CN110149226A - Improved particle swarm algorithm for multi-controller deployment problem in software defined network - Google Patents
Improved particle swarm algorithm for multi-controller deployment problem in software defined network Download PDFInfo
- Publication number
- CN110149226A CN110149226A CN201910402207.4A CN201910402207A CN110149226A CN 110149226 A CN110149226 A CN 110149226A CN 201910402207 A CN201910402207 A CN 201910402207A CN 110149226 A CN110149226 A CN 110149226A
- Authority
- CN
- China
- Prior art keywords
- particle
- controller
- worst
- velocity vector
- algorithm
- 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
- 239000002245 particle Substances 0.000 title claims abstract description 98
- 239000013598 vector Substances 0.000 claims abstract description 47
- 230000006872 improvement Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 239000000470 constituent Substances 0.000 claims description 3
- 230000001351 cycling effect Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an improved particle swarm algorithm for a multi-controller deployment problem in a software defined network, wherein each particle is represented as a solution of the multi-controller deployment problem by generating random particles and velocity vectors; in each iteration, the positions of the particles are updated according to the velocity vectors, and meanwhile, the velocity vectors of the particles are updated according to the global optimal value and the worst value of the particle swarm and the historical global optimal value and the worst value of the particles, so that the situation that the particles fall into a global optimal solution is avoided, and the reliability of an output result can be effectively improved; and finally, outputting the optimal particles in the particle swarm after the iteration condition is met, wherein the corresponding deployment scheme can effectively improve the corresponding performance, effectively improve the overall performance of the network and optimize the user experience.
Description
Technical field
The present invention relates to software defined network (SDN) technical field, multi-controller in especially a kind of software defined network
The improvement particle swarm algorithm of deployment issue.
Background technique
From 2016 to 2021 year, global IP network data traffic will increase nearly three times, the network flow dominated by Cisco
Measuring prediction project indicates, the network flow of whole the Internet will rise to annual 2.3ZB from annual 1000EB.
It is greatly increased due to predicting future network flow, traditional IP framework has been not suitable with future network
Demand.The network architecture that software defined network proposes recently as one has many advantages compared to traditional network, more can
Adapt to the challenge of future network scene.
Related SDN development studies have shown that in large-scale wide area network, single controller is not able to satisfy the demand of network,
Therefore, in 2012, Heller et al. proposes the multi-controller deployment issue in wide area network.Controller deployment issue is often referred to
Be how to determine the quantity of controller, the position of dispensing controller and controller and interchanger in software defined network
Mapping relations, to optimize network performance.In view of between the reliability of network, network data flow time delay in a network, controller
The performance indicators such as communication delay, load equilibrium between controller, in multi-controller environment, the different deployment positions of controller
Set the performance that will affect above-mentioned performance indicator.Suitable location of controls is selected, determines that controller is suitably reflected with inter-exchange
Relationship is penetrated, the overall performance of network can be effectively promoted, optimizes user experience.
Multi-controller deployment issue is a NP-Hard problem, and the research and its solution scheme to the problem have exhaustive calculation
Method, greedy algorithm, clustering algorithm, integer programming algorithm etc., but obtained solution is not highly desirable.
Summary of the invention
For overcome the deficiencies in the prior art, the present invention provides multi-controller deployment issue in a kind of software defined network
Improve particle swarm algorithm.
The technical solution adopted by the present invention to solve the technical problems is:
The improvement particle swarm algorithm of multi-controller deployment issue in a kind of software defined network, comprising the following steps:
Step S1, the performance index function f for obtaining the quantity k of network topology G and its required controller and needing to optimize, with
Machine generates multiple particles p, forms a population P, wherein each particle p represents a solution of multi-controller deployment issue
Certainly scheme (i.e. each particle represent a group controller position)；Specifically, the generation step of population P includes:
Step A1, integer number is carried out to network topology G, each number represents a node, and calculates between each node
Shortest path distance, store into a Distance matrix D.
Step A2, the number for randomly selecting k number amount also is indicated as a group controller position as a particle p,
On these positions simultaneously deployment controller and interchanger.
It step A3, is other interchanger dispensing controllers in network, it is ensured that each interchanger according to shortest path principle
Only it is connect with nearest controller.
Step A4, reflecting between location of controls, position switching mechanism and interchanger and the controller determined according to step A3
Penetrate relationship, the shortest path distance in the network stored in conjunction with Distance matrix D between each node, calculate controller with exchange
Total distance between machine, takes its average value as the average retardation of network, the index as assessment particle properties.
Step A5, circulation step A2-A4 obtains multiple particles p, constituent particle group P.
Step S2, the velocity vector for setting each particle p at random is denoted as v, and velocity vector v is formed by set
It is denoted as V, specifically, velocity vector v is the vector of 1*k (k is regarded as an one-dimensional vector).
Step S3, according to the current location of particle p and velocity vector, the position of each particle p, calculation formula are updated are as follows:
pnew=pold+v；
Wherein pnewFor the updated position particle p.
poldFor the current position particle p.
V is the velocity vector of particle p；Further, when velocity vector v is not integer, four houses are carried out to velocity vector V
Five enter rounding processing.
Step S4, the history optimal value and history worst-case value for finding each particle p, are denoted as pbestAnd pworst, find simultaneously
The history optimal value and history worst-case value of all particle p in entire population P, and it is denoted as gbestAnd gworst。
Step S5, the more velocity vector of new particle p, more new formula are as follows:
vnew=w*vold
+c1*r1*(pbest-pold)+c2*r2(gbest-pold)
+c3*(1-r1)*(pold-pworst)+c4*(1-r2)*(pold-gworst)；
Wherein, vnewFor the updated velocity vector of particle p.
Velocity inertia vector when w is particle p renewal speed vector, calculation formula are as follows:
W=0.5+ (fgbest-fgworst)/fgbest；
Wherein, fgbestFor the history optimal value g of all particle p in entire population PbestCorresponding performance index function.
fgworstFor the history worst-case value g of all particle p in entire population PworstCorresponding performance index function.
c1、c2、c3And c4It is 1.
r1And r2For in the random number of section [0,1].
Step S6, algorithm termination condition, loop iteration step S3-S6 are set, and judge whether to reach algorithm termination condition,
If so, terminating loop iteration, and export the particle p after last time recycles, the as optimal solution of multi-controller deployment issue
Certainly scheme, if it is not, then by vnewAs the velocity vector v in step S3, iterative step S3-S6 is continued cycling through；In the present embodiment,
When algorithm loop iteration number is more than 50, algorithm is terminated；Or as the g acquired in step S5bestAnd gworstNumerical value compare
In the g of last loop iterationbestAnd gworstNumerical value, when amplification is no more than 10%, algorithm terminate.
The beneficial effects of the present invention are: method of the invention has following advantages:
1, the present invention improves particle algorithm, can change the evolution speed of particle according to Population status dynamic, while also examining
Consider the worst-case value and optimal value in population, as one of the parameter of particle evolution speed, expand search space,
It effectively prevents particle swarm algorithm and falls into locally optimal solution, be more advantageous to and find globally optimal solution；
2, the solution obtained using the algorithm can be effectively reduced network close to the obtained optimal value of exhaust algorithm
Delay；
3, algorithm computational complexity is low, can quickly obtain solution, compared to exhaust algorithm, effectively reduces needed for solution
Time；
4, a particle is indicated with the position of controller, and calculate the performance of particle according to this, replacing other performance indicators
When, such as the reliability of network, the algorithm is still effective, is suitable for a variety of optimization scenes.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is the principle of the present invention block diagram；
Fig. 2 is flow chart of the invention.
Specific embodiment
Referring to Fig.1, Fig. 2, the improvement particle swarm algorithm of multi-controller deployment issue in a kind of software defined network, including with
Lower step:
Step S1, performance index function f (this for obtaining the quantity k of network topology G and its required controller and needing to optimize
In embodiment, performance index function is selected as the average delay of network), it is random to generate multiple particles p, a population P is formed,
Wherein, each particle p represents a solution of multi-controller deployment issue (i.e. each particle represents a group controller
Position)；Specifically, the generation step of population P includes:
Step A1, integer number is carried out to network topology G, each number represents a node, and calculates between each node
Shortest path distance, store into a Distance matrix D.
Step A2, the number for randomly selecting k number amount also is indicated as a group controller position as a particle p,
On these positions simultaneously deployment controller and interchanger.
It step A3, is other interchanger dispensing controllers in network, it is ensured that each interchanger according to shortest path principle
Only it is connect with nearest controller.
Step A4, reflecting between location of controls, position switching mechanism and interchanger and the controller determined according to step A3
Penetrate relationship, the shortest path distance in the network stored in conjunction with Distance matrix D between each node, calculate controller with exchange
Total distance between machine takes its average value as the average retardation of network, and as the indexs of assessment particle properties, (i.e. particle is suitable
Response).
Step A5, circulation step A2-A4 obtains multiple particles p, constituent particle group P.
Step S2, the velocity vector for setting each particle p at random is denoted as v, and velocity vector v is formed by set
It is denoted as V, specifically, velocity vector v is the vector of 1*k (k is regarded as an one-dimensional vector).
Step S3, according to the current location of particle p and velocity vector, the position of each particle p, calculation formula are updated are as follows:
pnew=pold+v；
Wherein pnewFor the updated position particle p.
poldFor the current position particle p.
V is the velocity vector of particle p；Further, due in step A1, using integer as network in node compile
Number, in the present embodiment, when velocity vector v is not integer, round processing is carried out to velocity vector V, to guarantee more
Particle position after new still is able to be mapped to corresponding network node.
Step S4, the history optimal value and history worst-case value for finding each particle p, are denoted as pbestAnd pworst, find simultaneously
The history optimal value and history worst-case value of all particle p in entire population P, and it is denoted as gbestAnd gworst。
Step S5, the more velocity vector of new particle p, more new formula are as follows:
vnew=w*vold
+c1*r1*(pbest-pold)+c2*r2(gbest-pold)
+c3*(1-r1)*(pold-pworst)+c4*(1-r2)*(pold-gworst)；
Wherein, vnewFor the updated velocity vector of particle p.
Velocity inertia vector when w is particle p renewal speed vector, calculation formula are as follows:
W=0.5+ (fgbest-fgworst)/fgbest；
Wherein, fgbestFor the history optimal value g of all particle p in entire population PbestCorresponding performance index function.
fgworstFor the history worst-case value g of all particle p in entire population PworstCorresponding performance index function.
c1、c2、c3And c4It is 1.
r1And r2For in the random number of section [0,1].
Similarly, as the v acquirednewValue when not being integer, to vnewCarry out round processing, it is ensured that it is subsequent more
New particle position still is able to be mapped to corresponding network node.
Step S6, algorithm termination condition, loop iteration step S3-S6 are set, and judge whether to reach algorithm termination condition,
If so, terminating loop iteration, and export the particle p after last time recycles, the as optimal solution of multi-controller deployment issue
Certainly scheme, if it is not, then by vnewAs the velocity vector v in step S3, iterative step S3-S6 is continued cycling through；In the present embodiment,
Algorithm termination condition are as follows: when algorithm loop iteration number is more than 50, algorithm is terminated；Or as the g acquired in step S5bestWith
gworstNumerical value compared to last loop iteration gbestAnd gworstNumerical value, when amplification is no more than 10%, algorithm terminate.
The present invention is expressed as multi-controller deployment issue by generating random particle and velocity vector with each particle
One solution；In the iteration of each round, according to the position of velocity vector more new particle, while according to the overall situation of population
The velocity vector of optimal value and worst-case value, the history global optimum of particle and worst-case value more new particle avoids falling into the overall situation most
Excellent solution can effectively improve the reliability of output result；Finally after meeting iterated conditional, the optimal grain in population is exported
Son, corresponding deployment scheme can effectively improve corresponding performance, effectively promote the overall performance of network, optimize user's body
It tests.
Above embodiment cannot limit the protection scope of the invention, and the personnel of professional skill field are not departing from
In the case where the invention general idea, the impartial modification and variation done still fall within the range that the invention is covered
Within.
Claims (5)
1. the improvement particle swarm algorithm of multi-controller deployment issue in a kind of software defined network, which is characterized in that it include with
Lower step:
Step S1, the performance index function f for obtaining the quantity k of network topology G and its required controller and needing to optimize, with
Machine generates multiple particles p, forms a population P, wherein each particle p represents a solution of multi-controller deployment issue
Certainly scheme (i.e. each particle represent a group controller position)；
Step S2, the velocity vector for setting each particle p at random is denoted as v, and velocity vector v is formed by set and is denoted as
V；
Step S3, according to the current location of particle p and velocity vector, the position of each particle p, calculation formula are updated are as follows:
pnew = pold+ v；
Wherein pnewFor the updated position particle p；
poldFor the current position particle p；
V is the velocity vector of particle p；
Step S4, the history optimal value and history worst-case value for finding each particle p, are denoted as pbestAnd pworst, while finding entire
The history optimal value and history worst-case value of all particle p in population P, and it is denoted as gbestAnd gworst；
Step S5, the more velocity vector of new particle p, more new formula are as follows:
vnew= w*vold
+c1*r1*(pbest-pold)+c2*r2(gbest-pold)
+c3* (1-r1)*(pold-pworst)+c4*(1-r2)*(pold-gworst)；
Wherein, vnewFor the updated velocity vector of particle p；
Velocity inertia vector when w is particle p renewal speed vector, calculation formula are as follows:
w = 0.5 + (fgbest-fgworst)/fgbest；
Wherein, fgbestFor the history optimal value g of all particle p in entire population PbestCorresponding performance index function；
fgworstFor the history worst-case value g of all particle p in entire population PworstCorresponding performance index function；
c1、c2、c3And c4It is 1；
r1And r2For in the random number of section [0,1]；
Step S6, algorithm termination condition, loop iteration step S3-S6 are set, and judge whether to reach algorithm termination condition, if
It is then to terminate loop iteration, and export the particle p after last time recycles, the as optimal solution of multi-controller deployment issue
Scheme, if it is not, then by vnewAs the velocity vector v in step S3, iterative step S3-S6 is continued cycling through.
2. the improvement particle swarm algorithm of multi-controller deployment issue in software defined network according to claim 1, special
Sign is in the step S1 that the generation step of population P includes:
Step A1, integer number is carried out to network topology G, each number represents a node, and calculates between each node
Shortest path distance, store into a Distance matrix D；
Step A2, the number for randomly selecting k number amount also is indicated as a group controller position, at these as a particle p
On position simultaneously deployment controller and interchanger；
Step A3, be other interchanger dispensing controllers in network according to shortest path principle, it is ensured that each interchanger only with
Nearest controller connection；
Step A4, the mapping between location of controls, position switching mechanism and interchanger and the controller determined according to step A3 is closed
System, the shortest path distance in the network stored in conjunction with Distance matrix D between each node, calculate controller and interchanger it
Between total distance, take its average value as the average retardation of network, the index as assessment particle properties；
Step A5, circulation step A2-A4 obtains multiple particles p, constituent particle group P.
3. the improvement particle swarm algorithm of multi-controller deployment issue in software defined network according to claim 2, special
Sign is in step S2 that velocity vector v is the vector of 1*k.
4. the improvement particle swarm algorithm of multi-controller deployment issue in software defined network according to claim 1, special
Sign is in the step S3, when velocity vector v is not integer, carries out round processing to velocity vector V.
5. the improvement particle swarm algorithm of multi-controller deployment issue in software defined network according to claim 1, special
Sign is in the step S6, and when algorithm loop iteration number is more than 50, algorithm is terminated；Or when acquiring in step S5
gbestAnd gworstNumerical value compared to last loop iteration gbestAnd gworstNumerical value, when amplification is no more than 10%, algorithm
It terminates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910402207.4A CN110149226B (en) | 2019-05-14 | 2019-05-14 | Improved particle swarm algorithm for multi-controller deployment problem in software defined network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910402207.4A CN110149226B (en) | 2019-05-14 | 2019-05-14 | Improved particle swarm algorithm for multi-controller deployment problem in software defined network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110149226A true CN110149226A (en) | 2019-08-20 |
| CN110149226B CN110149226B (en) | 2022-01-28 |
Family
ID=67595327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910402207.4A Active CN110149226B (en) | 2019-05-14 | 2019-05-14 | Improved particle swarm algorithm for multi-controller deployment problem in software defined network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110149226B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111650878A (en) * | 2020-06-15 | 2020-09-11 | 北京理工大学 | Method for optimizing programmability of flow when multiple controllers in software defined network fail |
| CN112217666A (en) * | 2020-09-29 | 2021-01-12 | 中国银行股份有限公司 | Software defined network optimization method and device |
| CN113452540A (en) * | 2020-03-27 | 2021-09-28 | 中国电信股份有限公司 | SDN configuration method and device and computer readable storage medium |
| CN113904933A (en) * | 2021-09-30 | 2022-01-07 | 中国船舶重工集团公司第七一九研究所 | Method for synchronously optimizing performance and reliability of digital network control system |
| CN114244720A (en) * | 2021-12-17 | 2022-03-25 | 湘潭大学 | Multi-controller deployment method based on improved particle swarm algorithm in SDN environment |
| CN115190021A (en) * | 2022-04-24 | 2022-10-14 | 北京中电飞华通信有限公司 | Slice deployment method for deterministic delay service and related equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140257767A1 (en) * | 2013-03-09 | 2014-09-11 | Bigwood Technology, Inc. | PSO-Guided Trust-Tech Methods for Global Unconstrained Optimization |
| CN107743147A (en) * | 2017-11-06 | 2018-02-27 | 柏域信息科技（上海）有限公司 | Dynamic cloud storage SDN controllers collocation method and device based on global optimization |
| CN108900330A (en) * | 2018-06-25 | 2018-11-27 | 电子科技大学 | A kind of multi-controller dispositions method defining network suitable for large scope software |
-
2019
- 2019-05-14 CN CN201910402207.4A patent/CN110149226B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140257767A1 (en) * | 2013-03-09 | 2014-09-11 | Bigwood Technology, Inc. | PSO-Guided Trust-Tech Methods for Global Unconstrained Optimization |
| CN107743147A (en) * | 2017-11-06 | 2018-02-27 | 柏域信息科技（上海）有限公司 | Dynamic cloud storage SDN controllers collocation method and device based on global optimization |
| CN108900330A (en) * | 2018-06-25 | 2018-11-27 | 电子科技大学 | A kind of multi-controller dispositions method defining network suitable for large scope software |
Non-Patent Citations (2)
| Title |
|---|
| XIBO YAO; HUA WANG;: "Maximizing Network Utilization for SDN Based on Particle Swarm Optimization", 《IEEE》 * |
| 樊自甫; 姚杰; 杨先辉: "基于时延优化的软件定义网络控制层部署策略", 《计算机应用》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113452540A (en) * | 2020-03-27 | 2021-09-28 | 中国电信股份有限公司 | SDN configuration method and device and computer readable storage medium |
| CN113452540B (en) * | 2020-03-27 | 2022-08-30 | 中国电信股份有限公司 | SDN configuration method and device and computer readable storage medium |
| CN111650878A (en) * | 2020-06-15 | 2020-09-11 | 北京理工大学 | Method for optimizing programmability of flow when multiple controllers in software defined network fail |
| CN112217666A (en) * | 2020-09-29 | 2021-01-12 | 中国银行股份有限公司 | Software defined network optimization method and device |
| CN112217666B (en) * | 2020-09-29 | 2022-02-25 | 中国银行股份有限公司 | Software defined network optimization method and device |
| CN113904933A (en) * | 2021-09-30 | 2022-01-07 | 中国船舶重工集团公司第七一九研究所 | Method for synchronously optimizing performance and reliability of digital network control system |
| CN113904933B (en) * | 2021-09-30 | 2023-08-25 | 中国船舶重工集团公司第七一九研究所 | Synchronous optimization method for performance and reliability of digital network control system |
| CN114244720A (en) * | 2021-12-17 | 2022-03-25 | 湘潭大学 | Multi-controller deployment method based on improved particle swarm algorithm in SDN environment |
| CN115190021A (en) * | 2022-04-24 | 2022-10-14 | 北京中电飞华通信有限公司 | Slice deployment method for deterministic delay service and related equipment |
| CN115190021B (en) * | 2022-04-24 | 2024-04-12 | 北京中电飞华通信有限公司 | Deterministic time delay service oriented slice deployment method and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110149226B (en) | 2022-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110149226A (en) | Improved particle swarm algorithm for multi-controller deployment problem in software defined network | |
| CN113285831B (en) | Network behavior knowledge intelligent learning method and device, computer equipment and storage medium | |
| Chen et al. | Multi-controller placement towards SDN based on Louvain heuristic algorithm | |
| WO2022237086A1 (en) | Control method and apparatus based on machine learning model | |
| CN114827021B (en) | Multimedia service flow acceleration system based on SDN and machine learning | |
| CN110120892B (en) | SDN multi-controller deployment method and system based on improved firefly algorithm | |
| CN117406844B (en) | Display card fan control method and related device based on neural network | |
| CN113225994B (en) | Intelligent air conditioner control method facing data center | |
| Lujic et al. | Resilient edge data management framework | |
| CN110390395A (en) | Improved genetic algorithm suitable for self-adaptive mutation crossing of SDN multi-controller deployment problem | |
| CN110275895B (en) | Filling equipment, device and method for missing traffic data | |
| CN116258059B (en) | Lithium battery temperature real-time prediction model based on multi-time space width learning model and construction method | |
| CN107396375B (en) | Quantum brain storm-based optimal target coverage method for heterogeneous sensor network | |
| BR112021013153A2 (en) | METHOD, SYSTEM AND COMPUTER PROGRAM PRODUCT FOR EVALUATION OF ENERGY CONSUMPTION IN INDUSTRIAL ENVIRONMENTS | |
| CN115022231B (en) | Optimal path planning method and system based on deep reinforcement learning | |
| US11558263B2 (en) | Network device association with network management system | |
| CN109347900A (en) | Based on the cloud service system Adaptive evolution method for improving wolf pack algorithm | |
| Gunavathie et al. | Traffic-aware optimal routing in software defined networks by predicting traffic using neural network | |
| CN115269162A (en) | SDN multi-controller-based ant colony improving load balancing method | |
| Shu et al. | A Dynamic Multipath Load Balancing Algorithm Based on Particle Swarm Optimization in DCN | |
| CN110768906A (en) | SDN-oriented energy-saving routing method based on Q learning | |
| CN109256774A (en) | A kind of power grid subgraph partitioning method and device based on voltage class | |
| CN104753963B (en) | The short stream accelerated method of data center based on redundancy and system | |
| CN109582351B (en) | Version compatibility method based on cloud computing and artificial intelligence and robot system | |
| CN114051273B (en) | Large-scale network dynamic self-adaptive path planning method based on deep learning |
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 |