An intelligent computing power scheduling method and system based on dynamic programming

Abstract

The present invention belongs to the technical field of data processing, and particularly relates to an intelligent computing power scheduling method and system based on dynamic programming. By real-time monitoring the current available resource information of multiple computing power clusters, calculating the resource difference value between clusters to evaluate the balance of resource allocation, and determining a preliminary computing power grouping scheme. On this basis, according to the historical task types and resource consumption characteristics, match the suitable task types for each group, and adjust the preliminary grouping scheme to form an optimized computing power grouping. Using the optimized computing power grouping, calculate the service capacity scores of each group according to the preset service level agreement, and provide a recommended set of computing power resource services to users after sorting by the scores. The present invention optimizes the computing power grouping through a dynamic evaluation mechanism, ensures the balanced resource allocation and can meet the requirements of different types of tasks, and improves the overall utilization rate and service quality of computing power resources.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to an intelligent computing power scheduling method and system based on dynamic programming. Background Art

[0002] In the current data center and cloud computing environment, the management and scheduling of computing power resources are crucial for ensuring service quality and improving resource utilization. Existing computing power scheduling methods mainly rely on preset rules or simple load balancing algorithms for resource allocation. These methods usually first collect the resource usage of each computing power cluster, and then determine the task allocation according to a certain strategy (such as round-robin, least connections, etc.). However, when facing a complex multi-cluster environment, these methods are prone to the problem of unbalanced resource allocation. Especially in the case of significant resource differences between clusters, traditional scheduling strategies often cannot effectively balance the loads of each cluster, resulting in some resources being idle while others are overloaded.

[0003] A key problem in the prior art is how to effectively evaluate these differences and make reasonable resource allocation decisions based on them when there are large resource differences between multiple computing power clusters. If the resource differences between clusters cannot be accurately measured, then optimal resource utilization may not be achieved during task scheduling, thereby affecting the performance and service level of the entire system. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent computing power scheduling method and system based on dynamic programming, which solves the problems mentioned in the above background art by real-time monitoring the resource usage of clusters and calculating the resource difference value between clusters to evaluate the balance of resource allocation.

[0005] To achieve the above purpose, on the one hand, the present invention proposes an intelligent computing power scheduling method based on dynamic programming, including:

[0006] S1: Determine the current available resource information of multiple computing power clusters, and calculate the resource difference value between each cluster according to the current available resource information; S2: Evaluate the balance of resource allocation between each cluster based on the resource difference value, and determine a preliminary computing power grouping scheme according to the balance of resource allocation; S3: Based on the preliminary computing power grouping scheme, match the suitable task types for each group according to the historical task type and resource consumption characteristics; S4: Adjust the preliminary grouping scheme in combination with the matching results of the task types to form an optimized computing power grouping; S5: Use the optimized computing power grouping to calculate the service ability score of each group according to the preset service level agreement; S6: Sort the optimized computing power grouping according to the service ability score, and provide the sorted computing power grouping to the user as a recommended set of computing power resource services.

[0007] Preferably, determining the current available resource information of multiple computing power clusters includes:

[0008] Collecting data on the processor utilization rate, memory usage rate, and network bandwidth occupancy rate of nodes within each cluster;

[0009] Applying the formula to calculate the comprehensive resource score of each cluster , where represents the processor utilization rate, represents the memory usage rate, represents the network bandwidth occupancy rate, and the coefficients α, β, γ represent the weights of the processor, memory, and network in the comprehensive evaluation respectively; Based on the comprehensive resource score

[0010] , compare the resource utilization situations between different clusters to determine the resource difference value , where represents the resource difference value between cluster and cluster and cluster .

[0011] Preferably, calculating the resource difference value between each cluster according to the current available resource information includes:

[0012] Normalize the processor utilization rate , memory usage rate , and network bandwidth occupancy rate of each cluster to obtain the normalized values , , ;

[0013] Use the formula to update the comprehensive resource score of each cluster to reflect the importance of the resources after normalization;

[0014] Calculate the resource difference value between any two clusters and , which is used as the basis for adjusting the preliminary computing power grouping scheme.

[0015] Preferably, evaluating the balance of resource allocation between each cluster based on the resource difference value includes:

[0016] Sum up the resource difference values of all clusters and calculate the average resource difference value ;

[0017] Use the formula to quantify the overall balance of resource allocation among clusters , where is the total number of clusters;

[0018] Based on the size of the overall balance to determine whether the resource allocation meets the predetermined balance standard.

[0019] Preferably, determine a preliminary computing power grouping scheme according to the balance of the resource allocation, including:

[0020] When the overall balance is lower than the predetermined threshold, group the clusters with resource difference values less than the predetermined threshold into the same group;

[0021] For each group, define the average resource score of the clusters within the group , and ensure that the difference between groups is minimized;

[0022] Evaluate the consistency of the internal resource distribution of each group through the formula , and select the combination with the smallest as the preliminary computing power grouping scheme.

[0023] Preferably, match the suitable task types for each group according to the historical task types and resource consumption characteristics, including:

[0024] Analyze the historical task records and extract the typical resource consumption patterns corresponding to the task types ;

[0025] Compare the resource characteristics of each computing power group with the typical resource consumption patterns , and apply a similarity metric to evaluate the matching degree;

[0026] Select the task type with the highest similarity metric as the task type recommended for processing by this group .

[0027] Preferably, adjust the preliminary grouping scheme in combination with the matching results of the task types to form an optimized computing power grouping, including:

[0028] For each group , recalculate the resource matching score based on the resource requirements of the highest recommended task type ;

[0029] If a certain group Resource matching score If it is lower than the preset threshold value, reallocate the clusters within this group to other groups to improve the resource matching score;

[0030] After adjustment, a final optimized computing power grouping scheme is formed, enabling the clusters within each group to better support the recommended task types.

[0031] Preferably, calculate the service ability scores of each group according to the preset service level agreement, including:

[0032] According to the requirements of the preset service level agreement, define quality of service indicators for each optimized group , including but not limited to response time, throughput, and reliability;

[0033] Apply the formula to calculate the service ability scores of each group , where , , are the weights of response time, throughput, and reliability respectively;

[0034] Based on the service ability scores , evaluate the ability of each group to provide services.

[0035] Preferably, provide the sorted computing power groups to the user as a recommended set of computing power resource services, including:

[0036] Construct a grouping sorting function based on the service ability scores , and this function outputs a sorted grouping sequence;

[0037] Apply the sorting function to all optimized groups to obtain a sorted grouping sequence ;

[0038] Traverse the sorted grouping sequence , and select the first groups as the candidate recommendation set;

[0039] Summarize the information of the candidate recommendation set into a recommendation list RecList, where RecList includes but is not limited to grouping identifiers, service ability scores, and reasons for recommendation;

[0040] Show the recommendation list RecList to the user so that the user can select a suitable set of computing power resource services according to their own needs.

[0041] On the other hand, the present invention proposes an intelligent computing power scheduling system based on dynamic programming, including:

[0042] A cluster resource status monitoring module, which is used to determine the current available resource information of multiple computing power clusters, and calculate the resource difference value between clusters according to the current available resource information;

[0043] A resource balance evaluation and preliminary grouping module, which is used to evaluate the balance of resource allocation between clusters based on the resource difference value, and determine a preliminary computing power grouping scheme according to the balance of the resource allocation;

[0044] A task type matching module, which is used to match the suitable task types for each group based on the historical task types and resource consumption characteristics on the basis of the preliminary computing power grouping scheme;

[0045] A grouping optimization and adjustment module, which is used to adjust the preliminary grouping scheme in combination with the matching result of the task type to form an optimized computing power grouping;

[0046] A service ability score calculation module, which is used to calculate the service ability scores of each group according to the preset service level agreement by using the optimized computing power grouping;

[0047] A computing power resource service recommendation module, which is used to sort the optimized computing power grouping according to the service ability scores, and provide the sorted computing power grouping to the user as a recommended set of computing power resource services.

[0048] The technical effects and advantages of the present invention: An intelligent computing power scheduling method and system based on dynamic programming proposed by the present invention have the following advantages compared with the prior art:

[0049] The present invention evaluates the balance of resource allocation by real-time monitoring the resource usage of clusters and calculating the resource difference value between clusters. Based on this dynamic evaluation mechanism, a more reasonable computing power grouping scheme can be determined, and through further task type matching and grouping optimization, it is ensured that the finally formed computing power grouping can better meet the needs of different types of tasks. In addition, by introducing a service level agreement to calculate the service ability scores of each group and sorting and recommending accordingly, the overall utilization rate and service quality of computing power resources can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flowchart of the intelligent computing power scheduling method based on dynamic programming of the present invention;

[0051] Figure 2 is a block diagram of the intelligent computing power scheduling system based on dynamic programming of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0052] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] The present invention provides an intelligent computing power scheduling method based on dynamic programming, aiming to evaluate the balance of resource allocation by real-time monitoring the current available resource information of multiple computing power clusters and calculating the resource difference value between clusters, and determine a preliminary computing power grouping scheme.

[0054] On this basis, match the suitable task types for each group according to the historical task types and resource consumption characteristics, and adjust the preliminary grouping scheme to form an optimized computing power grouping. Using the optimized computing power grouping, calculate the service capacity scores of each group according to the preset service level agreement, and provide the recommended computing power resource service set to the user after sorting by the scores. The present invention optimizes the computing power grouping through a dynamic evaluation mechanism, ensures the balance of resource allocation and can meet the requirements of different types of tasks, and improves the overall utilization rate and service quality of computing power resources. Specifically as follows:

[0055] As Figure 1 shown, in the intelligent computing power scheduling method based on dynamic programming in this embodiment, the following steps are included:

[0056] S1: Determine the current available resource information of multiple computing power clusters, and calculate the resource difference value between each cluster according to the current available resource information; by real-time determining the current available resource information of multiple computing power clusters and calculating the resource difference value between each cluster accordingly, the present invention can accurately reflect the resource usage and its differences between each cluster. This method of calculating the resource difference value based on real-time data helps to more precisely evaluate the actual load conditions of different clusters, thereby providing a solid foundation for subsequent resource allocation and scheduling. In this way, waste and over-concentration of resources can be avoided, ensuring that computing power resources are more evenly and effectively utilized, and further improving the operating efficiency and service quality of the overall system.

[0057] In addition, determining the current available resource information of multiple computing power clusters further includes:

[0058] Collect data on the processor utilization rate, memory usage rate, and network bandwidth occupancy rate of nodes within each cluster; specifically, regularly collect data on the processor utilization rate, memory usage rate, and network bandwidth occupancy rate from each node within each computing power cluster. For example, a node within cluster A may report that its processor utilization rate is 80%, its memory usage rate is 60%, and its network bandwidth occupancy rate is 40%.

[0059] Apply the formula to calculate the comprehensive resource score for each cluster , where represents the processor utilization rate, represents the memory usage rate, represents the network bandwidth occupancy rate, and the coefficients α, β, γ represent the weights of the processor, memory, and network in the comprehensive evaluation respectively;

[0060] Based on the comprehensive resource score , compare the resource utilization situations between different clusters to determine the resource difference value , where represents the cluster and the cluster and the resource difference value between them.

[0061] For example: Assume α = 0.5, β = 0.3, γ = 0.2. For cluster A, if its average processor utilization rate CPUA is 80%, its memory usage rate MEMA is 60%, and its network bandwidth occupancy rate NETA is 40%, then its comprehensive resource score RA is 0.5×80 + 0.3×60 + 0.2×40 = 64.

[0062] Through the above steps, the present invention can accurately obtain the current resource usage situation of each computing power cluster, and obtain a comprehensive resource score through weighted calculation. This score reflects the overall resource utilization level of the cluster. Further, by comparing the comprehensive resource scores of different clusters, the resource differences between the clusters can be clarified, which provides a reliable basis for subsequent resource allocation. This method not only improves the accuracy of resource evaluation, but also simplifies the quantification process of resource differences, making resource scheduling more refined and automated, thereby improving the usage efficiency and service quality of the overall computing power resources.

[0063] Calculating the resource difference value between clusters according to the current available resource information further includes:

[0064] Normalize the processor utilization rate , memory usage rate , and network bandwidth occupancy rate of each cluster to obtain the normalized values , , ;

[0065] Use the formula to update the comprehensive resource score of each cluster , so as to reflect the importance of resources after standardization; calculate the resource difference value and between any two clusters , and use this as the basis for adjusting the preliminary computing power grouping scheme.

[0066] By standardizing the resource utilization data of each cluster, the present invention eliminates the dimensional difference between different resource types, enabling the resource utilization rate to be compared under a unified standard. The updated comprehensive resource score more accurately reflects the importance of the current resource usage of each cluster, helping to more precisely evaluate the resource differences between clusters. The calculated resource difference value provides the basic data support for the subsequent optimization of the computing power grouping, ensuring that the grouping scheme is more reasonable, thereby improving the balance of resource allocation and the overall service level of the system.

[0067] S2: Evaluate the balance of resource allocation among clusters based on the resource difference value, and determine the preliminary computing power grouping scheme according to the balance of resource allocation; by evaluating the balance of resource allocation among computing power clusters based on the resource difference value and determining the preliminary computing power grouping scheme accordingly, the present invention can ensure that the resource usage within each group is more uniform. Such a grouping method helps to reduce the overload risk of some clusters while making full use of the resources of those clusters that are not fully utilized. Therefore, this method can improve the balance and utilization rate of the resources of the entire system, reduce the service bottleneck caused by improper resource allocation, and further improve the stability of the service and the user experience.

[0068] Specifically, evaluating the balance of resource allocation among clusters based on the resource difference value further includes:

[0069] Sum up the resource difference values of all clusters, and calculate the average resource difference value ; for example:

[0070] Suppose there are four clusters A, B, C, D, and their resource difference values are D AB = 0.04, D AC = 0.12, D AD = 0.08, D BC = 0.10, D BD = 0.06, D CD = 0.05.

[0071] Sum up all the resource difference values and calculate the average resource difference value:

[0072] =(0.04 + 0.12 + 0.08 + 0.10 + 0.06 + 0.05) / 6 = 0.0767。

[0073] Use the formula to quantify the overall balance of resource allocation among clusters , where is the total number of clusters;

[0074] For example: Assume represents the normalized resource difference value between cluster i and cluster j. Here, directly use .

[0075] The overall balance degree E = 1 / 4(4 - 1)(|0.04 - 0.0767| + |0.12 - 0.0767| + |0.08 - 0.0767| + |0.10 - 0.0767| + |0.06 - 0.0767| + |0.05 - 0.0767|).

[0076] E = 1 / 12(0.0367 + 0.0433 + 0.0033 + 0.0233 + 0.0167 + 0.0267) = 0.0228.

[0077] According to the magnitude of the overall balance degree to determine whether the resource allocation reaches the predetermined balance standard. Assume the threshold of the predetermined balance standard is 0.05. Since E = 0.0228 < 0.05, the resource allocation reaches the predetermined balance standard.

[0078] Through the above steps, the present invention can effectively evaluate the balance of resource allocation among clusters and determine a preliminary computing power grouping scheme accordingly. The advantage of this is that it can ensure more uniform resource allocation, reduce resource waste, and improve the utilization efficiency of computing power resources at the same time. By dividing clusters with resource difference values less than the predetermined threshold into the same group and ensuring the consistency of resource distribution within the group, the utilization of computing power resources can be further optimized, and the overall performance and service quality of the system can be improved.

[0079] Determining a preliminary computing power grouping scheme according to the balance of the resource allocation further includes:

[0080] When the overall balance degree is lower than the predetermined threshold, divide clusters with resource difference values less than the predetermined threshold into the same group; As shown above, since D AD = 0.08 and D CD= 0.05 is relatively small, and it can be considered to divide cluster A and D, as well as cluster C and D into one group. Suppose that finally A and D are selected as one group, and C and D are selected as another group from C and D, and the remaining B is a separate group. For each grouping, define the average resource score of the clusters within the group , and ensure that the differences between the groupings are minimized; evaluate the consistency of the internal resource distribution of each grouping through the formula , and select the combination with the minimum as the preliminary computing power grouping scheme.

[0081] Through the above steps, the present invention can determine a preliminary computing power grouping scheme according to the balance of resource allocation. This method ensures that clusters with resource difference values less than a predetermined threshold are divided into the same group, thereby improving the consistency of the internal resource distribution within the grouping, and further enhancing the balance and efficiency of resource utilization. By selecting the combination with the minimum as the preliminary computing power grouping scheme, it can better meet the requirements of different task types and improve the performance and service quality of the entire system.

[0082] S3: Based on the preliminary computing power grouping scheme, match the suitable task types for each grouping according to the historical task types and resource consumption characteristics; specifically as follows:

[0083] Analyze the historical task records and extract the typical resource consumption patterns corresponding to the task types ; compare the resource characteristics of each computing power grouping with the typical resource consumption patterns , and apply a similarity metric to evaluate the matching degree; select the task type with the highest similarity metric as the task type recommended to be processed by this grouping.

[0084] By matching the suitable task types for each grouping based on the historical task types and resource consumption characteristics on the basis of the preliminary grouping scheme, the present invention can achieve an efficient matching between tasks and computing power resources. This method can identify the optimal resource configuration for different types of tasks according to the past task execution situations, so that when allocating new tasks, they can be assigned to the computing power grouping that is most suitable for processing such tasks.

[0085] Doing so can not only improve the efficiency and success rate of task processing, but also further optimize the utilization of resources, reduce resource waste, and enhance the performance and service quality of the overall system.

[0086] S4: Adjust the preliminary grouping scheme in combination with the matching results of the task types to form an optimized computing power grouping; specifically as follows: including:

[0087] For each group , recalculate the resource matching score based on the resource requirements of its recommended task type ; if the resource matching score of a certain group is lower than the preset threshold value, reallocate the clusters within this group to other groups to improve the resource matching score; after adjustment, form the final optimized computing power grouping scheme, so that the clusters within each group can better support the recommended task types. The resource matching score By combining the matching results of the task types to adjust the preliminary grouping scheme to form the optimized computing power grouping, the present invention can ensure that the computing power resources within each group are more suitable for the task types to be processed. This method not only improves the pertinence and efficiency of task execution, but also makes the resource allocation more reasonable, reducing the performance bottleneck and resource waste caused by resource mismatch.

[0088] The optimized computing power grouping can better meet the requirements of different task types, thereby improving the overall response speed and service quality of the system, while ensuring the maximization of resource utilization benefits.

[0089] S5: Using the optimized computing power grouping, calculate the service capacity score of each group according to the preset service level agreement; specifically as follows: According to the requirements of the preset service level agreement, define service quality indicators

[0090] for each optimized group , including but not limited to response time, throughput and reliability; apply the formula , calculate the service capacity score of each group , where , , , are the weights of response time, throughput and reliability respectively; based on the service capacity score , evaluate the service providing ability of each group.

[0091] By using the optimized computing power grouping and calculating the service capacity score of each group according to the preset service level agreement, the present invention can quantify the service providing ability of different computing power groups. This method enables managers to objectively evaluate the performance of each group in terms of response time, throughput and reliability, etc., so as to better understand the current service level of the system.

[0092] Based on the service ability score, the management and scheduling of computing power resources can be carried out more scientifically, ensuring that important tasks are given priority, while improving user satisfaction and the overall service quality. In addition, the scoring mechanism also helps to identify potential service shortcomings and provides a basis for further optimizing the system.

[0093] S6: Sort the optimized computing power groups according to the service ability score, and provide the sorted computing power groups to the user as a recommended set of computing power resource services. Specifically as follows:

[0094] Construct a grouping sorting function based on the service ability score , and this function outputs a sorted grouping sequence; Apply the sorting function to all optimized groups to obtain a sorted grouping sequence ; Traverse the sorted grouping sequence , and select the first groups as the candidate recommendation set; Summarize the information of the candidate recommendation set into a recommendation list RecList, where RecList includes but is not limited to grouping identifiers, service ability scores, and recommendation reasons; Display the recommendation list RecList to the user so that the user can select a suitable set of computing power resource services according to their own needs.

[0095] By sorting the optimized computing power groups according to the service ability score and providing the sorted computing power groups to the user as a recommended set of computing power resource services, the present invention realizes the intelligent management of computing power resources.

[0096] This method enables users to intuitively understand the service ability and availability of different computing power groups, facilitating the user to select the most suitable computing power resources according to their own needs. At the same time, the recommendation mechanism based on scoring and sorting ensures that high-quality resources are recommended first, thereby improving the user experience when selecting and using computing power services and enhancing the reliability of the service and user satisfaction.

[0097] In addition, this method also helps to promote the efficient use of resources and reduce resource waste caused by blind selection.

[0098] On the other hand, the present invention proposes an intelligent computing power scheduling system based on dynamic programming, as Figure 2 shown, including: a cluster resource status monitoring module, a resource balance evaluation and preliminary grouping module, a task type matching module, a grouping optimization and adjustment module, a service ability score calculation module, and a computing power resource service recommendation module.

[0099] Specifically, the cluster resource status monitoring module is used to determine the current available resource information of multiple computing power clusters, and calculate the resource difference value between clusters according to the current available resource information;

[0100] Specifically, the resource balance evaluation and preliminary grouping module is used to evaluate the balance of resource allocation among clusters based on the resource difference value, and determine a preliminary computing power grouping scheme according to the balance of the resource allocation;

[0101] Specifically, the task type matching module is used to match the suitable task types for each group based on the historical task types and resource consumption characteristics on the basis of the preliminary computing power grouping scheme;

[0102] Specifically, the grouping optimization and adjustment module is used to adjust the preliminary grouping scheme in combination with the matching result of the task type to form an optimized computing power grouping;

[0103] Specifically, the service ability score calculation module is used to calculate the service ability scores of each group according to a preset service level agreement by using the optimized computing power grouping;

[0104] Specifically, the computing power resource service recommendation module is used to sort the optimized computing power grouping according to the service ability scores, and provide the sorted computing power grouping to the user as a recommended set of computing power resource services.

[0105] In addition, when the above-mentioned cluster resource status monitoring module, resource balance evaluation and preliminary grouping module, task type matching module, grouping optimization and adjustment module, service ability score calculation module, and computing power resource service recommendation module are executed, they are also used to implement other steps of the above-mentioned intelligent computing power scheduling method based on dynamic programming, which will not be elaborated here one by one.

[0106] In addition, the present invention also provides a terminal device. In this embodiment, the intelligent computing power scheduling method based on dynamic programming mainly applies to the terminal device, and the terminal device can be a device with display and processing functions such as a PC, a portable computer, a mobile terminal, etc.

[0107] Specifically, the terminal device may include a processor (such as a CPU), a communication bus, a user interface, a network interface, and a memory. Among them, the communication bus is used to realize the connection and communication between these components; the user interface may include a display screen (Display) and an input unit such as a keyboard (Keyboard); the network interface may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface); the memory may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory, and the memory may optionally be a storage device independent of the foregoing processor.

[0108] Among them, a readable storage medium is stored in the memory, and a computing power scheduling program is stored in the readable storage medium. The processor can call the computing power scheduling program stored in the memory and execute the intelligent computing power scheduling method based on dynamic programming provided by the embodiments of the present invention.

[0109] It can be understood that the readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. The computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanically encoded device, such as a punched card or raised structure in a groove having instructions stored thereon, and any suitable combination of the above. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through an optical fiber cable), or electrical signals transmitted through wires.

[0110] The computer-readable program instructions described herein can be downloaded from the computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0111] Computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0112] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent computing power scheduling method based on dynamic programming, characterized in that: include: S1: Determine currently available resource information of multiple computing power clusters, and calculate resource difference values ​​between the clusters based on the currently available resource information; S2: Evaluate the balance of resource allocation among clusters based on the resource difference value, and determine a preliminary computing power grouping plan according to the balance of resource allocation; S3: Based on the preliminary computing power grouping plan, match the appropriate task type for each group according to historical task types and resource consumption characteristics; S4: adjusting the preliminary computing power grouping scheme in combination with the matching result of the task type to form an optimized computing power grouping; S5: Using the optimized computing power grouping, calculate the service capability score of each group according to a preset service level agreement; S6: sorting the optimized computing power groups according to the service capability scores, and providing the sorted computing power groups to the user as a computing power resource service set recommendation; Determine the currently available resource information of multiple computing clusters, including: Collect data on processor utilization, memory usage, and network bandwidth usage of nodes in each cluster; Apply the formula Calculate each cluster Comprehensive resource score ,in Indicates the processor utilization, Indicates memory usage. represents the network bandwidth utilization, and the coefficients α, β, and γ represent the weights of the processor, memory, and network in the comprehensive evaluation respectively; Based on the comprehensive resource score , compare resource utilization between different clusters to determine resource differential values ,in Represents a cluster and clusters The resource difference between Processor utilization for each cluster , memory usage and network bandwidth utilization Perform standardization and obtain standardized values , , ; Using the formula Update each cluster Comprehensive resource score , to reflect the importance of the resource after normalization; Calculate any two clusters and The resource difference between , which will serve as the basis for adjusting the initial computing power grouping plan.

2. According to claim 1, a method for intelligent computing power scheduling based on dynamic programming is characterized in that: Evaluating the balance of resource allocation among clusters based on the resource difference value includes: Set the resource difference value of all clusters Summarize and calculate the average resource variance value ; Using the formula To quantify the overall balance of resource allocation among clusters ,in is the total number of clusters; According to the overall balance The size of the resource allocation is used to determine whether it reaches the predetermined balance standard.

3. According to claim 2, the intelligent computing power scheduling method based on dynamic programming is characterized in that: Determine the preliminary computing power grouping plan based on the balance of resource allocation, including: When the overall balance When the resource difference value is lower than the predetermined threshold, Clusters smaller than a predetermined threshold are divided into the same group; For each group, define the average resource score of the clusters in the group and ensure that Minimize the differences; By formula To evaluate each group Consistency of internal resource distribution, selection The minimized combination is used as the preliminary computing power grouping scheme.

4. According to claim 3, the intelligent computing power scheduling method based on dynamic programming is characterized in that: Match the appropriate task type for each group based on historical task types and resource consumption characteristics, including: Analyze historical task records and extract typical resource consumption patterns corresponding to task types ; Comparing the hashrate groups Resource characteristics and typical resource consumption patterns , applying similarity measure To assess the matching degree; Choosing a similarity measure Highest mission type As this group The type of task that is recommended for processing.

5. According to claim 4, a method for intelligent computing power scheduling based on dynamic programming is characterized in that: The preliminary computing power grouping scheme is adjusted in combination with the matching result of the task type to form an optimized computing power grouping, including: For each group , based on the highest recommended task type Recalculate resource matching scores based on resource requirements ; If a group Resource matching score If it is lower than the preset threshold, the clusters in the group are reallocated to other groups to improve the resource matching score; After adjustments, the final optimized computing power grouping plan is formed, so that the clusters in each group can better support their recommended task types.

6. The intelligent computing power scheduling method based on dynamic programming according to claim 5 is characterized in that: Calculate the service capability score of each group based on the preset service level agreement, including: According to the requirements of the preset service level agreement, each optimized group Defining Quality of Service Indicators , including but not limited to response time, throughput and reliability; Apply the formula , calculate each group Service capability rating ,in , , They are the weights of response time, throughput, and reliability; Based on the service capability score , assessing each group’s ability to provide services.

7. The intelligent computing power scheduling method based on dynamic programming according to claim 1 is characterized in that: Providing the user with the computing power grouping after the above sorting as a computing power resource service set recommendation, including: Build a service capability-based scoring Grouping sorting function , this function outputs the sorted group sequence; Applying a sort function For all optimized groups, get the sorted group sequence ; Traverse the sorted group sequence , before selecting groups as candidate recommendation sets; Aggregate the information of the candidate recommendation set into a recommendation list RecList, where RecList includes but is not limited to a group identifier, a service capability score, and a recommendation reason; The recommendation list RecList is displayed to the user so that the user can select a computing resource service set according to his or her needs.

8. An intelligent computing power scheduling system based on dynamic programming, characterized in that it includes: The cluster resource status monitoring module is used to determine the currently available resource information of multiple computing power clusters and calculate the resource difference value between each cluster based on the currently available resource information, including: collecting the processor utilization, memory usage and network bandwidth occupancy data of the nodes in each cluster; applying the formula Calculate each cluster Comprehensive resource score ,in Indicates the processor utilization, Indicates memory usage. represents the network bandwidth utilization rate, and the coefficients α, β, and γ represent the weights of the processor, memory, and network in the comprehensive evaluation respectively; based on the comprehensive resource score , compare resource utilization between different clusters to determine resource differential values ,in Represents a cluster and clusters The resource difference between the two clusters; the processor utilization of each cluster , memory usage and network bandwidth utilization Perform standardization and obtain standardized values , , ; Use the formula Update each cluster Comprehensive resource score , to reflect the importance of standardized resources; calculate any two clusters and The resource difference between , which will be used as the basis for adjusting the initial computing power grouping plan; A resource balance assessment and preliminary grouping module, used to assess the balance of resource allocation among clusters based on the resource difference value, and determine a preliminary computing power grouping scheme according to the balance of resource allocation; The task type matching module is used to match the appropriate task type for each group based on the initial computing power grouping plan and historical task types and resource consumption characteristics; A grouping optimization adjustment module, used to adjust the preliminary computing power grouping scheme in combination with the matching result of the task type to form an optimized computing power grouping; A service capability score calculation module, used to calculate the service capability score of each group according to a preset service level agreement by using the optimized computing power grouping; The computing power resource service recommendation module is used to sort the optimized computing power groups according to the service capability scores, and provide the users with the sorted computing power groups as a computing power resource service set recommendation.

Images