An intelligent scheduling method and system for optimizing distributed computing power scheduling strategies

Abstract

The present invention discloses an intelligent scheduling method and system for optimizing distributed computing power scheduling strategies, which relates to the technical field of intelligent scheduling. The method includes the following steps: self-checking of distributed computing power nodes; first evaluation and analysis of the distributed computing power of distributed computing power nodes; first intelligent scheduling according to the first comparison and analysis results; second evaluation and analysis of the distributed computing power of distributed computing power nodes; second intelligent scheduling according to the second comparison and analysis results; third evaluation and analysis of the distributed computing power of distributed computing power nodes; third intelligent scheduling according to the third comparison and analysis results. The present invention achieves the effect of improving the accuracy of distributed computing power resource scheduling through self-checking, first evaluation and analysis, second evaluation and analysis, and third evaluation and analysis, and respectively corresponding hierarchical optimization scheduling, and solves the problem of insufficient accuracy of distributed computing power resource scheduling corresponding to distributed power resources in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent scheduling, and particularly to an intelligent scheduling method and system for optimizing distributed computing power scheduling strategies. Background Art

[0002] With the booming development of the digital economy, data has become the new core production material, and computing power has become the key productive force. The construction of the new generation of information infrastructure, such as artificial intelligence, industrial Internet, and Internet of Things, has led to a sharp increase in the demand for computing power resources. At the same time, the rise of generative artificial intelligence and the need for big data processing have promoted the development of distributed computing power systems. These technologies require efficient computing power support to ensure the efficient operation of algorithms.

[0003] Existing intelligent scheduling methods for optimizing distributed computing power scheduling strategies are achieved through the following technologies, including: a multi-level computing power network system framework, which proposes a multi-level computing power network system framework to address challenges such as wide distribution heterogeneity, strong uncertainty, and high constraint complexity; a computing power network resource collaborative scheduling platform, which forms a computing power resource scheduling strategy between multiple public clouds and private clouds to achieve automatic optimal allocation of resources; cloud-edge-end collaborative scheduling technology, which integrates cloud-edge-end multi-level ubiquitous computing network resources through a computing power network; and cloud-native ubiquitous computing power scheduling technology. With the progress of cloud computing technology, cloud-native ubiquitous computing power scheduling technology has become the key to enterprises' cloud adoption to reduce costs and increase efficiency.

[0004] For example, the intelligent scheduling method based on a distributed architecture disclosed in the invention patent with the publication number CN117032968A includes: evaluating and analyzing the scale complexity degree of the distributed architecture system and the load status of each computing node, and expanding or reducing computing nodes through intelligent decision-making to achieve elastic expansion and structural optimization of the distributed architecture system. By real-time monitoring the load conditions of each computing node, and thereby intelligently matching the main path and multiple alternative paths for task processing, tasks or resources are allocated to different computing nodes to make full use of the computing power and storage resource capabilities of each node.

[0005] For example, an intelligent optimization method and system for computing power scheduling to improve power supply reliability disclosed in the invention patent announcement with the publication number CN117453398B includes: obtaining the distributed configuration data of the cloud computing system, performing digital twin modeling to obtain a cloud computing twin model, deploying intelligent sensors to collect operation data, obtaining device operation data, including historical operation data and real-time operation data, performing model update, performing power failure prediction to obtain power failure prediction results, obtaining optimization objectives, performing computing resource allocation, generating a resource allocation plan, allocating computing nodes to each data center, generating a computing power allocation plan, and performing computing power scheduling of the cloud computing system.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of the present application, it is found that the above technologies have at least the following technical problems:

[0007] In the prior art, for the intelligent scheduling method for optimizing the distributed computing power scheduling strategy of distributed power resources, considering numerous factors in a specific environment, there is a problem of large volatility in the distributed power resources themselves. The corresponding distributed computing power nodes cannot be simply scheduled according to a single factor, resulting in insufficient accuracy in scheduling the distributed computing power resources corresponding to the distributed power resources. Summary of the Invention

[0008] The embodiments of the present application provide an intelligent scheduling method and system for optimizing the distributed computing power scheduling strategy, which solve the problem of insufficient accuracy in scheduling the distributed computing power resources corresponding to the distributed power resources in the prior art, and achieve the effect of improving the accuracy of distributed computing power resource scheduling.

[0009] The embodiments of the present application provide an intelligent scheduling method for optimizing the distributed computing power scheduling strategy, including the following steps: self-checking of the distributed computing power node, and performing self-check adjustment of the distributed computing power according to the self-check of the distributed computing power node;

[0010] Performing a first evaluation and analysis on the distributed computing power of the distributed computing power node to obtain an evaluation value of the schedulable resources of the distributed computing power node; performing a first comparison and analysis on the evaluation value of the schedulable resources of the distributed computing power node with the corresponding threshold, and performing a first intelligent scheduling according to the result of the first comparison and analysis; performing a second evaluation and analysis on the distributed computing power of the distributed computing power node to obtain a risk evaluation value of the scheduled computing power resources of the distributed computing power node; performing a second comparison and analysis on the risk evaluation value of the scheduled computing power resources of the distributed computing power node with the corresponding threshold, and performing a second intelligent scheduling according to the result of the second comparison and analysis; performing a third evaluation and analysis on the distributed computing power of the distributed computing power node to obtain a comprehensive evaluation value of the scheduled computing power resources of the distributed computing power node; performing a third comparison and analysis on the comprehensive evaluation value of the scheduled computing power resources of the distributed computing power node with the corresponding threshold, and performing a third intelligent scheduling according to the result of the third comparison and analysis.

[0011] Further, the specific process of performing self-check adjustment of the distributed computing power according to the self-check of the distributed computing power node is as follows: the distributed computing power node performs a predefined self-checking scheme at a predefined self-checking time interval, and the predefined self-checking scheme is used for self-checking the computing power resources of the distributed computing power node to obtain self-checking parameters of the distributed computing power node; if the self-checking parameters of the distributed computing power node are greater than or equal to the self-checking parameter threshold of the distributed computing power node, the corresponding distributed computing power node is recorded as a faulty node, and the faulty node is notified to relevant personnel; if the self-checking parameters of the distributed computing power node are less than the self-checking parameter threshold of the distributed computing power node, the corresponding distributed computing power node is recorded as a faulty node to be detected and evaluated.

[0012] Further, the specific process of obtaining the schedulable resource evaluation value of the distributed computing power node is as follows: the number of available CPU cores, the available operating frequency of the CPU, and the available capacity of the CPU operating memory are collected through the CPU information query tool of the server of the distributed computing power node; the average CPU operating failure rate and the average CPU operating recovery time are collected through the failure log monitoring tool of the server of the distributed computing power node; the predefined number of CPU cores, the predefined operating frequency of the CPU, the predefined available capacity of the CPU operating memory, the predefined standard value of the CPU operating failure rate, and the predefined average CPU operating recovery time are extracted from the factory log of the server of the distributed computing power node; the weight factors of the average CPU operating failure rate for the schedulable resource evaluation value of the distributed computing power node, the weight factor of the average CPU operating recovery time for the schedulable resource evaluation value of the distributed computing power node, the weight factor of the number of available CPU cores for the schedulable resource evaluation value of the distributed computing power node, the weight factor of the available operating frequency of the CPU for the schedulable resource evaluation value of the distributed computing power node, and the weight factor of the available capacity of the CPU operating memory for the schedulable resource evaluation value of the distributed computing power node are obtained through the preset mapping relationship in the distributed computing power central database; thereby obtaining the schedulable resource evaluation value of the distributed computing power node of the distributed computing power node.

[0013] Further, the first intelligent scheduling according to the first comparative analysis result specifically includes: if the schedulable resource evaluation value of the distributed computing power node is less than or equal to the schedulable resource evaluation value of the distributed computing power node, the distributed computing power node is recorded as a non - callable distributed resource computing power node, and a node failure recovery plan is enabled for the non - callable distributed resource computing power node; the non - callable distributed resource computing power node is used to describe the distributed computing power node in the non - callable distributed computing power resources when the distributed computing power central database calls the distributed computing power resources; if the schedulable resource evaluation value of the distributed computing power node is greater than the schedulable resource evaluation value of the distributed computing power node, the distributed computing power node is recorded as a callable distributed resource computing power node; the callable distributed resource computing power node is used to describe the distributed computing power node in the callable distributed computing power resources when the distributed computing power central database calls the distributed computing power resources.

[0014] Further, the specific process of obtaining the risk assessment value of the distributed computing power node's scheduling of computing power resources is as follows: directly obtain the power task volume of the distributed computing power node and the renewable energy task volume of the distributed computing power node through the computing task scheduling tool of the distributed computing power node; directly extract from the distributed computing power central database the corrected factor of the distributed computing power demand prediction, the corrected factor of the light intensity for the renewable energy task volume of the distributed computing power node, the average historical power task volume of the distributed computing power node, and the average historical renewable energy task volume of the distributed computing power node; and thus analyze to obtain the risk assessment value of the distributed computing power node's scheduling of computing power resources for the callable distributed resource computing power node.

[0015] Further, the second intelligent scheduling according to the second comparative analysis result specifically includes: if the risk assessment value of the distributed computing power node's scheduling of computing power resources for the callable distributed resource computing power node is greater than or equal to the risk assessment threshold of the distributed computing power node's scheduling of computing power resources, then mark the corresponding callable distributed resource computing power node as a non-callable distributed resource computing power node, and add a distributed resource computing power node to the power resource area corresponding to the non-callable distributed resource computing power node; if the risk assessment value of the distributed computing power node's scheduling of computing power resources for the callable distributed resource computing power node is less than the risk assessment threshold of the distributed computing power node's scheduling of computing power resources, then mark the corresponding callable distributed resource computing power node as a first-level callable distributed resource computing power node.

[0016] Further, the specific process of obtaining the comprehensive evaluation value of the distributed computing power node's scheduling of computing power resources call includes: conduct the first evaluation analysis and the second evaluation analysis on the first-level callable distributed resource computing power node to obtain the evaluation value of the callable resources of the distributed computing power node of the first-level callable distributed resource computing power node and the risk assessment value of the distributed computing power node's scheduling of computing power resources of the first-level callable distributed resource computing power node; collect the network latency of the distributed computing power node through the network monitoring device; collect the server operating temperature and the server environment temperature through the server temperature monitoring device; and thus analyze to obtain the comprehensive evaluation value of the distributed computing power node's scheduling of computing power resources call for the first-level callable distributed resource computing power node.

[0017] Further, the third intelligent scheduling based on the third comparative analysis result specifically includes: if the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the first-level callable distributed resource computing power node is greater than or equal to the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, the first-level callable distributed resource computing power node is included in the list of callable distributed resource computing power nodes, and the computing power resources of the distributed resource computing power nodes in the list of callable distributed resource computing power nodes are scheduled according to the predefined node resource scheduling scheme; if the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the first-level callable distributed resource computing power node is less than the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, the first-level callable distributed resource computing power node is recorded as a second-level callable distributed resource computing power node, and virtualization technology, data compression technology and upgraded hardware capacity are used for the node server corresponding to the second-level callable distributed resource computing power node.

[0018] Further, the third intelligent scheduling based on the third comparative analysis result further includes: after the predefined intelligent scheduling distributed computing power detection time, a third evaluation and analysis is performed on the second-level callable distributed resource computing power node to obtain the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the second-level callable distributed resource computing power node; if the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the second-level callable distributed resource computing power node is greater than or equal to the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, no adjustment is made; if the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the second-level callable distributed resource computing power node is less than the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, relevant personnel are notified to add distributed computing power nodes in the corresponding area.

[0019] In this embodiment, if after the predefined intelligent scheduling distributed computing power detection time, the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the second-level callable distributed resource computing power node is less than the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, it indicates that the computing power resources in this area are generally insufficient, and relevant personnel need to be notified to add more nodes to the distributed system to disperse the load and improve the overall computing power.

[0020] An intelligent scheduling system for optimizing distributed computing power scheduling strategies provided by an embodiment of the present application includes a distributed computing power node self-checking module, a first evaluation and analysis module for distributed computing power, a first intelligent scheduling module for distributed computing power, a second evaluation and analysis module for distributed computing power, a second intelligent scheduling module for distributed computing power, a third evaluation and analysis module for distributed computing power, and a third intelligent scheduling module for distributed computing power: The distributed computing power node self-checking module is used for self-checking distributed computing power nodes and performing self-checking adjustment of distributed computing power according to the self-checking of distributed computing power nodes; The first evaluation and analysis module for distributed computing power is used for performing a first evaluation and analysis on the distributed computing power of distributed computing power nodes to obtain an evaluation value of schedulable resources of distributed computing power nodes; The first intelligent scheduling module for distributed computing power is used for performing a first comparative analysis on the evaluation value of schedulable resources of distributed computing power nodes with a corresponding threshold value and performing first intelligent scheduling according to the result of the first comparative analysis; The second evaluation and analysis module for distributed computing power is used for performing a second evaluation and analysis on the distributed computing power of distributed computing power nodes to obtain a risk evaluation value of scheduling computing power resources of distributed computing power nodes; The second intelligent scheduling module for distributed computing power is used for performing a second comparative analysis on the risk evaluation value of scheduling computing power resources of distributed computing power nodes with a corresponding threshold value and performing second intelligent scheduling according to the result of the second comparative analysis; The third evaluation and analysis module for distributed computing power is used for performing a third evaluation and analysis on the distributed computing power of distributed computing power nodes to obtain a comprehensive evaluation value of the invocation of scheduling computing power resources of distributed computing power nodes; The third intelligent scheduling module for distributed computing power is used for performing a third comparative analysis on the comprehensive evaluation value of the invocation of scheduling computing power resources of distributed computing power nodes with a corresponding threshold value and performing third intelligent scheduling according to the result of the third comparative analysis.

[0021] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0022] 1. Perform a first evaluation and analysis on the distributed computing power of distributed computing power nodes; perform first intelligent scheduling according to the result of the first comparative analysis; perform a second evaluation and analysis on the distributed computing power of distributed computing power nodes; perform second intelligent scheduling according to the result of the second comparative analysis; perform a third evaluation and analysis on the distributed computing power of distributed computing power nodes; perform third intelligent scheduling according to the result of the third comparative analysis, so as to realize the optimized scheduling of the computing power resources of distributed nodes at different levels, and further achieve the effect of improving the accuracy of distributed computing power resource scheduling, and solve the problem of insufficient accuracy of distributed computing power resource scheduling corresponding to distributed power resources in the prior art.

[0023] 2. Perform a second comparative analysis on the risk assessment value of the distributed computing power node's scheduled computing power resources and the corresponding threshold, and perform a second intelligent scheduling based on the results of the second comparative analysis. By identifying non-callable distributed resource computing power nodes and adding distributed resource computing power nodes, the utilization rate of the overall computing power resources is improved. By adding distributed resource computing power nodes, the redundancy of the system is increased, and thus the reliability of the distributed computing power scheduling method is improved.

[0024] 3. Perform a third comparative analysis on the comprehensive evaluation value of the distributed computing power node's scheduled computing power resources and the corresponding threshold, and perform a third intelligent scheduling based on the results of the third comparative analysis. Dynamically manage the distributed resource computing power nodes, adjust the resource allocation according to actual needs, identify potential risk points, and take corresponding measures, thereby improving the security of the distributed computing power scheduling method.

[0025] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of an intelligent scheduling method for optimizing a distributed computing power scheduling strategy provided by an embodiment of the present application;

[0027] Figure 2 It is a schematic structural diagram of an intelligent scheduling system for optimizing a distributed computing power scheduling strategy provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] By providing an intelligent scheduling method and system for optimizing a distributed computing power scheduling strategy, the embodiments of the present application solve the problem of insufficient accuracy in scheduling the distributed computing power resources corresponding to distributed power resources in the prior art. Through self-checking, first evaluation analysis, second evaluation analysis, and third evaluation analysis, and corresponding hierarchical optimization scheduling respectively, the effect of improving the accuracy of distributed computing power resource scheduling is achieved.

[0029] To better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0030] As Figure 1As shown in the figure, it is a flowchart of an intelligent scheduling method for distributed computing power scheduling strategy optimization provided by an embodiment of the present application. This method is applied to an intelligent scheduling system for distributed computing power scheduling strategy optimization. The method includes the following steps: self-check of distributed computing power nodes, and distributed computing power self-check adjustment according to the self-check of distributed computing power nodes; first evaluation and analysis of the distributed computing power of distributed computing power nodes to obtain the evaluated value of schedulable resources of distributed computing power nodes; first comparison and analysis of the evaluated value of schedulable resources of distributed computing power nodes with the corresponding threshold, and first intelligent scheduling according to the result of the first comparison and analysis; second evaluation and analysis of the distributed computing power of distributed computing power nodes to obtain the risk evaluation value of scheduling computing power resources of distributed computing power nodes; second comparison and analysis of the risk evaluation value of scheduling computing power resources of distributed computing power nodes with the corresponding threshold, and second intelligent scheduling according to the result of the second comparison and analysis; third evaluation and analysis of the distributed computing power of distributed computing power nodes to obtain the comprehensive evaluation value of scheduling and calling computing power resources of distributed computing power nodes; third comparison and analysis of the comprehensive evaluation value of scheduling and calling computing power resources of distributed computing power nodes with the corresponding threshold, and third intelligent scheduling according to the result of the third comparison and analysis.

[0031] Further, the specific process of distributed computing power self-check adjustment according to the self-check of distributed computing power nodes is as follows: the distributed computing power node performs a predefined self-check scheme every predefined self-check time. The predefined self-check scheme is used for the self-check of the computing power resources of the distributed computing power node to obtain the self-check parameters of the distributed computing power node; if the self-check parameters of the distributed computing power node are greater than or equal to the self-check parameter threshold of the distributed computing power node, the corresponding distributed computing power node is recorded as a faulty node, and the faulty node is notified to relevant personnel; if the self-check parameters of the distributed computing power node are less than the self-check parameter threshold of the distributed computing power node, the corresponding distributed computing power node is recorded as a faulty node to be detected and evaluated.

[0032] In this embodiment, the predefined self-check scheme is collected and stored locally on the node or sent to the central computing power scheduling center. The self-check parameter threshold is directly extracted from the distributed computing power central database. The predefined self-check scheme of the distributed computing power node can be automatically triggered every predefined self-check time, or manually triggered after a specific event (such as system startup, configuration change, fault recovery, etc.); the node executes the self-check program to collect hardware status information. The self-check parameters include CPU temperature, memory usage rate, hard disk usage duration, software version information, system configuration information, and network connection status.

[0033] Further, the specific process of obtaining the schedulable resource evaluation value of the distributed computing power node is as follows: The number of available CPU cores, the available operating frequency of the CPU, and the available capacity of the CPU operating memory are collected through the CPU information query tool of the server of the distributed computing power node; the average CPU operating failure rate and the average CPU operating recovery time are collected through the failure log monitoring tool of the server of the distributed computing power node; the predefined number of CPU cores, the predefined operating frequency of the CPU, the predefined available capacity of the CPU operating memory, the predefined standard value of the CPU operating failure rate, and the predefined average CPU operating recovery time are extracted from the factory log of the server of the distributed computing power node; the weight factors of the average CPU operating failure rate for the schedulable resource evaluation value of the distributed computing power node, the weight factor of the average CPU operating recovery time for the schedulable resource evaluation value of the distributed computing power node, the weight factor of the number of available CPU cores for the schedulable resource evaluation value of the distributed computing power node, the weight factor of the available operating frequency of the CPU for the schedulable resource evaluation value of the distributed computing power node, and the weight factor of the available capacity of the CPU operating memory for the schedulable resource evaluation value of the distributed computing power node are obtained through the preset mapping relationship in the distributed computing power central database; thus, the schedulable resource evaluation value of the distributed computing power node is obtained.

[0034] In this embodiment, the CPU information query tools include, for example, lscpu, cat, proc, and pu info. The failure log monitoring tools include, for example, Nagios and Zabbix.

[0035] The distributed computing power nodes of the distributed computing power scheduling system are numbered. JD0 represents the number of a distributed computing power node, and JD represents the total number of distributed computing power nodes.

[0036] The distributed computing power node detection time is divided into different distributed computing power node detection time periods according to the size of the predefined computing power node detection time window. The distributed computing power node detection time periods are numbered. JC0 represents the number of a distributed computing power node detection time period, and JC represents the total number of distributed computing power node detection time periods.

[0037] The schedulable resource evaluation value of the distributed computing power node is used to describe the relative basic level of the software computing power resources that can be called by the distributed computing power node.

[0038] represents the schedulable resource evaluation value of the JC0th distributed computing power node detection time period of the JD0th distributed computing power node.

[0039]

[0040] Indicates the number of CPU callable cores during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0041] Indicates the predefined number of CPU cores during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0042] Indicates the callable operating frequency of the CPU during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0043] Indicates the predefined operating frequency of the CPU during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0044] Indicates the callable capacity of the CPU operating memory during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0045] Indicates the predefined callable capacity of the CPU operating memory during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0046] Indicates the average failure rate of the CPU operation of the JD0th distributed computing power node.

[0047] Indicates the predefined failure rate standard value of the CPU operation of the JD0th distributed computing power node. Indicates the average recovery time of the CPU operation of the JD0th distributed computing power node.

[0048] Indicates the predefined average recovery time of the CPU operation of the JD0th distributed computing power node.

[0049] σ 1 Indicates the weight factor of the number of CPU callable cores for the evaluation value of the schedulable resources of the distributed computing power node.

[0050] σ 2 Indicates the weight factor of the callable operating frequency of the CPU for the evaluation value of the schedulable resources of the distributed computing power node.

[0051] σ 3 Indicates the weight factor of the callable capacity of the CPU operating memory for the evaluation value of the schedulable resources of the distributed computing power node.

[0052] The weight factors of the number of callable CPU cores for the evaluation value of the schedulable resources of distributed computing power nodes, the weight factors of the callable operating frequency of the CPU for the evaluation value of the schedulable resources of distributed computing power nodes, and the weight factors of the callable capacity of the CPU operating memory for the evaluation value of the schedulable resources of distributed computing power nodes respectively represent the numerical values of the influence degrees of the number of callable CPU cores, the callable operating frequency of the CPU, and the callable capacity of the CPU operating memory on the evaluation value of the schedulable resources of distributed computing power nodes.

[0053] The weight factors of the number of callable CPU cores for the evaluation value of the schedulable resources of distributed computing power nodes, the weight factors of the callable operating frequency of the CPU for the evaluation value of the schedulable resources of distributed computing power nodes, and the weight factors of the callable capacity of the CPU operating memory for the evaluation value of the schedulable resources of distributed computing power nodes can be directly obtained from the central database of distributed computing power through a pre-set mapping relationship. For example, construct a mapping set of the CPU utilization rate of real-time distributed computing power nodes and the corresponding weight factors of the number of callable CPU cores for the evaluation value of the schedulable resources of distributed computing power nodes, the weight factors of the callable operating frequency of the CPU for the evaluation value of the schedulable resources of distributed computing power nodes, and the weight factors of the callable capacity of the CPU operating memory for the evaluation value of the schedulable resources of distributed computing power nodes, and input the CPU utilization rate of real-time distributed computing power nodes into the mapping set to obtain the weight factors of the number of callable CPU cores for the evaluation value of the schedulable resources of distributed computing power nodes, the weight factors of the callable operating frequency of the CPU for the evaluation value of the schedulable resources of distributed computing power nodes, and the weight factors of the callable capacity of the CPU operating memory for the evaluation value of the schedulable resources of distributed computing power nodes, where the mapping relationship can be one-to-one or many-to-one.

[0054] ψ 1 Represents the weight factor of the average CPU operating failure rate for the evaluation value of the schedulable resources of distributed computing power nodes.

[0055] ψ 2 Represents the weight factor of the average CPU operating recovery time for the evaluation value of the schedulable resources of distributed computing power nodes.

[0056] The weight factor of the average CPU operating failure rate for the evaluation value of the schedulable resources of distributed computing power nodes and the weight factor of the average CPU operating recovery time for the evaluation value of the schedulable resources of distributed computing power nodes respectively represent the numerical values of the influence degrees of the average CPU operating failure rate and the average CPU operating recovery time on the evaluation value of the schedulable resources of distributed computing power nodes.

[0057] The weight factor of the average CPU operation failure rate for the evaluation value of the schedulable resources of the distributed computing power nodes and the weight factor of the average CPU operation recovery time for the evaluation value of the schedulable resources of the distributed computing power nodes can be directly obtained from the distributed computing power central database through a pre-set mapping relationship. For example, a real-time mapping set of the computing power resource call frequency of the distributed computing power nodes and the corresponding weight factors of the average CPU operation failure rate for the evaluation value of the schedulable resources of the distributed computing power nodes and the weight factors of the average CPU operation recovery time for the evaluation value of the schedulable resources of the distributed computing power nodes is constructed, and the real-time computing power resource call frequency of the distributed computing power nodes is input into the mapping set to obtain the weight factor of the average CPU operation failure rate for the evaluation value of the schedulable resources of the distributed computing power nodes and the weight factor of the average CPU operation recovery time for the evaluation value of the schedulable resources of the distributed computing power nodes, where the mapping relationship can be one-to-one or many-to-one.

[0058] Furthermore, a first intelligent scheduling is performed according to the first comparative analysis result, which specifically includes: if the evaluation value of the schedulable resources of the distributed computing power node is less than or equal to the evaluation value of the schedulable resources of the distributed computing power node, the distributed computing power node is recorded as a non-callable distributed resource computing power node, and a node failure recovery scheme is enabled for the non-callable distributed resource computing power node; the non-callable distributed resource computing power node is used to describe the distributed computing power node in the non-callable distributed computing power resources when the distributed computing power central database calls the distributed computing power resources; if the evaluation value of the schedulable resources of the distributed computing power node is greater than the evaluation value of the schedulable resources of the distributed computing power node, the distributed computing power node is recorded as a callable distributed resource computing power node; the callable distributed resource computing power node is used to describe the distributed computing power node in the callable distributed computing power resources when the distributed computing power central database calls the distributed computing power resources.

[0059] In this embodiment, the node failure recovery scheme, such as automatic restart and failover, can improve the availability and stability of the distributed computing power nodes.

[0060] Automatic restart: If the evaluation value of the schedulable resources of the distributed computing power node is less than or equal to the evaluation value of the schedulable resources of the distributed computing power node, it may be due to hardware failure or other problems. Set the judgment condition for automatic restart. For example, if the evaluation value of the schedulable resources of the distributed computing power node is less than or equal to the evaluation value of the schedulable resources of the distributed computing power node and the CPU utilization rate is less than the predefined CPU utilization rate threshold, then the distributed computing power node performs an automatic restart;

[0061] Fault transfer: If the evaluated value of the schedulable resources of a distributed computing power node is less than or equal to the evaluated value of the schedulable resources of the distributed computing power node, it may be due to hardware failures or other problems. The intelligent scheduling system will trigger the fault transfer mechanism to transfer the affected tasks to other nodes to ensure the continuity of tasks and the stability of the system.

[0062] If the evaluated value of the schedulable resources of a distributed computing power node is less than or equal to the evaluated value of the schedulable resources of the distributed computing power node, it indicates that the resources of this node are already relatively tight and there is no computing power margin for unified resource invocation of computing power.

[0063] Furthermore, the specific process of obtaining the risk assessment value of the scheduled computing power resources of the distributed computing power node is as follows: directly obtain the power task volume of the distributed computing power node and the renewable energy task volume of the distributed computing power node through the computing task scheduling tool of the distributed computing power node; directly extract the corrected factor of the power demand prediction of the distributed computing power, the corrected factor of the light intensity for the renewable energy task volume of the distributed computing power node, the average historical power task volume of the distributed computing power node, and the average historical renewable energy task volume of the distributed computing power node from the distributed computing central database; thus, analyze and obtain the risk assessment value of the scheduled computing power resources of the distributed resource computing power node that can be invoked.

[0064] In this embodiment, the risk assessment value of the scheduled computing power resources of the distributed computing power node is used to describe the relative risk level of the software computing power resources invoked by the distributed computing power node.

[0065] represents the risk assessment value of the scheduled computing power resources of the distributed computing power node in the JC0th detection time period of the JD0th distributed computing power node.

[0066]

[0067] e represents the natural constant;

[0068] represents the power task volume of the distributed computing power node in the JC0th detection time period of the JD0th distributed computing power node.

[0069] represents the average historical power task volume of the JD0th distributed computing power node.

[0070] The power task volume of the distributed computing power node. The power task volume refers to the number of computing tasks that need to be processed in the power system. The change in the task volume will affect the demand for computing power resources and thus affect the scheduling strategy.

[0071] Represents the maximum value of the distributed computing power node's renewable energy task volume during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0072] Represents the minimum value of the distributed computing power node's renewable energy task volume during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0073] Represents the average value of the distributed computing power node's historical renewable energy tasks of the JD0th distributed computing power node.

[0074] The renewable energy task volume, for example, the output of photovoltaic and wind power is affected by environmental factors and has large fluctuations. The volatility of this power resource will further affect the stability of the distributed node computing power resource invocation.

[0075] Represents the correction factor for the distributed computing power electricity demand prediction during the JC0th distributed computing power node detection period of the JD0th distributed computing power node, with a value range of (1, 2);

[0076] The distributed computing power electricity demand prediction correction factor represents the numerical value of the influence degree of the increased power task volume due to the electricity demand prediction fluctuation on the risk assessment value of the distributed computing power node's scheduling of computing power resources.

[0077] The increased power task volume due to the electricity demand prediction fluctuation can be directly extracted from the distributed computing power central database.

[0078] The distributed computing power electricity demand prediction correction factor can be directly obtained from the distributed computing power central database through a pre-set mapping relationship. For example, construct a mapping set of the increased power task volume due to the real-time electricity demand prediction fluctuation and its corresponding distributed computing power electricity demand prediction correction factor, and input the real-time increased power task volume due to the electricity demand prediction fluctuation into the mapping set to obtain the distributed computing power electricity demand prediction correction factor, where the mapping relationship can be one-to-one or many-to-one.

[0079] Represents the correction factor of the light intensity during the JC0th distributed computing power node detection period of the JD0th distributed computing power node for the distributed computing power node's renewable energy task volume, with a value range of (0, 2);

[0080] The correction factor of the light intensity for the distributed computing power node's renewable energy task volume represents the numerical value of the influence degree of the light intensity on the distributed computing power node's renewable energy task volume.

[0081] The light intensity is directly collected and extracted from the light intensity measuring instrument.

[0082] The correction factor of light intensity for the renewable energy task volume of distributed computing power nodes can be directly obtained from the central database of distributed computing power through a pre-set mapping relationship. For example, a real-time mapping set of light intensity and its corresponding correction factor of light intensity for the renewable energy task volume of distributed computing power nodes is constructed, and the real-time light intensity is input into the mapping set to obtain the correction factor of light intensity for the renewable energy task volume of distributed computing power nodes, where the mapping relationship can be one-to-one or many-to-one.

[0083] In an actual distributed power resource system, the volatility of the power resource itself is closely related to the computing tasks of the corresponding distributed nodes, and the computing tasks of the distributed nodes are related to the available distributed computing power resources. Therefore, in a region where the distributed power resources themselves have a high volatility period, even if the available distributed computing power resources are detected at a certain moment, in actual use, it may collide with the next peak of the distributed power resource volatility, resulting in the problem of failure to call the computing power resources of the distributed nodes. Therefore, for the distributed computing power nodes corresponding to the distributed power resource nodes with large volatility, the risk of calling computing power resources should be quantitatively evaluated. On the contrary, for nodes with relatively stable power resources and available computing power resource margins, the computing power resources can be safely called.

[0084] Furthermore, a second intelligent scheduling is performed according to the second comparative analysis result, which specifically includes: if the risk assessment value of scheduling computing power resources of the distributed computing power node of the callable distributed resource computing power node is greater than or equal to the risk assessment threshold of scheduling computing power resources of the distributed computing power node, the corresponding callable distributed resource computing power node is recorded as a non-callable distributed resource computing power node, and a distributed resource computing power node is added to the power resource area corresponding to the non-callable distributed resource computing power node; if the risk assessment value of scheduling computing power resources of the distributed computing power node of the callable distributed resource computing power node is less than the risk assessment threshold of scheduling computing power resources of the distributed computing power node, the corresponding callable distributed resource computing power node is recorded as a first-level callable distributed resource computing power node.

[0085] In this embodiment, if the risk assessment value of scheduling computing power resources of the distributed computing power node of the callable distributed resource computing power node is greater than or equal to the risk assessment threshold of scheduling computing power resources of the distributed computing power node, it indicates that the power resources in the power resource area corresponding to the callable distributed resource computing power node have large volatility, and a distributed resource computing power node should be added to the corresponding power resource area to reduce the pressure of available computing power resources of the distributed resource computing power node in the corresponding power resource area.

[0086] Further, a comprehensive evaluation value of the computing power resource invocation of the distributed computing power nodes is obtained, which specifically includes: performing a first evaluation analysis and a second evaluation analysis on the first-level callable distributed resource computing power nodes to obtain the distributed computing power node schedulable resource evaluation value of the first-level callable distributed resource computing power nodes and the distributed computing power node scheduling computing power resource risk evaluation value of the first-level callable distributed resource computing power nodes; collecting the network latency of the distributed computing power nodes through a network monitoring device; collecting the operating temperature and the environmental temperature of the server through a server temperature monitoring device; and thus analyzing and obtaining the comprehensive evaluation value of the distributed computing power node scheduling computing power resource invocation.

[0087] In this embodiment, the comprehensive evaluation value of the distributed computing power node scheduling computing power resource invocation is used to describe the comprehensive level of the software computing power resources that can be invoked by the distributed computing power nodes.

[0088] In the following text, the distributed computing power nodes include the first-level callable distributed resource computing power nodes. If the comprehensive evaluation value of the distributed computing power node scheduling computing power resource invocation of the first-level callable distributed resource computing power nodes is obtained, then the comprehensive evaluation value of the distributed computing power node scheduling computing power resource invocation of the corresponding distributed computing power nodes can be calculated, and the same applies to the different evaluation values of the callable distributed resource computing power nodes at other levels.

[0089]

[0090] Represents the distributed computing power node schedulable resource evaluation value of the JC0th distributed computing power node detection time period of the JD0th distributed computing power node.

[0091] Represents the distributed computing power node scheduling computing power resource risk evaluation value of the JC0th distributed computing power node detection time period of the JD0th distributed computing power node.

[0092] Represents the comprehensive evaluation value of the distributed computing power node scheduling computing power resource invocation of the JC0th distributed computing power node detection time period of the JD0th distributed computing power node.

[0093] Represents the network latency of the JC0th distributed computing power node detection time period of the JD0th distributed computing power node.

[0094] Represents the standard value of the network historical latency of the JC0th distributed computing power node detection time period of the JD0th distributed computing power node.

[0095] Network latency can affect data transmission and task execution efficiency, so it is also a factor that needs to be considered in scheduling.

[0096] Represents the server operating temperature during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0097] Represents the server ambient temperature during the JC0th distributed computing power node detection period of the JD0th distributed computing power node.

[0098] If the server operating temperature exceeds the ambient temperature by too much, it means that the server is operating at a relatively high load. There may still be available distributed computing power resources, but if the computing power resources are called, it will increase the operating pressure of the corresponding node, which may cause server damage under a higher load.

[0099] Represents the correction factor of light intensity for ambient temperature during the JC0th distributed computing power node detection period of the JD0th distributed computing power node, with a value range of (1, 2);

[0100] The correction factor of light intensity for ambient temperature represents the numerical value of the influence degree of light intensity on the ambient temperature of the distributed computing power node.

[0101] The correction factor of light intensity for ambient temperature can be directly obtained from the distributed computing power central database through a pre-set mapping relationship. For example, a real-time mapping set of light intensity and its corresponding correction factor of light intensity for ambient temperature is constructed, and the real-time light intensity is input into the mapping set to obtain the correction factor of light intensity for ambient temperature, where the mapping relationship can be one-to-one or many-to-one.

[0102] Furthermore, perform the third intelligent scheduling according to the third comparative analysis result, specifically including: if the comprehensive evaluation value of distributed computing power node scheduling for computing power resource invocation of the first-level callable distributed resource computing power node is greater than or equal to the comprehensive evaluation threshold of distributed computing power node scheduling for computing power resource invocation, then include the first-level callable distributed resource computing power node in the list of callable distributed resource computing power nodes, and perform computing power resource scheduling on the distributed resource computing power nodes in the list of callable distributed resource computing power nodes according to the predefined node resource scheduling scheme; if the comprehensive evaluation value of distributed computing power node scheduling for computing power resource invocation of the first-level callable distributed resource computing power node is less than the comprehensive evaluation threshold of distributed computing power node scheduling for computing power resource invocation, then record the first-level callable distributed resource computing power node as the second-level callable distributed resource computing power node, and use virtualization technology, data compression technology, and upgrade the hardware capacity for the node server corresponding to the second-level callable distributed resource computing power node.

[0103] In this embodiment, the comprehensive evaluation threshold for distributed computing power node scheduling of computing power resources is directly extracted from the distributed computing power central database. Virtualization technology: Utilize virtualization technologies such as virtual machines (VMs) or containers (such as Docker) to improve resource utilization; data compression and optimization, compress and optimize data to reduce the requirements for data transmission and storage; cache policy optimization can also be carried out: optimize the cache policy to reduce access to the main storage and improve data processing speed. Upgrade the hardware capacity, for example, upgrade hardware such as CPUs, GPUs, and memory to improve the computing power of the nodes; increase the storage capacity: increase the storage capacity to support more data and tasks; use solid-state drives (SSDs): Replace traditional hard disk drives (HDDs) with SSDs to improve data access speed; use dedicated hardware accelerators: For specific computing tasks, use dedicated hardware accelerators such as FPGAs or ASICs to improve performance.

[0104] Furthermore, for the third intelligent scheduling based on the third comparative analysis result, it also includes: After a predefined intelligent scheduling distributed computing power detection time, conduct a third evaluation and analysis on the secondary callable distributed resource computing power nodes to obtain the comprehensive evaluation value of the distributed computing power node scheduling of computing power resources for the secondary callable distributed resource computing power nodes; if the comprehensive evaluation value of the distributed computing power node scheduling of computing power resources for the secondary callable distributed resource computing power nodes is greater than or equal to the comprehensive evaluation threshold for distributed computing power node scheduling of computing power resources, do not adjust; if the comprehensive evaluation value of the distributed computing power node scheduling of computing power resources for the secondary callable distributed resource computing power nodes is less than the comprehensive evaluation threshold for distributed computing power node scheduling of computing power resources, notify the relevant personnel to add distributed computing power nodes in the corresponding area.

[0105] In this embodiment, if, after the predefined intelligent scheduling distributed computing power detection time, the comprehensive evaluation value of the distributed computing power node scheduling of computing power resources for the secondary callable distributed resource computing power nodes is less than the comprehensive evaluation threshold for distributed computing power node scheduling of computing power resources, it indicates that the computing power resources in this area are overall insufficient, and relevant personnel need to be notified to add more nodes to the distributed system to disperse the load and improve the overall computing power.

[0106] Such as Figure 2As shown in the figure, it is a schematic structural diagram of an intelligent scheduling system for optimizing distributed computing power scheduling strategies provided by an embodiment of the present application. The intelligent scheduling system for optimizing distributed computing power scheduling strategies provided by an embodiment of the present application includes a distributed computing power node self-checking module, a first evaluation and analysis module for distributed computing power, a first intelligent scheduling module for distributed computing power, a second evaluation and analysis module for distributed computing power, a second intelligent scheduling module for distributed computing power, a third evaluation and analysis module for distributed computing power, and a third intelligent scheduling module for distributed computing power: The distributed computing power node self-checking module is used for self-checking distributed computing power nodes and performing self-checking adjustment of distributed computing power according to the self-checking of distributed computing power nodes; The first evaluation and analysis module for distributed computing power is used for performing a first evaluation and analysis on the distributed computing power of distributed computing power nodes to obtain an evaluation value of the schedulable resources of distributed computing power nodes; The first intelligent scheduling module for distributed computing power is used for performing a first comparison and analysis on the evaluation value of the schedulable resources of distributed computing power nodes with the corresponding threshold value and performing a first intelligent scheduling according to the result of the first comparison and analysis; The second evaluation and analysis module for distributed computing power is used for performing a second evaluation and analysis on the distributed computing power of distributed computing power nodes to obtain an evaluation value of the risk of scheduling computing power resources of distributed computing power nodes; The second intelligent scheduling module for distributed computing power is used for performing a second comparison and analysis on the evaluation value of the risk of scheduling computing power resources of distributed computing power nodes with the corresponding threshold value and performing a second intelligent scheduling according to the result of the second comparison and analysis; The third evaluation and analysis module for distributed computing power is used for performing a third evaluation and analysis on the distributed computing power of distributed computing power nodes to obtain a comprehensive evaluation value of the invocation of scheduling computing power resources of distributed computing power nodes; The third intelligent scheduling module for distributed computing power is used for performing a third comparison and analysis on the comprehensive evaluation value of the invocation of scheduling computing power resources of distributed computing power nodes with the corresponding threshold value and performing a third intelligent scheduling according to the result of the third comparison and analysis.

[0107] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.

[0108] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0109] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0111] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0112] Obviously, those skilled in the art can make various changes and deformations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and deformations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and deformations.

Claims

1. An intelligent scheduling method for optimizing distributed computing power scheduling strategies, characterized in that, It includes the following steps: Self-check of distributed computing power nodes, and distributed computing power self-check adjustment based on the self-check of distributed computing power nodes; Conduct the first evaluation and analysis of the distributed computing power of the distributed computing power nodes to obtain the evaluated value of the schedulable resources of the distributed computing power nodes; Perform the first comparison and analysis of the evaluated value of the schedulable resources of the distributed computing power nodes with the corresponding threshold, and perform the first intelligent scheduling according to the result of the first comparison and analysis; Conduct the second evaluation and analysis of the distributed computing power of the distributed computing power nodes to obtain the risk evaluation value of the scheduled computing power resources of the distributed computing power nodes; Perform the second comparison and analysis of the risk evaluation value of the scheduled computing power resources of the distributed computing power nodes with the corresponding threshold, and perform the second intelligent scheduling according to the result of the second comparison and analysis; Conduct the third evaluation and analysis of the distributed computing power of the distributed computing power nodes to obtain the comprehensive evaluation value of the scheduled computing power resources of the distributed computing power nodes; Perform the third comparison and analysis of the comprehensive evaluation value of the scheduled computing power resources of the distributed computing power nodes with the corresponding threshold, and perform the third intelligent scheduling according to the result of the third comparison and analysis; The process of obtaining the comprehensive evaluation value of the scheduled computing power resources of the distributed computing power nodes specifically includes: Conduct the first evaluation and analysis and the second evaluation and analysis on the first-level callable distributed resource computing power nodes to obtain the evaluated value of the schedulable resources of the distributed computing power nodes of the first-level callable distributed resource computing power nodes and the risk evaluation value of the scheduled computing power resources of the distributed computing power nodes of the first-level callable distributed resource computing power nodes; Collect the network latency of the distributed computing power nodes through a network monitoring device; Collect the server operating temperature and the server environment temperature through a server temperature monitoring device; Thus, the comprehensive evaluation value of the scheduled computing power resources of the distributed computing power nodes of the first-level callable distributed resource computing power nodes is obtained through analysis.

2. The intelligent scheduling method for optimizing the distributed computing power scheduling strategy according to claim 1, characterized in that The specific process of the distributed computing power self-check adjustment according to the self-check of the distributed computing power nodes is as follows: The distributed computing power nodes perform a predefined self-check scheme at each predefined self-check time. The predefined self-check scheme is used for the self-check of the computing power resources of the distributed computing power nodes to obtain the self-check parameters of the distributed computing power nodes; If the self-check parameters of the distributed computing power nodes are greater than or equal to the self-check parameter threshold of the distributed computing power nodes, the corresponding distributed computing power nodes are marked as faulty nodes, and the faulty nodes are notified to relevant personnel; If the self-check parameters of the distributed computing power nodes are less than the self-check parameter threshold of the distributed computing power nodes, the corresponding distributed computing power nodes are marked as faulty nodes to be detected and evaluated.

3. The intelligent scheduling method for optimizing the distributed computing power scheduling strategy according to claim 1, characterized in that, The specific process of obtaining the evaluated value of the schedulable resources of the distributed computing power nodes is as follows: Collect the number of callable CPU cores, the callable operating frequency of the CPU, and the callable capacity of the CPU operating memory through the CPU information query tool of the server of the distributed computing power nodes; Collect the average failure rate of the CPU operation and the average recovery time of the CPU operation through the failure log monitoring tool of the server of the distributed computing power nodes; Extract the predefined number of CPU cores, the predefined operating frequency of the CPU, the predefined callable capacity of the CPU operating memory, the predefined standard value of the CPU operation failure rate, and the predefined average recovery time of the CPU operation from the factory log of the server of the distributed computing power nodes; Obtain the weight factor of the average CPU operation failure rate for the evaluation value of the schedulable resources of the distributed computing power node, the weight factor of the average CPU operation recovery time for the evaluation value of the schedulable resources of the distributed computing power node, the weight factor of the number of callable CPU cores for the evaluation value of the schedulable resources of the distributed computing power node, the weight factor of the callable operation frequency of the CPU for the evaluation value of the schedulable resources of the distributed computing power node, and the weight factor of the callable capacity of the CPU operation memory for the evaluation value of the schedulable resources of the distributed computing power node through the preset mapping relationship in the distributed computing power central database; Thus, obtain the evaluation value of the schedulable resources of the distributed computing power node for the distributed computing power node.

4. The intelligent scheduling method for optimizing the distributed computing power scheduling strategy according to claim 1, characterized in that, The first intelligent scheduling according to the first comparative analysis result specifically includes: If the evaluation value of the schedulable resources of the distributed computing power node of the distributed computing power node is less than or equal to the evaluation value of the schedulable resources of the distributed computing power node, then mark the distributed computing power node as a non-callable distributed resource computing power node, and enable the node failure recovery plan for the non-callable distributed resource computing power node; The non-callable distributed resource computing power node is used to describe the distributed computing power node in the non-callable distributed computing power resources when the distributed computing power central database calls the distributed computing power resources; If the evaluation value of the schedulable resources of the distributed computing power node of the distributed computing power node is greater than the evaluation value of the schedulable resources of the distributed computing power node, then mark the distributed computing power node as a callable distributed resource computing power node; The callable distributed resource computing power node is used to describe the distributed computing power node in the callable distributed computing power resources when the distributed computing power central database calls the distributed computing power resources.

5. The intelligent scheduling method for optimizing the distributed computing power scheduling strategy according to claim 1, wherein The specific process of obtaining the risk assessment value of the scheduled computing power resources of the distributed computing power node is as follows: Directly obtain the power task volume of the distributed computing power node and the renewable energy task volume of the distributed computing power node through the computing task scheduling tool of the distributed computing power node; Directly extract the corrected factor of the distributed computing power demand prediction, the corrected factor of the light intensity for the renewable energy task volume of the distributed computing power node, the average historical power task volume of the distributed computing power node, and the average historical renewable energy task volume of the distributed computing power node from the distributed computing power central database; Thus, analyze and obtain the risk assessment value of the scheduled computing power resources of the distributed computing power node for the callable distributed resource computing power node.

6. The intelligent scheduling method for optimizing the distributed computing power scheduling strategy according to claim 1, characterized in that, The second intelligent scheduling according to the second comparative analysis result specifically includes: If the risk assessment value of the scheduled computing power resources of the distributed computing power node of the callable distributed resource computing power node is greater than or equal to the risk assessment threshold of the scheduled computing power resources of the distributed computing power node, then mark the corresponding callable distributed resource computing power node as a non-callable distributed resource computing power node, and add distributed resource computing power nodes to the corresponding power resource area of the non-callable distributed resource computing power node; If the risk assessment value of the scheduled computing power resources of the distributed computing power node of the callable distributed resource computing power node is less than the risk assessment threshold of the scheduled computing power resources of the distributed computing power node, then mark the corresponding callable distributed resource computing power node as a first-level callable distributed resource computing power node.

7. The intelligent scheduling method for optimizing the distributed computing power scheduling strategy according to claim 1, characterized in that Performing the third intelligent scheduling according to the third comparative analysis result specifically includes: If the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the first-level callable distributed resource computing power node is greater than or equal to the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, the first-level callable distributed resource computing power node is included in the list of callable distributed resource computing power nodes, and the computing power resources of the distributed resource computing power nodes in the list of callable distributed resource computing power nodes are scheduled according to the predefined node resource scheduling scheme; If the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the first-level callable distributed resource computing power node is less than the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, the first-level callable distributed resource computing power node is recorded as a second-level callable distributed resource computing power node, and virtualization technology, data compression technology and upgraded hardware capacity are used for the node server corresponding to the second-level callable distributed resource computing power node.

8. The intelligent scheduling method for optimizing the distributed computing power scheduling strategy according to claim 1, characterized in that, Performing the third intelligent scheduling according to the third comparative analysis result further includes: After a predefined intelligent scheduling distributed computing power detection time, a third evaluation and analysis is performed on the second-level callable distributed resource computing power node to obtain the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the second-level callable distributed resource computing power node; If the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the second-level callable distributed resource computing power node is greater than or equal to the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, no adjustment is made; If the comprehensive evaluation value of the distributed computing power node scheduling computing power resource call of the second-level callable distributed resource computing power node is less than the comprehensive evaluation threshold of the distributed computing power node scheduling computing power resource call, relevant personnel are notified to add distributed computing power nodes in the corresponding area.

9. An intelligent scheduling system for optimizing distributed computing power scheduling strategies, which applies the intelligent scheduling method for optimizing distributed computing power scheduling strategies as described in any one of claims 1-8, characterized in that Including a distributed computing power node self-check module, a first evaluation and analysis module for distributed computing power, a first intelligent scheduling module for distributed computing power, a second evaluation and analysis module for distributed computing power, a second intelligent scheduling module for distributed computing power, a third evaluation and analysis module for distributed computing power and a third intelligent scheduling module for distributed computing power: The distributed computing power node self-check module: used for self-checking the distributed computing power node, and performing self-check adjustment of the distributed computing power according to the self-check of the distributed computing power node; The first evaluation and analysis module for distributed computing power: used for performing the first evaluation and analysis on the distributed computing power node to obtain the evaluation value of the schedulable resources of the distributed computing power node; The first intelligent scheduling module for distributed computing power: used for performing the first comparative analysis on the evaluation value of the schedulable resources of the distributed computing power node and the corresponding threshold, and performing the first intelligent scheduling according to the first comparative analysis result; The second evaluation and analysis module for distributed computing power: used for performing the second evaluation and analysis on the distributed computing power node to obtain the risk evaluation value of the distributed computing power node scheduling computing power resources; The second intelligent scheduling module for distributed computing power: used for performing the second comparative analysis on the risk evaluation value of the distributed computing power node scheduling computing power resources and the corresponding threshold, and performing the second intelligent scheduling according to the second comparative analysis result; The third evaluation and analysis module for distributed computing power: It is used to conduct the third evaluation and analysis of distributed computing power nodes to obtain the comprehensive evaluation value of the scheduling computing power resource invocation of distributed computing power nodes; The third intelligent scheduling module for distributed computing power: It is used to conduct the third comparison and analysis of the comprehensive evaluation value of the scheduling computing power resource invocation of distributed computing power nodes with the corresponding threshold, and perform the third intelligent scheduling according to the result of the third comparison and analysis.

Images