Resource scheduling system of prefabricated data center

Abstract

The invention discloses a resource scheduling system of a prefabricated data center, which relates to the related field of control and regulation systems, and comprises the following steps: acquiring configuration topology information of a plurality of prefabricated units by interacting a target scene; initial static scheduling decision making is carried out according to real-time task requirements, and an initial resource scheduling strategy set is generated; and analyzing the configuration topology information, obtaining connectivity characteristics of the plurality of prefabricated units, and obtaining real-time resource state information. And carrying out iterative decision optimization on the initial resource scheduling strategy set to obtain an optimized scheduling strategy set. And selecting the optimal first N optimal scheduling strategies from the optimal scheduling strategy set, outputting the optimal first N optimal scheduling strategies as a resource scheduling plan set, and performing resource scheduling control of the target prefabricated data center according to the resource scheduling plan set. The technical problems that in the prior art, resource scheduling of a prefabricated data center is poor in scheduling accuracy, an optimal resource scheduling strategy is difficult to obtain in a changeable environment, and consequently the resource utilization rate and the task execution efficiency are difficult to improve are solved.

Description

Technical Field

[0001] The present application relates to the field of control and regulation systems, and in particular to a resource scheduling system for a prefabricated data center. Background Art

[0002] With the rapid development of emerging technologies such as cloud computing, big data, and artificial intelligence, data centers, as the basic platform for information processing and storage, continue to increase in size and complexity. Traditional data centers are mostly based on fixed facilities and independent computer rooms, with long deployment cycles, limited scalability, high energy consumption, and difficulty in flexibly adapting to changing computing and storage needs. As a modular and highly integrated solution, prefabricated data centers modularly package infrastructure such as servers, network equipment, refrigeration and power supplies into standard units (prefabricated units), and then build an overall data center through reasonable topological connections. Compared with traditional data centers, prefabricated data centers are faster to deploy, more flexible to expand, more convenient to operate and maintain, and can flexibly combine resources according to application scenarios. However, in prefabricated data centers, the network topology composed of many prefabricated units is extremely complex, task requirements change in real time, and computing resources and environmental parameters fluctuate dynamically, making it difficult to accurately schedule and control prefabricated data center resources.

[0003] Therefore, in the prior art, resource scheduling of prefabricated data centers suffers from poor scheduling accuracy, and it is difficult to obtain the optimal resource scheduling strategy in a changing environment, resulting in technical problems such as difficulty in improving resource utilization and task execution efficiency. Summary of the invention

[0004] This application provides a resource scheduling system for prefabricated data centers, which solves the technical problems in the prior art that resource scheduling of prefabricated data centers is poor in scheduling accuracy, and it is difficult to obtain the optimal resource scheduling strategy in a changing environment, which leads to difficulty in improving resource utilization and task execution efficiency. Through multiple rounds of iterative decision optimization and sample point merging and streamlining strategies, combined with real-time equivalent connectivity characteristics and link pressure assessment, a set of resource scheduling plans that can be efficiently and dynamically called are finally obtained, thereby improving the resource utilization, task execution efficiency and operational stability of prefabricated data centers.

[0005] The present application provides a resource scheduling system for a prefabricated data center, the system comprising: an information acquisition module, used for interacting with a target scenario, and obtaining configuration topology information of a plurality of prefabricated units in a target prefabricated data center; a static scheduling decision acquisition module, used for making an initial static scheduling decision according to the real-time task requirements of the target prefabricated data center, and generating an initial resource scheduling strategy set; a resource status acquisition module, used for parsing the configuration topology information, obtaining connectivity characteristics of a plurality of the prefabricated units in the target prefabricated data center, and accessing and obtaining real-time resource status information of the plurality of the prefabricated units in real time, wherein the real-time resource status information includes computing resource status and environmental resource status; an optimization scheduling strategy acquisition module, used for performing iterative decision optimization of the initial resource scheduling strategy set according to the connectivity characteristics and the real-time resource status information, and obtaining a plurality of optimization results and storing them as an optimization scheduling strategy set; a scheduling control module, used for selecting the best top N optimization scheduling strategies from the optimization scheduling strategy set, outputting them as a resource scheduling plan set, and performing resource scheduling control of the target prefabricated data center according to the resource scheduling plan set.

[0006] In a possible implementation, the static scheduling decision acquisition module is also used to: access the task management terminal of the target prefabricated data center to extract the real-time task list; parse the real-time task list to obtain the resource consumption data of each real-time task, and output it as real-time resource expectations; perform iterative initial scheduling decisions based on the real-time resource expectations and the preset static resource scheduling strategy to obtain the initial resource scheduling strategy set.

[0007] In a possible implementation, the optimization scheduling strategy acquisition module is also used to: obtain the configuration parameter information of multiple prefabricated units in the target prefabricated data center according to the configuration topology information, and define an optimization constraint set according to the configuration parameter information, wherein the optimization constraint set includes at least unit resource capacity constraints, allocation consistency constraints, cross-module allocation constraints, module temperature constraints, and link load constraints; based on the optimization constraint set, perform repair cross-repair on the initial resource scheduling strategy set to obtain a repair resource scheduling strategy set; combine the initial resource scheduling strategy set with the repair resource scheduling strategy set to construct an optimization sample set, and based on the optimization sample set and the optimization constraint set, perform iterative decision optimization in combination with a preset objective function.

[0008] In a possible implementation, the optimization scheduling strategy acquisition module is also used to: in each iterative decision search, traverse the optimization sample set to extract a common target cluster, wherein the common target cluster is a sample subset with a common intersection in the optimization direction, wherein the sample subset includes at least N sample points, and N is greater than or equal to 3; calculate the objective function value of the common intersection and compare it with the objective function value of the N sample points in the common target cluster; if the objective function value of the common intersection is the optimal objective function value, merge the N sample points in the common target cluster into the common intersection to generate a new sample point.

[0009] In a possible implementation, the optimization scheduling strategy acquisition module is also used to: if the objective function value of the common intersection is the optimal objective function value, then traverse the common target cluster, calculate the distances between N sample points and the common intersection, and calculate the variance of the distances between the N sample points and the common intersection; if the distances between the N sample points and the common intersection are all less than a preset merging radius, and the variance of the distances between the N sample points and the common intersection is less than or equal to the preset variance, then take the common intersection as a new sample point, and calculate the vector sum of the optimization direction and optimization step of the N sample points in the common target cluster as the new optimization direction and optimization step; remove the N sample points in the common target cluster, and merge the new sample points into the optimized sample set.

[0010] In a possible implementation, the optimization scheduling strategy acquisition module is also used to: check the optimized sample set after generating new sample points, and count the number of sample points; if the number of sample points is less than a first preset sample size, terminate the extraction of the common target cluster and the merging of sample points; if the number of sample points is less than a second preset sample size, randomly mutate the new sample points until the number of sample points is greater than or equal to the second preset sample size and less than the first preset sample size, wherein the second preset sample size is smaller than the first preset sample size.

[0011] In a possible implementation, the scheduling control module is also used to: fit the connectivity characteristics and the real-time resource status information to obtain real-time equivalent connectivity characteristics; based on the real-time equivalent connectivity characteristics, evaluate the link pressure coefficient of the optimization result in the optimization scheduling strategy set, and generate a link pressure sequence accordingly; select the first N optimization results in the link pressure sequence as a resource scheduling plan set, and perform resource scheduling control of the target prefabricated data center according to the resource scheduling plan set.

[0012] In a possible implementation, the scheduling control module is also used to: serialize the resource scheduling plan set to generate a plan calling sequence; perform resource scheduling control with the first resource scheduling plan at the top of the plan calling sequence, and monitor the resource usage of the target prefabricated data center in real time; if the real-time monitoring results show that the resource usage exceeds the limit, call the next resource scheduling plan of the first resource scheduling plan in the plan calling sequence to perform resource scheduling control until the real-time monitoring results show that the resource usage does not exceed the limit; based on the resource scheduling plan called when the resource usage does not exceed the limit, perform feedback adjustment for iterative decision optimization.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application provides a resource scheduling system for a prefabricated data center, including: obtaining configuration topology information of multiple prefabricated units in a target prefabricated data center through an interactive target scenario. Performing an initial static scheduling decision according to the real-time task requirements of the target prefabricated data center, and generating an initial resource scheduling strategy set. Parsing the configuration topology information, obtaining connectivity characteristics of multiple prefabricated units in the target prefabricated data center, and accessing and obtaining real-time resource status information of multiple prefabricated units in real time. According to the connectivity characteristics and the real-time resource status information, iterative decision optimization of the initial resource scheduling strategy set is performed, and multiple optimization results are obtained and stored as an optimized scheduling strategy set. The top N optimal optimization scheduling strategies are selected from the optimized scheduling strategy set, output as a resource scheduling plan set, and resource scheduling control of the target prefabricated data center is performed according to the resource scheduling plan set. The technical problem that the resource scheduling of the prefabricated data center in the prior art has poor scheduling accuracy, it is difficult to obtain the optimal resource scheduling strategy in a changing environment, and it is difficult to improve resource utilization and task execution efficiency is solved. Through multiple rounds of iterative decision optimization and sample point merging and streamlining strategies, combined with real-time equivalent connectivity characteristics and link pressure assessment, we finally obtain a set of resource scheduling plans that can be efficiently and dynamically called, thereby improving the resource utilization, task execution efficiency and operation stability of the prefabricated data center. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1A schematic diagram of the structure of a resource scheduling system for a prefabricated data center provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of a process for obtaining an initial resource scheduling strategy set in a resource scheduling system of a prefabricated data center in the present application.

[0017] Explanation of the reference numerals: information collection module 11 , static scheduling decision acquisition module 12 , resource status acquisition module 13 , optimized scheduling strategy acquisition module 14 , scheduling control module 15 . DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, systems, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application embodiment provides a resource scheduling system for a prefabricated data center, such as Figure 1 As shown, the system comprises: The information collection module 11 is used to interact with the target scene and obtain the configuration topology information of multiple prefabricated units in the target prefabricated data center.

[0022] The static scheduling decision acquisition module 12 is used to make an initial static scheduling decision according to the real-time task requirements of the target prefabricated data center and generate an initial resource scheduling strategy set.

[0023] The resource status acquisition module 13 is used to parse the configuration topology information, obtain the connectivity characteristics of the multiple prefabricated units of the target prefabricated data center, and access the multiple prefabricated units in real time to obtain real-time resource status information, wherein the real-time resource status information includes computing resource status and environmental resource status.

[0024] A prefabricated data center is a modular data center structure that pre-integrates and packages infrastructure modules such as cabinets, servers, network switching equipment, refrigeration systems, and power systems into standardized modules, i.e., prefabricated units, and then connects and constructs several such prefabricated units in a certain topological manner. Through interactive target scenarios, the target scenarios are application configuration scenarios of target prefabricated data centers, such as prefabricated data centers in servers, etc., and various parameters and internal configurations of the target prefabricated data center are recorded in the target scenarios. The configuration topology information of multiple prefabricated units in the target prefabricated data center of the target scenario is obtained, and the configuration topology information includes the connection relationship and distribution structure of each prefabricated unit in the target prefabricated data center and the configuration information of the corresponding prefabricated units. Subsequently, an initial static scheduling decision is made according to the real-time task requirements of the target prefabricated data center to generate an initial resource scheduling strategy set.

[0025] Further, the configuration topology information is parsed to obtain connectivity characteristics of multiple prefabricated units, such as connectivity relationship, number of routes passed, physical connectivity distance, link rate, etc. And real-time access is performed to obtain real-time resource status information of multiple prefabricated units, such as CPU / GPU utilization, memory status, network bandwidth status, and storage IO throughput. The real-time resource status information includes computing resource status and environmental resource status, and the environmental resource status is environmental data, such as module temperature, power consumption, etc.

[0026] like Figure 2 As shown, the static scheduling decision acquisition module 12 is also used to: access the task management terminal of the target prefabricated data center to extract the real-time task list. Parse the real-time task list to obtain the resource consumption data of each real-time task, and output it as the real-time resource expectation. Iterate the initial scheduling decision based on the real-time resource expectation and the preset static resource scheduling strategy to obtain the initial resource scheduling strategy set.

[0027] An initial static scheduling decision is made according to the real-time task requirements of the target prefabricated data center, and an initial resource scheduling strategy set is generated, including: accessing the task management end of the target prefabricated data center, the task management end is a management interface or management module in the data center responsible for receiving, maintaining and allocating computing tasks, extracting the real-time task list of the task management end, that is, a list of all tasks that are currently ready to be executed or are being executed, including the basic attributes of these tasks and the corresponding resource requirements. By parsing the real-time task list, the basic attributes of each task such as data processing volume, demand processing time, etc., and the resource requirements of the task, such as memory requirements, network bandwidth requirements, and storage IO throughput are obtained. According to the resource requirements, the resource consumption data of the real-time task is obtained, including: memory consumption, network bandwidth consumption, and storage IO throughput, and the resource consumption data is output as real-time resource expectations. Further, based on the real-time resource expectations and the preset static resource scheduling strategy, an iterative initial scheduling decision is made to obtain the initial resource scheduling strategy set. The preset static resource scheduling strategy is a preset fixed resource scheduling strategy, and the preset static resource scheduling strategy only allocates the corresponding prefabricated units that meet the requirements according to the resource consumption data of the real-time task. For example, for CPU-intensive tasks, resources are allocated to prefabricated computing units with stronger computing power. For tasks that require high network bandwidth, modules with more redundant network links are selected first.

[0028] The optimization scheduling strategy acquisition module 14 is used to perform iterative decision optimization of the initial resource scheduling strategy set according to the connectivity characteristics and the real-time resource status information, and obtain multiple optimization results and store them as the optimization scheduling strategy set. The scheduling control module 15 is used to select the best top N optimization scheduling strategies from the optimization scheduling strategy set, output them as a resource scheduling plan set, and perform resource scheduling control of the target prefabricated data center according to the resource scheduling plan set.

[0029] According to the connectivity characteristics and the real-time resource status information, the initial resource scheduling strategy set is iterated and optimized by obtaining multiple iterative optimization results and storing them as an optimized scheduling strategy set. Finally, the optimized scheduling strategy set is sorted by strategy according to the output result of the objective function from roughly small to large, and the top N optimal optimization scheduling strategies are selected and output as a resource scheduling plan set, and the resource scheduling control of the target prefabricated data center is performed according to the resource scheduling plan set. The technical problem that the resource scheduling of the prefabricated data center in the prior art has poor scheduling accuracy, it is difficult to obtain the optimal resource scheduling strategy in a changing environment, and it is difficult to improve resource utilization and task execution efficiency is solved. Through multiple rounds of iterative decision optimization and sample point merging and streamlining strategies, combined with real-time equivalent connectivity characteristics and link pressure evaluation, a set of resource scheduling plans that can be efficiently and dynamically called are finally obtained, thereby improving the resource utilization, task execution efficiency and operation stability of the prefabricated data center.

[0030] The optimization scheduling strategy acquisition module 14 is also used to: obtain the configuration parameter information of multiple prefabricated units in the target prefabricated data center according to the configuration topology information, and define an optimization constraint set according to the configuration parameter information, wherein the optimization constraint set includes at least unit resource capacity constraints, allocation consistency constraints, cross-module allocation constraints, module temperature constraints, and link load constraints. Based on the optimization constraint set, the initial resource scheduling strategy set is repaired and crossed to obtain a repair resource scheduling strategy set. An optimization sample set is constructed by combining the initial resource scheduling strategy set with the repair resource scheduling strategy set, and based on the optimization sample set and the optimization constraint set, iterative decision-making optimization is performed in combination with a preset objective function.

[0031] According to the connectivity characteristics and the real-time resource status information, the initial resource scheduling strategy set is iterated and optimized, and multiple optimization results are obtained and stored as an optimized scheduling strategy set, including: according to the configuration topology information, multiple prefabricated unit configuration parameter information in the target prefabricated data center is obtained, and the configuration parameter information is the initial configuration parameter of the prefabricated unit, and the optimization constraint set is defined according to the configuration parameter information, wherein the optimization constraint set includes at least unit resource capacity constraint, allocation consistency constraint, cross-module allocation constraint, module temperature constraint, and link load constraint. The unit resource capacity constraint is that the total amount of resources such as CPU, memory, and bandwidth allocated to the unit cannot exceed its maximum carrying capacity. The allocation consistency constraint is that each task must be fully allocated to at least one module. When it can be allocated to one unit, the selection of multiple allocation units for a single task is not performed. The cross-module allocation constraint is the maximum limit on the number of allocated units. When the limit is exceeded, the corresponding allocation strategy will not be adopted. The module temperature constraint is the maximum temperature constraint for task allocation, and the task allocation is not performed for temperatures higher than the constraint. The link load constraint is that the data transmission on the network link cannot exceed the upper limit of the designed bandwidth to maintain normal data exchange speed and delay performance. In the initial resource scheduling strategy set, there may be a part of the strategies that do not meet the above constraints. Based on the optimization constraint set, the initial resource scheduling strategy set is repaired and crossed, that is, each scheduling strategy in the initial resource scheduling strategy set is constrained and screened according to the optimization constraint set to obtain the repair resource scheduling strategy set. Combine the initial resource scheduling strategy set with the repair resource scheduling strategy set to construct an optimization sample set. After obtaining the optimization sample set, the key characteristic indicators of each strategy are marked: such as CPU utilization, memory utilization, number of units, and current temperature data of the device. And based on the optimization sample set and the optimization constraint set, combined with the preset objective function, iterative decision-making optimization is performed. The preset objective function is: : a is the quality of the optimization sample. The larger a is, the higher the strategy adaptability is. b is the current temperature data of the unit in the optimization sample. When there are multiple units, b is the average of the current temperature data of multiple units. y is the resource utilization rate. The resource utilization rate is the average calculation result of the CPU utilization rate and the memory utilization rate. m and n are positive integers greater than 1, and m is greater than n.

[0032] The optimization scheduling strategy acquisition module 14 is also used to: in each iterative decision search, traverse the optimization sample set to extract a common target cluster, wherein the common target cluster is a sample subset with a common intersection in the optimization direction, wherein the sample subset includes at least N sample points, and N is greater than or equal to 3. Calculate the objective function value of the common intersection and compare it with the objective function value of the N sample points in the common target cluster. If the objective function value of the common intersection is the optimal objective function value, merge the N sample points in the common target cluster into the common intersection to generate a new sample point.

[0033] According to the connectivity characteristics and the real-time resource status information, the initial resource scheduling strategy set is iterated and optimized, and multiple optimization results are obtained and stored as an optimized scheduling strategy set, which also includes: each iterative optimization search is performed on the sample set, evaluated and improved to find a better resource scheduling strategy. In this process, since the sample size may be large, some sample points may be close in the multidimensional resource allocation space and point to similar optimization directions. These similar sample points may represent a relatively stable optimal area or a potential local optimal solution. Among them, the sample point refers to the coordinate point of a specific resource allocation scheme in the multidimensional variable space (for example, multiple dimensions such as CPU allocation, memory allocation, and network bandwidth allocation). In order to accelerate convergence and reduce redundant calculations, the common target cluster is extracted by traversing the optimized sample set, and these close sample points are classified, merged and simplified. When extracting the common target cluster, N sample points with a common intersection are obtained, and the common intersection is the center of a circular area containing N sample points. A sample subset is formed according to the N sample points, and the sample subset includes at least N sample points, and N is greater than or equal to 3. The objective function value of the common intersection is calculated and compared with the objective function values ​​of the N sample points in the common target cluster. If the objective function value of the common intersection is the optimal objective function value, then the common intersection can represent N sample points, and the N sample points in the common target cluster are merged into the common intersection to generate a new sample point.

[0034] The optimization scheduling strategy acquisition module 14 is also used for: if the objective function value of the common intersection is the optimal objective function value, then traverse the common target cluster, calculate the distance between the N sample points and the common intersection, and calculate the variance of the distance between the N sample points and the common intersection. If the distances between the N sample points and the common intersection are all less than the preset merging radius, and the variance of the distances between the N sample points and the common intersection is less than or equal to the preset variance, then the common intersection is used as a new sample point, and the vector sum of the optimization direction and optimization step of the N sample points in the common target cluster is calculated as the new optimization direction and optimization step. Remove the N sample points in the common target cluster, and merge the new sample points into the optimized sample set.

[0035] When the objective function value of the common intersection is the optimal objective function value, the common target cluster is traversed, the distance between the N sample points and the common intersection is calculated, and the variance of the distance between the N sample points and the common intersection is calculated. If the distance between the N sample points and the common intersection is less than the preset merging radius, and the variance of the distance between the N sample points and the common intersection is less than or equal to the preset variance, the common intersection is used as a new sample point, and the vector sum of the optimization direction and the optimization step of the N sample points in the common target cluster is calculated as the new optimization direction and optimization step. The preset variance is a pre-set variance parameter, and the larger the variance, the more obvious the corresponding distance fluctuation. When it is less than or equal to the preset variance, the higher the concentration of the corresponding sample point. The preset merging radius is the maximum radius for merging multiple sample points with the common intersection. Remove the N sample points in the common target cluster, and merge the new sample points into the optimized sample set.

[0036] The optimization scheduling strategy acquisition module 14 is also used to: check the optimized sample set after generating new sample points, and count the number of sample points. If the number of sample points is less than the first preset sample size, the extraction of the common target cluster and the merging of the sample points are terminated. If the number of sample points is less than the second preset sample size, the new sample points are randomly mutated until the number of sample points is greater than or equal to the second preset sample size and less than the first preset sample size, wherein the second preset sample size is less than the first preset sample size.

[0037] The N sample points in the common target cluster are merged into the common intersection to generate a new sample point, and then the optimized sample set after the new sample point is generated is checked to count the number of sample points. If the number of sample points is less than the first preset sample size, at this time, the number of samples can meet the requirements, and the extraction of the common target cluster and the merging of sample points are terminated. The first preset sample size is a preset sample size parameter. If the number of sample points is less than the second preset sample size, the new sample points are randomly mutated until the number of sample points is greater than or equal to the second preset sample size and less than the first preset sample size, wherein the second preset sample size is less than the first preset sample size.

[0038] The scheduling control module 15 is also used to fit the connectivity characteristics and the real-time resource status information to obtain real-time equivalent connectivity characteristics. Based on the real-time equivalent connectivity characteristics, the link pressure coefficient of the optimization result in the optimization scheduling strategy set is evaluated, and a link pressure sequence is generated accordingly. The first N optimization results in the link pressure sequence are selected as a resource scheduling plan set, and resource scheduling control of the target prefabricated data center is performed according to the resource scheduling plan set.

[0039] Fitting the connectivity characteristics with the real-time resource status information, that is, using the real-time resource status information to modify the theoretical connectivity characteristics, specifically, based on the connected load, such as the load rate of the network, weighted adjustment can be made for different connected links. For example, the link with a higher network load can multiply its connection distance by a coefficient greater than 1, so as to obtain a real-time equivalent connectivity characteristic that is closer to the current real environment. Based on the real-time equivalent connectivity characteristics, the link pressure coefficient of the optimization result in the optimization scheduling strategy set is evaluated, and a link pressure sequence is generated accordingly. The higher the pressure coefficient, the lower the ranking. The first N optimization results in the link pressure sequence are selected as the resource scheduling plan set, and the resource scheduling control of the target prefabricated data center is performed according to the resource scheduling plan set.

[0040] The scheduling control module 15 is also used to: serialize the resource scheduling plan set and generate a plan calling sequence. Perform resource scheduling control with the first resource scheduling plan at the top of the plan calling sequence, and monitor the resource usage of the target prefabricated data center in real time. If the real-time monitoring result shows that the resource usage exceeds the limit, call the next resource scheduling plan of the first resource scheduling plan in the plan calling sequence to perform resource scheduling control until the real-time monitoring result shows that the resource usage does not exceed the limit. Based on the resource scheduling plan called when the resource usage does not exceed the limit, feedback adjustment of iterative decision optimization is performed.

[0041] The resource scheduling control of the target prefabricated data center is performed according to the resource scheduling plan set, including: serializing the resource scheduling plan set according to the initial sorting to generate a plan calling sequence. The resource scheduling control is performed with the first resource scheduling plan at the top of the plan calling sequence, and the resource scheduling control is performed by the plan that is ranked first in the plan calling sequence, and the resource usage of the target prefabricated data center is monitored in real time. If the real-time monitoring result shows that the resource usage exceeds the limit, that is, there is a situation where the resource usage limit is exceeded, then the next resource scheduling plan of the first resource scheduling plan in the plan calling sequence is called to perform resource scheduling control until the real-time monitoring result shows that the resource usage is not exceeded. Based on the resource scheduling plan called when the resource usage is not exceeded, feedback adjustment of iterative decision optimization is performed.

[0042] The embodiment of the present application obtains the configuration topology information of multiple prefabricated units in the target prefabricated data center through an interactive target scenario. An initial static scheduling decision is made according to the real-time task requirements of the target prefabricated data center to generate an initial resource scheduling strategy set. The configuration topology information is parsed to obtain the connectivity characteristics of the multiple prefabricated units in the target prefabricated data center, and the real-time resource status information of the multiple prefabricated units is obtained by real-time access, wherein the real-time resource status information includes the computing resource status and the environmental resource status. According to the connectivity characteristics and the real-time resource status information, an iterative decision optimization of the initial resource scheduling strategy set is performed, and multiple optimization results are obtained and stored as an optimized scheduling strategy set. The top N optimal optimization scheduling strategies are selected from the optimized scheduling strategy set, and the output is a resource scheduling plan set, and the resource scheduling control of the target prefabricated data center is performed according to the resource scheduling plan set. The technical problem that the resource scheduling of the prefabricated data center in the prior art has poor scheduling accuracy, it is difficult to obtain the optimal resource scheduling strategy in a variable environment, and it is difficult to improve resource utilization and task execution efficiency is solved. Through multiple rounds of iterative decision optimization and sample point merging and streamlining strategies, combined with real-time equivalent connectivity characteristics and link pressure assessment, we finally obtain a set of resource scheduling plans that can be efficiently and dynamically called, thereby improving the resource utilization, task execution efficiency and operation stability of the prefabricated data center.

[0043] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A resource scheduling system for a prefabricated data center, characterized in that: The system comprises: An information collection module, used for interacting with a target scenario and obtaining configuration topology information of multiple prefabricated units in a target prefabricated data center; A static scheduling decision acquisition module is used to make initial static scheduling decisions based on the real-time task requirements of the target prefabricated data center and generate an initial resource scheduling strategy set; A resource status acquisition module, used to parse the configuration topology information, obtain connectivity characteristics of the plurality of prefabricated units of the target prefabricated data center, and access and obtain the plurality of prefabricated units in real time to obtain real-time resource status information, wherein the real-time resource status information includes computing resource status and environmental resource status; An optimized scheduling strategy acquisition module is used to perform iterative decision optimization of the initial resource scheduling strategy set according to the connectivity characteristics and the real-time resource status information, and obtain multiple optimization results and store them as an optimized scheduling strategy set; A scheduling control module, used to select the best top N optimization scheduling strategies from the optimization scheduling strategy set, output them as a resource scheduling plan set, and perform resource scheduling control of the target prefabricated data center according to the resource scheduling plan set; The optimization scheduling strategy acquisition module is also used for: According to the configuration topology information, obtain configuration parameter information of a plurality of the prefabricated units in the target prefabricated data center, and define an optimization constraint set according to the configuration parameter information, wherein the optimization constraint set includes at least a unit resource capacity constraint, an allocation consistency constraint, a cross-module allocation constraint, a module temperature constraint, and a link load constraint; Based on the optimization constraint set, performing repair cross-talk on the initial resource scheduling strategy set to obtain a repair resource scheduling strategy set; Combining the initial resource scheduling strategy set with the repair resource scheduling strategy set to construct an optimization sample set, and performing iterative decision optimization based on the optimization sample set and the optimization constraint set in combination with a preset objective function; Wherein, the dispatch control module is also used for: Serializing the resource scheduling plan set to generate a plan calling sequence; Using the first resource scheduling plan at the top of the plan call sequence to perform resource scheduling control, and monitor the resource usage of the target prefabricated data center in real time; If the real-time monitoring result shows that the resource usage exceeds the limit, calling the next resource scheduling plan of the first resource scheduling plan in the plan calling sequence to perform resource scheduling control until the real-time monitoring result shows that the resource usage does not exceed the limit; Based on the resource scheduling plan that is called when the resource usage does not exceed the limit, feedback adjustment of iterative decision-making optimization is performed.

2. A resource scheduling system for a prefabricated data center as claimed in claim 1, characterized in that: The static scheduling decision acquisition module is also used for: Access the task management terminal of the target prefabricated data center and extract the real-time task list; Parsing the real-time task list to obtain resource consumption data of each real-time task, and outputting the data as real-time resource expectation; An iterative initial scheduling decision is performed based on the real-time resource expectation and a preset static resource scheduling strategy to obtain the initial resource scheduling strategy set.

3. A resource scheduling system for a prefabricated data center as claimed in claim 2, characterized in that: The optimized scheduling strategy acquisition module is also used for: In each iterative decision optimization, the optimization sample set is traversed to extract a common target cluster, wherein the common target cluster is a sample subset having a common intersection in the optimization direction, wherein the sample subset includes at least N sample points, and N is greater than or equal to 3; Calculate the objective function value of the common intersection point and compare it with the objective function values ​​of the N sample points in the common target cluster; If the objective function value of the common intersection is the optimal objective function value, the N sample points in the common target cluster are merged into the common intersection to generate a new sample point.

4. A resource scheduling system for a prefabricated data center as claimed in claim 3, characterized in that: The optimized scheduling strategy acquisition module is also used for: If the objective function value of the common intersection is the optimal objective function value, traverse the common target cluster, calculate the distances between N sample points and the common intersection, and calculate the variance of the distances between the N sample points and the common intersection; If the distances between the N sample points and the common intersection are all less than the preset merging radius, and the variance of the distances between the N sample points and the common intersection is less than or equal to the preset variance, the common intersection is taken as a new sample point, and the vector sum of the optimization direction and the optimization step of the N sample points in the common target cluster is calculated as the new optimization direction and optimization step; The N sample points in the common target cluster are removed, and the new sample points are merged into the optimized sample set.

5. The resource scheduling system for a prefabricated data center according to claim 3, characterized in that: The optimized scheduling strategy acquisition module is also used for: Checking the optimized sample set after generating new sample points, and counting the number of sample points; If the number of sample points is less than the first preset sample size, terminating the extraction of the common target cluster and the merging of the sample points; If the number of sample points is less than the second preset sample size, random mutation is performed on the new sample points until the number of sample points is greater than or equal to the second preset sample size and less than the first preset sample size, wherein the second preset sample size is smaller than the first preset sample size.

6. The resource scheduling system for a prefabricated data center according to claim 1, characterized in that: The dispatch control module is also used for: Fitting the connectivity feature with the real-time resource status information to obtain a real-time equivalent connectivity feature; Based on the real-time equivalent connectivity characteristics, evaluating the link pressure coefficient of the optimization result of the optimization scheduling strategy concentration, and generating a link pressure sequence accordingly; The first N optimization results in the link pressure sequence are selected as a resource scheduling plan set, and resource scheduling control of the target prefabricated data center is performed according to the resource scheduling plan set.

Images