in SDN is obtained first, sets up a kind of Load Balancing Model, its optimization aim is to make net
Maximum link utilization in network is minimized, i.e., make to be distributed generally evenly in each link by the flow in network in time
On.In the Load Balancing Model, not only link bandwidth capacity is limited, while being additionally contemplates that the limit of interchanger flow table capacity
System;
Then, propose that a kind of ant colony optimization algorithm solves Load Balancing Model, put forward ant colony optimization algorithm mainly basis
New probability formula selection next node is until reach destination node;When all ants complete a search procedure, that is, complete one
Secondary loop iteration;When terminating one cycle, setting is updated to the pheromone updating rule in respective link, changed until meeting
During for end condition, solve current best path collection and merge output.
Further, the ant colony optimization algorithm solves Load Balancing Model and specifically includes following steps:
101st, the initialization of network node, is that the link and telephone net node between each telephone net node set constraint bar
Part, and initialize parameter needed for network;
102nd, M ant is to send data source nodes from ant nest, judges telephone net node u flow table capacity φuIt is
The no flow table item demand for meeting data flow, the telephone net node for being unsatisfactory for qualifications is deleted, the link being connected with this is also deleted
Remove, kth ant selects next node according to new probability formula;
Whether be purpose node, if not destination node, then go to 102, continually look for if the 103rd, judging next node
Next node;If next node is destination node, current ant track is observed whether in path list, if not
In path list, then this path is added in routing table;
104th, judge whether ant all completes an iteration process, if not, continuing 102;Otherwise, to the information in network
Element carries out global renewal, continues the loop iteration process of next round;
105th, judge whether all to meet algorithm end condition, if meeting end condition, continue 106, otherwise, hold
Row 102;
106th, algorithm terminates, and selects current best path collection and merges output.
Further, it is that the link and telephone net node between each telephone net node set constraints, tool in 101
Body includes:Limitation of the link load constraint i.e. to maximum load on linkWherein K tables
Show the traffic request in network, λkStream k bandwidth request is represented,Represent that Business Stream k represents chain by link uv, c (u, v)
Road uv bandwidth, θ represents the maximum link utilization in network, telephone net node constraint, i.e. node flow conservation constraintsWith node flow table capacity limitWherein φuTable
Show telephone net node u capacity, according to constraints, obtain the optimal path for minimizing the maximum link utilization in network
Disaggregation.
Further, the step 102 ant selection next node needs to meet:
Wherein, v ∈ allowedk, alpha, gamma, κ represents three heuristic greedy methods, the weight for adjusting heuristic information;duv
(t) it is, apart from heuristic information, to takeχu(t) remaining space in t node u forward tables is represented,
TakeWhereinRepresent the regular number of forwarding in t node u.
Further, it is described in 104, when all ants complete an iteration after, obtain final path set P=
(p1... pk... p|k|), pk∈Q|k|, k ∈ K, QkRepresent to meet the feasible set of routes that condition is limited, and calculate link utilizationWherein l represents link (u, v), γp(l) load of link, order are representedAfter circulation terminates for the first time, according to the link utilization calculated
Show that maximum link utilization is designated as α1, similarly, when ant carries out second of circulation, the maximum link that can obtain network is utilized
Rate α2If, α2< α1, then to α2Corresponding link carries out the renewal of global information element.
Further, the renewal rule of the global information element is:τuv(t+n)=(1- ρ) τuv(t)+Δτuv(t), its
In, pheromones incremental representation isThe expense in path is represented, Q represents controller parameter, and user can make by oneself
Justice, ρ represents the parameter of pheromones volatilization.
Advantages of the present invention and have the beneficial effect that:
The present invention takes full advantage of SDN framves on the basis of the topological structure and traffic characteristic of data central site network
A kind of advantage of the centerized fusion of structure, it is proposed that dynamic load leveling dispatching algorithm based on link real time load.The present invention
Mainly there is two ways for the load balance process of link:One is that controller is path according to each link-state information of acquisition
One weight is set, is then stream one optimal transmission paths of selection according to weight size when there is flow arrival in network;Two are
When system detectio to link in network load distribution and it is uneven when, then the part stream on highest loaded link is dispatched to it
On his link, to reduce the load on the link.
The present invention proposes a kind of ant group optimization load-balancing algorithm based on SDN.Present invention firstly provides one kind load
Equilibrium model, in the model, is not only limited link bandwidth capacity, while being additionally contemplates that the limitation of interchanger flow table capacity.
Then, propose that a kind of ant colony optimization algorithm solves above-mentioned model.When carried ant colony optimization algorithm is mainly selection next node
Calculating to respective nodes probability and setting when terminating one cycle to the pheromone updating rule in respective link.
Brief description of the drawings
Fig. 1 is the stream that the present invention provides the ant group optimization Load Balance Routing Algorithms based on SDN that preferred embodiment is provided
Cheng Tu;
Fig. 2 is the transmission success rate comparison diagram of ACLB algorithms proposed by the present invention and PDMF, GDMR algorithm;
Fig. 3 is the maximum link utilization comparison diagram of ACLB algorithms proposed by the present invention and PDMF, GDMR algorithm;
Fig. 4 is that the interchanger flow table item quantitative comparison of ACLB algorithms proposed by the present invention and PDMF, GDMR algorithm schemes.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, detailed
Carefully describe.Described embodiment is only a part of embodiment of the present invention.
The present invention solve above-mentioned technical problem technical scheme be:
Fig. 1 show the flow chart of the ant group optimization Load Balance Routing Algorithms proposed by the present invention based on SDN, specific bag
Include:
The first step:The initialization of network node, is that the link and telephone net node between each telephone net node set constraint
Condition, and initialize parameter needed for network;
Constraints described above is link load constraint and telephone net node constraint.Limitation to maximum load on linkWherein K represents the traffic request in network, λkStream k bandwidth request is represented,Represent that Business Stream k represents link uv bandwidth by link uv, c (u, v), θ represents the maximum link utilization in network.
Telephone net node is constrained, i.e. node flow conservation constraintsWith node flow table
Capacity limitWherein φuRepresent telephone net node u capacity.According to constraints, obtaining makes in network
Maximum link utilization minimize optimal path disaggregation.
Second step:From ant nest, (the transmission data source nodes) judges telephone net node u flow table capacity φ to M antu
The flow table item demand of data flow whether is met, the telephone net node for being unsatisfactory for qualifications is deleted, the link being connected with this
Delete, kth ant selects next node according to new probability formula;
Ant selection next node needs to meet:
Wherein, v ∈ allowedk, alpha, gamma, κ represents three heuristic greedy methods, the weight for adjusting heuristic information;duv
(t) it is, apart from heuristic information, to takeχu(t) remaining space in t node u forward tables is represented,
TakeWhereinRepresent the regular number of forwarding in t node u.
3rd step:Whether be purpose node, if not destination node, then go to second step if judging next node, after
It is continuous to find next node;If next node is destination node, current ant track is observed whether in path list,
If not in path list, this path be added in routing table;
4th step:Judge whether ant all completes an iteration process, if not, continuing second step;Otherwise, in network
Pheromones carry out global renewal, continue the loop iteration process of next round;
After all ants complete an iteration, final path collection p=(p are obtained1... pk... p|k|), pk∈Q|k|, k
∈K,QkRepresent to meet the feasible set of routes that condition is limited, and calculate link utilizationIts
Middle l represents link (u, v), γp(l) load of link, order are represented
After circulation terminates for the first time, show that maximum link utilization is designated as α according to the link utilization calculated1, similarly, enter in ant
During second of circulation of row, the maximum link utilization α of network can obtain2If, α2< α1, then to α2Corresponding link carries out global
The renewal of pheromones, updating rule is:τuv(t+n)=(1- ρ) τuv(t)+Δτuv(t), wherein, pheromones incremental representation iscostuvExpression path uv expense, and Q=1, ρ=0.3.
5th step:Judgement is all to meet algorithm end condition, if meeting end condition, continues the 6th step, otherwise
Words, perform second step;
Affiliated end condition is designated as reaching the maximum iteration set by the present invention.
6th step:Algorithm terminates, and selects current best path collection and merges output.
Performance to ACLB algorithms proposed by the present invention is contrasted and analyzed, and uses mean transit delay, link bandwidth
Three network performance indexes of utilization rate and load distribution are contrasted with PDMF, GDMR algorithm.
In the present embodiment, Fig. 2 provides the transmission success rate contrast that the present invention carries ACLB algorithms and PDMF, GDMR algorithm
Figure.As seen from Figure 2:Carried implementation ACLB algorithms are more stable compared with the average delay obtained by PDMF algorithms and GDMR algorithms
And it is smaller.Due to the link load that ACLB algorithms not only consider in transmitting data stream, effectively reduce network and produce congestion
Possibility, and interchanger flow table capacity is considered when looking for next interchanger using probability from source node to destination node
Limitation, so as to improve the handling capacity of network.GDMR transmission success rate will be less than PDMR transmission success rate, because
GDMR realizes the load balancing of network using splitting traffic, and splitting traffic can produce substantial amounts of packet loss, be connect so as to cause
The data stream size when data flow received is much smaller than transmission, so as to greatly reduce network transmission success rate.
In the present embodiment, Fig. 3 provides the maximum link utilization that the present invention carries ACLB algorithms and PDMF, GDMR algorithm
Comparison diagram.As seen from Figure 3:The maximum link utilization of carried implementation ACLB algorithms is less than PDMF algorithms and GDMR algorithms.
Because PDMR considers the limitation of interchanger flow table internal memory in transmitting data stream, emphatically, gathered around so as to increase in network
Fill in the possibility of phenomenon;ACLB algorithms are that under equal loading condition, compared with GDMP, PDMF, maximum link utilization is minimum
The possibility for occurring network congestion is minimum (when the maximum link utilization in network reaches 100% it is believed that being sent out in network
Raw congestion), the performance of network is also optimal.
In the present embodiment, Fig. 4 provides the flow table item number contrast that the present invention carries ACLB algorithms and PDMF, GDMR algorithm
Figure.As seen from Figure 4:Carried implementation ACLB algorithms are compared with the interchanger flow table item number obtained by PDMF algorithms and GDMR algorithms
Mesh is more evenly distributed.GDMR algorithms do not account for the limitation of flow table capacity, so that it is uneven to cause interchanger flow table resource to use,
The flow table of interchanger 2,3,6,8 using 93% or so of the up to capacity of flow table, or even interchanger 6 there occurs flow table rule beyond
The maximum capacity of flow table, and flow table rule takes 15% or so of flow table capacity in interchanger 9,10;ACLB algorithms pass through probability
When selecting next interchanger, it is contemplated that the residual capacity of interchanger flow table is used as one of heuristic greedy method, interchanger stream
The residual capacity of table is more, and the next-hop probability for being selected as transmitting data stream is bigger, so as to effectively avoid in interchanger
The flow table rule of generation exceeds flow table maximum capacity, can uniformly use the flow table resource in respective switch.
The above embodiment is interpreted as being merely to illustrate the present invention rather than limited the scope of the invention.
After the content for the record for having read the present invention, technical staff can make various changes or modifications to the present invention, these equivalent changes
Change and modification equally falls into the scope of the claims in the present invention.
Claims (6)
1. a kind of ant group optimization Load Balance Routing Algorithms based on SDN, it is characterised in that comprise the following steps:
Each link-state information in SDN is obtained first, sets up a kind of Load Balancing Model, its optimization aim is made in network
Maximum link utilization minimize, i.e., make to be distributed generally evenly on each link by the flow in network in time,
In the Load Balancing Model, not only link bandwidth capacity is limited, while being additionally contemplates that the limitation of interchanger flow table capacity;
Then, propose that a kind of ant colony optimization algorithm solves Load Balancing Model, carry ant colony optimization algorithm mainly according to probability
Formula selection next node is until reach destination node;When all ants complete a search procedure, that is, complete once to follow
Ring iterative;When terminating one cycle, setting is updated to the pheromone updating rule in respective link, until it is whole to meet iteration
Only during condition, solve current best path collection and merge output.
2. the ant group optimization Load Balance Routing Algorithms according to claim 1 based on SDN, it is characterised in that the ant
Colony optimization algorithm solves Load Balancing Model and specifically includes following steps:
101st, the initialization of network node, is that the link and telephone net node between each telephone net node set constraints, and
Initialize parameter needed for network;
102nd, M ant is to send data source nodes from ant nest, judges telephone net node u flow table capacity φuWhether meet
The flow table item demand of data flow, the telephone net node for being unsatisfactory for qualifications is deleted, the link being connected with this is also deleted, kth
Ant selects next node according to new probability formula;
Whether be purpose node, if not destination node, then go to 102, continually look for next if the 103rd, judging next node
Individual node;If next node is destination node, current ant track is observed whether in path list, if Bu roads
In the list of footpath, then this path is added in routing table;
104th, judge whether ant all completes an iteration process, if not, continuing 102;Otherwise, the pheromones in network are entered
The global loop iteration process for updating, continuing next round of row;
105th, judge whether all to meet algorithm end condition, if meeting end condition, continue 106, otherwise, perform
102;
106th, algorithm terminates, and selects current best path collection and merges output.
3. the ant group optimization Load Balance Routing Algorithms according to claim 2 based on SDN, it is characterised in that in 101,
It is that the link between each telephone net node and telephone net node set constraints, specifically includes:Link load constraint is i.e. to link
The limitation of upper maximum loadWherein K represents the traffic request in network, λkRepresent stream
K bandwidth request,Represent that Business Stream k represents link uv bandwidth by link uv, c (u, v), θ represents the maximum chain in network
Road utilization rate, telephone net node constraint, i.e. node flow conservation constraints
With node flow table capacity limitWherein φuTelephone net node u capacity is represented, according to constraints, is asked
The optimal path disaggregation that the maximum link utilization sent as an envoy in network is minimized.
4. the ant group optimization Load Balance Routing Algorithms according to claim 2 based on SDN, it is characterised in that described
Step 102 ant selection next node needs to meet:
Wherein, v ∈ allowedk, alpha, gamma, κ represents three heuristic greedy methods, the weight for adjusting heuristic information;duv(t)
Apart from heuristic information, to takeχu(t) remaining space in t node u forward tables is represented, is takenWhereinRepresent the regular number of forwarding in t node u.
5. the ant group optimization Load Balance Routing Algorithms according to claim 4 based on SDN, it is characterised in that it is described
In 104, after all ants complete an iteration, final path set P=(p are obtained1,…pk,…p|k|),pk∈Q|k|, k
∈K,QkRepresent to meet the feasible set of routes that condition is limited, and calculate link utilizationWherein
L represents link (u, v), γp(l) load of link, order are representedThe
After one cycle terminates, show that maximum link utilization is designated as α according to the link utilization calculated1, similarly, carried out in ant
During second of circulation, the maximum link utilization α of network can obtain2If, α2< α1, then to α2Corresponding link carries out global letter
Cease the renewal of element.
6. the ant group optimization Load Balance Routing Algorithms according to claim 5 based on SDN, it is characterised in that described complete
Office pheromones renewal rule be:τuv(t+n)=(1- ρ) τuv(t)+Δτuv(t), wherein, pheromones incremental representation isThe expense in path is represented, Q represents controller parameter, user can be with self-defined, and ρ represents that pheromones are volatilized
Parameter.
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 true CN107094115A (en) | 2017-08-25 |
CN107094115B 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) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107454630A (en) * | 2017-09-25 | 2017-12-08 | 中国联合网络通信集团有限公司 | Load-balancing method and load balancing router |
CN107579923A (en) * | 2017-09-18 | 2018-01-12 | 迈普通信技术股份有限公司 | The balancing link load method and SDN controllers of a kind of SDN |
CN108512772A (en) * | 2018-03-09 | 2018-09-07 | 重庆邮电大学 | Quality-of-service based data center's traffic scheduling method |
CN109039897A (en) * | 2018-07-20 | 2018-12-18 | 南京邮电大学 | A kind of software definition backhaul network method for routing based on service-aware |
CN110233798A (en) * | 2018-03-05 | 2019-09-13 | 华为技术有限公司 | Data processing method, apparatus and system |
CN110730131A (en) * | 2019-10-22 | 2020-01-24 | 电子科技大学 | SDN satellite network multi-QoS constraint routing method based on improved ant colony |
CN112149788A (en) * | 2020-09-28 | 2020-12-29 | 复旦大学 | Minimum overhead route generation method based on ant colony algorithm |
CN112311670A (en) * | 2019-12-04 | 2021-02-02 | 重庆邮电大学 | Machine learning route optimization method for software defined network |
CN113068224A (en) * | 2021-03-29 | 2021-07-02 | 烽火通信科技股份有限公司 | Ant colony algorithm implementation method and device for constructing mesh transmission system |
CN113542121A (en) * | 2021-07-05 | 2021-10-22 | 浙江大学 | Load balancing routing method for tree data center link layer based on annealing method |
CN115426360A (en) * | 2022-08-09 | 2022-12-02 | 徐州医科大学 | Graph theory-based hierarchical self-adaptive load balancing method and system |
CN115499376A (en) * | 2022-07-29 | 2022-12-20 | 天翼云科技有限公司 | Load balancing method, system, electronic equipment and storage medium |
CN115499306A (en) * | 2022-07-29 | 2022-12-20 | 天翼云科技有限公司 | Method and device for constructing traffic scheduling model, electronic equipment and storage medium |
TWI801812B (en) * | 2020-02-24 | 2023-05-11 | 四零四科技股份有限公司 | Device and method of handling routing paths for streams in a time-sensitive networking network |
CN116192720A (en) * | 2021-11-26 | 2023-05-30 | 中国联合网络通信集团有限公司 | Link optimization method and device, electronic equipment and storage medium |
Citations (6)
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 |
US20150195178A1 (en) * | 2014-01-09 | 2015-07-09 | Ciena Corporation | Method for resource optimized network virtualization overlay transport in virtualized data center environments |
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 |
-
2017
- 2017-05-19 CN CN201710358160.7A patent/CN107094115B/en active Active
Patent Citations (6)
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 |
US20150195178A1 (en) * | 2014-01-09 | 2015-07-09 | Ciena Corporation | Method for resource optimized network virtualization overlay transport in virtualized data center environments |
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)
Title |
---|
CHUNZHI WANG;GANG ZHANG;HUI XU;HONGWEI CHEN: "An ACO-based Link Load-Balancing Algorithm in SDN", 《 2016 7TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND BIG DATA (CCBD)》 * |
SHANWEN YI;HUA WANG;XIBO YAO;CHUANGEN GAO;LINBO ZHAI: "Maximizing Network Utilization for SDN Based on WiseAnt Colony Optimization", 《 2016 IEEE 18TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS》 * |
魏凯: "基于蚁群算法SDN负载均衡的研究", 《中国优秀硕士学位论文全文数据库(电子期刊)》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107579923A (en) * | 2017-09-18 | 2018-01-12 | 迈普通信技术股份有限公司 | The balancing link load method and SDN controllers of a kind of SDN |
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 |
CN107454630A (en) * | 2017-09-25 | 2017-12-08 | 中国联合网络通信集团有限公司 | Load-balancing method and load balancing router |
US11522789B2 (en) | 2018-03-05 | 2022-12-06 | Huawei Technologies Co., Ltd. | Data processing method, apparatus, and system for combining data for a distributed calculation task in a data center network |
CN110233798A (en) * | 2018-03-05 | 2019-09-13 | 华为技术有限公司 | Data processing method, apparatus and system |
CN110233798B (en) * | 2018-03-05 | 2021-02-26 | 华为技术有限公司 | Data processing method, device and system |
US11855880B2 (en) | 2018-03-05 | 2023-12-26 | Huawei Technologies Co., Ltd. | Data processing method, apparatus, and system for combining data for a distributed calculation task in a data center network |
CN108512772A (en) * | 2018-03-09 | 2018-09-07 | 重庆邮电大学 | Quality-of-service based data center's traffic scheduling method |
CN109039897A (en) * | 2018-07-20 | 2018-12-18 | 南京邮电大学 | A kind of software definition backhaul network method for routing based on service-aware |
CN110730131A (en) * | 2019-10-22 | 2020-01-24 | 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 |
CN112311670A (en) * | 2019-12-04 | 2021-02-02 | 重庆邮电大学 | Machine learning route optimization method for software defined network |
TWI801812B (en) * | 2020-02-24 | 2023-05-11 | 四零四科技股份有限公司 | Device and method of handling routing paths for streams in a time-sensitive networking network |
CN112149788A (en) * | 2020-09-28 | 2020-12-29 | 复旦大学 | Minimum overhead route generation method based on ant colony algorithm |
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 |
CN113068224A (en) * | 2021-03-29 | 2021-07-02 | 烽火通信科技股份有限公司 | Ant colony algorithm implementation method and device for constructing mesh transmission system |
CN113542121A (en) * | 2021-07-05 | 2021-10-22 | 浙江大学 | Load balancing routing method for tree data center link layer based on annealing method |
CN116192720A (en) * | 2021-11-26 | 2023-05-30 | 中国联合网络通信集团有限公司 | Link optimization method and device, electronic equipment and storage medium |
CN115499306A (en) * | 2022-07-29 | 2022-12-20 | 天翼云科技有限公司 | Method and device for constructing traffic 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 |
CN115499376A (en) * | 2022-07-29 | 2022-12-20 | 天翼云科技有限公司 | Load balancing method, system, electronic equipment and storage medium |
WO2024021486A1 (en) * | 2022-07-29 | 2024-02-01 | 天翼云科技有限公司 | Load balancing method and system, and electronic device and storage medium |
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 |
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 |
CN115426360A (en) * | 2022-08-09 | 2022-12-02 | 徐州医科大学 | Graph theory-based hierarchical self-adaptive load balancing method and system |
Also Published As
Publication number | Publication date |
---|---|
CN107094115B (en) | 2020-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107094115A (en) | A kind of ant group optimization Load Balance Routing Algorithms based on SDN | |
CN106411733B (en) | A kind of SDN dynamic load leveling dispatching method based on link real time load | |
CN106533960B (en) | A kind of data center network method for routing based on Fat-Tree structure | |
CN107819695A (en) | A kind of distributed AC servo system SiteServer LBS and method based on SDN | |
CN104335537B (en) | For the system and method for the multicast multipath of layer 2 transmission | |
Grundy et al. | Promoting congestion control in opportunistic networks | |
Verma et al. | Integrated routing protocol for opportunistic networks | |
CN107579923A (en) | The balancing link load method and SDN controllers of a kind of SDN | |
CN104579964A (en) | Dynamic route architecture system for quantum cryptography network | |
CN103929782B (en) | A kind of resources balance multi-path route method suitable for industrial wireless sensor network | |
CN104301305B (en) | Interest bag is forwarded under information centre's network method and forwarding terminal | |
CN109962774B (en) | Quantum cipher network key relay dynamic routing method | |
CN103348639A (en) | Path selection method and control server | |
CN105050149A (en) | Routing method for overcoming congestion of tree type Zigbee network | |
CN105681438A (en) | Centralized caching decision strategy in content-centric networking | |
CN105743804A (en) | Data flow control method and system | |
CN100505675C (en) | Distributed self-organising dynamic route method based on ant algorithm | |
CN107454630A (en) | Load-balancing method and load balancing router | |
CN107864092A (en) | A kind of cloud content distribution method, device based on multicasting technology | |
Liang et al. | The effect of routing under local information using a social insect metaphor | |
Liang et al. | Intelligent packets for dynamic network routing using distributed genetic algorithm | |
CN110300426A (en) | Route selection method and device in a kind of wireless self-networking | |
CN106792971A (en) | Network node system of selection based on ant group algorithm | |
Chen et al. | An efficient neural network-based next-hop selection strategy for multi-hop VANETs | |
CN109525494A (en) | Opportunistic network routing mechanism implementation method based on message next-hop Dynamic Programming |
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 |