CN116339973A - Digital twin cloud platform computing resource scheduling method based on particle swarm optimization algorithm - Google Patents

Digital twin cloud platform computing resource scheduling method based on particle swarm optimization algorithm Download PDF

Info

Publication number
CN116339973A
CN116339973A CN202211708427.8A CN202211708427A CN116339973A CN 116339973 A CN116339973 A CN 116339973A CN 202211708427 A CN202211708427 A CN 202211708427A CN 116339973 A CN116339973 A CN 116339973A
Authority
CN
China
Prior art keywords
individuals
population
individual
resource scheduling
target value
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.)
Pending
Application number
CN202211708427.8A
Other languages
Chinese (zh)
Inventor
刘再斌
范涛
马良
韩保山
李贵红
李鹏
巨朝晖
雷晓荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
XI'AN RESEARCH INSTITUTE OF CHINA COAL RESEARCH INSTITUTE
Original Assignee
XI'AN RESEARCH INSTITUTE OF CHINA COAL RESEARCH INSTITUTE
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by XI'AN RESEARCH INSTITUTE OF CHINA COAL RESEARCH INSTITUTE filed Critical XI'AN RESEARCH INSTITUTE OF CHINA COAL RESEARCH INSTITUTE
Priority to CN202211708427.8A priority Critical patent/CN116339973A/en
Publication of CN116339973A publication Critical patent/CN116339973A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • 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
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to a digital twin cloud platform computing resource scheduling method based on a particle swarm optimization algorithm, which comprises the following steps: determining the number of allocable virtual resources; determining an optimization target of a resource scheduling task; the decision variable in the optimization target is a resource scheduling scheme, and the resource scheduling scheme is a resource scheduling task number of each allocable virtual resource operation; and solving an optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme. According to the particle swarm optimization algorithm-based digital twin cloud platform computing resource scheduling method, the problem of digital twin cloud platform computing resource scheduling is solved by combining cross compiling operation on the basis of a traditional particle swarm algorithm, and the cloud platform computing resource scheduling performance is effectively improved.

Description

Digital twin cloud platform computing resource scheduling method based on particle swarm optimization algorithm
Technical Field
The application relates to the technical field of cloud computing, in particular to a digital twin cloud platform computing resource scheduling method based on a particle swarm optimization algorithm.
Background
The concept of resource scheduling is a process of adjusting resources among resource requesters according to specific resource allocation rules and methods in specific resource allocation. In the digital twin cloud platform, computing resources of the cloud platform are required to be distributed according to tasks as required, so that the cloud platform can distribute limited resources to each digital twin task, the total time consumption of completing the tasks by the system is shortest, and the system utilization rate is highest. At present, a plurality of scholars at home and abroad have developed extensive researches on the problem of cloud computing resource scheduling. At present, the cloud platform resource computing method can be divided into a traditional method and a heuristic algorithm according to the principle. The method can obtain better results when the method is used for solving the problems of small scale and simple calculation resource scheduling, but with the gradual increase of the calculation resources of the cloud platform and the increase of the task quantity, the algorithms gradually have the problems of long response time, easy sinking into local optimal solutions, poor convergence efficiency and the like, so that the quality of the calculation resource scheduling scheme is lower.
Disclosure of Invention
In order to overcome at least one defect in the prior art, the application provides a digital twin cloud platform computing resource scheduling method based on a particle swarm optimization algorithm.
In a first aspect, a method for scheduling computing resources of a digital twin cloud platform based on a particle swarm optimization algorithm is provided, including:
determining the number of allocable virtual resources;
determining an optimization target of a resource scheduling task; the decision variable in the optimization target is a resource scheduling scheme, and the resource scheduling scheme is a resource scheduling task number of each allocable virtual resource operation;
and solving an optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme.
In one embodiment, solving an optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme comprises:
step S31, generating an initial population of a resource scheduling scheme, wherein each individual in the initial population is the initial resource scheduling scheme;
step S32, calculating an optimization target value for each individual in the current population;
step S33, determining the optimal individuals in the current population according to the optimal target value;
step S34, if the number of times of calculating the optimization target value reaches the maximum evaluation number, ending, wherein the optimal individual in the current population is the optimal resource scheduling scheme; otherwise, step S35 is performed;
step S35, randomly selecting 2 unselected individuals in the current population, marking the selected individuals as 2 parent individuals, and crossing the selected individuals by adopting a binary crossing simulation method to obtain 2 child individuals; if the optimization target value of the 2 child individuals is better than the optimization target value of the 2 father individuals, replacing the 2 father individuals in the current population with the 2 child individuals; if the optimization target value of the 2 child individuals is not better than the optimization target value of the 2 parent individuals, the process is not performed, the number of individuals in the current population is set as N, and the step S35 is repeatedly performed
Figure BDA0004025540800000021
Next, step S36 is then performed;
step S36, if the optimization degree between the optimal individuals in the previous generation population and the optimal individuals in the current population is smaller than a set threshold, performing mutation operation on all the individuals to obtain a mutated offspring population; if the optimized target value of the individuals in the variant child population is better than the optimized target value of the individuals before the variant, replacing the individuals in the current population with the variant individuals, and if the optimized target value of the variant individuals is not better than the optimized target value of the individuals in the child population, not processing, and executing the step 37;
step S37, update each individual in the current population, return to step S32.
In one embodiment, updating each individual in the current population includes:
the speed of the individual is updated using the following formula:
Figure BDA0004025540800000031
wherein c 1 And c 2 Is an acceleration factor, r 1 And r 2 Is a random value uniformly distributed in 0 to 1,
Figure BDA0004025540800000032
is the speed of the ith individual in the k+1th generation population, ω is the inertial weight, +.>
Figure BDA0004025540800000033
Is the speed of the ith individual in the kth generation population,/>
Figure BDA0004025540800000034
Is the position of the optimal individual in all populations of the 1 st to the kth generation,/>
Figure BDA0004025540800000035
Is the position of the ith individual in the kth generation population,/->
Figure BDA0004025540800000036
Is the location of the optimal individual in the kth generation population;
updating the location of the individual using the following formula:
Figure BDA0004025540800000037
wherein,,
Figure BDA0004025540800000038
is the position of the ith individual in the k+1th generation population,/for the population>
Figure BDA0004025540800000039
Is the position of the ith individual in the kth generation population,/->
Figure BDA00040255408000000310
Is the speed of the ith individual in the k+1 generation population.
In a second aspect, a digital twin cloud platform computing resource scheduling device based on a particle swarm optimization algorithm is provided, including:
an allocable virtual resource quantity determining module for determining the quantity of allocable virtual resources;
the optimization target determining module is used for determining an optimization target of the resource scheduling task; the decision variable in the optimization target is a resource scheduling scheme, and the resource scheduling scheme is a resource scheduling task number of each allocable virtual resource operation;
and the optimization target solving module is used for solving the optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme.
In one embodiment, the optimization objective solving module is further configured to:
step S31, generating an initial population of a resource scheduling scheme, wherein each individual in the initial population is the initial resource scheduling scheme;
step S32, calculating an optimization target value for each individual in the current population;
step S33, determining the optimal individuals in the current population according to the optimal target value;
step S34, if the number of times of calculating the optimization target value reaches the maximum evaluation number, ending, wherein the optimal individual in the current population is the optimal resource scheduling scheme; otherwise, step S35 is performed;
step S35, randomly selecting 2 unselected individuals in the current population, marking the selected individuals as 2 parent individuals, and crossing the selected individuals by adopting a binary crossing simulation method to obtain 2 child individuals; optimization purposes for 2 child individualsIf the bid value is better than the optimized target value of 2 father individuals, replacing 2 father individuals in the current population with 2 child individuals; if the optimization target value of the 2 child individuals is not better than the optimization target value of the 2 parent individuals, the process is not performed, the number of individuals in the current population is set as N, and the step S35 is repeatedly performed
Figure BDA0004025540800000041
Next, step S36 is then performed;
step S36, if the optimization degree between the optimal individuals in the previous generation population and the optimal individuals in the current population is smaller than a set threshold, performing mutation operation on all the individuals to obtain a mutated offspring population; if the optimized target value of the individuals in the variant child population is better than the optimized target value of the individuals before the variant, replacing the individuals in the current population with the variant individuals, and if the optimized target value of the variant individuals is not better than the optimized target value of the individuals in the child population, not processing, and executing the step 37;
step S37, update each individual in the current population, return to step S32.
In one embodiment, the optimization objective solving module is further configured to:
the speed of the individual is updated using the following formula:
Figure BDA0004025540800000051
wherein c 1 And c 2 Is an acceleration factor, r 1 And r 2 Is a random value uniformly distributed in 0 to 1,
Figure BDA0004025540800000052
is the speed of the ith individual in the k+1th generation population, ω is the inertial weight, +.>
Figure BDA0004025540800000053
Is the speed of the ith individual in the kth generation population,/>
Figure BDA0004025540800000054
Is the position of the optimal individual in all populations of the 1 st to the kth generation,/>
Figure BDA0004025540800000055
Is the position of the ith individual in the kth generation population,/->
Figure BDA0004025540800000056
Is the location of the optimal individual in the kth generation population;
updating the location of the individual using the following formula:
Figure BDA0004025540800000057
wherein,,
Figure BDA0004025540800000058
is the position of the ith individual in the k+1th generation population,/for the population>
Figure BDA0004025540800000059
Is the position of the ith individual in the kth generation population,/->
Figure BDA00040255408000000510
Is the speed of the ith individual in the k+1 generation population.
Compared with the prior art, the application has the following beneficial effects: according to the particle swarm optimization algorithm-based digital twin cloud platform computing resource scheduling method, the problem of digital twin cloud platform computing resource scheduling is solved by combining cross compiling operation on the basis of a traditional particle swarm algorithm, and the cloud platform computing resource scheduling performance is effectively improved.
Drawings
The present application may be better understood by reference to the following description taken in conjunction with the accompanying drawings, which are incorporated in and form a part of this specification, together with the following detailed description. In the drawings:
FIG. 1 shows a flow diagram of a digital twin cloud platform computing resource scheduling method based on a particle swarm optimization algorithm according to an embodiment of the present application;
fig. 2 shows a block diagram of a digital twin cloud platform computing resource scheduling device based on a particle swarm optimization algorithm according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application will be described hereinafter with reference to the accompanying drawings. In the interest of clarity and conciseness, not all features of an actual embodiment are described in the specification. It will of course be appreciated that in the development of any such actual embodiment, numerous implementation-specific decisions may be made to achieve the developers' specific goals, and that these decisions may vary from one implementation to another.
It should be noted that, in order to avoid obscuring the present application with unnecessary details, only the device structures closely related to the solution according to the present application are shown in the drawings, and other details not greatly related to the present application are omitted.
It is to be understood that the present application is not limited to the described embodiments due to the following description with reference to the drawings. In this context, embodiments may be combined with each other, features replaced or borrowed between different embodiments, one or more features omitted in one embodiment, where possible.
The application provides a digital twin cloud platform computing resource scheduling method based on a particle swarm optimization algorithm, which is characterized in that a computing resource scheduling model at the current moment is determined according to the remaining condition of computing resources of the digital twin cloud platform at each scheduling moment and the progress condition of tasks, the total time consumption of the tasks and the resource utilization rate are optimized, and an improved particle swarm algorithm is utilized for solving to obtain a mine digital twin cloud platform computing resource scheduling scheme.
An embodiment of the present application provides a method for scheduling computing resources of a digital twin cloud platform based on a particle swarm optimization algorithm, and fig. 1 shows a flow chart of the method for scheduling computing resources of the digital twin cloud platform based on the particle swarm optimization algorithm according to an embodiment of the present application, where the method includes:
step S1, determining the number of allocable virtual resources; in the step, the allocatable computing resources and the pre-allocated computing tasks are determined according to the residual condition of the computing resources of the digital twin cloud platform at the current scheduling moment and the task progress condition, and the number of allocatable virtual resources is D, namely the dimension of a decision variable;
step S2, determining an optimization target of a resource scheduling task; the decision variable in the optimization target is a resource scheduling scheme, and the resource scheduling scheme is a resource scheduling task number of each allocable virtual resource operation; the optimization targets comprise 2 optimization targets for minimizing the total time consumption of the task and maximizing the resource utilization rate, and the constraint conditions comprise constraint conditions such as task performance requirements; let the decision variable vector X for the problem, element X in X i Task number, f, representing the operation of the ith virtual computing resource 1 (x), 2 () Is the 2 optimized objective functions for the task,
Figure BDA0004025540800000071
for user-defined optimization objective weight g i () And h j () Is a constraint. The optimization model of the task is;
Figure BDA0004025540800000072
s.t.g i ()≤0,i＝1,2,…D,
h j ()＝0,j＝1,2,…D,
and S3, solving an optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme.
In one embodiment, solving an optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme comprises:
step S31, generating an initial population of a resource scheduling scheme, wherein each individual in the initial population is the initial resource scheduling scheme; in this step, the initial population may be generated using a random method or according to a scheduling rule.
Step S32, calculating an optimization target value for each individual in the current population;
step S33, determining the optimal individuals in the current population according to the optimal target value; here, the individual whose optimization target value is the smallest may be adopted as the optimal individual.
Step S34, if the number of times of calculating the optimization target value reaches the maximum evaluation number, ending, wherein the optimal individual in the current population is the optimal resource scheduling scheme; otherwise, step S35 is performed; here, the maximum number of evaluations may be 10000.
Step S35, randomly selecting 2 unselected individuals in the current population, marking the selected individuals as 2 parent individuals, and crossing the selected individuals by adopting a binary crossing simulation method to obtain 2 child individuals; if the optimization target value of the 2 child individuals is better than the optimization target value of the 2 father individuals, replacing the 2 father individuals in the current population with the 2 child individuals; if the optimization target value of the 2 child individuals is not better than the optimization target value of the 2 parent individuals, the process is not performed, the number of individuals in the current population is set as N, and the step S35 is repeatedly performed
Figure BDA0004025540800000081
Next, step S36 is then performed; the crossover process may use a crossover probability of 0.5.
Step S36, if the optimization degree between the optimal individuals in the previous generation population and the optimal individuals in the current population is smaller than a set threshold, performing mutation operation on all the individuals to obtain a mutated offspring population; if the optimized target value of the individuals in the variant child population is better than the optimized target value of the individuals before the variant, replacing the individuals in the current population with the variant individuals, and if the optimized target value of the variant individuals is not better than the optimized target value of the individuals in the child population, not processing, and executing the step 37; here, the set threshold is selected according to the actual situation, and the optimization degree can be obtained by calculating the difference between the optimization target value of the child individual and the optimization target value of the parent individual.
Step S37, update each individual in the current population, return to step S32.
In the embodiment, compared with the traditional particle swarm algorithm, a crossover operator and a mutation operator are added, so that the searching capability of the algorithm can be improved.
In one embodiment, updating each individual in the current population includes:
the speed of the individual is updated using the following formula:
Figure BDA0004025540800000091
wherein c 1 And c 2 Is an acceleration factor, r 1 And r 2 Is a random value uniformly distributed in 0 to 1,
Figure BDA0004025540800000092
is the speed of the ith individual in the k+1th generation population, ω is the inertial weight, +.>
Figure BDA0004025540800000093
Is the speed of the ith individual in the kth generation population,/>
Figure BDA0004025540800000094
Is the position of the optimal individual in all populations of the 1 st to the kth generation,/>
Figure BDA0004025540800000095
Is the position of the ith individual in the kth generation population,/->
Figure BDA0004025540800000096
Is the location of the optimal individual in the kth generation population;
updating the location of the individual using the following formula:
Figure BDA0004025540800000097
wherein,,
Figure BDA0004025540800000098
is the k+thThe position of the ith individual in the generation 1 population,/->
Figure BDA0004025540800000099
Is the position of the ith individual in the kth generation population,/->
Figure BDA00040255408000000910
Is the speed of the ith individual in the k+1 generation population.
In this example, a population X' = (X) consisting of n=100 individuals 1 ,X 2 …X i …X 100 ) D-dimensional vector X i ＝(X i1 ,X i2 ,X i3 …X iD ) Representing the position of the ith individual in the population, namely representing the task number to be allocated to the D schedulable virtual computing resources, the speed of the ith individual is V i ＝(V i1 ,V i2 ,…V iD ) By P b Representing the position of the optimal individual, P b ＝(P b1 ,P b2 ,P b3 …P bD ) The method comprises the steps of carrying out a first treatment on the surface of the By P g Representing the position of the optimal individual in the previous generation population, P g ＝P g1 ,P g2 ,P g3 …P gD )。
The embodiment of the application also provides a digital twin cloud platform computing resource scheduling device based on the particle swarm optimization algorithm, and fig. 2 shows a structural block diagram of the digital twin cloud platform computing resource scheduling device based on the particle swarm optimization algorithm according to the embodiment of the application, where the device includes:
an allocatable virtual resource quantity determining module 21 for determining the quantity of allocatable virtual resources;
an optimization objective determining module 22, configured to determine an optimization objective of a resource scheduling task; the decision variable in the optimization target is a resource scheduling scheme, and the resource scheduling scheme is a resource scheduling task number of each allocable virtual resource operation;
and the optimization target solving module 23 is used for solving the optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme.
In one embodiment, the optimization objective solving module 23 is further configured to:
step S31, generating an initial population of a resource scheduling scheme, wherein each individual in the initial population is the initial resource scheduling scheme;
step S32, calculating an optimization target value for each individual in the current population;
step S33, determining the optimal individuals in the current population according to the optimal target value;
step S34, if the number of times of calculating the optimization target value reaches the maximum evaluation number, ending, wherein the optimal individual in the current population is the optimal resource scheduling scheme; otherwise, step S35 is performed;
step S35, randomly selecting 2 unselected individuals in the current population, marking the selected individuals as 2 parent individuals, and crossing the selected individuals by adopting a binary crossing simulation method to obtain 2 child individuals; if the optimization target value of the 2 child individuals is better than the optimization target value of the 2 father individuals, replacing the 2 father individuals in the current population with the 2 child individuals; if the optimization target value of the 2 child individuals is not better than the optimization target value of the 2 parent individuals, the process is not performed, the number of individuals in the current population is set as N, and the step S35 is repeatedly performed
Figure BDA0004025540800000111
Next, step S36 is then performed;
step S36, if the optimization degree between the optimal individuals in the previous generation population and the optimal individuals in the current population is smaller than a set threshold, performing mutation operation on all the individuals to obtain a mutated offspring population; if the optimized target value of the individuals in the variant child population is better than the optimized target value of the individuals before the variant, replacing the individuals in the current population with the variant individuals, and if the optimized target value of the variant individuals is not better than the optimized target value of the individuals in the child population, not processing, and executing the step 37;
step S37, update each individual in the current population, return to step S32.
In one embodiment, the optimization objective solving module 23 is further configured to:
the speed of the individual is updated using the following formula:
Figure BDA0004025540800000112
wherein c 1 And c 2 Is an acceleration factor, r 1 And r 2 Is a random value uniformly distributed in 0 to 1,
Figure BDA0004025540800000121
is the speed of the ith individual in the k+1th generation population, ω is the inertial weight, +.>
Figure BDA0004025540800000122
Is the speed of the ith individual in the kth generation population,/>
Figure BDA0004025540800000123
Is the position of the optimal individual in all populations of the 1 st to the kth generation,/>
Figure BDA0004025540800000124
Is the position of the ith individual in the kth generation population,/->
Figure BDA0004025540800000129
Is the location of the optimal individual in the kth generation population;
updating the location of the individual using the following formula:
Figure BDA0004025540800000125
wherein,,
Figure BDA0004025540800000126
is the position of the ith individual in the k+1th generation population,/for the population>
Figure BDA0004025540800000127
Is the firstThe position of the ith individual in the k-generation population,/->
Figure BDA0004025540800000128
Is the speed of the ith individual in the k+1 generation population.
In sum, the digital twin cloud platform computing resource scheduling method based on the particle swarm optimization algorithm solves the problem of digital twin cloud platform computing resource scheduling by combining cross compiling operation on the basis of the traditional particle swarm algorithm, and effectively improves the cloud platform computing resource scheduling performance.
The foregoing is merely various embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (6)

1. The digital twin cloud platform computing resource scheduling method based on the particle swarm optimization algorithm is characterized by comprising the following steps of:
determining the number of allocable virtual resources;
determining an optimization target of a resource scheduling task; the decision variable in the optimization target is a resource scheduling scheme, and the resource scheduling scheme is a resource scheduling task number of each allocable virtual resource operation;
and solving the optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme.
2. The method of claim 1, wherein solving the optimization objective using a particle swarm optimization algorithm results in an optimal resource scheduling scheme, comprising:
step S31, generating an initial population of a resource scheduling scheme, wherein each individual in the initial population is the initial resource scheduling scheme;
step S32, calculating an optimization target value for each individual in the current population;
step S33, determining the optimal individuals in the current population according to the optimal target value;
step S34, if the times of calculating the optimization target value reach the maximum evaluation times, ending, wherein the optimal individual in the current population is the optimal resource scheduling scheme; otherwise, step S35 is performed;
step S35, randomly selecting 2 unselected individuals in the current population, marking the selected individuals as 2 parent individuals, and crossing the selected individuals by adopting a binary crossing simulation method to obtain 2 child individuals; if the optimization target value of the 2 child individuals is better than the optimization target value of the 2 father individuals, replacing the 2 father individuals in the current population with the 2 child individuals; if the optimization target value of the 2 child individuals is not better than the optimization target value of the 2 parent individuals, the process is not performed, the number of individuals in the current population is set as N, and the step S35 is repeatedly performed
Figure FDA0004025540790000021
Next, step S36 is then performed;
step S36, if the optimization degree between the optimal individuals in the previous generation population and the optimal individuals in the current population is smaller than a set threshold, performing mutation operation on all the individuals to obtain a mutated offspring population; if the optimized target value of the individuals in the variant child population is better than the optimized target value of the individuals before the variant, replacing the individuals in the current population with the individuals after the variant, and if the optimized target value of the individuals after the variant is not better than the optimized target value of the individuals in the child population, not processing, and executing the step 37;
step S37, updating each individual in the current population, and returning to step S32.
3. The method of claim 2, wherein updating each individual in the current population comprises:
the speed of the individual is updated using the following formula:
Figure FDA0004025540790000022
wherein c 1 And C 2 Is an acceleration factor, r 1 And t 2 Is a random value uniformly distributed between 0 and 1, V i k+1 Is the speed of the ith individual in the k+1st generation population, ω is the inertial weight, V i k Is the speed of the ith individual in the kth generation population,
Figure FDA0004025540790000023
is the position of the optimal individual in all populations of the 1 st to the kth generation,/>
Figure FDA0004025540790000024
Is the position of the ith individual in the kth generation population,/->
Figure FDA0004025540790000025
Is the location of the optimal individual in the kth generation population;
updating the location of the individual using the following formula:
Figure FDA0004025540790000031
wherein,,
Figure FDA0004025540790000032
is the position of the ith individual in the k+1th generation population,/for the population>
Figure FDA0004025540790000033
Is the position of the ith individual in the kth generation of population, V i k+1 Is the speed of the ith individual in the k+1 generation population.
4. The utility model provides a digital twin cloud platform computational resource scheduling device based on particle swarm optimization algorithm which characterized in that includes:
an allocable virtual resource quantity determining module for determining the quantity of allocable virtual resources;
the optimization target determining module is used for determining an optimization target of the resource scheduling task; the decision variable in the optimization target is a resource scheduling scheme, and the resource scheduling scheme is a resource scheduling task number of each allocable virtual resource operation;
and the optimization target solving module is used for solving the optimization target by adopting a particle swarm optimization algorithm to obtain an optimal resource scheduling scheme.
5. The apparatus of claim 4, wherein the optimization objective solving module is further to:
step S31, generating an initial population of a resource scheduling scheme, wherein each individual in the initial population is the initial resource scheduling scheme;
step S32, calculating an optimization target value for each individual in the current population;
step S33, determining the optimal individuals in the current population according to the optimal target value;
step S34, if the times of calculating the optimization target value reach the maximum evaluation times, ending, wherein the optimal individual in the current population is the optimal resource scheduling scheme; otherwise, step S35 is performed;
step S35, randomly selecting 2 unselected individuals in the current population, marking the selected individuals as 2 parent individuals, and crossing the selected individuals by adopting a binary crossing simulation method to obtain 2 child individuals; if the optimization target value of the 2 child individuals is better than the optimization target value of the 2 father individuals, replacing the 2 father individuals in the current population with the 2 child individuals; if the optimization target value of the 2 child individuals is not better than the optimization target value of the 2 parent individuals, the process is not performed, the number of individuals in the current population is set as N, and the step S35 is repeatedly performed
Figure FDA0004025540790000041
Next, step S36 is then performed;
step S36, if the optimization degree between the optimal individuals in the previous generation population and the optimal individuals in the current population is smaller than a set threshold, performing mutation operation on all the individuals to obtain a mutated offspring population; if the optimized target value of the individuals in the variant child population is better than the optimized target value of the individuals before the variant, replacing the individuals in the current population with the individuals after the variant, and if the optimized target value of the individuals after the variant is not better than the optimized target value of the individuals in the child population, not processing, and executing the step 37;
step S37, updating each individual in the current population, and returning to step S32.
6. The apparatus of claim 5, wherein the optimization objective solving module is further to:
the speed of the individual is updated using the following formula:
Figure FDA0004025540790000051
wherein c 1 And c 2 Is an acceleration factor, r 1 And r 2 Is a random value uniformly distributed between 0 and 1, V i k+1 Is the speed of the ith individual in the k+1st generation population, ω is the inertial weight, V i k Is the speed of the ith individual in the kth generation population,
Figure FDA0004025540790000052
is the position of the optimal individual in all populations of the 1 st to the kth generation,/>
Figure FDA0004025540790000053
Is the position of the ith individual in the kth generation population,/->
Figure FDA0004025540790000054
Is the location of the optimal individual in the kth generation population;
updating the location of the individual using the following formula:
Figure FDA0004025540790000055
wherein,,
Figure FDA0004025540790000056
is the position of the ith individual in the k+1th generation population,/for the population>
Figure FDA0004025540790000057
Is the position of the ith individual in the kth generation of population, V i k+1 Is the speed of the ith individual in the k+1 generation population.
CN202211708427.8A 2022-12-29 2022-12-29 Digital twin cloud platform computing resource scheduling method based on particle swarm optimization algorithm Pending CN116339973A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211708427.8A CN116339973A (en) 2022-12-29 2022-12-29 Digital twin cloud platform computing resource scheduling method based on particle swarm optimization algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211708427.8A CN116339973A (en) 2022-12-29 2022-12-29 Digital twin cloud platform computing resource scheduling method based on particle swarm optimization algorithm

Publications (1)

Publication Number Publication Date
CN116339973A true CN116339973A (en) 2023-06-27

Family

ID=86884725

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211708427.8A Pending CN116339973A (en) 2022-12-29 2022-12-29 Digital twin cloud platform computing resource scheduling method based on particle swarm optimization algorithm

Country Status (1)

Country Link
CN (1) CN116339973A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117236458A (en) * 2023-11-13 2023-12-15 国开启科量子技术(安徽)有限公司 Quantum computing task scheduling method, device, medium and equipment of quantum cloud platform

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117236458A (en) * 2023-11-13 2023-12-15 国开启科量子技术(安徽)有限公司 Quantum computing task scheduling method, device, medium and equipment of quantum cloud platform
CN117236458B (en) * 2023-11-13 2024-03-26 国开启科量子技术(安徽)有限公司 Quantum computing task scheduling method, device, medium and equipment of quantum cloud platform

Similar Documents

Publication Publication Date Title
CN111065103B (en) Multi-objective optimization wireless sensor network node deployment method
CN110851272B (en) Cloud task scheduling method based on phagocytic particle swarm genetic hybrid algorithm
CN108776612A (en) A kind of cloud computing method for allocating tasks, device, equipment and storage medium
Afshar et al. Optimizing multi-reservoir operation rules: an improved HBMO approach
US8250007B2 (en) Method of generating precedence-preserving crossover and mutation operations in genetic algorithms
CN105929690B (en) A kind of Flexible Workshop Robust Scheduling method based on decomposition multi-objective Evolutionary Algorithm
CN110138612A (en) A kind of cloud software service resource allocation methods based on QoS model self-correcting
CN109451012B (en) End cloud collaborative load balancing scheduling method, system and storage medium
CN112784362A (en) Hybrid optimization method and system for unmanned aerial vehicle-assisted edge calculation
CN106202092A (en) The method and system that data process
CN106227599A (en) The method and system of scheduling of resource in a kind of cloud computing system
CN114585006B (en) Edge computing task unloading and resource allocation method based on deep learning
CN113708969A (en) Cooperative embedding method of cloud data center virtual network based on deep reinforcement learning
CN108764322A (en) A kind of flow data set constituent class method and apparatus based on concept drift
CN112685138A (en) Multi-workflow scheduling method based on multi-population hybrid intelligent optimization in cloud environment
CN111885493B (en) Micro-cloud deployment method based on improved cuckoo search algorithm
CN116339973A (en) Digital twin cloud platform computing resource scheduling method based on particle swarm optimization algorithm
CN109656713A (en) A kind of container dispatching method based on edge calculations frame
CN112486651A (en) Cloud test platform task scheduling method based on improved genetic algorithm
Niu et al. Cloud resource scheduling method based on estimation of distirbution shuffled frog leaping algorithm
CN116321189A (en) Server deployment method based on deep reinforcement learning in edge-oriented computing
CN113298315A (en) Electric vehicle charging station site selection optimization method based on double-layer coding
CN110009749A (en) A kind of virtual objects localization method, calculates equipment and storage medium at device
CN115190135B (en) Distributed storage system and copy selection method thereof
CN118101500B (en) Service deployment method and system under edge environment based on improved genetic algorithm

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