CN118175561A - Quick prediction and matching method for cost-driven service function chain - Google Patents
Quick prediction and matching method for cost-driven service function chain Download PDFInfo
- Publication number
- CN118175561A CN118175561A CN202410589061.XA CN202410589061A CN118175561A CN 118175561 A CN118175561 A CN 118175561A CN 202410589061 A CN202410589061 A CN 202410589061A CN 118175561 A CN118175561 A CN 118175561A
- Authority
- CN
- China
- Prior art keywords
- service
- service function
- function chain
- attribute
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000006243 chemical reaction Methods 0.000 claims abstract description 37
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 238000005381 potential energy Methods 0.000 claims description 24
- 230000009466 transformation Effects 0.000 claims description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 4
- QAPUWNJNUGPVPM-NTUXHYESSA-N (17z,23z)-3-butyl-4,6,8,10,12,14,16,27-octahydroxy-17,28-dimethyl-1-oxacyclooctacosa-17,19,21,23,25-pentaen-2-one Chemical compound CCCCC1C(O)CC(O)CC(O)CC(O)CC(O)CC(O)CC(O)\C(C)=C/C=CC=C\C=C/C=CC(O)C(C)OC1=O QAPUWNJNUGPVPM-NTUXHYESSA-N 0.000 claims description 3
- 230000003139 buffering effect Effects 0.000 claims description 3
- 239000003054 catalyst Substances 0.000 claims description 3
- QAPUWNJNUGPVPM-UHFFFAOYSA-N chainin Natural products CCCCC1C(O)CC(O)CC(O)CC(O)CC(O)CC(O)CC(O)C(C)=CC=CC=CC=CC=CC(O)C(C)OC1=O QAPUWNJNUGPVPM-UHFFFAOYSA-N 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 230000010365 information processing Effects 0.000 claims description 3
- 238000005295 random walk Methods 0.000 claims description 3
- 238000013468 resource allocation Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 7
- 238000005265 energy consumption Methods 0.000 abstract 1
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
- H04W28/24—Negotiating SLA [Service Level Agreement]; Negotiating QoS [Quality of Service]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Molecular Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Biomedical Technology (AREA)
- Automation & Control Theory (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a quick prediction and matching method of a service function chain driven by cost, which relates to the technical field of new generation information, and utilizes a fuzzy mathematic theory RST and a chemical reaction optimization algorithm CRO as core search tools to efficiently match service for service requests; the invention improves QOS through the fuzzy mathematical theory model, effectively shortens service matching time, obviously reduces system energy consumption cost, and improves matching efficiency of service function chains and overall throughput of a communication system.
Description
Technical Field
The invention relates to the technical field of new generation information, in particular to a cost-driven service function chain rapid prediction and matching method.
Background
Along with the explosive development of 5G communication technology, the advanced manufacturing industry and the Internet communication technology are deeply integrated by the industrial Internet of things, and the industrial Internet of things becomes one of the most important application scenes of 5G. Along with the emergence of a large number of industrial equipment terminal nodes and mass network services in the industrial Internet of things scene, the demands of time sensitivity and deterministic task transmission are met as primary tasks. Considering that the performance requirements of different terminal nodes may vary greatly in a dynamic environment, how to quickly and guarantee the service for matching the service request becomes a difficulty. Fuzzy set theory may define fuzzy rules and membership functions to quantify QoS levels of services to help select services that meet user requirements (SLAs). The chemical reaction optimization algorithm has high flexibility, and the optimal route and the optimal cost for solving the service function chain have the unique advantages. How to utilize fuzzy set theory to strengthen chemical reaction optimization algorithm as tool research of matching service chain has great significance.
The introduction of fuzzy set theory in dynamic communication environments has great advantages. A fuzzy logic reasoning method is presented to improve the performance and adaptability of a communication system. Traffic requests typically involve multiple QoS parameters such as response time, availability, throughput, etc., while these parameters tend to be qualitative, ambiguous, and uncertain. How to evaluate this qualitative ambiguity versus quantitative access matching mechanism in a dynamic service request environment is a challenge.
Chemical reaction optimization algorithms, which are one of the branches of the optimization algorithm, exhibit their unique advantages in solving optimization problems, especially NP (non-deterministic polynomial) hard problems. In the field of service matching, CRO can be effectively applied to service composition, service selection and service configuration problems to achieve optimization of service quality and improvement of system efficiency. However, the performance of the CRO algorithm depends largely on its parameter configuration, which may lead to premature convergence of the algorithm to a locally optimal solution or a search inefficiency when solving large-scale, dynamic service matching problems.
Therefore, a cost-driven service function chain fast prediction and matching method is needed to solve the above problems.
Disclosure of Invention
The invention aims to provide a quick prediction and matching method for a service function chain driven by cost, which adopts a fuzzy mathematical theory, effectively solves the ambiguity and uncertainty in a large-scale service request, and screens the service function chain potentially meeting the basic requirements of the service in a system to the maximum extent.
In order to achieve the above purpose, the present invention provides a method for quickly predicting and matching a service function chain driven by cost, comprising the following steps:
S1: for real-time service request information and active service function chain information collected by a radio access information processing control center, respectively extracting service request and service function chain characteristics by adopting cross-domain transformation, and jointly establishing an objective function model;
S2: introducing a Bayesian network, acquiring network request attribute feature preference, introducing a fuzzy set theoretical model, and screening out a service function chain fuzzy set meeting business requirements;
S3: and solving an objective function model, introducing a chemical reaction optimization algorithm into a matching system, adjusting the layout and resource allocation of a service function chain, and minimizing service response time and resource utilization rate.
Preferably, in step S1, the following steps are specifically adopted:
s11: extracting network request and service function chain characteristics by using cross-domain transformation, wherein a heterogeneous network diagram comprising network business and online service function chain of requesting service at a certain moment is WhereinIs a collection of network requests,Is an online service function chain set, and the information characteristic of the network request and the service function chain is represented by a matrixRepresentation, whereinFor network request or service function chain number,Is the dimension of information features, network trafficThe mapping of information in different dimensions is realized by adopting linear transformation:
（1）
Wherein the method comprises the steps of Representing requestIn attribute spaceData characteristics ofIs a transformation matrix to transform trafficData information ofMapping to attribute spaceThe service function chain information is mapped to the same space domain; the attribute information of the network request is divided into a core attribute C and a non-core attribute D;
S12: establishing a quality of service model, establishing a quality of service model for a quality of service level (QoS) of a service function chain ：
（2）
Wherein,As binary variables, the service function chain satisfies the basic requirement/>, of the businessTime,; Otherwise；Network function attributes required for virtual requests provided for service function chains,Is an attributeWeight value ofRequesting a number of features for the network;
s13: establishing a matching system cost model and a service function chain CostExpressed as:
（3）
Where n represents the number of network functions in the VNF set, m represents the number of features in the repository, Indicating service function chain completionFirst/>, of personal network functionsCost of the individual features; the resources required by the VNF in the virtual service depend on the virtualized resource pool,Expressed as:
（4）
Where N is the number of physical nodes needed to provide the virtual resources needed, Representing the number of different resources, their costs and the sum of the costs of the different resource deployments as network functions,Respectively represent the composition of the firstFirst/>, of personal network functionsFrequency, power and amount of resources consumed by service resources required by each feature,Representing frequency, power, and unit price of service, respectively; /(I)The cost required to implement network functions for deploying resources is expressed as:
（5）
Wherein, Is a weight factor of different resources, satisfiesAnd (2) and；
When the virtual resource is composed of a plurality of physical nodes, N >1:
， representing coordination of N APs to achieve the/> First/>, of personal network functionsCost for individual features;
when the AP provides various physical resources, 0< N <1:
Wherein/> Expressed asFunctionalThe N virtual function modules with the characteristics share the resources at the required cost;
in the other case of the use of a gas, ；
S14: establishing an objective function model, establishing an objective function model by combining a service quality model and a matching system cost model, and matching an optimal service function chain for a network request by optimizing service quality and matching system cost, wherein the objective function model is a set of objective function modelsThe definition is as follows:
（6）
Wherein the method comprises the steps of Is a parameterFor serving functional chainQuality of service provided,For the cost of servicing a functional chain,As binary variables, when serving functional chainMeeting basic requirement C of business,; In other cases；Is the base of a natural logarithmic function;
probability model of objective function Expressed as an optimization problem:
。
Preferably, in step S2, the method specifically includes the following steps:
S21: obtaining network request attribute feature weights using a bayesian network The degree of association between attributes and categories is characterized by using a Bayesian network:
（7）
（8）
Wherein, Is mutual information used to represent the correlation between different information,Representing service function chain categoryAnd attribute featuresCorrelation ofRepresenting service function chain attribute featuresAndCorrelation between; For category/> Prior probability ofIs a conditional probability,Is an attributeThe probability of the presence of a compound,Is an attribute featureAndProbability of simultaneous existence;
Assigning weights to the attributes based on the degrees of dependence, and normalizing the degrees of dependence:
（9）
（10）
Where S is the number of non-core attributes, the preference of the attributes is as follows:
，（14）
s22: acquiring service function chain fuzzy sets belonging to service requests by utilizing fuzzy set theory, and establishing a heterogeneous graph according to the service requests and the service function chain information acquired in the step S11 ，For a service request entering the system at a certain moment,For this purpose, an online service function chain, whereinAre non-empty finite sets.
Preferably, in step S22, the following steps are included:
acquiring service function chain fuzzy set by fuzzy set theory, wherein fuzzy relation exists between network request and service function chain Expressed as:
（15）
Wherein, Is a determined attribute category，Representing virtual requestIn the attribute categoryAttribute value determined below,Representing service function chainIn the attribute categoryDetermining a property value;
Constructing service requests Upper and lower fuzzy bounds:
，（16）
Obtaining service function chain fuzzy set belonging to service request through fuzzy rule 。
Preferably, in step S3, solving the objective function model specifically includes:
Solving an objective function model by using a chemical reaction optimization algorithm, and searching an optimal solution in the set by using the chemical reaction optimization algorithm according to the service function chain fuzzy set and the attribute weight obtained in the step S2; representing a solution,/> Represents theThe structure of each molecule comprises potential energy PE and kinetic energy KE, and the potential energy is the molecular structureA quantized version of energy, buff representing the buffering energy resulting from an invalid molecular collision; the method specifically comprises the following steps:
S31: the reaction of the collision is carried out, Is the molecular structure after collision,ForStructure of lowest potential energy of individual molecules,Based on the traditional CRO, the Gaussian model pair/>, which is the structure with the lowest potential energy of the current global molecule, is adoptedMolecularPerturbation is carried out, and a random walking model is shown in theThe structure with the lowest potential energy in the individual molecules walks between the structure with the lowest global potential energy, and after the molecules strike the wall, a new molecular structure is obtained, as shown in the following formula:
（17）
Wherein, Representation ofThe lowest potential energy of individual molecules adds a gaussian perturbation,Is a random number, and the sufficient and necessary condition for collision reaction generation is；
According to the law of conservation of energy, the molecular kinetic energy after the reaction is:
（18）
In the above-mentioned method, the step of, For energy conversion efficiency,，Is a known threshold;
S32: the decomposition reaction is carried out, and the catalyst is prepared, AndIs the structure of two molecules generated by the decomposition reaction, pairUsing gaussian perturbation, then random walk generation:
（19）
the conditions under which the decomposition reaction occurs are ；
The kinetic energy of the new molecule generated is expressed as:
（20）
s33: exchange reaction is carried out, and the two molecular structures are AndDuring the molecular exchange, adding random values into the molecular structure:
（21）
Wherein, RepresentationAnyPartial energy substitution，Is a randomly generated molecular structure; the conditions under which the exchange reaction occurs are:
（22）
Wherein the method comprises the steps of Kinetic energy/>, which is a temporary variable, of new molecules through the law of conservation of energyThe method comprises the following steps:
（23）
S34: carrying out synthesis reaction, two molecular structures AndCombined reaction takes place,；
The conditions under which the synthesis reaction takes place are:
（22）
kinetic energy of newly generated molecules according to law of conservation of energy The method comprises the following steps:
（23）
in service function chain fuzzy set F Carrying out chemical reaction, recording the result P obtained by the molecular state with the lowest potential energy,And comparing the obtained result with the global optimum MAX (P), iterating until the global optimum is found, and matching the service function chain to the corresponding network request.
Therefore, the cost-driven service function chain rapid prediction and matching method has the following beneficial effects:
(1) The invention not only ensures that the matching system meets the basic requirement of the service request, but also can dynamically adjust the service link according to the actual situation and balance the network resource consumption through the optimization based on the cost and the performance.
(2) The invention not only can improve the performance and the adaptability of the communication system, but also can better cope with the change and the challenges in the dynamic environment.
(3) The invention adopts the fuzzy mathematical theory, effectively solves the ambiguity and uncertainty in large-scale service requests, and screens the service function chains potentially meeting the basic requirements of the service in the system to the maximum extent.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a flow chart of a cost-driven service function chain fast prediction and matching method of the present invention;
Detailed Description
The technical scheme of the invention is further described below through the attached drawings and the embodiments.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
As used herein, the word "comprising" or "comprises" and the like means that elements preceding the word encompass the elements recited after the word, and not exclude the possibility of also encompassing other elements. The terms "inner," "outer," "upper," "lower," and the like are used for convenience in describing and simplifying the description based on the orientation or positional relationship shown in the drawings, and do not denote or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the invention, but the relative positional relationship may be changed when the absolute position of the object to be described is changed accordingly. In the present invention, unless explicitly specified and limited otherwise, the term "attached" and the like should be construed broadly, and may be, for example, fixedly attached, detachably attached, or integrally formed; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances. The term "about" as used herein has a meaning well known to those skilled in the art, and preferably means that the term is modified by a value within the range of + -50%, + -40%, + -30%, + -20%, + -10%, + -5% or + -1%.
As shown in fig. 1, the invention provides a method for quickly predicting and matching a service function chain driven by cost, which comprises the following steps:
S1: for real-time service request information and active service function chain information collected by a radio access information processing control center, respectively extracting service request and service function chain characteristics by adopting cross-domain transformation, and jointly establishing an objective function model; in step S1, the following steps are specifically adopted:
s11: extracting network request and service function chain characteristics by using cross-domain transformation, wherein a heterogeneous network diagram comprising network business and online service function chain of requesting service at a certain moment is WhereinIs a collection of network requests,Is an online service function chain set, and the information characteristic of the network request and the service function chain is represented by a matrixRepresentation, whereinFor network request or service function chain number,Is the dimension of information features, network trafficThe mapping of information in different dimensions is realized by adopting linear transformation:
（1）
Wherein the method comprises the steps of Representing requestIn attribute spaceData characteristics ofIs a transformation matrix to transform trafficData information ofMapping to attribute spaceThe service function chain information is mapped to the same space domain; the attribute information of the network request is divided into a core attribute C and a non-core attribute D;
S12: establishing a quality of service model, establishing a quality of service model for a quality of service level (QoS) of a service function chain ：
（2）
Wherein,As binary variables, the service function chain satisfies the basic requirement/>, of the businessTime,; Otherwise；Network function attributes required for virtual requests provided for service function chains,Is an attributeWeight value ofRequesting a number of features for the network;
s13: establishing a matching system cost model and a service function chain CostExpressed as:
（3）
Where n represents the number of network functions in the VNF set, m represents the number of features in the repository, Indicating service function chain completionFirst/>, of personal network functionsCost of the individual features; the resources required by the VNF in the virtual service depend on the virtualized resource pool,Expressed as:
（4）
Where N is the number of physical nodes needed to provide the virtual resources needed, Representing the number of different resources, their costs and the sum of the costs of the different resource deployments as network functions,Respectively represent the composition of the firstFirst/>, of personal network functionsFrequency, power and amount of resources consumed by service resources required by each feature,Representing frequency, power, and unit price of service, respectively; /(I)The cost required to implement network functions for deploying resources is expressed as:
（5）
Wherein, Is a weight factor of different resources, satisfiesAnd (2) and；
When the virtual resource is composed of a plurality of physical nodes, N >1:
， representing coordination of N APs to achieve the/> First/>, of personal network functionsCost for individual features;
when the AP provides various physical resources, 0< N <1:
Wherein/> Expressed asFunctionalThe N virtual function modules with the characteristics share the resources at the required cost;
in the other case of the use of a gas, ；
S14: establishing an objective function model, establishing an objective function model by combining a service quality model and a matching system cost model, and matching an optimal service function chain for a network request by optimizing service quality and matching system cost, wherein the objective function model is a set of objective function modelsThe definition is as follows:
（6）
Wherein the method comprises the steps of Is a parameterFor serving functional chainQuality of service provided,For the cost of servicing a functional chain,As binary variables, when serving functional chainMeeting basic requirement C of business,; In other cases；Is the base of a natural logarithmic function;
probability model of objective function Expressed as an optimization problem:
。
s2: introducing a Bayesian network, acquiring network request attribute feature preference, introducing a fuzzy set theoretical model, and screening out a service function chain fuzzy set meeting business requirements; in step S2, the method specifically includes the following steps:
S21: obtaining network request attribute feature weights using a bayesian network The degree of association between attributes and categories is characterized by using a Bayesian network:
（7）
（8）
Wherein, Is mutual information used to represent the correlation between different information,Representing service function chain categoryAnd attribute featuresCorrelation ofRepresenting service function chain attribute featuresAndCorrelation between; For category/> Prior probability ofIs a conditional probability,Is an attributeThe probability of the presence of a compound,Is an attribute featureAndProbability of simultaneous existence;
Assigning weights to the attributes based on the degrees of dependence, and normalizing the degrees of dependence:
（9）
（10）
Where S is the number of non-core attributes, the preference of the attributes is as follows:
，（14）
s22: acquiring service function chain fuzzy sets belonging to service requests by utilizing fuzzy set theory, and establishing a heterogeneous graph according to the service requests and the service function chain information acquired in the step S11 ，For a service request entering the system at a certain moment,For this purpose, an online service function chain, whereinAre non-empty finite sets. The step S22 includes the steps of:
acquiring service function chain fuzzy set by fuzzy set theory, wherein fuzzy relation exists between network request and service function chain Expressed as:
（15）
Wherein, Is a determined attribute category，Representing virtual requestIn the attribute categoryAttribute value determined below,Representing service function chainIn the attribute categoryDetermining a property value;
Constructing service requests Upper and lower fuzzy bounds:
，（16）
Obtaining service function chain fuzzy set belonging to service request through fuzzy rule 。
S3: and solving an objective function model, introducing a chemical reaction optimization algorithm into a matching system, adjusting the layout and resource allocation of a service function chain, and minimizing service response time and resource utilization rate. In step S3, the solving the objective function model specifically includes:
Solving an objective function model by using a chemical reaction optimization algorithm, and searching an optimal solution in the set by using the chemical reaction optimization algorithm according to the service function chain fuzzy set and the attribute weight obtained in the step S2; representing a solution,/> Represents theThe structure of each molecule comprises potential energy PE and kinetic energy KE, and the potential energy is the molecular structureA quantized version of energy, buff representing the buffering energy resulting from an invalid molecular collision; the method specifically comprises the following steps:
S31: the reaction of the collision is carried out, Is the molecular structure after collision,ForStructure of lowest potential energy of individual molecules,Based on the traditional CRO, the Gaussian model pair/>, which is the structure with the lowest potential energy of the current global molecule, is adoptedMolecularPerturbation is carried out, and a random walking model is shown in theThe structure with the lowest potential energy in the individual molecules walks between the structure with the lowest global potential energy, and after the molecules strike the wall, a new molecular structure is obtained, as shown in the following formula:
（17）
Wherein, Representation ofThe lowest potential energy of individual molecules adds a gaussian perturbation,Is a random number, and the sufficient and necessary condition for collision reaction generation is；/>
According to the law of conservation of energy, the molecular kinetic energy after the reaction is:
（18）
In the above-mentioned method, the step of, For energy conversion efficiency,，Is a known threshold;
S32: the decomposition reaction is carried out, and the catalyst is prepared, AndIs the structure of two molecules generated by the decomposition reaction, pairUsing gaussian perturbation, then random walk generation:
（19）
the conditions under which the decomposition reaction occurs are ；
The kinetic energy of the new molecule generated is expressed as:
（20）
s33: exchange reaction is carried out, and the two molecular structures are AndDuring the molecular exchange, adding random values into the molecular structure:
（21）
Wherein, RepresentationAnyPartial energy substitution，Is a randomly generated molecular structure; the conditions under which the exchange reaction occurs are:
（22）
Wherein the method comprises the steps of Kinetic energy/>, which is a temporary variable, of new molecules through the law of conservation of energyThe method comprises the following steps:
（23）
S34: carrying out synthesis reaction, two molecular structures AndCombined reaction takes place,；
The conditions under which the synthesis reaction takes place are:
（22）
kinetic energy of newly generated molecules according to law of conservation of energy The method comprises the following steps: /(I)
（23）
In service function chain fuzzy set FCarrying out chemical reaction, recording the result P obtained by the molecular state with the lowest potential energy,And comparing the obtained result with the global optimum MAX (P), iterating until the global optimum is found, and matching the service function chain to the corresponding network request.
Therefore, the invention adopts the quick prediction and matching method of the service function chain driven by cost, adopts the fuzzy mathematical theory, effectively solves the ambiguity and uncertainty in large-scale service requests, and screens the service function chain which potentially meets the basic requirements of the service in the system to the maximum extent; the matching system not only meets the basic requirements of service requests, but also can dynamically adjust service links according to actual conditions and balance network resource consumption through optimization based on cost and performance; not only can the performance and adaptability of the communication system be improved, but also the change and the challenges in the dynamic environment can be better dealt with.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (5)
1. A quick prediction and matching method of a service function chain driven by cost is characterized by comprising the following steps:
S1: for real-time service request information and active service function chain information collected by a radio access information processing control center, respectively extracting service request and service function chain characteristics by adopting cross-domain transformation, and jointly establishing an objective function model;
S2: introducing a Bayesian network, acquiring network request attribute feature preference, introducing a fuzzy set theoretical model, and screening out a service function chain fuzzy set meeting business requirements;
S3: and solving an objective function model, introducing a chemical reaction optimization algorithm into a matching system, adjusting the layout and resource allocation of a service function chain, and minimizing service response time and resource utilization rate.
2. The method for quickly predicting and matching a cost-driven service function chain according to claim 1, wherein the method comprises the following steps: in step S1, the following steps are specifically adopted:
s11: extracting network request and service function chain characteristics by using cross-domain transformation, wherein a heterogeneous network diagram comprising network business and online service function chain of requesting service at a certain moment is WhereinIs a collection of network requests,Is an online service function chain set, and the information characteristic of the network request and the service function chain is represented by a matrixRepresentation, whereinFor network request or service function chain number,Is the dimension of information features, network trafficThe mapping of information in different dimensions is realized by adopting linear transformation:
（1）
Wherein the method comprises the steps of Representing requestIn attribute spaceData characteristics ofIs a transformation matrix to transform trafficData information ofMapping to attribute spaceThe service function chain information is mapped to the same space domain; the attribute information of the network request is divided into a core attribute C and a non-core attribute D;
S12: establishing a quality of service model, and establishing the quality of service model aiming at the quality of service level QoS of a service function chain ：
（2）
Wherein,As binary variables, the service function chain satisfies the basic requirement/>, of the businessTime,; Otherwise；Network function attributes required for virtual requests provided for service function chains,Is an attributeWeight value ofRequesting a number of features for the network;
s13: establishing a matching system cost model and a service function chain CostExpressed as:
（3）
Where n represents the number of network functions in the VNF set, m represents the number of features in the repository, Indicating service function chain completionFirst/>, of personal network functionsCost of the individual features; the resources required by the VNF in the virtual service depend on the virtualized resource pool,Expressed as:
（4）
Where N is the number of physical nodes needed to provide the virtual resources needed, Representing the number of different resources, their costs and the sum of the costs of the different resource deployments as network functions,Respectively represent the composition of the firstFirst/>, of personal network functionsFrequency, power and amount of resources consumed by service resources required by each feature,Representing frequency, power, and unit price of service, respectively; /(I)The cost required to implement network functions for deploying resources is expressed as:
（5）
Wherein, Is a weight factor of different resources, satisfiesAnd (2) and；
When the virtual resource is composed of a plurality of physical nodes, N >1:
， representing coordination of N APs to achieve the/> First/>, of personal network functionsCost for individual features;
when the AP provides various physical resources, 0< N <1:
Wherein/> Expressed asFunctionalThe N virtual function modules with the characteristics share the resources at the required cost;
in the other case of the use of a gas, ；
S14: establishing an objective function model, establishing an objective function model by combining a service quality model and a matching system cost model, and matching an optimal service function chain for a network request by optimizing service quality and matching system cost, wherein the objective function model is a set of objective function modelsThe definition is as follows:
（6）
Wherein the method comprises the steps of Is a parameterFor serving functional chainQuality of service provided,For the cost of servicing a functional chain,As binary variables, when serving functional chainMeeting basic requirement C of business,; In other cases；Is the base of a natural logarithmic function;
probability model of objective function Expressed as an optimization problem:
。
3. The method for quickly predicting and matching a cost-driven service function chain according to claim 1, wherein the method comprises the following steps: in step S2, the method specifically includes the following steps:
S21: obtaining network request attribute feature weights using a bayesian network The degree of association between attributes and categories is characterized by using a Bayesian network:
（7）
（8）
Wherein, Is mutual information used to represent the correlation between different information,Representing service function chain categoryAnd attribute featuresCorrelation ofRepresenting service function chain attribute featuresAndCorrelation between; For category/> Prior probability ofIs a conditional probability,Is an attributeThe probability of the presence of a compound,Is an attribute featureAndProbability of simultaneous existence;
Assigning weights to the attributes based on the degrees of dependence, and normalizing the degrees of dependence:
（9）
（10）
Where S is the number of non-core attributes, the preference of the attributes is as follows:
，（14）
s22: acquiring service function chain fuzzy sets belonging to service requests by utilizing fuzzy set theory, and establishing a heterogeneous graph according to the service requests and the service function chain information acquired in the step S11 ，For a service request entering the system at a certain moment,For this purpose, an online service function chain, whereinAre non-empty finite sets.
4. A method for fast predicting and matching a cost-driven service function chain according to claim 3, wherein: in step S22, the following steps are included:
acquiring service function chain fuzzy set by fuzzy set theory, wherein fuzzy relation exists between network request and service function chain Expressed as:
（15）
Wherein, Is a determined attribute category，Representing virtual requestIn the attribute categoryAttribute value determined below,Representing service function chainIn the attribute categoryDetermining a property value;
Constructing service requests Upper and lower fuzzy bounds:
，（16）
Obtaining service function chain fuzzy set belonging to service request through fuzzy rule 。
5. The method for quickly predicting and matching a cost-driven service function chain according to claim 1, wherein the method comprises the following steps: in step S3, the solving the objective function model specifically includes:
Solving an objective function model by using a chemical reaction optimization algorithm, and searching an optimal solution in the set by using the chemical reaction optimization algorithm according to the service function chain fuzzy set and the attribute weight obtained in the step S2; representing a solution,/> Represents theThe structure of each molecule comprises potential energy PE and kinetic energy KE, and the potential energy is the molecular structureA quantized version of energy, buff representing the buffering energy resulting from an invalid molecular collision; the method specifically comprises the following steps:
S31: the reaction of the collision is carried out, Is the molecular structure after collision,ForStructure of lowest potential energy of individual molecules,Based on the traditional CRO, the Gaussian model pair/>, which is the structure with the lowest potential energy of the current global molecule, is adoptedMolecularPerturbation is carried out, and a random walking model is shown in theThe structure with the lowest potential energy in the individual molecules walks between the structure with the lowest global potential energy, and after the molecules strike the wall, a new molecular structure is obtained, as shown in the following formula:
（17）
Wherein, Representation ofThe lowest potential energy of individual molecules adds a gaussian perturbation,Is a random number, and the sufficient and necessary condition for collision reaction generation is；
According to the law of conservation of energy, the molecular kinetic energy after the reaction is:
（18）
In the above-mentioned method, the step of, For energy conversion efficiency,，Is a known threshold;
S32: the decomposition reaction is carried out, and the catalyst is prepared, AndIs the structure of two molecules generated by the decomposition reaction, pairUsing gaussian perturbation, then random walk generation:
（19）
the conditions under which the decomposition reaction occurs are ；
The kinetic energy of the new molecule generated is expressed as:
（20）
s33: exchange reaction is carried out, and the two molecular structures are AndDuring the molecular exchange, adding random values into the molecular structure:
（21）
Wherein, RepresentationAnyPartial energy substitution，Is a randomly generated molecular structure; the conditions under which the exchange reaction occurs are:
（22）
Wherein the method comprises the steps of Kinetic energy/>, which is a temporary variable, of new molecules through the law of conservation of energyThe method comprises the following steps:
（23）
S34: carrying out synthesis reaction, two molecular structures AndCombined reaction takes place,；
The conditions under which the synthesis reaction takes place are:
（22）
kinetic energy of newly generated molecules according to law of conservation of energy The method comprises the following steps:
（23）
in service function chain fuzzy set F Carrying out chemical reaction, recording the result P obtained by the molecular state with the lowest potential energy,And comparing the obtained result with the global optimum MAX (P), iterating until the global optimum is found, and matching the service function chain to the corresponding network request.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410589061.XA CN118175561B (en) | 2024-05-13 | 2024-05-13 | Quick prediction and matching method for cost-driven service function chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410589061.XA CN118175561B (en) | 2024-05-13 | 2024-05-13 | Quick prediction and matching method for cost-driven service function chain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118175561A true CN118175561A (en) | 2024-06-11 |
| CN118175561B CN118175561B (en) | 2024-07-16 |
Family
ID=91354931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410589061.XA Active CN118175561B (en) | 2024-05-13 | 2024-05-13 | Quick prediction and matching method for cost-driven service function chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118175561B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110996334A (en) * | 2019-12-09 | 2020-04-10 | 衡阳师范学院 | Virtualized wireless network function arrangement strategy |
| CN111368888A (en) * | 2020-02-25 | 2020-07-03 | 重庆邮电大学 | Service function chain fault diagnosis method based on deep dynamic Bayesian network |
| WO2023247721A1 (en) * | 2022-06-24 | 2023-12-28 | Yokogawa Insilico Biotechnology Gmbh | A concept for training and using at least one machine-learning model for modelling kinetic aspects of a biological organism |
| CN117610428A (en) * | 2023-12-07 | 2024-02-27 | 安徽大学 | New energy automobile lithium battery working condition parameter prediction method, device and medium based on fuzzy time sequence |
-
2024
- 2024-05-13 CN CN202410589061.XA patent/CN118175561B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110996334A (en) * | 2019-12-09 | 2020-04-10 | 衡阳师范学院 | Virtualized wireless network function arrangement strategy |
| CN111368888A (en) * | 2020-02-25 | 2020-07-03 | 重庆邮电大学 | Service function chain fault diagnosis method based on deep dynamic Bayesian network |
| WO2023247721A1 (en) * | 2022-06-24 | 2023-12-28 | Yokogawa Insilico Biotechnology Gmbh | A concept for training and using at least one machine-learning model for modelling kinetic aspects of a biological organism |
| CN117610428A (en) * | 2023-12-07 | 2024-02-27 | 安徽大学 | New energy automobile lithium battery working condition parameter prediction method, device and medium based on fuzzy time sequence |
Non-Patent Citations (1)
| Title |
|---|
| 吴菲菲, 中国博士学位论文全文数据库 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118175561B (en) | 2024-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113242568B (en) | Task unloading and resource allocation method in uncertain network environment | |
| Goudarzi et al. | A fast hybrid multi-site computation offloading for mobile cloud computing | |
| Liu et al. | Deep learning meets wireless network optimization: Identify critical links | |
| Sert et al. | Increasing energy efficiency of rule-based fuzzy clustering algorithms using CLONALG-M for wireless sensor networks | |
| Supraja et al. | Optimized neural network for spectrum prediction using genetic algorithm in cognitive radio networks | |
| Wang et al. | Dynamic resource allocation for jointing vehicle-edge deep neural network inference | |
| Lan et al. | Deep reinforcement learning for computation offloading and caching in fog-based vehicular networks | |
| CN114698128A (en) | Anti-interference channel selection method and system for cognitive satellite-ground network | |
| Surendran et al. | Lens-Oppositional Wild Geese Optimization Based Clustering Scheme for Wireless Sensor Networks Assists Real Time Disaster Management. | |
| Rafiq et al. | [Retracted] Mitigation Impact of Energy and Time Delay for Computation Offloading in an Industrial IoT Environment Using Levenshtein Distance Algorithm | |
| CN118175561B (en) | Quick prediction and matching method for cost-driven service function chain | |
| Anoop et al. | Exploitation whale optimization based optimal offloading approach and topology optimization in a mobile ad hoc cloud environment | |
| Liu et al. | Spectrum allocation optimization for cognitive radio networks using binary firefly algorithm | |
| Liu et al. | Efficient resource allocation for IoT applications in mobile edge computing via dynamic request scheduling optimization | |
| Lin et al. | Energy-Efficient Cooperative Task Offloading in NOMA-Enabled Vehicular Fog Computing | |
| CN114885345B (en) | System computing energy efficiency maximization resource allocation method based on differential evolution algorithm | |
| Fei et al. | Joint computational and wireless resource allocation in multicell collaborative fog computing networks | |
| Jeon et al. | Special issue on real‐time behavioral monitoring in IoT applications using big data analytics | |
| Liu et al. | Intelligent computation offloading for educational virtual reality applications in smart campus using MoCell | |
| Yao et al. | A Data-driven method for adaptive resource requirement allocation via probabilistic solar load and market forecasting utilizing digital twin | |
| Ordouei et al. | Efficient energy management in a smart city based on multi-agent systems over the Internet of Things platform | |
| Teng et al. | Application research of chaotic binary particle swarm optimization algorithm in dynamic spectrum allocation | |
| Zhan et al. | A hybrid GA-TS algorithm for optimizing networked manufacturing resources configuration | |
| Tam et al. | An evolutionary algorithm for data aggregation tree construction in three-dimensional wireless sensor networks | |
| Chen et al. | Two-Stage Evolutionary Search for Efficient Task Offloading in Edge Computing Power Networks |
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 |