An intelligent scheduling and resource optimization allocation method based on dynamic task priority

Abstract

The application relates to the technical field of intelligent scheduling, in particular to an intelligent scheduling and resource optimization allocation method based on dynamic task priority, which comprises the following steps: collecting task information and load information, constructing a multi-dimensional task priority calculation model, dynamically adjusting the priority of the task, determining the task scheduling sequence according to a dynamic priority task scheduling sequence optimization algorithm based on the priority of the task, intelligently allocating resources based on the priority of the task and the task scheduling sequence, simultaneously acquiring monitoring data and quantitatively processing the monitoring data, optimizing the task scheduling sequence based on quantitative feedback, and adjusting the priority of the task and the resource allocation in real time. The application effectively improves the efficiency of task scheduling, reduces energy consumption, and optimizes resource utilization by dynamically adjusting the priority of the task, optimizing the task scheduling sequence, introducing branch optimization and local search strategies, and combining real-time monitoring and feedback mechanisms, and is suitable for resource management and scheduling optimization in a multi-task environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent scheduling, and particularly to an intelligent scheduling and resource optimization allocation method based on dynamic task priority. BACKGROUND

[0002] In today's task scheduling and resource management systems, especially in the fields of industrial control, data processing and cloud computing, the optimization of task scheduling and resource allocation is always the key to improving system efficiency and reducing operating costs.

[0003] However, existing technologies still face multiple challenges when facing complex task scheduling. Traditional task scheduling strategies are mostly based on static priority and simple rules, which makes them lack sufficient adaptability in dynamic environments.

[0004] For example, the Chinese invention patent with the authorization announcement number CN116560860B discloses a real-time optimization adjustment method for resource priority based on machine learning, which includes: step 1, obtaining and confirming the demand information of the received task, and marking the completion priority of the task; step 2, obtaining the resource application request information for the task; step 3, selecting the corresponding first resource from the total resource pool according to the resource application request information, and preliminarily allocating the first resource to the task; step 4, analyzing the conflict of multiple tasks based on completion priority and resource application request information based on a machine learning model; step 5, obtaining and processing the conflict analysis, and generating corresponding scheduling instructions to optimize the scheduling of the preliminarily allocated first resource in the total resource pool.

[0005] However, the existing scheduling method fails to fully consider the different priorities of tasks, the resource requirements at runtime, and the real-time changes of the system environment, resulting in suboptimal configuration of resources and affecting the execution efficiency and response time of tasks. Especially when dealing with high-concurrency tasks and large-scale data, traditional scheduling systems often rely on fixed algorithms for task allocation and cannot flexibly adjust in real time according to the priority, complexity and resource constraints of tasks. At the same time, existing systems often ignore the optimization of energy efficiency, causing energy waste during system operation, especially in resource-constrained situations, which cannot achieve reasonable scheduling of resources and balance of energy efficiency, resulting in increased costs and overload of system load.

[0006] Therefore, there is an urgent need for an intelligent scheduling and resource optimization allocation method based on dynamic task priority. SUMMARY

[0007] To overcome the problems in the prior art, the present application aims to provide an intelligent scheduling and resource optimization allocation method based on dynamic task priority.

[0008] To achieve the above object, the present application provides the following technical scheme: a kind of intelligent scheduling and resource optimization allocation method based on dynamic task priority, comprising the following steps:

[0009] S1: collection task information and load information, according to load information and task information, constructs multi-dimensional task priority calculation model and dynamically adjusts the priority of task;Then based on the priority of task, in combination with resource use and energy consumption requirement, based on dynamic priority task scheduling sequence optimization algorithm determines task scheduling sequence;

[0010] S2: based on task priority and task scheduling sequence, introduce resource allocation model intelligent allocation resource, execute task;While real-time monitoring task execution process obtains monitoring data, and quantitatively processes monitoring data, obtains quantized feedback;Based on quantized feedback, the task scheduling sequence is optimized, and the priority of task and resource allocation are adjusted in real time.

[0011] The present application is further provided: the task information includes task ID, task type, estimated execution time, initially set priority, resource demand and energy efficiency requirement;

[0012] The load information includes, such as resource utilization, energy consumption data and work load.

[0013] The task information and load information are collected in real time by monitoring tool or API interface.

[0014] The present application is further provided: in step S1, the multi-dimensional task priority calculation model dynamically adjusts the priority of task according to the type of task, urgency, resource demand and energy efficiency requirement, which is expressed by the following formula:

[0015] ;

[0016] Wherein, is the dynamic priority of task At Time, indicates the degree to which the current task should be processed preferentially among multiple tasks; 、 、 、 is weight coefficient, Indicates the demand function of task To resource; is the energy efficiency demand function of task Reflects the requirement of task to energy efficiency; Is the urgency function of task ; Is the historical performance function of task ; Is global adjustment factor, indicates the load Impact on task priority;

[0017] The global adjustment factor is defined as:

[0018] ;

[0019] in, It represents the amount of resources currently in use, including the usage of all resources such as CPU, memory, and storage. It represents the total amount of resources, including all available CPUs, memory, storage, etc. It is a task resource requirements, This represents the amount of resources currently available for the task, indicating the resources available during task execution. This is a tuning factor, a parameter that controls the degree of impact of load. A global tuning factor automatically lowers the priority of tasks when the load is high.

[0020] The present invention is further configured such that, in step S1, the task scheduling order determination based on the dynamic priority task scheduling order optimization algorithm specifically involves establishing a comprehensive objective function based on the optimization objective, dynamically adjusting the scheduling strategy, and updating the task order by calculating the priority and execution time of each task.

[0021] ;

[0022] in, It is a comprehensive objective function that aims to represent the task scheduling optimization result under the current state. This function attempts to take into account multiple aspects such as task priority, resource utilization, energy efficiency, and execution time to find an optimized task scheduling order. It is the first weighting coefficient, used to measure the impact of resource utilization on the optimization objective; It is the second weighting coefficient, used to measure the impact of energy efficiency on the optimization objective; It is the third weighting coefficient, used to measure the impact of task execution time on the optimization objective; It is a task At any moment The priority is calculated using a multi-dimensional task priority calculation model. It is a task Resources The actual utilization rate is the ratio of the amount of resources actually used in the task to the actual resource utilization rate. The proportion of the total; It is the first The total amount of such resources can be resources such as CPU, memory, and bandwidth; It is the number of tasks in the task set; It refers to the types and quantities of resources; It is a task The need for energy efficiency; It is a task Execution time.

[0023] This invention further incorporates branch optimization and local search strategies to improve task scheduling performance. The task order is updated using the following formula:

[0024] ;

[0025] in, It is a task In the optimized execution order; It is a task Resources The demand; It is a dynamic time adjustment factor during task execution, representing the change in task execution time; yes The actual usage data was used to measure the resource load.

[0026] The present invention is further configured such that the resource allocation model is calculated using the following formula:

[0027] ;

[0028] in, At any moment Task Resources need to be allocated The amount allocated; It is a task Resources The initial demand will be determined based on expert experience; It is the attenuation coefficient in scheduling, used to control the degree to which the execution order affects resource allocation.

[0029] The above formula intelligently allocates the amount of resources required for each task based on the ratio between task priority and resource demand.

[0030] The present invention is further configured such that, in step S2, the quantization processing of the monitoring data specifically involves defining quantization feedback. For the task At any moment Monitoring data feedback values:

[0031] ;

[0032] in, It is a task At any moment Quantitative feedback value of the task execution time error and the energy efficiency ratio, representing the optimization feedback in the task execution, reflecting the effectiveness and efficiency of the task in the execution process; is the actual execution time of the task at the time point ; is the expected execution time of the task at the time point ; is an exponential adjustment factor, used to adjust the influence degree of the task execution time error on the quantitative feedback, determining the influence degree of the deviation between the actual execution time and the expected time of the task on the task feedback; is the total resource consumption of the task at the time point , calculated by ; is the energy efficiency consumption of the task in the execution process.

[0033] The above formula combines the execution time error and the energy efficiency ratio of the task, and obtains the quantitative feedback by weighting in the form of exponential and ratio. In this way, not only the time delay in the task execution process can be captured, but also the volatility of the task resource usage and the energy efficiency consumption can be considered.

[0034] The application further sets that the monitoring data includes the progress of the task and the usage of the resource; and the usage of the resource includes the CPU usage rate, the memory usage amount and the energy consumption.

[0035] The application further sets that the task scheduling sequence is optimized and updated based on the quantitative feedback, and the formula for adjusting the priority is as follows:

[0036] ;

[0037] Wherein, is the priority of the task at the time point after adjustment; is the weight of the quantitative feedback on the priority adjustment of the task; is an exponential adjustment coefficient, representing the acceleration degree of the feedback on the priority change.

[0038] The application further sets that the task scheduling sequence is optimized based on the adjusted task priority, in combination with the resource usage and the energy consumption requirement, by using the dynamic priority-based task scheduling sequence optimization algorithm, and the optimized task execution sequence is obtained;

[0039] The resource allocation model is updated according to the adjusted task priority and the optimized task execution sequence, and the adjusted resource allocation amount is obtained.​

[0040] In summary, the beneficial effects of the above technical solutions of the present application are as follows:

[0041] 1. The present application dynamically adjusts the priority of tasks according to resource requirements, energy efficiency requirements, urgency, and historical performance, etc. factors through a multi-dimensional task priority calculation model, ensuring that the system can prioritize the execution of the most critical or resource-consuming tasks, effectively improving the efficiency of task scheduling.

[0042] 2. The intelligent scheduling and resource optimization allocation method based on dynamic task priority dynamically adjusts the task priority, optimizes the task scheduling order, introduces branch optimization and local search strategies, and combines real-time monitoring and feedback mechanisms, which has significant advantages in practical applications, effectively improving the efficiency of task scheduling, reducing energy consumption, and optimizing resource utilization, and is suitable for resource management and scheduling optimization in a multi-task environment. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 The flow chart of the intelligent scheduling and resource optimization allocation method based on dynamic task priority. DETAILED DESCRIPTION

[0045] In order to make those skilled in the art better understand the technical solutions of the present application, the following will clearly and completely describe the technical solutions of the present application combined with the drawings of the present application. Based on the embodiments in the present application, other similar embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0046] The present application will be further described below combined with the drawings and preferred embodiments.

[0047] EMBODIMENT

[0048] As shown in the preferred embodiment of the present application, an intelligent scheduling and resource optimization allocation method based on dynamic task priority includes the following steps: Figure 1

[0049] ​S1: Collect task information and load information, construct a multi-dimensional task priority calculation model according to the load information and the task information, dynamically adjust the priority of the task, and then determine the task scheduling sequence based on the dynamic priority task scheduling sequence optimization algorithm based on the priority of the task, the resource usage and the energy consumption requirement.

[0050] The task information and the load information are collected in real time through a monitoring tool or an API interface. For example, the task information is collected by using an SNMP protocol or performance monitoring software (such as Prometheus and Zabbix), and the task information includes a task ID, a task type, a predicted execution time, a preliminarily set priority, resource requirements, energy efficiency requirements and the like. The load information includes resource utilization, energy consumption data, workloads and the like.

[0051] After the task information and the load information are collected, a multi-dimensional task priority calculation model is constructed. The multi-dimensional task priority calculation model dynamically adjusts the priority of the task according to the type, urgency, resource requirements and energy efficiency requirements of the task, and the priority calculation formula of the task is as follows:

[0052] ;

[0053] Among them, is the dynamic priority of the task at the moment, which represents the degree to which the current task should be processed preferentially among multiple tasks; is a weight coefficient, and each task feature, such as resource requirements, energy efficiency requirements, urgency and historical performance, occupies a weight in the priority calculation, and the weight is determined according to an empirical method; is a weight coefficient, and each task feature, such as resource requirements, energy efficiency requirements, urgency and historical performance, occupies a weight in the priority calculation, and the weight is determined according to an empirical method; represents the demand of the task for resources, which can be defined by the ratio of the required resources of the task, such as CPU, memory and storage, to the current resources, and reflects the occupation degree of the task for the resources. In the formula:

[0054]

[0055] ; Among them,

[0056] is the demand vector of the task for resources, which represents the amount of different resources required during the execution of the task, including resource requirements such as CPU, memory, storage and bandwidth, and each component represents the demand of a resource; is the current available resource, which represents the available amount of each resource. is the demand vector of the task for resources, which represents the amount of different resources required during the execution of the task, including resource requirements such as CPU, memory, storage and bandwidth, and each component represents the demand of a resource;

[0057] is the current available resource, which represents the available amount of each resource. ​​​​​The energy efficiency demand function reflects the energy efficiency requirement of the task, i.e. the energy consumption constraint of the task during execution, and optimizes the energy efficiency consumption during the execution of the task. Generally, a task will consume a certain amount of energy when executed, and thus the energy efficiency thereof needs to be optimized. The energy efficiency demand function is defined as:

[0058]

[0059] wherein, is the maximum energy efficiency requirement of the task , representing the maximum energy efficiency consumption allowed during execution of the task, specified by the business requirement or energy efficiency standard of the task; is the energy consumption during actual execution of the task ; and is an adjustment factor used to adjust the influence degree of the energy efficiency requirement.

[0060] is the urgency of the task , i.e. the priority of the task to be completed within a certain time, calculated according to the difference between the deadline of the task and the current time, and the higher the urgency of the task, the higher the priority thereof should be, so that the urgent task obtains a higher weight in the priority calculation:

[0061]

[0062] wherein, is the deadline of the task ; is the current time; is a parameter for controlling the influence of the urgency, used to adjust the influence of the difference between the deadline and the current time on the urgency of the task;

[0063] is the historical performance function of the task , representing the influence of the past execution of the task on the current priority thereof, used to dynamically adjust the priority of the task according to the historical execution performance thereof; the historical performance function is calculated by the average execution time of the task:

[0064]

[0065] wherein, is the historical average execution time of the task , representing the average time required by the task during past execution; is the maximum allowed execution time of the task.

[0066] is a global adjustment factor, representing the influence of the load on the priority of the task, and the ratio between the current load and the resource requirement of the task will affect the execution order of the task. The global adjustment factor is defined as:​​​

[0067] ;

[0068] in, It represents the amount of resources currently in use, including the usage of all resources such as CPU, memory, and storage. It represents the total amount of resources, including all available CPUs, memory, storage, etc. It is a task resource requirements, This represents the amount of resources currently available for the task, indicating the resources available during task execution. This is a tuning factor, a parameter that controls the degree of impact of load. A global tuning factor automatically lowers the priority of tasks when the load is high.

[0069] Based on task priority, combined with resource usage and energy consumption requirements, a dynamic priority-based task scheduling order optimization algorithm is used to determine the task scheduling order. This algorithm comprehensively considers the task's resource requirements, energy efficiency requirements, and load, employing a complex mathematical model and multi-objective optimization process to achieve efficient task scheduling. The specific implementation process is as follows:

[0070] Based on dynamic priority adjustments, task scheduling order is achieved through multi-objective optimization. The optimization objectives are: maximizing resource utilization, minimizing energy consumption, and optimizing task execution latency. To this end, a comprehensive objective function is designed:

[0071] ;

[0072] in, It is a comprehensive objective function that aims to represent the task scheduling optimization result under the current state. This function attempts to take into account multiple aspects such as task priority, resource utilization, energy efficiency, and execution time to find an optimized task scheduling order. It is the first weighting coefficient, used to measure the impact of resource utilization on the optimization objective; It is the second weighting coefficient, used to measure the impact of energy efficiency on the optimization objective; It is the third weighting coefficient, used to measure the impact of task execution time on the optimization objective; It is a task At any moment The priority is calculated using a multi-dimensional task priority calculation model. It is a task Resources The actual utilization rate is the ratio of the amount of resources actually used in the task to the actual resource utilization rate. The proportion of total resources. The goal is to improve overall resource utilization by prioritizing tasks with lower resource requirements during scheduling; It is the first The total amount of such resources can be resources such as CPU, memory, and bandwidth; It is the number of tasks in the task set; It refers to the types and quantities of resources; It is a task The need for energy efficiency; It is a task Execution time.

[0073] The aforementioned comprehensive objective function optimizes task execution order by maximizing resource utilization, minimizing energy consumption, and minimizing task latency. The scheduling strategy is dynamically adjusted by calculating the priority and execution duration of each task.

[0074] Furthermore, to improve task scheduling efficiency, branch optimization and local search strategies are introduced. First, a rough framework for task scheduling is determined using existing branch backtracking strategies, which involves calculating preliminary task priorities and generating a general scheduling order. Then, based on existing local search strategies, each scheduling order is optimized to ultimately determine the task execution order.

[0075] During this process, the task order is updated using the following formula:

[0076] ;

[0077] in, It is a task In the optimized execution order; It is a task Resources The demand; It is a dynamic time adjustment factor during task execution, representing the change in task execution time; yes The actual usage data was used to measure the resource load.

[0078] The above formula combines resource requirements, energy efficiency, resource utilization, and task execution time to generate a final scheduling order for each task. The task scheduling order is obtained through this process.

[0079] S2: Based on task priority and task scheduling order, a resource allocation model is introduced to intelligently allocate resources and execute tasks; at the same time, the task execution process is monitored in real time to obtain monitoring data, and the monitoring data is quantified to obtain quantitative feedback; based on the quantitative feedback, the task scheduling order is optimized, and task priority and resource allocation are adjusted in real time.

[0080] Based on the task priority and the task scheduling order, a resource allocation model is introduced to realize intelligent allocation of resources. The allocation of resources not only ensures that tasks with high priority can be executed preferentially, but also dynamically allocates resources according to the resource requirements (such as CPU time, memory usage, bandwidth, etc.) of the tasks. The resource allocation model can be represented by the following formula:

[0081] ;

[0082] wherein, is the allocation amount of the resource to the task at time ; is the preliminary demand amount of the resource by the task ; determined according to expert experience; is a decay coefficient in scheduling, used to control the influence degree of the execution order on the allocation of resources. The role of the above formula is to intelligently allocate the resource amount required by each task based on the proportional relationship between the task priority and the resource requirement.

[0083] Further, after the task starts to execute, the execution process of the task is monitored in real time to obtain monitoring data, including the progress of the task, the usage of the resource, such as CPU usage, memory usage, energy consumption, etc.

[0084] In order to extract valuable information from the above monitoring data, a quantitative feedback mechanism is introduced. The purpose of the quantitative feedback is to convert the real-time monitoring data into effective guidance information for task scheduling. In the quantitative feedback mechanism, the quantitative feedback is defined as the monitoring data feedback value of the task at time , and the formula is as follows:

[0085] ;

[0086] wherein, is the quantitative feedback value of the task at time , indicating the optimization feedback in the execution of the task, including the execution time error and the resource usage efficiency, reflecting the effectiveness and efficiency of the task in the execution process; is the actual execution time of the task at time ; is the expected execution time of the task at time ; is an exponential adjustment factor, used to adjust the influence degree of the task execution time error on the quantitative feedback, determining the influence degree of the deviation between the actual execution time and the expected time of the task on the feedback of the task. for the task at time total resource consumption; for the task during execution energy efficiency consumption.

[0087] The above formula combines the execution time error and energy efficiency ratio of the task, and obtains quantitative feedback by weighting in the form of exponential and ratio. In this way, not only the time delay during task execution can be captured, but also the volatility of task resource use and energy efficiency consumption can be considered.

[0088] Based on the quantitative feedback , the priority of the task and the resource allocation are dynamically adjusted. The traditional priority adjustment strategy only depends on the static priority of the task or the current resource demand, while the present application intelligently optimizes the task priority and resources through the feedback adjustment mechanism, considering the execution state, resource utilization and energy efficiency of the task.

[0089] Firstly, according to the quantitative feedback of the task , the priority of the task is adjusted. The formula for adjusting the priority is as follows:

[0090] ;

[0091] Among them, is the adjusted priority of the task at time ; is the weight of the quantitative feedback on the adjustment of the task priority; is an exponential adjustment coefficient, indicating the acceleration degree of feedback on the change of priority.

[0092] The adjusted task priority will increase or decrease according to the quantitative feedback information, reflecting the deviation in task execution.

[0093] Based on the adjusted task priority , combined with the resource use and energy consumption requirements, the task scheduling sequence is optimized through the dynamic priority-based task scheduling sequence optimization algorithm, and the optimized task execution sequence is obtained.

[0094] According to the adjusted task priority and the optimized task execution sequence , the resource allocation is re-performed, and the adjusted resource allocation amount is obtained. The optimization formula of resource allocation is as follows:

[0095] ;

[0096] In summary, a method of intelligent scheduling and resource optimization allocation based on dynamic task priority is completed.

[0097] Finally, it should be noted that the above content is only used to illustrate the technical solutions of the present application, and is not a limitation on the scope of protection of the present application. Simple modifications or equivalent replacements of the technical solutions of the present application made by those skilled in the art do not deviate from the essence and scope of the technical solutions of the present application.

Claims

1. A method for intelligent scheduling and resource optimization allocation based on dynamic task priority, characterized in that, The method comprises the following steps: S1: collecting task information and load information, constructing a multi-dimensional task priority calculation model according to the load information and the task information to dynamically adjust the priority of the task; and based on the priority of the task, combining resource usage and energy consumption requirements, determining a task scheduling sequence based on a dynamic priority task scheduling sequence optimization algorithm, specifically, establishing a comprehensive objective function based on an optimization objective, dynamically adjusting a scheduling strategy by calculating the priority and execution time of each task, and updating the task sequence; The comprehensive objective function is represented by the following formula: wherein, is a comprehensive objective function; is a first weight coefficient for measuring the influence of resource utilization on the optimization objective; is a second weight coefficient for measuring the influence of energy efficiency on the optimization objective; is a third weight coefficient for measuring the influence of task execution time on the optimization objective; is a task priority at time , which is calculated by a multi-dimensional task priority calculation model; is a task actual utilization rate of resources ; is the total amount of the first resource; is the number of tasks in the task set; is the number of types of resources; is a task demand for energy efficiency; is a task execution time; Branch optimization and local search strategies are introduced to improve the effect of task scheduling, and the updating of the task sequence is performed by the following formula: wherein, is a task in an optimized execution order; is a task to a resource demand; is a dynamic time adjustment factor during task execution, indicating the change of task execution time; is actual usage, measuring the load of the resource; S2: based on the task priority and the task scheduling sequence, a resource allocation model is introduced to intelligently allocate resources; at the same time, the task execution process is monitored in real time, monitoring data is obtained, and the monitoring data is quantitatively processed to obtain quantitative feedback; based on the quantitative feedback, the task scheduling sequence is optimized, and the task priority and resource allocation are adjusted in real time; The resource allocation model is calculated by the following formula: wherein, is the time instant the task needs to be allocated to the resource ; is the preliminary demand of the task for the resource ; is a decay coefficient in the scheduling, used to control the influence degree of the execution order on the resource allocation. The quantification of the monitoring data is specifically defining a quantification feedback for the task at the time of the monitoring data feedback value: wherein, is the task at time quantitative feedback value, representing the optimization feedback in task execution, including execution time error and resource usage efficiency, reflecting the effectiveness and efficiency of the task in the execution process; is the task at time actual execution time; is the task at time expected execution time; is an exponential adjustment factor, used to adjust the influence degree of task execution time error on quantitative feedback; is the total resource consumption of task at time ; is the consumption of resource efficiency in the process of task execution.

2. The method for intelligent scheduling and resource optimization allocation based on dynamic task priority according to claim 1, characterized in that, The task information includes task ID, task type, estimated execution time, initially set priority, resource requirement and energy efficiency requirement; The load information includes resource utilization rate, energy consumption data and work load. 3.The method of claim 1, wherein, In step S1, the multi-dimensional task priority calculation model dynamically adjusts the priority of the task according to the type, urgency, resource requirement and energy efficiency requirement of the task, and is represented by the following formula: wherein, is a task in a dynamic priority at a time instant; 、 、 、 is a weight coefficient; denotes a task demand function for resources; is a task energy efficiency demand function, reflecting the energy efficiency requirement of the task; is a task urgency function; is a task historical performance function; is a global adjustment factor, representing the influence of the load on the task priority; The global adjustment factor is defined as: in, This represents the amount of resources currently in use. It is the total amount of resources; It is a task resource requirements, This represents the amount of resources currently available for the task. It is an adjustment factor, a parameter that controls the degree of influence of the load.

4. The method for intelligent scheduling and resource optimization allocation based on dynamic task priority according to claim 1, characterized in that, The monitoring data includes the progress of the task and the usage of the resource; the usage of the resource includes CPU usage rate, memory usage and energy consumption.

5. The method for intelligent scheduling and resource optimization allocation based on dynamic task priority according to claim 4, characterized in that, The formula for updating the priority based on the quantitative feedback to optimize the task scheduling sequence is as follows: wherein, is the adjusted task At time priority; is the weight of the quantized feedback on the adjustment of the task priority; is the exponential adjustment coefficient, indicating the acceleration degree of the feedback on the priority change.

6. The method for intelligent scheduling and resource optimization allocation based on dynamic task priority according to claim 5, characterized in that, Based on the adjusted task priority , in combination with resource usage and energy consumption requirements, the task scheduling sequence is optimized through a dynamic priority-based task scheduling sequence optimization algorithm, and an optimized task execution sequence is obtained ; According to the adjusted task priority And the optimized task execution sequence Update the resource allocation model Get the adjusted resource allocation amount.

Images