A resource configuration method and system for automated multi-dimensional computing

Abstract

The present invention provides a resource configuration method for automated multi-dimensional computing. First, according to the characteristics and requirements of computing tasks, at least two configuration algorithms are selected according to a configuration algorithm selection strategy; according to machine learning and optimization algorithms, configuration parameters of the configuration algorithms are determined; the selected at least two configuration algorithms are cross-fused in pairs by using a feature fusion method to obtain fused configuration algorithms; resource configuration results obtained by the fused configuration algorithms are comprehensively weighted according to calculation rules and weight allocation strategies to obtain final resource configuration results; calculations are performed according to the resource configuration results, the calculation results are monitored in real time, and the configuration algorithms are switched according to the configuration algorithm selection strategy, and the above steps are repeated to obtain the final resource configuration results; the present invention fuses multiple configuration algorithms through a composite calculation method, and adjusts the configuration algorithms in real time, thereby improving the efficiency and accuracy of calculations in multiple dimensions.

Description

Technical Field

[0001] The present invention relates to the field of resource configuration, and in particular to a resource configuration method and system for automated multi-dimensional computing. Background Art

[0002] The current resource allocation method is relatively simple and cannot be adjusted and changed in real time according to the characteristics and needs of computing tasks in different periods. The computing efficiency and accuracy are low, resulting in the inability to meet customer needs. Summary of the invention

[0003] The main purpose of the present invention is to overcome the above-mentioned defects in the prior art and to propose a resource configuration method and system for automated multi-dimensional computing. Through a composite computing method, multiple configuration algorithms are integrated, and the selection of the configuration algorithm is combined with the characteristics and requirements of the computing task. The configuration algorithm is adjusted in real time according to the changes in the computing task, thereby improving the efficiency and accuracy of the computing in multiple dimensions.

[0004] The technical solution adopted by the present invention is:

[0005] A resource configuration method for automated multi-dimensional computing, comprising:

[0006] S1: Select at least two configuration algorithms based on the characteristics and requirements of the computing task and the configuration algorithm selection strategy;

[0007] S2: Determine the configuration parameters of the configuration algorithm by analyzing historical data and model training based on machine learning and optimization algorithms;

[0008] S3: The selected configuration algorithms, which are not less than two, are cross-fused in pairs by using a feature fusion method to obtain a fused configuration algorithm;

[0009] S4: Comprehensively weight the resource configuration results obtained by the fused configuration algorithm according to the calculation rules and weight allocation strategy to obtain the final resource configuration result;

[0010] S5: Perform calculations based on the resource configuration results, monitor the calculation results in real time, select a strategy based on the configuration algorithm to switch the configuration algorithm, and repeat steps S2-S4.

[0011] Specifically, the characteristics and requirements of the computing task include, but are not limited to: computing complexity, data scale, computing amount, parallelism, and computing resources required for the computing task.

[0012] Specifically, the configuration algorithm selection strategy is as follows:

[0013] First, determine the configuration algorithm library based on the characteristics, applicable scenarios, and performance indicators of different algorithms;

[0014] For different computing tasks, the configuration algorithms in the configuration algorithm library are evaluated and tested for performance, including indicators such as computing time, resource utilization, and accuracy;

[0015] Optimize and adjust the configuration algorithm based on the evaluation results;

[0016] Use experimental data and actual application scenarios for verification, and finally determine the configuration algorithms corresponding to different computing tasks;

[0017] The configuration algorithm selection strategy is determined according to the configuration algorithms corresponding to different computing tasks.

[0018] Specifically, the configuration algorithm selection strategy also includes an evaluation of the configuration algorithm, and the evaluation indicators include but are not limited to accuracy, recall rate, calculation time and memory consumption.

[0019] Specifically, according to machine learning and optimization algorithms, configuration parameters of the configuration algorithm are determined by analyzing historical data and model training. The machine learning and optimization algorithms include but are not limited to support vector machines, decision trees, and deep neural network models.

[0020] Specifically, at least two selected configuration algorithms are cross-fused in pairs using a feature fusion method to obtain a fused configuration algorithm, specifically:

[0021] A first configuration algorithm and a second configuration algorithm are selected, the first configuration algorithm and the second configuration algorithm are calculated in parallel, and the results of the first configuration algorithm and the second configuration algorithm are weighted averaged, and the first configuration algorithm is calibrated using the weighted average result to obtain a fused first configuration algorithm;

[0022] The first configuration algorithm and the second configuration algorithm are calculated in parallel, and after weighted averaging the results of the second configuration algorithm and the first configuration algorithm, the second configuration algorithm is calibrated using the averaged result to obtain a fused second configuration algorithm.

[0023] Specifically, the resource configuration results obtained by the fused configuration algorithm are comprehensively weighted according to the calculation rules and weight allocation strategy to obtain the final resource configuration result. The calculation rules and weight allocation strategy adopt an integrated learning method, and the integrated learning method includes but is not limited to Bagging, Boosting and Stacking.

[0024] Another aspect of the present invention provides a resource configuration system for automated multi-dimensional computing, including:

[0025] Configuration algorithm selection unit: selects at least two configuration algorithms according to the characteristics and requirements of the computing task and the configuration algorithm selection strategy.

[0026] Configuration parameter determination unit: determines the configuration parameters of the configuration algorithm by analyzing historical data and model training based on machine learning and optimization algorithms;

[0027] Configuration algorithm fusion unit: select at least two configuration algorithms, cross-fuse configuration algorithm models in pairs by using the fusion feature method, and obtain the fused configuration algorithm;

[0028] Configuration result synthesis unit: the resource configuration results obtained by the fused configuration algorithm are comprehensively weighted according to the calculation rules and weight distribution strategy to obtain the final resource configuration result;

[0029] Adjustment cycle unit: perform calculations based on resource configuration results, monitor the calculation results in real time, select strategies based on the configuration algorithm to switch the configuration algorithm, and calculate again to obtain the final resource configuration results.

[0030] On the other hand, the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a resource configuration method for automated multi-dimensional computing when executing the computer program.

[0031] Another aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of a resource configuration method for automated multi-dimensional computing.

[0032] It can be seen from the above description of the present invention that, compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention provides a resource configuration method for automated multi-dimensional computing. First, according to the characteristics and requirements of computing tasks, at least two configuration algorithms are selected according to a configuration algorithm selection strategy; according to machine learning and optimization algorithms, configuration parameters of the configuration algorithms are determined by analyzing historical data and model training; the selected at least two configuration algorithms are cross-fused in pairs by a feature fusion method to obtain a fused configuration algorithm; the resource configuration results obtained by the fused configuration algorithm are comprehensively weighted according to a computing rule and a weight allocation strategy to obtain a final resource configuration result; calculations are performed according to the resource configuration results, the calculation results are monitored in real time, and the configuration algorithms are switched according to the configuration algorithm selection strategy, and the above steps are repeated to obtain the final resource configuration result; the present invention proposes an automated multi-dimensional computing resource configuration method and system, which fuses multiple configuration algorithms through a composite computing method, and the selection of the configuration algorithms is combined with the characteristics and requirements of computing tasks, and the configuration algorithms are adjusted in real time according to changes in the computing tasks, so as to improve the efficiency and accuracy of computing in multiple dimensions. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flow chart of a resource configuration method for automated multi-dimensional computing provided by an embodiment of the present invention;

[0035] Figure 2 A framework diagram of a resource configuration system for automated multi-dimensional computing provided by an embodiment of the present invention;

[0036] Figure 3 A schematic diagram of an electronic device provided by an embodiment of the present invention;

[0037] Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention.

[0038] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. DETAILED DESCRIPTION

[0039] The present invention proposes a resource configuration method for automated multi-dimensional computing. Through a composite computing method, multiple configuration algorithms are integrated. The selection of configuration algorithms is combined with the characteristics and requirements of computing tasks. The configuration algorithms are adjusted in real time according to changes in computing tasks, thereby improving the efficiency and accuracy of computing in multiple dimensions.

[0040] like Figure 1 , a resource configuration method for automated multi-dimensional computing, comprising;

[0041] S101: selecting at least two configuration algorithms according to the characteristics and requirements of the computing task and the configuration algorithm selection strategy;

[0042] Algorithm selection and configuration: First, understand the characteristics, applicable scenarios and performance indicators of different algorithms, determine the algorithm library, and evaluate and test the performance of the algorithm for different computing tasks, including indicators such as computing time, resource utilization and accuracy. Based on the evaluation results, optimize and adjust the algorithm to improve computing efficiency and accuracy, considering the limitations and constraints of computing resources. Finally, verify it using experimental data and actual application scenarios; ultimately determine the configuration algorithms corresponding to different computing tasks, thereby determining the configuration algorithm selection strategy.

[0043] For different computing tasks, first, we analyze the characteristics and requirements of the computing tasks to understand the computing complexity, data scale, computing amount, parallelism and other characteristics of the tasks, as well as the requirements of the tasks for computing resources (CPU, memory, GPU, etc.).

[0044] Algorithm candidate set: Select a suitable algorithm candidate set based on the characteristics and requirements of the task. There may be multiple algorithms that can solve the same problem. These algorithms have different performance in different situations. Sorting algorithms: such as quick sort, merge sort, bubble sort, etc. Machine learning algorithms: such as support vector machine (SVM), decision tree, deep neural network, etc. Data mining algorithms: such as association rule mining, cluster analysis, classification algorithms, etc.

[0045] Performance evaluation indicators: define appropriate performance evaluation indicators to measure the performance of the algorithm. These indicators may include execution time, resource utilization, precision, accuracy, recall, computation time, and memory consumption;

[0046] Verification and testing: Verify the performance and accuracy of the configuration algorithm selection strategy, conduct a large number of test cases and experiments, and ensure that the configuration algorithm can be correctly selected in different situations.

[0047] Algorithm library and tool support: Use existing optimization algorithm libraries and tools, such as NumPy, SciPy, TensorFlow, etc., to provide various optimization algorithms and configuration options; or provide algorithm configuration and optimization interfaces and interfaces based on open source and commercial software to facilitate users to select and configure algorithms.

[0048] S102: According to the machine learning and optimization algorithm, by analyzing historical data and model training, determine the configuration parameters of the configuration algorithm;

[0049] Specifically, according to machine learning and optimization algorithms, configuration parameters of the configuration algorithm are determined by analyzing historical data and model training. The machine learning and optimization algorithms include but are not limited to support vector machines, decision trees, and deep neural network models.

[0050] S103: fusing the configuration algorithm models of at least two selected configuration algorithms in pairs by cross-fusing feature methods to obtain a fused configuration algorithm;

[0051] Specifically, at least two selected configuration algorithms are cross-fused in pairs using a feature fusion method to obtain a fused configuration algorithm, specifically:

[0052] A first configuration algorithm and a second configuration algorithm are selected, the first configuration algorithm and the second configuration algorithm are calculated in parallel, and the results of the first configuration algorithm and the second configuration algorithm are weighted averaged, and the first configuration algorithm is calibrated using the weighted average result to obtain a fused first configuration algorithm;

[0053] The first configuration algorithm and the second configuration algorithm are calculated in parallel, and after weighted averaging the results of the second configuration algorithm and the first configuration algorithm, the second configuration algorithm is calibrated using the averaged result to obtain a fused second configuration algorithm.

[0054] S104: Comprehensively weighting the resource configuration results obtained by the fused configuration algorithm according to the calculation rules and weight distribution strategy to obtain the final resource configuration result;

[0055] Specifically, the resource configuration results obtained by the fused configuration algorithm are comprehensively weighted according to the calculation rules and weight allocation strategy to obtain the final resource configuration result. The calculation rules and weight allocation strategy adopt an integrated learning method, and the integrated learning method includes but is not limited to Bagging, Boosting and Stacking.

[0056] S105: Perform calculations according to the resource configuration results, monitor the calculation results in real time, select a strategy according to the configuration algorithm to switch the configuration algorithm, and repeat steps S2-S4.

[0057] like Figure 2 Another aspect of the present invention provides a resource configuration system for automated multi-dimensional computing, including:

[0058] Configuration algorithm selection unit 201: selects at least two configuration algorithms according to the characteristics and requirements of the computing task and the configuration algorithm selection strategy.

[0059] Algorithm selection and configuration: First, understand the characteristics, applicable scenarios and performance indicators of different algorithms, determine the algorithm library, and evaluate and test the performance of the algorithm for different computing tasks, including indicators such as computing time, resource utilization and accuracy. Based on the evaluation results, optimize and adjust the algorithm to improve computing efficiency and accuracy, considering the limitations and constraints of computing resources. Finally, verify it using experimental data and actual application scenarios; ultimately determine the configuration algorithms corresponding to different computing tasks, thereby determining the configuration algorithm selection strategy.

[0060] For different computing tasks, first, we analyze the characteristics and requirements of the computing tasks to understand the computing complexity, data scale, computing amount, parallelism and other characteristics of the tasks, as well as the requirements of the tasks for computing resources (CPU, memory, GPU, etc.).

[0061] Algorithm candidate set: Select a suitable algorithm candidate set based on the characteristics and requirements of the task. There may be multiple algorithms that can solve the same problem. These algorithms have different performance in different situations. Sorting algorithms: such as quick sort, merge sort, bubble sort, etc. Machine learning algorithms: such as support vector machine (SVM), decision tree, deep neural network, etc. Data mining algorithms: such as association rule mining, cluster analysis, classification algorithms, etc.

[0062] Performance evaluation indicators: define appropriate performance evaluation indicators to measure the performance of the algorithm. These indicators may include execution time, resource utilization, precision, accuracy, recall, computation time, and memory consumption;

[0063] Verification and testing: Verify the performance and accuracy of the configuration algorithm selection strategy, conduct a large number of test cases and experiments, and ensure that the configuration algorithm can be correctly selected in different situations.

[0064] Algorithm library and tool support: Use existing optimization algorithm libraries and tools, such as NumPy, SciPy, TensorFlow, etc., to provide various optimization algorithms and configuration options; or provide algorithm configuration and optimization interfaces and interfaces based on open source and commercial software to facilitate users to select and configure algorithms.

[0065] Configuration parameter determination unit 202: determines configuration parameters of the configuration algorithm by analyzing historical data and model training according to machine learning and optimization algorithms;

[0066] Specifically, according to machine learning and optimization algorithms, configuration parameters of the configuration algorithm are determined by analyzing historical data and model training. The machine learning and optimization algorithms include but are not limited to support vector machines, decision trees, and deep neural network models.

[0067] Configuration algorithm fusion unit 203: fuses the selected at least two configuration algorithms in pairs by cross-fusing the configuration algorithm models using a feature fusion method to obtain a fused configuration algorithm;

[0068] Specifically, at least two selected configuration algorithms are cross-fused in pairs using a feature fusion method to obtain a fused configuration algorithm, specifically:

[0069] A first configuration algorithm and a second configuration algorithm are selected, the first configuration algorithm and the second configuration algorithm are calculated in parallel, and the results of the first configuration algorithm and the second configuration algorithm are weighted averaged, and the first configuration algorithm is calibrated using the weighted average result to obtain a fused first configuration algorithm;

[0070] The first configuration algorithm and the second configuration algorithm are calculated in parallel, and after weighted averaging the results of the second configuration algorithm and the first configuration algorithm, the second configuration algorithm is calibrated using the averaged result to obtain a fused second configuration algorithm.

[0071] Configuration result synthesis unit 204: performs comprehensive weighting on the resource configuration results obtained by the fused configuration algorithm according to the calculation rules and weight distribution strategy to obtain the final resource configuration result;

[0072] Specifically, the resource configuration results obtained by the fused configuration algorithm are comprehensively weighted according to the calculation rules and weight allocation strategy to obtain the final resource configuration result. The calculation rules and weight allocation strategy adopt an integrated learning method, and the integrated learning method includes but is not limited to Bagging, Boosting and Stacking.

[0073] Adjustment cycle unit 205: performs calculation according to the resource configuration result, monitors the calculation result in real time, switches the configuration algorithm according to the configuration algorithm selection strategy, and calculates again to obtain the final resource configuration result.

[0074] Figure 3 As shown, an embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer code 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer code 311, an automated multi-dimensional computing resource configuration method provided by an embodiment of the present invention is implemented.

[0075] Since the electronic device introduced in this embodiment is the device used to implement the embodiment of the present invention, based on the method introduced in the embodiment of the present invention, the technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present invention is not introduced in detail here. As long as the equipment used by the technical personnel in this field to implement the method in the embodiment of the present invention falls within the scope of protection of the present invention.

[0076] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention.

[0077] like Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, an automated multi-dimensional computing resource configuration method provided by an embodiment of the present invention is implemented.

[0078] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] The present invention provides a resource configuration method for automated multi-dimensional computing. First, according to the characteristics and requirements of computing tasks, at least two configuration algorithms are selected according to a configuration algorithm selection strategy; according to machine learning and optimization algorithms, configuration parameters of the configuration algorithms are determined by analyzing historical data and model training; the selected at least two configuration algorithms are cross-fused in pairs by a feature fusion method to obtain a fused configuration algorithm; the resource configuration results obtained by the fused configuration algorithm are comprehensively weighted according to a computing rule and a weight allocation strategy to obtain a final resource configuration result; calculations are performed according to the resource configuration results, the calculation results are monitored in real time, and the configuration algorithms are switched according to the configuration algorithm selection strategy, and the above steps are repeated to obtain the final resource configuration result; the present invention proposes an automated multi-dimensional computing resource configuration method and system, which fuses multiple configuration algorithms through a composite computing method, and the selection of the configuration algorithms is combined with the characteristics and requirements of computing tasks, and the configuration algorithms are adjusted in real time according to changes in the computing tasks, so as to improve the efficiency and accuracy of computing in multiple dimensions.

[0081] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. The various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.

[0082] The above is only a specific implementation of the present invention, but the design concept of the present invention is not limited thereto. Any non-substantial changes to the present invention using this concept shall be deemed as an infringement of the protection scope of the present invention.

Claims

1. A resource configuration method for automated multi-dimensional computing, characterized in that: include; S1: Select at least two configuration algorithms based on the characteristics and requirements of the computing task and the configuration algorithm selection strategy; S2: Determine the configuration parameters of the configuration algorithm by analyzing historical data and model training based on machine learning and optimization algorithms; The configuration algorithm selection strategy also includes an evaluation of the configuration algorithm, and the evaluation indicators include but are not limited to accuracy, recall, computing time and memory consumption; Determining configuration parameters of the configuration algorithm by analyzing historical data and model training according to machine learning and optimization algorithms, the machine learning and optimization algorithms including but not limited to support vector machines, decision trees, and deep neural network models; S3: The selected configuration algorithms, which are not less than two, are cross-fused in pairs by using a feature fusion method to obtain a fused configuration algorithm; A first configuration algorithm and a second configuration algorithm are selected, the first configuration algorithm and the second configuration algorithm are calculated in parallel, and the results of the first configuration algorithm and the second configuration algorithm are weighted averaged, and the first configuration algorithm is calibrated using the weighted average result to obtain a fused first configuration algorithm; The first configuration algorithm and the second configuration algorithm are calculated in parallel, and the results of the second configuration algorithm and the first configuration algorithm are weighted averaged, and the second configuration algorithm is calibrated using the averaged result to obtain a fused second configuration algorithm; S4: Comprehensively weight the resource configuration results obtained by the fused configuration algorithm according to the calculation rules and weight allocation strategy to obtain the final resource configuration result; S5: Perform calculations based on the resource configuration results, monitor the calculation results in real time, select a strategy based on the configuration algorithm to switch the configuration algorithm, and repeat steps S2-S4.

2. The resource configuration method for automated multi-dimensional computing according to claim 1, characterized in that: The characteristics and requirements of the computing task specifically include but are not limited to: computing complexity, data scale, computing amount, parallelism, and computing resources required for the computing task.

3. The resource configuration method for automated multi-dimensional computing according to claim 1, characterized in that: The configuration algorithm selection strategy is specifically as follows: First, determine the configuration algorithm library based on the characteristics, applicable scenarios, and performance indicators of different algorithms; For different computing tasks, the configuration algorithms in the configuration algorithm library are evaluated and tested for performance, including computing time, resource utilization, and accuracy indicators; Optimize and adjust the configuration algorithm based on the evaluation results; Use experimental data and actual application scenarios for verification, and finally determine the configuration algorithms corresponding to different computing tasks; The configuration algorithm selection strategy is determined according to the configuration algorithms corresponding to different computing tasks.

4. The resource configuration method for automated multi-dimensional computing according to claim 1, characterized in that: The resource configuration results obtained by the fused configuration algorithm are comprehensively weighted according to the calculation rules and weight allocation strategy to obtain the final resource configuration result. The calculation rules and weight allocation strategy adopt an integrated learning method, and the integrated learning method includes but is not limited to Bagging, Boosting and Stacking.

5. An automated multi-dimensional computing resource allocation system, characterized in that: include: Configuration algorithm selection unit: selects at least two configuration algorithms according to the characteristics and requirements of the computing task and the configuration algorithm selection strategy; Configuration parameter determination unit: determines the configuration parameters of the configuration algorithm by analyzing historical data and model training based on machine learning and optimization algorithms; The configuration algorithm selection strategy also includes an evaluation of the configuration algorithm, and the evaluation indicators include but are not limited to accuracy, recall, computing time and memory consumption; Determining configuration parameters of the configuration algorithm by analyzing historical data and model training according to machine learning and optimization algorithms, the machine learning and optimization algorithms including but not limited to support vector machines, decision trees, and deep neural network models; Configuration algorithm fusion unit: select at least two configuration algorithms, cross-fuse configuration algorithm models in pairs by using the fusion feature method, and obtain the fused configuration algorithm; A first configuration algorithm and a second configuration algorithm are selected, the first configuration algorithm and the second configuration algorithm are calculated in parallel, and the results of the first configuration algorithm and the second configuration algorithm are weighted averaged, and the first configuration algorithm is calibrated using the weighted average result to obtain a fused first configuration algorithm; The first configuration algorithm and the second configuration algorithm are calculated in parallel, and the results of the second configuration algorithm and the first configuration algorithm are weighted averaged, and the second configuration algorithm is calibrated using the averaged result to obtain a fused second configuration algorithm; Configuration result synthesis unit: the resource configuration results obtained by the fused configuration algorithm are comprehensively weighted according to the calculation rules and weight distribution strategy to obtain the final resource configuration result; Adjustment cycle unit: perform calculations based on resource configuration results, monitor the calculation results in real time, select strategies based on the configuration algorithm to switch the configuration algorithm, and calculate again to obtain the final resource configuration results.

6. An electronic device, characterized in that: include: A memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method steps of any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps of any one of claims 1 to 4 are implemented.

Images