Resource optimization scheduling method and device, computer equipment and readable storage medium

Abstract

The invention relates to a resource optimization scheduling method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring real-time state data of each equipment end; determining a scenario analysis result of the computing platform according to the real-time state data and a preset scenario analysis model; determining a resource allocation strategy according to the scene analysis result and a preset resource allocation model; and adjusting at least one of the task quantity or the resource quantity of each device end according to the resource allocation strategy. By adopting the method, the resource utilization rate of the computing platform can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of resource scheduling, and in particular to a resource optimization scheduling method, apparatus, computer equipment and readable storage medium. Background Art

[0002] With the rapid development of information technology, various complex systems continue to emerge, such as production management systems in smart factories, cloud computing platforms in large-scale data centers, etc. These systems face the processing requirements of multiple types of tasks, and the task characteristics and resource requirements vary greatly.

[0003] Related technologies usually use static task scheduling strategies and fixed resource allocation schemes, which can easily lead to problems such as resource waste when facing fluctuations in task requirements or resource shortages. Summary of the invention

[0004] Based on this, it is necessary to provide a resource optimization scheduling method, device, computer equipment and readable storage medium that can improve resource utilization in response to the above technical problems.

[0005] In a first aspect, the present application provides a resource optimization scheduling method, which is applied to a computing platform, wherein the computing platform includes at least one device end; the method includes:

[0006] Acquire real-time status data of each of the devices;

[0007] Determining a scenario analysis result of the computing platform according to each of the real-time status data and a preset scenario analysis model;

[0008] Determine a resource allocation strategy based on the scenario analysis results and a preset resource allocation model;

[0009] According to the resource allocation strategy, at least one of the task amount or resource amount of each of the device ends is adjusted.

[0010] In one embodiment, determining the scenario analysis result of the computing platform according to each of the real-time status data and a preset scenario analysis model includes:

[0011] Preprocessing the real-time status data;

[0012] Performing data conversion processing on the preprocessed real-time status data to obtain real-time situation parameters;

[0013] The real-time situation parameters are input into the situation analysis model to obtain the situation analysis result.

[0014] In one of the embodiments, the real-time status data includes device load data and network traffic data, and the real-time context data includes discrete parameters and quantized parameters;

[0015] The performing data conversion processing on the pre-processed real-time status data to obtain real-time situation parameters includes:

[0016] Performing data conversion processing on the network traffic data to obtain discrete parameters, wherein the discrete parameters are used to indicate the degree of network congestion at the corresponding device end;

[0017] The device load data is subjected to data conversion processing to obtain a quantization parameter, wherein the quantization parameter is used to indicate a task processing capability of a corresponding device end.

[0018] In one embodiment, adjusting the task amount of each device terminal according to the resource allocation strategy includes:

[0019] Determine a first target device end and a second target device end from the plurality of device ends, wherein the amount of resources of the first target device end is lower than a first preset threshold, the amount of resources of the second target device end is higher than a second preset threshold, and the first preset threshold is lower than the second preset threshold;

[0020] Evaluating the priority of each task in the first target device end;

[0021] Determining a target task according to the priority of each task in the first target device end;

[0022] Migrate the target task to the second target device end.

[0023] In one embodiment, the method further comprises:

[0024] Obtaining task execution results and resource usage results of each of the device ends;

[0025] Determining an evaluation result of a resource allocation strategy according to the task execution result and the resource usage result;

[0026] The resource allocation model is optimized according to the evaluation result.

[0027] In one of the embodiments, the resource allocation model is a load balancing resource allocation model or a priority-based resource allocation model.

[0028] In a second aspect, the present application provides a resource optimization scheduling device, which is applied to a computing platform, wherein the computing platform includes at least one device end; the device includes:

[0029] A first acquisition module, used to acquire real-time status data of each of the device terminals;

[0030] A first determination module, configured to determine a scenario analysis result of the computing platform according to each of the real-time status data and a preset scenario analysis model;

[0031] A second determination module is used to determine a resource allocation strategy according to the scenario analysis result and a preset resource allocation model;

[0032] The first adjustment module is used to adjust at least one of the task amount or resource amount of each device end according to the resource allocation strategy.

[0033] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the resource optimization scheduling method in any of the above embodiments when executing the computer program.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the resource optimization scheduling method in any of the above embodiments are implemented.

[0035] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the resource optimization scheduling method in any of the above embodiments.

[0036] The above-mentioned resource optimization scheduling method, device, computer equipment and readable storage medium, the resource optimization scheduling method is applied to a computing platform, the computing platform includes at least one device end, the device end is used to perform various tasks, first obtain the real-time status data of each device end, such as the network traffic of the device end, the length of the task queue, the computing resource utilization rate, etc., then, some analysis and processing can be performed on the obtained real-time status data of each device end, the processed data is input into the preset situation analysis model, and the situation analysis result of the computing platform is determined by the situation analysis model, and the situation analysis result can include the qualitative and quantitative description results of the current runtime situation. Afterwards, according to the situation analysis results, the optimal resource allocation strategy is determined by the preset resource allocation model, and the allocation instructions are issued to the relevant equipment in time to adjust at least one of the task amount or resource amount of each device end to ensure the timeliness of resource adjustment. Through the resource optimization scheduling method of the present application, it is possible to realize the dynamic perception of the task requirements and resource consumption of each device end, and adaptive task scheduling and resource allocation are performed according to the runtime situation, so as to improve the overall performance and resource utilization efficiency of the computing platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] FIG1 is a schematic diagram of a flow chart of a resource optimization scheduling method in one embodiment;

[0039] FIG2 is a schematic diagram of a flow chart of step S102 in one embodiment;

[0040] FIG3 is a schematic diagram of a flow chart of step S202 in one embodiment;

[0041] FIG4 is a schematic diagram of a flow chart of step S104 in one embodiment;

[0042] FIG5 is a schematic diagram of a flow chart of a resource optimization scheduling method in another embodiment;

[0043] FIG6 is a structural block diagram of a resource optimization scheduling device in one embodiment;

[0044] FIG. 7 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] As mentioned in the background technology section, with the rapid development of information technology, various complex systems continue to emerge, such as production management systems in smart factories and cloud computing platforms in large-scale data centers. These systems face the processing requirements of multiple types of tasks, and the task characteristics and resource requirements vary greatly. In intelligent transportation systems, traffic flow monitoring tasks require real-time processing of large amounts of data, which requires high computing resources and network bandwidth; while vehicle scheduling tasks focus more on real-time and reliability. When dealing with complex task scheduling and resource management, related technologies lack an effective dynamic adjustment mechanism and are difficult to meet the needs of efficient system operation.

[0047] Static task scheduling strategies and fixed resource allocation schemes are usually adopted in related technologies. For example, the task management system within traditional enterprises allocates tasks according to preset task priorities and fixed resource allocation rules, without fully considering the dynamic changes of factors such as task volume and resource status during system operation. When the type or number of tasks changes suddenly, it is difficult for the existing technology to quickly adjust the scheduling strategy, which may cause the task queue time to be too long or the key tasks to be unable to be processed in time. For example, during e-commerce promotion activities, the order processing tasks increase sharply, and the traditional scheduling system may not be able to allocate sufficient resources in time, causing order processing delays. And it is impossible to perceive the usage status and remaining situation of resources in real time, and it is impossible to make effective adjustments when resources are tight or idle. For example, in a distributed computing environment, some computing nodes may be in a high-load state due to uneven task allocation, while other nodes are idle, and the overall system resource utilization is low. It can be seen that when facing fluctuations in task requirements or tight resources, the related technology is prone to problems such as low task execution efficiency, lack of flexibility in task scheduling, inability to adapt to dynamic changes in task requirements, and unreasonable resource allocation, inability to optimize according to actual resource consumption, and waste of resources.

[0048] In a first aspect, the present application provides a resource optimization scheduling method. Referring to FIG1 , the resource optimization scheduling method includes steps S101 to S104.

[0049] S101: Acquire real-time status data of each device.

[0050] It can be understood that the computing platform includes at least one device end and one control end. Multiple sensors can be installed on each device end, such as CPU usage sensor, memory occupancy sensor, network flow sensor, etc., to monitor the operating status of each device end in real time and obtain the CPU usage, remaining memory, network flow and other data of each device end in real time. At the same time, each device end can also feed back the information of its own tasks to the control end in real time, so that the control end can understand the operating status of each device end in real time.

[0051] The sensor type and the data indicators collected can be adjusted according to the application scenario. For example, in a medical equipment monitoring system, a physiological signal sensor can be added to collect patient vital signs data as part of the contextual information to better schedule medical-related tasks.

[0052] S102: Determine the scenario analysis result of the computing platform according to the real-time status data and the preset scenario analysis model.

[0053] After receiving the real-time operation data from each device, the control end can perform preliminary processing such as data aggregation, cleaning, and removal of outliers and noise on these real-time operation data. Afterwards, the control end can input the processed data into a pre-built scenario analysis model. The scenario analysis model can analyze and process these processed data and combine them into a contextual description of the runtime scenario. For example, it can determine the current operating state of the computing platform by comprehensively considering parameters such as the degree of network congestion, device task processing capability, and remaining resources, and provide quantitative evaluation indicators, and finally output the qualitative and quantitative description results of the current runtime scenario, that is, the scenario analysis results of the computing platform.

[0054] S103: Determine a resource allocation strategy based on the scenario analysis results and a preset resource allocation model.

[0055] After obtaining the scenario analysis results, the optimal resource allocation strategy can be calculated by referring to the pre-set resource allocation model. For example, when the computing platform is under high load, more computing resources and network bandwidth are allocated to key tasks first; for devices with limited resources, some non-critical tasks are migrated to devices with abundant resources, and the allocation of storage resources on each device is reasonably adjusted. Finally, the resource allocation strategy is output to guide each device to adjust its resources.

[0056] S104: Adjust at least one of the task amount or resource amount of each device end according to the resource allocation strategy.

[0057] After receiving the resource allocation strategy, each device can adjust its own task volume or at least one of its resource volumes accordingly according to the resource allocation strategy, for example, transferring some non-critical tasks, giving priority to critical tasks, and allocating more computing resources and network bandwidth to critical tasks.

[0058] The above-mentioned resource optimization scheduling method, device, computer equipment and readable storage medium, the resource optimization scheduling method is applied to a computing platform, the computing platform includes at least one device end, the device end is used to perform various tasks, first obtain the real-time status data of each device end, such as the network traffic of the device end, the length of the task queue, the computing resource utilization rate, etc., then, some analysis and processing can be performed on the obtained real-time status data of each device end, the processed data is input into the preset situation analysis model, and the situation analysis result of the computing platform is determined by the situation analysis model, and the situation analysis result can include the qualitative and quantitative description results of the current runtime situation. Afterwards, according to the situation analysis results, the optimal resource allocation strategy is determined by the preset resource allocation model, and the allocation instructions are issued to the relevant equipment in time to adjust at least one of the task amount or resource amount of each device end to ensure the timeliness of resource adjustment. Through the resource optimization scheduling method of the present application, it is possible to realize the dynamic perception of the task requirements and resource consumption of each device end, and adaptive task scheduling and resource allocation are performed according to the runtime situation, so as to improve the overall performance and resource utilization efficiency of the computing platform.

[0059] In an exemplary embodiment, please refer to FIG. 2 , step S102 , determining the scenario analysis result of the computing platform according to each real-time status data and a preset scenario analysis model, including steps S201 to S203 .

[0060] S201: Preprocessing the real-time status data.

[0061] In one example, after receiving the real-time status data uploaded by each device, the control end may first clean the real-time status data to remove abnormal values ​​and noise and other pre-processing.

[0062] S202: Perform data conversion processing on the pre-processed real-time status data to obtain real-time situation parameters.

[0063] Afterwards, the preprocessed real-time status data can be converted into formatted real-time situational parameters that can be recognized and read by the situational analysis model. In an example, the real-time situational parameters may include network congestion level, device task processing capability, and remaining resources, etc.

[0064] S203: Input the real-time situation parameters into the situation analysis model to obtain the situation analysis results.

[0065] The scenario analysis model can determine the current operating status of the computing platform by analyzing parameters such as the degree of network congestion, device task processing capabilities, and remaining resources on each device side, and output scenario analysis results. The scenario analysis results may include qualitative results and quantitative results. In an example, qualitative results may include high-load production, low-load maintenance, and normal operation, and quantitative results may include indicators such as the load index and resource tension of the computing platform.

[0066] In an exemplary embodiment, the real-time status data includes device load data and network traffic data, and the real-time context data includes discrete parameters and quantized parameters. Please refer to FIG. 3 , step S202 , performing data conversion processing on the pre-processed real-time status data to obtain real-time context parameters, including step S301 and step S302 .

[0067] S301: Perform data conversion processing on network traffic data device load data to obtain discrete parameters, where the discrete parameters are used to indicate the degree of network congestion at the corresponding device end.

[0068] In one example, the real-time status data includes network traffic data, and the control end can convert the continuous network traffic data of each device end into a discrete parameter indicating the degree of network congestion of the corresponding device end. The higher the discrete parameter, the higher the degree of network congestion of the device end.

[0069] S302: Perform data conversion processing on the device load data to obtain a quantization parameter, where the quantization parameter is used to indicate the task processing capability of the corresponding device end.

[0070] Similarly, real-time status data includes device load data. The control end can quantify the device load data of each device end to obtain quantization parameters. The quantization parameters can be used to indicate the task processing capability of the corresponding device end. For example, the higher the quantization parameter of the device end, the busier the device end is.

[0071] In an exemplary embodiment, please refer to FIG. 4 , step S104 , adjusting the task amount of each device end according to the resource allocation strategy, including steps S401 to S404 .

[0072] S401: Determine a first target device end and a second target device end from a plurality of device ends.

[0073] In one example, the situational analysis results can not only indicate the operating state of the entire computing platform and provide quantitative evaluation indicators of the computing platform, but also indicate the operating state of each device end and provide quantitative evaluation indicators of each device end. If the computing platform as a whole is in normal operation or low-load maintenance state, and some device ends are in high-load production state, it is necessary to obtain the resource allocation strategy according to the preset resource allocation model. For example, the first target device end and the second target device end can be determined according to the amount of resources of each device end, wherein the amount of resources of the first target device end is lower than the first preset threshold, the amount of resources of the second target device end is higher than the second preset threshold, and the first preset threshold is less than the second preset threshold.

[0074] S402: Evaluate the priority of each task in the first target device.

[0075] It is understandable that there may be multiple tasks on a device at the same time, and the device needs to process these tasks. Therefore, the control end can assess the priorities of the multiple tasks of the first target device according to a preset algorithm.

[0076] S403: Determine the target task according to the priority of each task in the first target device end.

[0077] Afterwards, some tasks with lower priorities may be determined as target tasks in order of priority from low to high.

[0078] S404: Migrate the target task to the second target device.

[0079] By migrating the target task to the second target device end with sufficient resources, the first target device end can have more resources to prioritize tasks with higher priorities. In another example, after the target task is migrated to the second target device end, the control end can also allocate more resources to the first target device end to further ensure that the first target device end can have more resources to prioritize tasks with higher priorities.

[0080] In the application, the control end can also select appropriate task allocation, resource allocation and network management strategies from the preset strategy library according to the results of scenario analysis. For example, when the network is congested, a flow control strategy is adopted to reduce the data transmission of tasks with lower priority; when the task requirements change, the task allocation ratio is adjusted according to factors such as task priority and resource utilization. At the same time, the migration timing and target node of the task between each device end are determined according to factors such as task priority and resource utilization. Finally, the task scheduling instructions are output to control the execution process of the task.

[0081] In an exemplary embodiment, referring to FIG. 5 , the resource optimization scheduling method further includes steps S501 to S503 .

[0082] S501: Obtain task execution results and resource usage results of each device end.

[0083] After each device has adjusted the task volume and / or resource volume according to the resource allocation strategy, it can feed back the task execution results and resource usage results to the control end in real time. The task execution results may include information such as the task completion time and whether the task was successfully completed, and the resource usage results may include information such as the computing resources and network bandwidth actually consumed to execute the task.

[0084] S502: Determine the evaluation result of the resource allocation strategy according to the task execution result and the resource usage result.

[0085] The control end can evaluate the effectiveness of the current resource allocation strategy based on the received task execution results and resource usage results.

[0086] S503: Optimize the resource allocation model according to the evaluation results.

[0087] If the evaluation results indicate that the effectiveness of the current resource allocation strategy is low, such as the task execution efficiency is not up to expectations or the resource waste is serious, the control end can adjust the policy parameters in a timely manner (such as adjusting the task priority weight, resource allocation ratio, etc.). In the application, the situational analysis model can also be used for further evaluation. For example, if it is found that the execution efficiency of a task has not improved after migration, it may be that the second target device is not selected properly. At this time, the situational analysis model can be used to re-evaluate the status of each device and adjust the migration strategy. Ultimately, it ensures that the computing platform can continuously optimize its operation according to the actual situation.

[0088] In an exemplary embodiment, the resource allocation model is a load balancing resource allocation model or a priority-based resource allocation model. The situation analysis model is a rule-based classification model or a machine learning clustering model.

[0089] In summary, the resource optimization scheduling method of the present application can effectively solve the problem of lack of flexibility in task scheduling. By obtaining the real-time status data of each device end and combining the situational analysis model, the control end can grasp the changes in task requirements in real time. When the task volume suddenly increases or the task priority changes, the resource allocation strategy is adjusted quickly to give priority to key tasks and avoid task backlogs. For example, during the examination of the online education platform, a large number of answer data processing tasks are generated. The system can allocate more resources in time to ensure that the answer data is processed quickly, which improves the timeliness of task processing and the overall throughput of the system. The present application also realizes the reasonable allocation of resources. Based on the situational analysis results output by the situational analysis model, the control end accurately understands the resource consumption of each device end. When resources are tight, tasks are reasonably migrated to the device end with abundant resources to avoid idle and wasteful resources and improve resource utilization. For example, in a big data analysis platform, computing resources can be dynamically allocated between different cluster nodes according to task requirements to reduce hardware costs. In addition, this application also improves the reliability and stability of the system. Through the feedback and optimization mechanism of this application, the control end can promptly discover scheduling and resource allocation problems. When network fluctuations or node failures cause abnormal task execution, the control end can quickly adjust tasks and resources to avoid computing platform failures caused by local problems and ensure business continuity. For example, in a financial transaction system, when the network is abnormal, the task execution node can be quickly switched to ensure that transaction processing is not affected.

[0090] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0091] Based on the same inventive concept, the embodiment of the present application also provides a resource optimization scheduling device for implementing the resource optimization scheduling method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more resource optimization scheduling device embodiments provided below can refer to the limitations of the resource optimization scheduling method above, and will not be repeated here.

[0092] In an exemplary embodiment, as shown in Figure 6, the present application provides a resource optimization scheduling device, which is applied to a computing platform, and the computing platform includes at least one device end; the resource optimization scheduling device includes a first acquisition module 601, a first determination module 602, a second determination module 603 and a first adjustment module 604.

[0093] The first acquisition module 601 is used to acquire the real-time status data of each device end.

[0094] The first determination module 602 is used to determine the scenario analysis result of the computing platform according to various real-time status data and a preset scenario analysis model.

[0095] The second determination module 603 is used to determine a resource allocation strategy according to the scenario analysis result and a preset resource allocation model.

[0096] The first adjustment module 604 is used to adjust at least one of the task amount or resource amount of each device end according to the resource allocation strategy.

[0097] In an exemplary embodiment, the first determination module 602 includes: a first preprocessing submodule, a first conversion submodule and a first acquisition submodule.

[0098] The first preprocessing submodule is used to preprocess the real-time status data.

[0099] The first conversion submodule is used to perform data conversion processing on the preprocessed real-time status data to obtain real-time situation parameters.

[0100] The first acquisition submodule is used to input the real-time situation parameters into the situation analysis model to obtain the situation analysis results.

[0101] In an exemplary embodiment, the real-time status data includes device load data and network traffic data, and the real-time context data includes discrete parameters and quantized parameters. The first conversion submodule includes:

[0102] The first conversion unit is used to perform data conversion processing on the network traffic data to obtain discrete parameters, wherein the discrete parameters are used to indicate the degree of network congestion at the corresponding device end;

[0103] The second conversion unit is used to perform data conversion processing on the device load data to obtain a quantization parameter, wherein the quantization parameter is used to indicate the task processing capability of the corresponding device end.

[0104] In an exemplary embodiment, the first adjustment module includes a first determination submodule, a first evaluation submodule, a first assessment submodule, and a first migration submodule.

[0105] The first determination submodule is used to determine a first target device end and a second target device end from multiple device ends, wherein the amount of resources of the first target device end is lower than a first preset threshold, the amount of resources of the second target device end is higher than a second preset threshold, and the first preset threshold is lower than the second preset threshold.

[0106] The first evaluation submodule is used to evaluate the priority of each task in the first target device end.

[0107] The second determination submodule is used to determine the target task according to the priority of each task in the first target device end.

[0108] The first migration submodule is used to migrate the target task to the second target device end.

[0109] In an exemplary embodiment, the resource optimization scheduling device further includes a second acquisition module, a third determination module and a first optimization module.

[0110] The second acquisition module is used to obtain the task execution results and resource usage results of each device end.

[0111] The third determination module is used to determine the evaluation result of the resource allocation strategy according to the task execution result and the resource usage result.

[0112] The first optimization module is used to optimize the resource allocation model according to the evaluation result.

[0113] In an exemplary embodiment, the resource allocation model is a load balancing resource allocation model or a priority-based resource allocation model.

[0114] Each module in the above-mentioned resource optimization scheduling device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0115] In an exemplary embodiment, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the resource optimization scheduling method in any of the above embodiments when executing the computer program.

[0116] A computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG7. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store real-time status data of each device end. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a resource optimization scheduling method is implemented.

[0117] Those skilled in the art will understand that the structure shown in FIG. 7 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0118] In an exemplary embodiment, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the resource optimization scheduling method in any of the above embodiments are implemented.

[0119] In one embodiment, the present application provides a computer program product, including a computer program, which implements the steps of the resource optimization scheduling method in any of the above embodiments when executed by a processor.

[0120] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0121] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0122] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0123] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A resource optimization scheduling method, characterized in that: Applied to a computing platform, the computing platform includes at least one device end; the method includes: Acquire real-time status data of each of the devices; Determining a scenario analysis result of the computing platform according to each of the real-time status data and a preset scenario analysis model; Determine a resource allocation strategy based on the scenario analysis results and a preset resource allocation model; According to the resource allocation strategy, at least one of the task amount or resource amount of each of the device ends is adjusted.

2. The method according to claim 1, characterized in that: Determining the scenario analysis result of the computing platform according to each of the real-time status data and the preset scenario analysis model includes: Preprocessing the real-time status data; Performing data conversion processing on the preprocessed real-time status data to obtain real-time situation parameters; The real-time situation parameters are input into the situation analysis model to obtain the situation analysis result.

3. The method according to claim 2, characterized in that The real-time status data includes equipment load data and network traffic data, and the real-time situation data includes discrete parameters and quantized parameters; The performing data conversion processing on the pre-processed real-time status data to obtain real-time situation parameters includes: Performing data conversion processing on the network traffic data to obtain discrete parameters, wherein the discrete parameters are used to indicate the degree of network congestion at the corresponding device end; The device load data is subjected to data conversion processing to obtain a quantization parameter, wherein the quantization parameter is used to indicate a task processing capability of a corresponding device end.

4. The method according to claim 1, characterized in that: According to the resource allocation strategy, the task amount of each device is adjusted, including: Determine a first target device end and a second target device end from the plurality of device ends, wherein the amount of resources of the first target device end is lower than a first preset threshold, the amount of resources of the second target device end is higher than a second preset threshold, and the first preset threshold is lower than the second preset threshold; Evaluating the priority of each task in the first target device end; Determining a target task according to the priority of each task in the first target device end; Migrate the target task to the second target device end.

5. The method according to claim 1, characterized in that The method further comprises: Obtaining task execution results and resource usage results of each of the device ends; Determining an evaluation result of a resource allocation strategy according to the task execution result and the resource usage result; The resource allocation model is optimized according to the evaluation result.

6. The method according to claim 1, characterized in that The resource allocation model is a load balancing resource allocation model or a priority-based resource allocation model.

7. A resource optimization scheduling device, characterized in that: Applied to a computing platform, the computing platform includes at least one device end; the device includes: A first acquisition module, used to acquire real-time status data of each of the device terminals; A first determination module, configured to determine a scenario analysis result of the computing platform according to each of the real-time status data and a preset scenario analysis model; A second determination module is used to determine a resource allocation strategy according to the scenario analysis result and a preset resource allocation model; The first adjustment module is used to adjust at least one of the task amount or resource amount of each device end according to the resource allocation strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images