CN115599522A - Task scheduling method, device and equipment for cloud computing platform - Google Patents
Task scheduling method, device and equipment for cloud computing platform Download PDFInfo
- Publication number
- CN115599522A CN115599522A CN202211316809.6A CN202211316809A CN115599522A CN 115599522 A CN115599522 A CN 115599522A CN 202211316809 A CN202211316809 A CN 202211316809A CN 115599522 A CN115599522 A CN 115599522A
- Authority
- CN
- China
- Prior art keywords
- target
- task
- tasks
- cluster
- scheduling
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012163 sequencing technique Methods 0.000 claims abstract description 95
- 230000008901 benefit Effects 0.000 claims abstract description 15
- 238000005265 energy consumption Methods 0.000 claims description 80
- 238000004422 calculation algorithm Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 16
- 230000002068 genetic effect Effects 0.000 claims description 15
- 210000000349 chromosome Anatomy 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 5
- 230000036962 time dependent Effects 0.000 claims description 4
- 230000002759 chromosomal effect Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 11
- 230000004044 response Effects 0.000 description 9
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 3
- 108090000623 proteins and genes Proteins 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
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
- G06F9/48—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
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/48—Indexing scheme relating to G06F9/48
- G06F2209/484—Precedence
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (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 invention provides a method, a device and equipment for scheduling tasks of a cloud computing platform.A scheme selects proper sequencing parameters based on the cluster type of scheduling tasks, so that when scheduling is carried out based on a sequencing result, compared with a list heuristic method, the method and the equipment can carry out cluster processing on parallel tasks, and the execution time length is reasonably reduced; compared with a clustering heuristic method, the task scheduling method has the advantages that tasks can be ordered in advance, the execution sequence is more reasonable, and waste of idle time resources is reduced.
Description
Technical Field
The invention relates to the technical field of refrigeration equipment, in particular to a task scheduling method, device and equipment for a cloud computing platform.
Background
Scheduling of a cloud computing platform generally refers to resource scheduling and task scheduling, and the resource scheduling refers to reasonable and effective allocation of physical resources; task scheduling refers to the rational distribution of tasks to appropriate computing resources. Because the task environment is diverse and unpredictable, the task requirements of the system are dynamic, making it difficult to efficiently schedule tasks to meet the fast response requirements of the system. Meanwhile, the energy consumption of the cloud computing platform is also an important factor to be considered when task scheduling is carried out, and along with the continuous expansion of the cloud computing data center, the energy consumption of the data center is increased at a geometric speed. Reducing the energy consumption of the system gradually becomes a key difficult problem to be solved urgently in the cloud computing data center. Meanwhile, reducing the energy consumption of the data center is also significant for realizing carbon neutralization.
Currently, the reduction of energy consumption is mainly achieved by dynamically adjusting the operation power of the equipment, and the method has the disadvantage of influencing the overall performance of the system, thereby influencing the response speed of the system. Due to the randomness of the tasks, the system has no available prior information during the multi-task scheduling, and the scheduling system must adaptively schedule the tasks. And after the scheduling is finished, the scheduling performance of the system, such as the response speed of the system, the energy consumption of the platform and the like, is evaluated and fed back to the platform scheduling center, so that the performance is better, and the optimal scheduling strategy of the system multitask is realized.
In the existing technical scheme, the main ways to implement task scheduling of the cloud computing platform are as follows:
the list heuristic method is used for sequencing, scheduling and executing the tasks by distributing priorities to the tasks; in addition, the clustering heuristic is also a commonly used method, and the main idea is to process tasks in the same cluster, reduce parallelism by sequencing parallel tasks, increase parallel execution time, and reduce communication delay between tasks by sacrificing parallelism.
The list heuristic may perform well with limited resources, but may result in increased task completion time and slower response speed due to the need to determine priority and resource selection policies in advance; clustering heuristics can handle the case of unlimited resources and reduce communication delays, but with the problems of load imbalance and wasted idle time resources.
Disclosure of Invention
In view of this, embodiments of the present invention provide a cloud computing platform task scheduling method capable of comprehensively considering scheduling energy consumption and scheduling duration, so as to solve the problems of a slow response speed and waste of idle time resources in the existing scheduling method.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
a task scheduling method for a cloud computing platform comprises the following steps:
acquiring a target scheduling task;
judging the cluster type of the target task, wherein the cluster type comprises a linear cluster and a nonlinear cluster;
extracting a sequencing parameter corresponding to the target task based on the cluster type of the target task;
sequencing the target tasks based on the sequencing parameters by adopting a preset sequencing rule;
and scheduling the sorted target tasks based on the sorting result.
Optionally, in the cloud computing platform task scheduling method, the sequencing parameters include a duration and energy consumption, when the cluster type of the target task is a linear cluster, the duration refers to a longest execution time corresponding to the target task, and the energy consumption refers to total energy consumption corresponding to the target task;
when the cluster type of the target task is a non-linear cluster, the duration refers to the execution duration of the target task, and the energy consumption refers to the execution energy consumption of the target task.
Optionally, in the cloud computing platform task scheduling method, the sorting the target tasks based on the sorting parameters by using a preset sorting rule includes:
and sequencing the target tasks according to the energy consumption of the target tasks, wherein the lower the energy consumption, the higher the priority of the target tasks is, the higher the priority of the target tasks with the same energy consumption is, the longer the priority of the target tasks is, and when the cluster type of the target tasks is a nonlinear cluster, the sequencing result and the target tasks are led into the cluster to which the target tasks are adapted.
Optionally, in the cloud computing platform task scheduling method, the sorting the target tasks based on the sorting parameters by using a preset sorting rule includes:
sequencing the target tasks based on the time length to obtain a first sequencing result;
sequencing the target tasks based on energy consumption to obtain a second sequencing result;
calculating the average value of the first sequencing result and the second sequencing result to sequence the target tasks to obtain a third sequencing result;
if the third sequencing results of the two target tasks are the same, the higher the priority of the target task in the second sequencing result is, the higher the priority of the target task in the third sequencing result is;
and when the cluster type of the target task is a nonlinear cluster, introducing a sequencing result and the target task into a cluster adapted to the target task.
Optionally, in the cloud computing platform task scheduling method, scheduling the ordered target tasks based on the ordering result includes: and scheduling the tasks in the current scheduling period by adopting a genetic algorithm based on the sequencing result.
Optionally, in the cloud computing platform task scheduling method, the benefit function of the genetic algorithm is as follows:
F(j)＝FitnessTime(j)+1/s(j)；
wherein the content of the first and second substances,
the subTask j，i In order to determine the energy consumption of the ith scheduling task allocated to the jth physical resource, avgTask is the average value of the energy consumption of all scheduling tasks, and n is the total number of scheduling tasks corresponding to chromosomes;
the FitnessTime is a time-dependent chromosomal benefit function.
A cloud computing platform task scheduling device, comprising:
the scheduling task acquisition unit is used for acquiring a target scheduling task;
the cluster type judging unit is used for judging the cluster type of the target task, and the cluster type comprises a linear cluster and a nonlinear cluster;
the sequencing unit is used for extracting sequencing parameters corresponding to the target tasks based on the cluster types of the target tasks; sequencing the target tasks based on the sequencing parameters by adopting a preset sequencing rule;
and the scheduling unit is used for scheduling the sequenced target tasks based on the sequencing result.
Optionally, in the cloud computing platform task scheduling device, the sorting parameters include duration and energy consumption;
when the cluster type of the target task is a linear cluster, the duration refers to the longest execution time corresponding to the target task, and the energy consumption refers to total energy consumption corresponding to the target task;
when the cluster type of the target task is a non-linear cluster, the duration refers to the execution duration of the target task, and the energy consumption refers to the execution energy consumption of the target task.
Optionally, in the cloud computing platform task scheduling device, when the sorting unit sorts the target tasks based on the sorting parameters by using a preset sorting rule, the sorting unit is specifically configured to:
and sequencing the target tasks according to the energy consumption of the target tasks, wherein the lower the energy consumption, the higher the priority of the target tasks is, the higher the priority of the target tasks with the same energy consumption is, the longer the priority of the target tasks is, and when the cluster type of the target tasks is a nonlinear cluster, the sequencing result and the target tasks are led into the cluster to which the target tasks are adapted.
A cloud computing platform task scheduling device, comprising:
a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program, and implement each step of the cloud computing platform task scheduling method according to any one of the above.
Based on the technical scheme, in the scheme provided by the embodiment of the invention, the appropriate sequencing parameters are selected based on the cluster type of the scheduling task, so that when the scheduling is carried out based on the sequencing result, compared with a list heuristic method, the parallel tasks can be subjected to cluster processing, and the execution time is reasonably reduced; compared with a clustering heuristic method, the task scheduling method has the advantages that tasks can be ordered in advance, the execution sequence is more reasonable, and waste of idle time resources is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of a task scheduling method for a cloud computing platform disclosed in an embodiment of the present application;
fig. 2 is a schematic structural diagram of a task scheduling apparatus of a cloud computing platform disclosed in an embodiment of the present application;
FIG. 3 is a schematic diagram of a scheduling flow of a genetic algorithm;
fig. 4 is a schematic structural diagram of a task scheduling device of a cloud computing platform disclosed in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
First, some of the vocabularies used in this application are explained:
nonlinear clustering: if two independent neighbor tasks exist in the same cluster, the cluster is called a nonlinear cluster.
Linear clustering: concept as opposed to nonlinear clustering. No two independent neighbor tasks in the same cluster are called linear clusters.
The application provides a task scheduling algorithm based on prediction for how to allocate tasks to reasonable computing resources, so that the system response speed of a platform and the energy consumption cost of the platform are balanced. The basic scheme of the method consists of two parts, namely task preprocessing and adaptive scheduling. Aiming at task preprocessing, counting the maximum task execution time and energy consumption of a linear cluster; for non-linear clusters, prioritizing them is employed to reduce parallelism. A list ordering of the corresponding tasks is obtained. After an ordered task sequence is obtained through task preprocessing, a benefit function for minimizing energy consumption is constructed, and tasks are scheduled and executed through a genetic algorithm, so that balance between the response speed of a balance system and the energy consumption of a platform is achieved.
Specifically, referring to fig. 1, a specific process of task scheduling of a cloud computing platform disclosed in the embodiment of the present application may include:
step S101: acquiring a target scheduling task;
the target tasks are all acquired tasks needing to be scheduled.
Step S102: and judging the cluster type of the target task, wherein the cluster type comprises a linear cluster and a nonlinear cluster.
After the target task is acquired, judging the cluster type of the target task, judging whether the target task belongs to a linear cluster or a nonlinear cluster, judging whether the target task is the linear cluster or the nonlinear cluster by judging whether the target task has a neighbor task or not when judging that the target task is the linear cluster or the nonlinear cluster, wherein when the target task has the neighbor task, the cluster type of the target task is the linear cluster, and when the target task does not have the neighbor task, the cluster type of the target task is the nonlinear cluster. That is, when the target task has neighbor tasks and the number of the neighbor tasks is greater than or equal to 1, it is indicated that the cluster type of the target task is a linear cluster, otherwise, the cluster type of the target task is a nonlinear cluster.
Step S103: and extracting a sequencing parameter corresponding to the target task based on the cluster type of the target task.
In the technical solution disclosed in the embodiment of the present application, the cluster types of the target tasks are different, and when the target tasks are sorted, the adopted sorting parameters are different, and the values of the sorting parameters of different target tasks are different, which may cause different priorities of the target tasks in the sorting result.
In the technical solution disclosed in the embodiment of the present application, the sequencing parameters may include duration and energy consumption, where specific reference objects of the duration and the energy consumption are different when the cluster type of the target task is a linear cluster and a nonlinear cluster, specifically, when the cluster type of the target task is a linear cluster, the duration refers to a longest execution time corresponding to the target task, the energy consumption refers to total energy consumption corresponding to the target task, and the longest execution time and the total energy consumption refer to execution time and energy consumption of a single scheduling task; when the cluster type of the target task is a non-linear cluster, the duration refers to the execution duration of the target task, and the energy consumption refers to the execution energy consumption of the target task.
Step S104: and sequencing the target tasks based on the sequencing parameters by adopting a preset sequencing rule.
When the cluster type of the target task is a linear cluster, the step specifically includes counting the longest execution time and total energy consumption corresponding to the target task, and sequencing the target task according to a preset sequencing rule until the target task is executed in the cluster.
When the cluster type of the target task is a nonlinear cluster, the target task is specifically sequenced according to a preset sequencing rule through the execution duration and the energy consumption of the target task, and an ordered task sequence is obtained.
Step S105: and scheduling the sorted target tasks based on the sorting result.
In this embodiment, steps S101-S104 are a preprocessing part of this embodiment, which is performed in a preprocessing module, and step S105 is an adaptive scheduling part of this application, which is performed in an adaptive scheduling module.
In this step, after the target tasks are sorted, the adaptive scheduling module divides time into time slices to process the target tasks to be scheduled, schedules corresponding tasks in a scheduling period through a relevant scheduling algorithm, stores delayed tasks in a delayed execution matrix for tasks which cannot be processed in the current scheduling period, and gives priority to the delayed tasks in the next scheduling period.
According to the technical scheme disclosed by the embodiment of the application, the appropriate sequencing parameters are selected based on the cluster type of the scheduling task, so that when scheduling is carried out based on the sequencing result, compared with a list heuristic method, the parallel tasks can be subjected to cluster processing, and the execution time is reasonably reduced; compared with the clustering heuristic method, the method can pre-sequence the tasks, so that the execution sequence is more reasonable, and the waste of idle time resources is reduced.
Specifically, in the present scheme, when the ranked target tasks are scheduled based on the ranking result, the scheduling Algorithm used may be a Genetic Algorithm (Genetic Algorithm, GA) which was originally proposed by John holland in the united states in the 70 th 20 th century, and the Algorithm was designed and proposed according to the evolution law of organisms in nature. The method is a calculation model of the biological evolution process for simulating natural selection and genetic mechanism of Darwinian biological evolution theory, and is a method for searching an optimal solution by simulating the natural evolution process. The algorithm converts the solving process of the problem into the processes of crossover, mutation and the like of chromosome genes in the similar biological evolution by a mathematical mode and by utilizing computer simulation operation. When a complex combined optimization problem is solved, a better optimization result can be obtained faster compared with some conventional optimization algorithms. Genetic algorithms have been widely used by people in the fields of combinatorial optimization, machine learning, signal processing, adaptive control, artificial life, and the like. The genetic algorithm is adopted to schedule the target task in the current scheduling period, and the task execution duration and the energy consumption can be comprehensively considered through the benefit function of the genetic algorithm, so that the balance between the system response speed and the energy consumption is achieved.
Referring to fig. 2, the scheduling process of the genetic algorithm on the target task can be summarized as follows:
step S201: the chromosomes encode.
And coding the chromosome in a resource-target task corresponding mode.
Step S202: and generating an initial population.
And (3) assuming the size S of the population, the number M of target tasks to be scheduled in the current scheduling period and the number R of resources, initializing to generate S chromosomes, wherein the length of the chromosomes is M, and the value of the genes is a random integer between [1, R ].
Step S203: a fitness function.
In this step, the energy consumption problem is measured by using the standard deviation of the task energy consumption allocated on each resource on the chromosome, and the fitness function of the standard deviation of the task energy consumption allocated on the physical resources on the chromosome is as follows:
the subtask j, i is energy consumption of a target task i allocated to a jth physical resource, j represents the physical resource, avgTask is an average value of energy consumption of all scheduling tasks (target tasks to be scheduled) on a chromosome, and n is the total number of scheduling tasks corresponding to the chromosome;
the benefit function of the genetic algorithm is defined as follows
F(j)＝FitnessTime(j)+1/s(j)
Where FitnessTime is a time-dependent chromosomal benefit function.
The benefit function comprehensively considers the task execution duration and the task energy consumption, so that an optimal or suboptimal solution is obtained; the time-dependent chromosome benefit function refers to a function reflecting how the execution time of the task affects the chromosome performance by taking the execution time of the task as an independent variable. The shorter the execution time is, the higher the benefit is. It may be made the inverse of the order of duration (from short to long) of all task executions;
in principle, the shorter the task duration is, the lower the energy consumption is from the average energy consumption, the larger the benefit function is. The creation idea of the genetic algorithm is derived from a natural selection principle of high or low in the biological evolution theory, the optimal or suboptimal solution is searched through evolution, and the duration and the energy consumption have a coupling relation, so that the duration is longer and the energy consumption is larger, the task execution duration and the energy consumption can be comprehensively considered through a benefit function, and the balance between the system response speed and the energy consumption is achieved.
Step S204: cross variation
According to the fitness value of each individual, selecting some excellent individuals from the previous generation group according to a certain rule or method, and then inheriting the excellent individuals into the next generation group. The KTLBCGA adopts roulette selection as a selection operator, and the iteration termination condition of the genetic algorithm is that iteration is terminated to a certain algebra.
The technical solution disclosed in this embodiment discloses two preset ordering rules, which can implement ordering the target tasks, where one preset ordering rule is:
and sequencing the target tasks according to the energy consumption of the target tasks, wherein the lower the energy consumption, the higher the priority of the target tasks is, the target tasks with the same energy consumption, the longer the time duration, the higher the priority of the target tasks is, and when the cluster type of the target tasks is a nonlinear cluster, the sequencing result and the target tasks are led into the cluster adapted to the target tasks.
Another preset ordering rule is: the method comprises the following steps:
sequencing the target tasks based on the duration to obtain a first sequencing result;
sequencing the target tasks based on energy consumption to obtain a second sequencing result;
calculating the average value of the first sequencing result and the second sequencing result to sequence the target tasks to obtain a third sequencing result, wherein the average value of the first sequencing result can be the average value of the sequencing names of the target tasks in the first sequencing result and the second sequencing result;
if the third sorting results of the two target tasks are the same, the higher the priority of the target task in the second sorting result is, the higher the priority of the target task in the third sorting result is;
and when the cluster type of the target task is a linear cluster, introducing a sequencing result and the target task into a cluster adapted to the target task.
The embodiment of the present invention discloses a cloud computing platform task scheduling device, and please refer to the content of the method embodiment above, for the specific work content of each unit in the device.
The cloud computing platform task scheduling device provided by the embodiment of the invention is described below, and the cloud computing platform task scheduling device described below and the cloud computing platform task scheduling method described above can be referred to in a corresponding manner.
Referring to fig. 3, a cloud computing platform task scheduling device disclosed in an embodiment of the present application may include:
the scheduling task acquisition unit A is used for acquiring a target scheduling task;
the cluster type judging unit B is used for judging the cluster type of the target task, wherein the cluster type comprises a linear cluster and a nonlinear cluster;
the sequencing unit C is used for extracting sequencing parameters corresponding to the target tasks based on the cluster types of the target tasks; sequencing the target tasks based on the sequencing parameters by adopting a preset sequencing rule;
and the scheduling unit D is used for scheduling the sequenced target tasks based on the sequencing result.
Corresponding to the method, when the sorting unit sorts the target tasks based on the sorting parameters by using a preset sorting rule, the sorting unit is specifically configured to:
and sequencing the target tasks according to the energy consumption of the target tasks, wherein the lower the energy consumption, the higher the priority of the target tasks is, the higher the priority of the target tasks with the same energy consumption is, the longer the priority of the target tasks is, and when the cluster type of the target tasks is a nonlinear cluster, the sequencing result and the target tasks are led into the cluster to which the target tasks are adapted.
Fig. 4 is a hardware structure diagram of a cloud computing platform task scheduling device according to an embodiment of the present invention, which is shown in fig. 4 and may include: at least one processor 100, at least one communication interface 200, at least one memory 300, and at least one communication bus 400;
in the embodiment of the present invention, the number of the processor 100, the communication interface 200, the memory 300, and the communication bus 400 is at least one, and the processor 100, the communication interface 200, and the memory 300 complete the communication with each other through the communication bus 400; it is clear that the communication connections shown by the processor 100, the communication interface 200, the memory 300 and the communication bus 400 shown in fig. 4 are merely optional;
optionally, the communication interface 200 may be an interface of a communication module, such as an interface of a GSM module;
the processor 100 may be a central processing unit CPU or an Application Specific Integrated Circuit ASIC or one or more Integrated circuits configured to implement embodiments of the present invention.
Wherein, the processor 100 is specifically configured to:
acquiring a target scheduling task;
judging the cluster type of the target task, wherein the cluster type comprises a linear cluster and a nonlinear cluster;
extracting a sequencing parameter corresponding to the target task based on the cluster type of the target task;
sequencing the target tasks based on the sequencing parameters by adopting a preset sequencing rule;
and scheduling the sorted target tasks based on the sorting result.
The processor is further configured to perform other steps disclosed in the above method embodiments, and a detailed description thereof is omitted here.
For convenience of description, the above system is described with the functions divided into various modules, which are described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware implementations of the invention.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments, which are substantially similar to the method embodiments, are described in a relatively simple manner, and reference may be made to some descriptions of the method embodiments for relevant points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A task scheduling method for a cloud computing platform is characterized by comprising the following steps:
acquiring a target scheduling task;
judging the cluster type of the target task, wherein the cluster type comprises a linear cluster and a nonlinear cluster;
extracting a sequencing parameter corresponding to the target task based on the cluster type of the target task;
sequencing the target tasks based on the sequencing parameters by adopting a preset sequencing rule;
and scheduling the sorted target tasks based on the sorting result.
2. The task scheduling method of the cloud computing platform according to claim 1, wherein the sequencing parameters include duration and energy consumption, when the cluster type of the target task is a linear cluster, the duration refers to the longest execution time corresponding to the target task, and the energy consumption refers to total energy consumption corresponding to the target task;
when the cluster type of the target task is a nonlinear cluster, the duration refers to execution duration of the target task, and the energy consumption refers to execution energy consumption of the target task.
3. The task scheduling method of the cloud computing platform according to claim 2, wherein the target tasks are ranked based on the ranking parameters by using a preset ranking rule, and the method comprises the following steps:
and sequencing the target tasks according to the energy consumption of the target tasks, wherein the lower the energy consumption, the higher the priority of the target tasks is, the higher the priority of the target tasks with the same energy consumption is, the longer the priority of the target tasks is, and when the cluster type of the target tasks is a linear cluster, the sequencing result and the target tasks are led into the cluster to which the target tasks are adapted.
4. The task scheduling method of the cloud computing platform according to claim 2, wherein the target tasks are ranked based on the ranking parameters by using a preset ranking rule, and the method comprises the following steps:
sequencing the target tasks based on the time length to obtain a first sequencing result;
sequencing the target tasks based on energy consumption to obtain a second sequencing result;
calculating the average value of the first sequencing result and the second sequencing result to sequence the target tasks to obtain a third sequencing result;
if the third sequencing results of the two target tasks are the same, the higher the priority of the target task in the second sequencing result is, the higher the priority of the target task in the third sequencing result is;
and when the cluster type of the target task is a linear cluster, importing the sequencing result and the target task into a cluster adapted to the target task.
5. The cloud computing platform task scheduling method according to claim 2, wherein scheduling the ordered target tasks based on the ordering result includes: and scheduling the tasks in the current scheduling period by adopting a genetic algorithm based on the sequencing result.
6. The image recognition neural network training optimization method of claim 5, wherein the benefit function of the genetic algorithm is:
F(j)＝FitnessTime(j)+1/s(j)；
wherein the content of the first and second substances,
the subTask j，i In order to determine the energy consumption of the ith scheduling task allocated to the jth physical resource, avgTask is the average value of the energy consumption of all scheduling tasks, and n is the total number of scheduling tasks corresponding to chromosomes;
the FitnessTime is a time-dependent chromosomal benefit function.
7. A task scheduling device of a cloud computing platform is characterized by comprising:
the scheduling task acquisition unit is used for acquiring a target scheduling task;
the cluster type judging unit is used for judging the cluster type of the target task, and the cluster type comprises a linear cluster and a nonlinear cluster;
the sorting unit is used for extracting sorting parameters corresponding to the target tasks based on the cluster types of the target tasks; sequencing the target tasks based on the sequencing parameters by adopting a preset sequencing rule;
and the scheduling unit is used for scheduling the sequenced target tasks based on the sequencing result.
8. The cloud computing platform task scheduling device of claim 7, wherein the sequencing parameters include duration and energy consumption;
when the cluster type of the target task is a linear cluster, the duration refers to the longest execution time corresponding to the target task, and the energy consumption refers to total energy consumption corresponding to the target task;
when the cluster type of the target task is a non-linear cluster, the duration refers to the execution duration of the target task, and the energy consumption refers to the execution energy consumption of the target task.
9. The cloud computing platform task scheduling device according to claim 8, wherein the sorting unit, when sorting the target tasks based on the sorting parameter by using a preset sorting rule, is specifically configured to:
and sequencing the target tasks according to the energy consumption of the target tasks, wherein the lower the energy consumption, the higher the priority of the target tasks is, the higher the priority of the target tasks with the same energy consumption is, the longer the priority of the target tasks is, and when the cluster type of the target tasks is a nonlinear cluster, the sequencing result and the target tasks are led into the cluster to which the target tasks are adapted.
10. A task scheduling device of a cloud computing platform, comprising:
a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the cloud computing platform task scheduling method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211316809.6A CN115599522A (en) | 2022-10-26 | 2022-10-26 | Task scheduling method, device and equipment for cloud computing platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211316809.6A CN115599522A (en) | 2022-10-26 | 2022-10-26 | Task scheduling method, device and equipment for cloud computing platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115599522A true CN115599522A (en) | 2023-01-13 |
Family
ID=84849835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211316809.6A Pending CN115599522A (en) | 2022-10-26 | 2022-10-26 | Task scheduling method, device and equipment for cloud computing platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115599522A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116302451A (en) * | 2023-05-18 | 2023-06-23 | 广州豪特节能环保科技股份有限公司 | Offline energy-saving scheduling method and system for cloud computing data center |
-
2022
- 2022-10-26 CN CN202211316809.6A patent/CN115599522A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116302451A (en) * | 2023-05-18 | 2023-06-23 | 广州豪特节能环保科技股份有限公司 | Offline energy-saving scheduling method and system for cloud computing data center |
| CN116302451B (en) * | 2023-05-18 | 2023-08-08 | 广州豪特节能环保科技股份有限公司 | Offline energy-saving scheduling method and system for cloud computing data center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107659433B (en) | Cloud resource scheduling method and equipment | |
| Simaria et al. | A genetic algorithm based approach to the mixed-model assembly line balancing problem of type II | |
| Wang et al. | Load balancing task scheduling based on genetic algorithm in cloud computing | |
| CN109800071A (en) | A kind of cloud computing method for scheduling task based on improved adaptive GA-IAGA | |
| CN103092683A (en) | Scheduling used for analyzing data and based on elicitation method | |
| CN104065745A (en) | Cloud computing dynamic resource scheduling system and method | |
| CN110008023B (en) | Cloud computing system budget constraint random task scheduling method based on genetic algorithm | |
| CN108427602B (en) | Distributed computing task cooperative scheduling method and device | |
| Chakravarthi et al. | TOPSIS inspired cost-efficient concurrent workflow scheduling algorithm in cloud | |
| CN114327811A (en) | Task scheduling method, device and equipment and readable storage medium | |
| CN117271101B (en) | Operator fusion method and device, electronic equipment and storage medium | |
| CN115599522A (en) | Task scheduling method, device and equipment for cloud computing platform | |
| CN109710372A (en) | A kind of computation-intensive cloud workflow schedule method based on cat owl searching algorithm | |
| He | Optimization of edge delay sensitive task scheduling based on genetic algorithm | |
| CN114675953A (en) | Resource dynamic scheduling method, device, equipment and computer readable storage medium | |
| CN117639043A (en) | Electric automobile dispatching method and device under wind power cooperation, terminal equipment and medium | |
| Singh et al. | Market-inspired dynamic resource allocation in many-core high performance computing systems | |
| CN115545329A (en) | Integrated dynamic scheduling method suitable for clothing manufacturing production line | |
| CN114980216A (en) | Dependent task unloading system and method based on mobile edge calculation | |
| Javadi-Moghaddam et al. | Resource allocation in cloud computing using advanced imperialist competitive algorithm. | |
| CN114327925A (en) | Power data real-time calculation scheduling optimization method and system | |
| Shen et al. | Coevolutionary scheduling of dynamic software project considering the new skill learning | |
| Liu et al. | Resource management in cloud based on deep reinforcement learning | |
| CN110689320A (en) | Large-scale multi-target project scheduling method based on co-evolution algorithm | |
| CN117519942A (en) | Task scheduling method and device of cloud computing platform, storage medium and electronic equipment |
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 |