CN113452540A - SDN configuration method and device and computer readable storage medium - Google Patents
SDN configuration method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN113452540A CN113452540A CN202010227064.0A CN202010227064A CN113452540A CN 113452540 A CN113452540 A CN 113452540A CN 202010227064 A CN202010227064 A CN 202010227064A CN 113452540 A CN113452540 A CN 113452540A
- Authority
- CN
- China
- Prior art keywords
- individual
- individuals
- determining
- sdn
- iterative
- 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
Images
Classifications
-
- 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
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- 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
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/35—Switches specially adapted for specific applications
Abstract
The invention discloses a method and a device for SDN configuration and a computer readable storage medium, and relates to the technical field of SDN. The SDN configuration method comprises the following steps: randomly generating a plurality of individuals, wherein each individual comprises a plurality of genes, and each gene corresponds to configuration information of one service under the SDN switch; performing a plurality of iterative updates to the plurality of individuals, wherein for each individual of the plurality of individuals, at least one iterative update comprises: determining a first test individual of the individuals through a differential evolution algorithm; determining a second trial individual of the individuals by randomly rearranging the genes of the intermediate individuals; determining the individual with the highest fitness among the individual, the first test individual of the individual and the second test individual of the individual as an updating result of the individual in the iterative updating; and determining the configuration information of each service under the SDN switch according to the result of the repeated iteration updating. Therefore, the invention can efficiently and reasonably realize the optimal configuration of multiple resources and multiple services of the SDN network.
Description
Technical Field
The present invention relates to the field of SDN technologies, and in particular, to a method and an apparatus for SDN configuration, and a computer-readable storage medium.
Background
The SDN network separates a control plane from a data plane and controls the distributed data plane through a centralized controller platform. In a control plane, a programmable SDN controller acquires relevant parameters of the full-network SDN switch through a uniform interface (such as an OpenFlow protocol), so that the flexibility of managing, configuring network resources and deploying network protocols is improved. In a data plane, the SDN switch provides a data forwarding function, and network data packets of various services can be matched quickly. The SDN network solves the problems of low service deployment efficiency, poor service adaptability, difficulty in guaranteeing service quality and the like in the traditional network.
Disclosure of Invention
The inventor discovers that the service types under the SDN switch are more after analysis, and a scheme for efficiently and reasonably distributing resources for the SDN switch does not exist in the related technology.
The embodiment of the invention aims to solve the technical problem that: how to efficiently and reasonably allocate resources for an SDN switch.
According to a first aspect of some embodiments of the present invention, there is provided an SDN configuration method, including: randomly generating a plurality of individuals, wherein each individual comprises a plurality of genes, and each gene corresponds to configuration information of one service under the SDN switch; performing a plurality of iterative updates to the plurality of individuals, wherein for each individual of the plurality of individuals, at least one iterative update comprises: determining a first test individual of the individuals through a differential evolution algorithm; determining a second trial individual of the individuals by randomly rearranging the genes of the intermediate individuals; determining the individual with the highest fitness among the individual, the first test individual of the individual and the second test individual of the individual as an updating result of the individual in the iterative updating; and determining the configuration information of each service under the SDN switch according to the result of the repeated iteration updating.
In some embodiments, determining a first trial individual of the individuals by a differential evolution algorithm comprises: adding the results of multiplying the difference between the value of the gene of the first individual except the individual and the values of the genes of the second individual and the third individual by a preset coefficient for each gene in the individual, and determining the addition result as the value of the gene in the middle individual of the individual, wherein the value of the gene in the middle individual is in a preset range; and crossing the individuals with the intermediate individuals to obtain a first test individual.
In some embodiments, the plurality of individuals are randomly generated based on a constraint condition, wherein the constraint condition is that the sum of bandwidths required by the services under the SDN switch is less than a bandwidth preset by the SDN switch.
In some embodiments, the SDN configuration method further comprises: determining configuration information of each service under the SDN switch according to the value of the gene in the individual; and determining the sum of computing resources consumed by each service under the SDN switch according to the configuration information of each service, wherein the sum is used as the individual fitness.
In some embodiments, the configuration information includes the number of services, processing power, and power consumption.
In some embodiments, the plurality of iterative updates comprises a first iterative update and a second iterative update; performing a first iterative update on a plurality of individuals comprises: determining a first test individual of the individuals through a differential evolution algorithm; determining the individual with the highest fitness among the individuals and the first test individuals of the individuals as an updating result of the individual in the iterative updating; performing a second iterative update on the plurality of individuals comprises: determining a first test individual of the individuals through a differential evolution algorithm; determining a second trial individual of the individuals by randomly rearranging the genes of the intermediate individuals; and determining the individual with the highest fitness among the individual, the first test individual of the individual and the second test individual of the individual as an updating result of the individual in the current iteration updating.
In some embodiments, performing multiple iterative updates on multiple individuals comprises: executing a preset number of first iteration updates; a second iterative update is performed a plurality of times until a termination condition is satisfied.
In some embodiments, performing multiple iterative updates on multiple individuals comprises: executing a plurality of first iteration updates until the fitness of the individual is reduced to a degree smaller than a preset degree; a second iterative update is performed a plurality of times until a termination condition is satisfied.
According to a second aspect of some embodiments of the present invention, there is provided an SDN configuration apparatus, including: the system comprises an initialization module, a service module and a service module, wherein the initialization module is configured to randomly generate a plurality of individuals, each individual comprises a plurality of genes, and each gene corresponds to configuration information of one service under an SDN switch; an iterative update module configured to perform a plurality of iterative updates for a plurality of individuals, wherein for each individual of the plurality of individuals, at least one iterative update comprises: determining a first test individual of the individuals through a differential evolution algorithm; determining a second trial individual of the individuals by randomly rearranging the genes of the intermediate individuals; determining the individual with the highest fitness among the individual, the first test individual of the individual and the second test individual of the individual as an updating result of the individual in the iterative updating; and the configuration information determining module is configured to determine the configuration information of each service under the SDN switch according to the result of the multiple iterative updating.
According to a third aspect of some embodiments of the present invention, there is provided an SDN configuration apparatus, including: a memory; and a processor coupled to the memory, the processor configured to perform any of the SDN configuration methods described above based on instructions stored in the memory.
According to a fourth aspect of some embodiments of the present invention, there is provided a computer readable storage medium having a computer program stored thereon, wherein the program when executed by a processor implements any one of the SDN configuration methods described above.
Some embodiments of the above invention have the following advantages or benefits: the method of the embodiment of the invention realizes a double difference algorithm. By adopting the traditional difference algorithm, the total configuration of the genes and services of the individuals randomly changes in a larger range, and the large-step evolution is realized; and then the numerical values of the genes in the individuals are unchanged, and the sequences are randomly exchanged, so that the fitness value of the individuals is changed in a small range, and small-step evolution is realized. By combining the two evolution modes, the local search capability can be improved by utilizing the random rearrangement of the individual genes, so that the calculation process is accelerated to converge to an optimal value, and the optimal configuration of multiple resources and multiple services of the SDN network is efficiently and reasonably realized. In addition, the scheme of the invention can utilize real number coding, and the calculation amount is small.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Figure 1 illustrates a flow diagram of an SDN configuration method according to some embodiments of the invention.
FIG. 2 illustrates a flow diagram of an iterative update method according to some embodiments of the present invention.
FIG. 3 is a flow diagram illustrating an iterative update method according to further embodiments of the present invention.
Figure 4 illustrates a structural schematic of an SDN configuration apparatus according to some embodiments of the invention.
Figure 5 illustrates a block diagram of an SDN configuration apparatus according to further embodiments of the present invention.
Figure 6 illustrates a block diagram of an SDN configuration apparatus according to further embodiments of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Figure 1 illustrates a flow diagram of an SDN configuration method according to some embodiments of the invention. As shown in fig. 1, the SDN configuration method of this embodiment includes steps S102 to S110.
In step S102, a plurality of individuals are randomly generated, where each individual includes a plurality of genes, and each gene corresponds to configuration information of one service under the SDN switch. The number of generated individuals can be determined according to a preset population scale.
In some embodiments, the configuration information includes the number of services, processing power, and power consumption. Taking the number as an example, if there are four services under the SDN switch, then { x } may be used1,x2,x3,x4Form of (i) } denotes individuals, x1、x2、x3、x4Respectively representing the number of four services. Similarly, 12 variables may be used to represent the number of four services, processing power, and power consumption. Specifically, for each individual, binary coding may be performed on the value of each variable corresponding to the individual, and all the coding results are spliced into a complete code as one individual.
In some embodiments, the plurality of individuals are randomly generated based on a constraint condition, wherein the constraint condition is that the sum of bandwidths required by the services under the SDN switch is less than a bandwidth preset by the SDN switch. Therefore, the generated SDN configuration result corresponding to the individual can be applied to the SDN switch, and the configuration efficiency is improved.
For example, the bandwidth B preset by the SDN switch may be divided into NbAnd determining the number of bandwidth required by the service according to the information of each service. The constraints may be as shown in equation (1).
In formula (1), i is the service identifier, N is the number of service classes, and biRepresenting the number of bandwidth parts occupied by each service i, niIndicates the number of services i, and ni＝[0,Nb]. Thus, when the randomly generated individuals do not comply with the constraint of equation (1), they can be regenerated.
After initializing the individuals, performing a plurality of iterative updates on the generated plurality of individuals, wherein for each individual in the plurality of individuals, at least one iterative update comprises steps S104 to S108.
In step S104, a first trial individual of the individuals is determined by a differential evolution algorithm.
In some embodiments, for each gene in the individuals, adding the results of multiplying the difference between the value of the gene of the first individual other than the individual and the values of the genes of the second and third individuals by a preset coefficient, and determining the addition result as the value of the gene in an intermediate individual of the individuals, wherein the value of the gene in the intermediate individual is within a preset range; and crossing the individuals with the intermediate individuals to obtain a first test individual.
For example, the j-th individual's intermediate individual ajValue a of Gene iijDetermined using equation (2). a isij＝[xip1+F(xip2–xip3)],0≤aij≤Nb,aij≠xip1≠xip2≠xip3 (2)
In the formula (2), xip1、xip2And xip3The values of gene i in individuals p1, p2 and p3 of the same generation as individual j, respectively, were randomly selectedAnd (4) selecting. F represents a predetermined mutation operator belonging to [0,2 ]]The interval of (2) is a real constant coefficient. In some embodiments, F may be set to 0.5. If the population converges prematurely, F or the population size may increase. In practical application, an optimal F value can be obtained by adjusting the value of F according to an application scene and related parameters, so that the population size is reduced as much as possible under the condition of ensuring convergence to global optimum. "[]"denotes a rounding operation, and may be selected to round up, round down, or round down as desired.
When a isijWhen the value is less than or equal to 0 or the calculated aijP1, p2 and p3 may be reselected and recalculated when the value of at least one of p1, p2 or p3 is equal; when a isijWhen > S, let aijS is the upper limit of the value of the predetermined gene.
After obtaining the intermediate individuals, each gene trial can be crossed, for example, using equation (3), to obtain a first test individual bj。
In the formula (3), bijRepresenting an individual bjThe gene i among them; CR ∈ [0,1 ]]Representing the cross probability; rand (0,1) represents taking a random integer in the range of (1, N). This crossing can ensure bjAt least one component of which is composed of an intermediate body ajProvided is a method.
After the analysis, the inventor finds that the traditional differential algorithm evolves to correct the value of each individual based on the difference vector of the population. However, as the evolution algebra increases, the differences between individuals gradually decrease, which may result in that the population is not updated any more without converging to the optimal solution. Therefore, the invention adds the small step evolution method of the step S106 on the basis of the large step evolution of the traditional differential algorithm evolution so as to improve the local search capability.
In step S106, a second trial individual of individuals is identified by randomly rearranging the genes of the intermediate individuals. That is, the resulting second test individual still possessed the genes of the original intermediate individual, but the order was changed.
In step S108, the individual with the highest fitness among the individual, the first test individual of the individuals, and the second test individual of the individuals is determined as the update result of the individual in the current iteration update.
In some embodiments, configuration information for each service under the SDN switch is determined from the value of the gene in the individual; and determining the sum of computing resources consumed by each service under the SDN switch according to the configuration information of each service, wherein the sum is used as the individual fitness.
In some embodiments, the sum of computing resources comprises an aggregate of processing power and power consumption.
For example, equation (4) may be employed to determine individual yjFitness f (y) ofj)。
In the formula (4), λ1And λ2A preset weighting factor greater than zero; n represents the number of the service types, and i is a service identifier; j represents an individual identifier; v. ofijGenes representing processing power, w, representing services i in an individual jijGenes representing power consumption, v representing services i in an individual jijA number-representing gene representing a business i in an individual j. M is the population size, i.e. the number of individuals.
Thus, minimization of computing resources consumed by services under the SDN switch may be targeted for iterative updates, such that the consumption of switch computing resources is reduced by iteratively determining individual corresponding configuration information.
The iterative process may be terminated based on preset conditions. The termination conditions include: the preset iteration number is reached, or the fitness value reaches a preset value, or the population after continuous multiple iterations is not updated, and the like.
In step S110, configuration information of each service under the SDN switch is determined according to a result of the multiple iterative updates.
The method of the above embodiment implements a double difference algorithm. By adopting the traditional difference algorithm, the total configuration of the genes and services of the individuals randomly changes in a larger range, and the large-step evolution is realized; and then the numerical values of the genes in the individuals are unchanged, and the sequences are randomly exchanged, so that the fitness value of the individuals is changed in a small range, and small-step evolution is realized. By combining the two evolution modes, the local search capability can be improved by utilizing the random rearrangement of the individual genes, so that the calculation process is accelerated to converge to an optimal value, and the optimal configuration of multiple resources and multiple services of the SDN network is realized. In addition, the scheme of the invention can utilize real number coding, and the calculation amount is small.
In some embodiments, different iterative update approaches may be employed at different stages of the computation. For example, a first iterative update and a second iterative update are included.
And setting a traditional differential evolution algorithm to be adopted by the first iteration updating, wherein the traditional differential evolution algorithm comprises the following steps: determining a first test individual of the individuals through a differential evolution algorithm; and determining the individual with the highest fitness among the individuals and the first test individuals of the individuals as the updating result of the individual in the current iteration updating.
Assuming that the second iterative update adopts the double differential evolution algorithm in the foregoing embodiment, the method includes: determining a first test individual of the individuals through a differential evolution algorithm; determining a second trial individual of the individuals by randomly rearranging the genes of the intermediate individuals; and determining the individual with the highest fitness among the individual, the first test individual of the individual and the second test individual of the individual as an updating result of the individual in the current iteration updating.
Embodiments using two iterative update approaches in the iterative process are described below with reference to fig. 2 and 3.
FIG. 2 illustrates a flow diagram of an iterative update method according to some embodiments of the present invention. As shown in fig. 2, the iterative update method of this embodiment includes steps S202 to S204.
In step S202, a preset number of first iterative updates are performed.
In step S204, a plurality of second iterative updates are performed until a termination condition is satisfied.
The method has relatively small calculation amount and high calculation efficiency.
FIG. 3 illustrates a flow diagram of an iterative update method according to some embodiments of the present invention. As shown in fig. 3, the iterative update method of this embodiment includes steps S302 to S304.
In step S302, a plurality of first iterative updates are performed until the fitness of the individual decreases by less than a preset value.
In step S304, a plurality of second iterative updates are performed until a termination condition is satisfied.
The method carries out second iterative updating at a proper time, and can achieve better searching effect.
An embodiment of the SDN configuration apparatus of the present invention is described below with reference to fig. 4.
Figure 4 illustrates a structural schematic of an SDN configuration apparatus according to some embodiments of the invention. As shown in fig. 4, the SDN configuration apparatus 40 of this embodiment includes: an initialization module 410 configured to randomly generate a plurality of individuals, wherein each individual includes a plurality of genes, and each gene corresponds to configuration information of one service under the SDN switch; an iterative update module 420 configured to perform a plurality of iterative updates for a plurality of individuals, wherein for each individual of the plurality of individuals, at least one iterative update comprises: determining a first test individual of the individuals through a differential evolution algorithm; determining a second trial individual of the individuals by randomly rearranging the genes of the intermediate individuals; determining the individual with the highest fitness among the individual, the first test individual of the individual and the second test individual of the individual as an updating result of the individual in the iterative updating; and a configuration information determining module 430 configured to determine configuration information of each service under the SDN switch according to the result of the multiple iterative updates.
In some embodiments, the iterative update module 420 is further configured to add, for each gene in the individuals, the result of multiplying the difference between the value of the gene of the first individual other than the individual and the values of the genes of the second and third individuals by a preset coefficient, determine the result of the addition as the value of the gene in an intermediate individual of the individuals, wherein the value of the gene in the intermediate individual is within a preset range; and crossing the individuals with the intermediate individuals to obtain a first test individual.
In some embodiments, the initialization module 410 is further configured to randomly generate a plurality of individuals based on a constraint condition, wherein the constraint condition is that a sum of bandwidths required by the services under the SDN switch is smaller than a bandwidth preset by the SDN switch.
In some embodiments, the SDN configuration device 40 further comprises: a fitness calculation module 440 configured to determine configuration information of each service under the SDN switch according to a value of a gene in an individual; and determining the sum of computing resources consumed by each service under the SDN switch according to the configuration information of each service, wherein the sum is used as the individual fitness.
In some embodiments, the configuration information includes the number of services, processing power, and power consumption.
In some embodiments, the plurality of iterative updates comprises a first iterative update and a second iterative update; the first iterative update includes: determining a first test individual of the individuals through a differential evolution algorithm; determining the individual with the highest fitness among the individuals and the first test individuals of the individuals as an updating result of the individual in the iterative updating; the second iterative update includes: determining a first test individual of the individuals through a differential evolution algorithm; determining a second trial individual of the individuals by randomly rearranging the genes of the intermediate individuals; and determining the individual with the highest fitness among the individual, the first test individual of the individual and the second test individual of the individual as an updating result of the individual in the current iteration updating.
In some embodiments, the iterative update module 420 is further configured to perform a preset number of first iterative updates; a second iterative update is performed a plurality of times until a termination condition is satisfied.
In some embodiments, the iterative update module 420 is further configured to perform a plurality of first iterative updates until the fitness of the individual decreases by less than a preset magnitude; a second iterative update is performed a plurality of times until a termination condition is satisfied.
In some embodiments, the SDN configuration device 40 may be connected to or located inside the SDN controller, so as to issue the calculation result to the SDN controller, and the SDN controller configures the switch connected thereto according to the calculation result.
Figure 5 illustrates a block diagram of an SDN configuration apparatus according to further embodiments of the present invention. As shown in fig. 5, the SDN configuration apparatus 50 of this embodiment includes: a memory 510 and a processor 520 coupled to the memory 510, the processor 520 configured to execute the SDN configuration method in any of the foregoing embodiments based on instructions stored in the memory 510.
Figure 6 illustrates a block diagram of an SDN configuration apparatus according to further embodiments of the invention. As shown in fig. 6, the SDN configuration apparatus 60 of this embodiment includes: the memory 610 and the processor 620 may further include an input/output interface 630, a network interface 640, a storage interface 650, and the like. These interfaces 630, 640, 650 and the connections between the memory 610 and the processor 620 may be, for example, via a bus 660. The input/output interface 630 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 640 provides a connection interface for various networking devices. The storage interface 650 provides a connection interface for external storage devices such as an SD card and a usb disk.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is configured to implement any one of the SDN configuration methods when executed by a processor.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (11)
1. An SDN configuration method, comprising:
randomly generating a plurality of individuals, wherein each individual comprises a plurality of genes, and each gene corresponds to configuration information of one service under the SDN switch;
performing a plurality of iterative updates to the plurality of individuals, wherein for each individual of the plurality of individuals, at least one iterative update comprises:
determining a first test individual of the individuals through a differential evolution algorithm;
determining a second trial individual of said individuals by randomly rearranging the genes of said intermediate individuals; and
determining an individual with the highest fitness among the individual, a first test individual of the individuals and a second test individual of the individuals as an updating result of the individual in the current iteration updating;
and determining the configuration information of each service under the SDN switch according to the result of the multiple iterative updating.
2. The SDN configuration method of claim 1, wherein the determining, by a differential evolution algorithm, a first trial individual of the individuals comprises:
for each gene in the individuals, adding results of multiplying the difference between the value of the gene of a first individual other than the individuals and the value of the gene of a second individual and a third individual by a preset coefficient, and determining the addition result as the value of the gene in an intermediate individual of the individuals, wherein the value of the gene in the intermediate individual is within a preset range;
and crossing the individuals with the intermediate individuals to obtain first test individuals.
3. The SDN configuration method of claim 1, wherein the plurality of individuals are randomly generated based on a constraint condition, wherein the constraint condition is that a sum of bandwidths required by the traffic under the SDN switch is smaller than a bandwidth preset by the SDN switch.
4. The SDN configuration method of claim 1, further comprising:
determining configuration information of each service under the SDN switch according to the value of the gene in the individual;
and determining the sum of the computing resources consumed by each service under the SDN switch according to the configuration information of each service, wherein the sum is used as the fitness of the individual.
5. The SDN configuration method according to any one of claims 1-4, wherein the configuration information comprises number of services, processing power and power consumption.
6. The SDN configuration method of any one of claims 1-4, wherein the plurality of iterative updates comprises a first iterative update and a second iterative update;
performing a first iterative update on the plurality of individuals comprises:
determining a first test individual of the individuals through a differential evolution algorithm; and
determining the individual with the highest fitness among the individual and the first test individual of the individuals as an updating result of the individual in the current iteration updating; performing a second iterative update on the plurality of individuals comprises:
determining a first test individual of the individuals through a differential evolution algorithm;
determining a second trial individual of said individuals by randomly rearranging the genes of said intermediate individuals; and
and determining the individual with the highest fitness among the individual, the first test individual of the individual and the second test individual of the individual as the updating result of the individual in the current iteration updating.
7. The SDN configuration method of claim 6, wherein the plurality of iterative updates to the plurality of individuals comprises:
executing a preset number of first iteration updates;
a second iterative update is performed a plurality of times until a termination condition is satisfied.
8. The SDN configuration method of claim 6, wherein the plurality of iterative updates to the plurality of individuals comprises:
executing a plurality of first iteration updates until the fitness of the individual is reduced to a degree smaller than a preset degree;
a second iterative update is performed a plurality of times until a termination condition is satisfied.
9. An SDN configuration apparatus comprising:
the system comprises an initialization module, a service module and a service module, wherein the initialization module is configured to randomly generate a plurality of individuals, each individual comprises a plurality of genes, and each gene corresponds to configuration information of one service under an SDN switch;
an iterative update module configured to perform a plurality of iterative updates on the plurality of individuals, wherein for each individual of the plurality of individuals, at least one iterative update comprises: determining a first test individual of the individuals through a differential evolution algorithm; determining a second trial individual of said individuals by randomly rearranging the genes of said intermediate individuals; determining an individual with the highest fitness among the individual, a first test individual of the individuals and a second test individual of the individuals as an updating result of the individual in the current iteration updating;
and the configuration information determining module is configured to determine configuration information of each service under the SDN switch according to the result of the multiple iterative updating.
10. An SDN configuration apparatus comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the SDN configuration method of any of claims 1-8 based on instructions stored in the memory.
11. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the SDN configuration method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010227064.0A CN113452540B (en) | 2020-03-27 | 2020-03-27 | SDN configuration method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010227064.0A CN113452540B (en) | 2020-03-27 | 2020-03-27 | SDN configuration method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113452540A true CN113452540A (en) | 2021-09-28 |
| CN113452540B CN113452540B (en) | 2022-08-30 |
Family
ID=77807651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010227064.0A Active CN113452540B (en) | 2020-03-27 | 2020-03-27 | SDN configuration method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113452540B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180006928A1 (en) * | 2016-06-30 | 2018-01-04 | Futurewei Technologies, Inc. | Multi-controller control traffic balancing in software defined networks |
| 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 |
| CN109151837A (en) * | 2018-08-21 | 2019-01-04 | 广东工业大学 | A kind of controller and gateway combine disposition optimization algorithm |
| CN110149226A (en) * | 2019-05-14 | 2019-08-20 | 电子科技大学中山学院 | Improved particle swarm algorithm for multi-controller deployment problem in software defined network |
| CN110390395A (en) * | 2019-07-15 | 2019-10-29 | 电子科技大学中山学院 | Improved genetic algorithm suitable for self-adaptive mutation crossing of SDN multi-controller deployment problem |
-
2020
- 2020-03-27 CN CN202010227064.0A patent/CN113452540B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180006928A1 (en) * | 2016-06-30 | 2018-01-04 | Futurewei Technologies, Inc. | Multi-controller control traffic balancing in software defined networks |
| 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 |
| CN109151837A (en) * | 2018-08-21 | 2019-01-04 | 广东工业大学 | A kind of controller and gateway combine disposition optimization algorithm |
| CN110149226A (en) * | 2019-05-14 | 2019-08-20 | 电子科技大学中山学院 | Improved particle swarm algorithm for multi-controller deployment problem in software defined network |
| CN110390395A (en) * | 2019-07-15 | 2019-10-29 | 电子科技大学中山学院 | Improved genetic algorithm suitable for self-adaptive mutation crossing of SDN multi-controller deployment problem |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113452540B (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Galinier et al. | An efficient memetic algorithm for the graph partitioning problem | |
| Gao et al. | Hierarchical multi-agent optimization for resource allocation in cloud computing | |
| Bhimani et al. | Accelerating K-Means clustering with parallel implementations and GPU computing | |
| CN108664330B (en) | cloud resource allocation method based on variable neighborhood search strategy | |
| CN108667657B (en) | SDN-oriented virtual network mapping method based on local feature information | |
| CN107911300B (en) | Multicast routing optimization method based on whale algorithm and application of multicast routing optimization method on Spark platform | |
| US20190377606A1 (en) | Smart accelerator allocation and reclamation for deep learning jobs in a computing cluster | |
| Apolloni et al. | Empirical evaluation of distributed differential evolution on standard benchmarks | |
| CN108399105B (en) | Software and hardware partitioning method based on improved brainstorming algorithm | |
| WO2009142011A1 (en) | Decision device with minimum power transmission loss system, method, and program | |
| CN113472671A (en) | Method and device for determining multicast route and computer readable storage medium | |
| CN111340192A (en) | Network path allocation model training method, path allocation method and device | |
| CN107872405A (en) | Distributed bandwidth allocation and regulation | |
| CN113452540B (en) | SDN configuration method and device and computer readable storage medium | |
| CN107257307B (en) | Spark-based method for solving multi-terminal cooperative access network by parallelization genetic algorithm | |
| Im et al. | Tight bounds for online vector scheduling | |
| Liu et al. | Automated traffic engineering in SDWAN: Beyond reinforcement learning | |
| Di et al. | Cost efficient virtual infrastructure mapping using subgraph isomorphism | |
| Hiwa et al. | Novel search scheme for multi-objective evolutionary algorithms to obtain well-approximated and widely spread Pareto solutions | |
| Garg et al. | Heuristic and reinforcement learning algorithms for dynamic service placement on mobile edge cloud | |
| WO2017213537A1 (en) | Parallel optimization of homogeneous systems | |
| CN114021708B (en) | Data processing method, device and system, electronic equipment and storage medium | |
| Zerwas et al. | Ismael: Using machine learning to predict acceptance of virtual clusters in data centers | |
| CN113015179B (en) | Network resource selection method and device based on deep Q network and storage medium | |
| CN108520025B (en) | Service node determination method, device, equipment and medium |
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 |