Resource scheduling optimization method for satellite remote education network

Abstract

The invention discloses a resource scheduling optimization method for a satellite remote education network, and relates to the technical field of satellite communication, and the method comprises the steps: receiving task requests sent by a plurality of users through a server, combining the same requests in the task requests into one task request, and obtaining a to-be-scheduled task pool; then solving the tasks in the to-be-scheduled task pool through a multivariate initialization intelligent optimization algorithm to obtain a task scheduling sequence, and finally allocating resources for the tasks according to the task scheduling sequence to execute the corresponding tasks. According to the method, the utilization efficiency of satellite remote education resources is improved.

Description

Technical Field

[0001] The present invention relates to the field of satellite communication technology, and in particular to a resource scheduling optimization method for a satellite distance education network in remote areas. Background Art

[0002] With the rapid development of digital technology and the digital transformation of education, satellite distance education has become an important form of education, especially in remote and resource-poor areas. For example, satellite distance education uses geosynchronous satellites to achieve wide coverage and efficient transmission of educational resources, providing valuable learning opportunities for these areas.

[0003] In the field of satellite distance education network resource scheduling, there are a series of complex and critical challenges. For example, the demand for educational resources presents similar and clustered characteristics in a specific period. At the beginning of the school year, students of the same grade tend to request the same teaching materials in a concentrated manner. Repeated applications for highly similar resources lead to redundant allocation of resources, increase system burden, and bring challenges to scheduling.

[0004] Therefore, there is an urgent need for a resource scheduling method to improve the utilization efficiency of satellite distance education resources. Summary of the invention

[0005] Based on this, it is necessary to provide a resource scheduling optimization method for satellite distance education network to address the above technical problems and improve the utilization efficiency of satellite distance education resources.

[0006] The present invention adopts the following technical solutions:

[0007] The present invention provides a resource scheduling method, comprising:

[0008] Receive task requests sent by multiple users, and merge the same requests in the task requests into one task request to obtain a task pool to be scheduled;

[0009] The tasks in the task pool to be scheduled are solved by a multi-initialized intelligent optimization algorithm to obtain a task scheduling sequence;

[0010] Allocate resources to tasks according to the task scheduling sequence to execute the corresponding tasks.

[0011] In one embodiment, identical requests in the task requests are merged into one task request to obtain a task pool to be scheduled, including:

[0012] Get the bandwidth size requested by each task;

[0013] Classify the task requests according to the bandwidth size of each task request to obtain a variety of sorting queues with different bandwidths;

[0014] Merge the task requests for the same resources in each sorting queue into one task request;

[0015] The merged sorting queues are integrated to obtain a pool of tasks to be scheduled.

[0016] In one embodiment, the task requests are classified according to the bandwidth size of each task request, including:

[0017] If the bandwidth of the task request is less than or equal to the first preset threshold, the task request is allocated to a low bandwidth queue;

[0018] If the bandwidth of the task request is greater than the first preset threshold and less than or equal to the second preset threshold, the task request is allocated to the medium bandwidth queue;

[0019] If the bandwidth of the task request is greater than the second preset threshold and less than or equal to the third preset threshold, the task request is allocated to the high bandwidth queue;

[0020] If the bandwidth of the task request exceeds the third preset threshold, the task request is allocated to the ultra-high bandwidth queue.

[0021] In one embodiment, the multi-initialization intelligent optimization algorithm is a multi-initialization particle swarm-genetic hybrid optimization algorithm; the multi-initialization intelligent optimization algorithm is used to solve the tasks in the task pool to be scheduled to obtain a task scheduling sequence, including:

[0022] Generate an initial population through diversified initial strategies; the initial population includes multiple individuals, each of which corresponds to an initial scheduling strategy for tasks in the task pool to be scheduled;

[0023] According to the initial population, the multi-initialized particle swarm-genetic hybrid optimization algorithm is iterated to obtain the task scheduling sequence.

[0024] In one embodiment, generating an initial population by a diversified initial strategy includes:

[0025] Generate the first population according to the random initialization method;

[0026] Generate a second population according to the crossover and mutation operations in the genetic algorithm;

[0027] Based on the initialization method of specific rules, the third population is generated;

[0028] The first population, the second population and the third population are determined as initial populations.

[0029] In one embodiment, the third population is determined based on a specific rule-based initialization method, including:

[0030] The third group is determined by sorting the tasks according to their urgency, and the third group is determined based on the sorting method of the tasks on bandwidth requirements.

[0031] In one embodiment, according to the initial population, the multi-initialized particle swarm-genetic hybrid optimization algorithm is iterated to obtain a task scheduling sequence, including:

[0032] According to the initial population, calculate the fitness values ​​of multiple individuals;

[0033] Sort multiple fitness values, and according to the fitness value sorting results, use the particle swarm algorithm to process the individuals with higher fitness and the preset proportion, and use the genetic algorithm to process the remaining individuals with lower fitness, to obtain an updated population;

[0034] According to the updated population, the task scheduling sequence is determined.

[0035] In one embodiment, determining a task scheduling sequence according to the updated population includes:

[0036] If the multi-initialized particle swarm-genetic hybrid optimization algorithm does not meet the iteration termination condition, the step of iterating the multi-initialized particle swarm-genetic hybrid optimization algorithm is performed through the updated population;

[0037] If the multi-initialized particle swarm-genetic hybrid optimization algorithm meets the preset iteration termination condition, the optimal individual in the updated population is output;

[0038] The scheduling strategy corresponding to the optimal individual is determined as the task scheduling strategy.

[0039] In one embodiment, the method further comprises:

[0040] After the task is completed, the execution result of the task is fed back to the corresponding user.

[0041] In one embodiment, the method further comprises:

[0042] After completing the tasks, conduct a comprehensive analysis of the execution effects of multiple tasks to obtain evaluation results;

[0043] According to the evaluation results, the multi-initialization intelligent optimization algorithm is iteratively optimized and updated.

[0044] The present invention provides a resource scheduling device, comprising:

[0045] A receiving module is used to receive task requests sent by multiple users, and merge the same requests in the task requests into one task request to obtain a task pool to be scheduled;

[0046] A solution module is used to solve the tasks in the task pool to be scheduled by using a multi-initialization intelligent optimization algorithm to obtain a task scheduling sequence;

[0047] The resource allocation module is used to allocate resources to tasks according to the task scheduling sequence to execute the corresponding tasks.

[0048] The present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the resource scheduling method is implemented.

[0049] The present invention provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the resource scheduling method when executing the program.

[0050] At least one of the above-mentioned technical solutions adopted by the present invention can achieve the following beneficial effects: first, by classifying and merging the same tasks, not only the structure of the waiting queue is simplified, but also redundant requests are reduced, the scheduling efficiency of educational resources is improved, and resource waste is avoided; further, this mechanism can reduce repeated applications for system resources, reduce redundant allocation of resources, and reduce the system burden by merging the same task requests, thereby improving the overall bandwidth utilization efficiency of the system.

[0051] Moreover, solving the task scheduling problem through a multi-initialization intelligent optimization algorithm can improve the efficiency and accuracy of task scheduling in the satellite distance education network, thereby improving the overall system performance of the satellite distance education network. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0053] Figure 1 An application environment diagram of a resource scheduling method in an embodiment;

[0054] Figure 2 A schematic diagram of a resource scheduling method in one embodiment;

[0055] Figure 3 is a flow chart of a resource scheduling method in another embodiment;

[0056] Figure 4 is a flow chart of a resource scheduling method in another embodiment;

[0057] Figure 5 is a flow chart of a resource scheduling method in another embodiment;

[0058] Figure 6 is a flow chart of a resource scheduling method in another embodiment;

[0059] Figure 7 is a flow chart of a resource scheduling method in another embodiment;

[0060] Figure 8 A schematic diagram of the structure of a satellite distance education task delivery and scheduling model in one embodiment;

[0061] Fig. 9 is a structural block diagram of a resource scheduling device in one embodiment;

[0062] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0064] The resource scheduling method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, multiple terminals 102 communicate with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0065] With the increase in educational needs, existing satellite communication systems are facing the problems of insufficient resource utilization and inefficiency. Specifically, the increase in the number and complexity of tasks makes the task processing requirements of education centers increasingly complex, while the existing resource scheduling methods cannot effectively cope with these challenges, resulting in resource waste and system performance degradation. Therefore, there is an urgent need for an optimized resource scheduling method to improve the task scheduling efficiency and overall system performance of satellite distance education networks.

[0066] In the field of satellite distance education network resource scheduling, there are a series of complex and critical challenges. First, the current satellite network resource scheduling algorithms are mainly designed for specific data transmission tasks, such as effectively handling the transmission of remote sensing images. These algorithms perform well when dealing with a single data type, but show certain limitations in managing diverse educational content, such as video conferencing, real-time classroom broadcasts, and online homework submission.

[0067] Secondly, the demand for educational resources shows similar and clustered characteristics in specific periods. For example, at the beginning of the school year, students of the same grade tend to request the same teaching materials. Repeated applications for highly similar resources lead to redundant allocation of resources, increase system burden, and bring challenges to scheduling.

[0068] Based on this, the applicant adopts a method combining theoretical analysis with experimental verification to conduct research. By deeply analyzing the problems faced in the resource scheduling of the satellite distance education network, the resource scheduling optimization problem of the satellite distance education network is transformed into a task scheduling model, thereby providing a resource scheduling method, receiving task requests sent by multiple users through a server, and merging the same requests in the task requests into one task request to obtain a task pool to be scheduled; then the tasks in the task pool to be scheduled are solved by a multi-initialization intelligent optimization algorithm to obtain a task scheduling sequence, and finally resources are allocated to the tasks according to the task scheduling sequence to execute the corresponding tasks. First, the way of merging the same tasks not only simplifies the structure of the waiting queue, but also reduces redundant requests, improves the scheduling efficiency of educational resources, and avoids resource waste; further, this mechanism can reduce repeated applications for system resources, reduce redundant resource allocation, and reduce system burden by merging the same task requests, thereby improving the overall bandwidth utilization efficiency of the system. In addition, solving the task scheduling problem by a multi-initialization intelligent optimization algorithm can improve the efficiency and accuracy of resource scheduling of the satellite distance education network, thereby improving the overall system performance of the satellite distance education network.

[0069] In addition, the satellite network's unique broadcasting function demonstrates its unique advantages in this scenario. This one-to-many transmission mode can significantly improve resource allocation efficiency, but the existing resource scheduling methods do not fully utilize the satellite network's natural advantages in broadcast transmission.

[0070] Therefore, designing an effective satellite distance education network resource scheduling strategy is of great practical significance. This requires the scheduling strategy to make full use of the satellite's broadcast characteristics and flexibly respond to centralized resource demands at different time points to achieve efficient services for multiple users, promote educational equity, and enable students in remote areas to enjoy the same educational resources and opportunities as urban students.

[0071] The resource scheduling method provided in this application can be applied to the resource scheduling optimization of satellite distance education networks in remote areas, and is particularly suitable for distance education systems that rely on satellite communications. It can effectively optimize the use of satellite bandwidth and network resources, ensure the efficient transmission and real-time interaction of educational content, and improve the coverage and quality of educational services. In addition, the method can also be integrated into the education resource management platform and intelligent scheduling system to help optimize resource allocation and task scheduling. It is suitable for education content providers and public service platforms to promote the efficient use and fair popularization of education resources.

[0072] In one embodiment, Figure 2 As shown, a resource scheduling method is provided, which is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0073] S201, receiving task requests sent by multiple users, and merging identical requests in the task requests into one task request to obtain a task pool to be scheduled.

[0074] When a user needs to remotely perform a task request from the education center, for example, data transmission of remote sensing images, video conferencing, real-time classroom broadcasting or online homework, the user can send a task request to the server of the education center through the terminal. It is understandable that multiple users can send task requests to the server at the same time or at different times, and the task requests sent by multiple users to the server can be the same or different.

[0075] Therefore, the server can receive task requests sent by multiple users from multiple terminals. After the server receives the task requests, it can merge the same requests from different users into one unit request, that is, one task request. At the same time, the request number attribute of the corresponding task is increased by 1.

[0076] Among them, the method of merging the same requests in the task requests into one task request can be that each task request carries the task and the task type, and the task requests corresponding to the same task type are determined as the same request. Therefore, the same requests can be directly screened out and merged according to the task type corresponding to the task request, ensuring that the task types in the task requests are different, thereby reducing resource redundancy.

[0077] After the same requests in the task requests are merged, the remaining task requests are used as a task pool to be scheduled, and the task pool to be scheduled includes multiple tasks to be processed.

[0078] S202, solving the tasks in the task pool to be scheduled by using a multi-initialization intelligent optimization algorithm to obtain a task scheduling sequence.

[0079] Among them, the multi-initialization intelligent optimization algorithm can be pre-trained, and the tasks in the task pool to be scheduled can be directly input into the multi-initialization intelligent optimization algorithm to obtain the task scheduling sequence output by the multi-initialization intelligent optimization algorithm, wherein the task scheduling sequence can represent the order in which each task is executed.

[0080] The task scheduling sequence can be composed of a set of decimal codes. For example, the tasks in the task pool to be scheduled are: Task = {t1, t2, t3, ..., t n}The task scheduling sequence obtained through the decimal code set is: Task Sequences ={seq1,seq2,...seq n}, in this mapping, the task scheduling sequence seq i It forms a one-to-one relationship with the tasks in the task pool to be scheduled, where seq i Satisfy the condition seq i ∈{1,2,...n-1,n}. Through the decimal encoding method, the task scheduling and sorting problem can be processed and optimized more intuitively and effectively, thereby improving the rational allocation and utilization of resources.

[0081] Optionally, the multivariate initialization intelligent optimization algorithm may select a particle swarm and / or a genetic algorithm to ensure that the optimization process can achieve optimal improvement of system performance by constructing an objective function and corresponding constraints.

[0082] S203: Allocate resources to tasks according to the task scheduling sequence to execute corresponding tasks.

[0083] After obtaining the task scheduling sequence, the server executes the task according to the task scheduling sequence.

[0084] Moreover, after completing the task, the execution result of the task is fed back to the corresponding user, and after completing the task, the execution effects of multiple tasks are comprehensively analyzed to obtain an evaluation result, and based on the evaluation result, the multi-initialization intelligent optimization algorithm is iteratively optimized and updated.

[0085] For example, after completing the task through the task scheduling sequence, the performance of the education center system can be evaluated, and the operation effect of the entire system can be comprehensively analyzed, including key indicators such as task completion rate and resource utilization efficiency. Then, based on the evaluation results, multiple rounds of iterative optimization of the multi-initialization intelligent optimization algorithm are performed to optimize the parameters in the multi-initialization intelligent optimization algorithm, continuously improve the algorithm and system model, and finally achieve the optimal technical solution.

[0086] In the embodiment of the present application, the method of merging the same tasks not only simplifies the structure of the waiting queue, but also reduces redundant requests, improves the scheduling efficiency of educational resources, and avoids resource waste; further, this mechanism can reduce repeated applications for system resources, reduce redundant allocation of resources, and reduce system burden by merging the same task requests, thereby improving the overall bandwidth utilization efficiency of the system. In addition, by solving the task scheduling problem through a multi-initialization intelligent optimization algorithm, the efficiency and accuracy of satellite distance education network resource scheduling can be improved, thereby improving the overall system performance of the satellite distance education network.

[0087] In one embodiment, Figure 3 As shown, the same requests in the task requests are merged into one task request to obtain a task pool to be scheduled, including the following steps:

[0088] S301, obtaining the bandwidth size of each task request, and classifying the task requests according to the bandwidth size of each task request to obtain sorting queues of multiple different bandwidths.

[0089] After receiving the task request, the bandwidth required by each task request is determined, and then the task requests are classified according to the bandwidth.

[0090] For example, before classifying the task requests, four sorting queues with different bandwidths can be initialized first: a low-bandwidth queue, a medium-bandwidth queue, a high-bandwidth queue, and an ultra-high-bandwidth queue. Then, the received task requests are classified. If the bandwidth of the task request is less than or equal to a first preset threshold, the task request is assigned to the low-bandwidth queue; if the bandwidth of the task request is greater than the first preset threshold and less than or equal to the second preset threshold, the task request is assigned to the medium-bandwidth queue; if the bandwidth of the task request is greater than the second preset threshold and less than or equal to the third preset threshold, the task request is assigned to the high-bandwidth queue; if the bandwidth of the task request exceeds the third preset threshold, the task request is assigned to the ultra-high-bandwidth queue.

[0091] Among them, the first preset threshold can be 5, the second preset threshold can be 10, and the third preset threshold can be 15; it should be noted that the embodiment of the present application does not limit the specific values ​​of the first preset threshold, the second preset threshold and the third preset threshold, and can be set according to actual conditions.

[0092] Then, a low bandwidth queue, a medium bandwidth queue, a high bandwidth queue, and an ultra-high bandwidth queue are used as the result of request classification, that is, sorted queues of multiple different bandwidths.

[0093] S302: Merge the task requests for the same resource in each sorting queue into one task request.

[0094] The implementation method of merging the task requests for the same resources in each sorting queue into one task request can be: after the classification is completed, the tasks requesting the same resources in each sorting queue can be identified, and in each sorting queue, the task requests corresponding to the tasks requesting the same resources are merged into one unit request, that is, as one task request, eliminating the redundancy of the same requests.

[0095] S303, integrating the merged sorting queues to obtain a task pool to be scheduled.

[0096] After the merging is completed, the four queues, namely, the low bandwidth queue, the medium bandwidth queue, the high bandwidth queue, and the ultra-high bandwidth queue, may be integrated into a final queue.

[0097] There is no limitation on the integration method. For example, random integration is possible: {high bandwidth queue, medium bandwidth queue, ultra-high bandwidth queue, low bandwidth queue}; integration can also be performed based on priority, for example, integration is performed in a descending order of bandwidth: {ultra-high bandwidth queue, high bandwidth queue, medium bandwidth queue, low bandwidth queue}.

[0098] For example, the sorting queues include low bandwidth queue, medium bandwidth queue, high bandwidth queue and ultra-high bandwidth queue. Figure 4 As shown, Figure 4 The figure is a flowchart of a simplified task queue structure.

[0099] In one embodiment, the specific process of merging and integrating task requests can be: 1. Create four empty queues: first initialize four empty queues for task merging; create a new queue to store the merged results; and store the task requests in the corresponding queues according to the bandwidth size, and then traverse each queue separately to merge the tasks requesting the same educational resources into one unit task. (That is, the request number attribute of the task is increased by 1), and finally insert the tasks of the four queues into the new queue. Finally, a new queue is obtained, which contains all the tasks of the four original queues.

[0100] In the embodiment of the present application, the user attributes of the tasks are merged to reduce repeated applications for system resources, reduce redundant allocation of resources, and reduce the burden on the system, thereby improving the overall bandwidth utilization efficiency of the system.

[0101] In an exemplary embodiment, the multivariate initialization intelligent optimization algorithm is a multivariate initialization particle swarm-genetic hybrid optimization algorithm (Multivarlate initialization PSO-GA strategy, MIPGS); Figure 5 As shown, the tasks in the task pool to be scheduled are solved by a multi-initialization intelligent optimization algorithm to obtain a task scheduling sequence, including the following steps:

[0102] S501, generating an initial population through a diversified initial strategy; the initial population includes a plurality of individuals, each of which corresponds to an initial scheduling strategy for tasks in the task pool to be scheduled.

[0103] The multivariate initialization technique is used to generate a diverse initial population. The choice of the initial solution will have a direct impact on the quality of the solution. In order to enhance the performance of the particle swarm-genetic optimization algorithm, the applicant adopted a multivariate initialization strategy in the process of exploring the initial solution, aiming to increase the diversity of the population, help better explore the solution space, and improve the efficiency of the algorithm and the quality of the solution.

[0104] In the initialization technology, random initialization is a simple and direct method, which generates the initial population by randomly selecting points in the solution space. Although this method is easy to implement, it may cause uneven distribution of the population in the solution space, thereby affecting the diversity and efficiency of the algorithm. To improve this, heuristic initialization can be applied to optimization problems, especially by using crossover and mutation operations such as genetic algorithms to generate more optimized initial solutions. Therefore, in this application, heuristic methods can be used to generate task scheduling sequences to improve the quality of the initial solution and algorithm performance. In addition, this application also explores initialization methods based on specific rules. For example, sorting tasks according to urgency can ensure the efficiency of processing high-priority tasks and support the timely completion of key tasks. At the same time, a sorting method based on task bandwidth requirements is introduced, so that tasks with higher resource requirements can obtain required resources first, thereby reducing delays caused by insufficient resources.

[0105] Based on this, the diversified initialization strategy in this application can combine three initialization methods: random initialization, heuristic algorithm initialization, and specific rule initialization. Each method targets different problem characteristics and together builds a multi-faceted and dynamic initial population framework.

[0106] Therefore, the method of generating the initial population through the diversified initial strategy can be: generating the first population according to the random initialization method; generating the second population according to the crossover and mutation manipulation in the genetic algorithm; and generating the third population based on the initialization method based on specific rules; finally, determining the first population, the second population and the third population as the initial population.

[0107] Among them, the method of determining the third group based on the initialization method of specific rules can be: determining the third group by sorting according to the urgency of the tasks, and determining the third group based on the sorting method of the bandwidth requirements of the tasks. For example, the task request carries task attributes, and the correspondence between the pre-set task attributes and the task urgency can be used to determine the urgency of the task corresponding to the task request, and the most urgent task is set to be executed first, the least urgent task is executed last, and so on, to determine the third group; the resource sequence for executing the corresponding task can be determined according to the task attributes, and the task with the highest resource demand is set to obtain the required resources first, and the task with the lowest resource demand is set to obtain the possible resources last. In this way, the third group is generated.

[0108] It should be noted that the sizes of the first population, the second population and the third population are not limited and can be determined according to actual conditions. The size of the population is the number of particles in the population, and each particle can be represented as a task scheduling sequence of all tasks in the task pool to be scheduled.

[0109] S502, iterating the multi-initialized particle swarm-genetic hybrid optimization algorithm according to the initial population to obtain a task scheduling sequence.

[0110] Since the initial population represents a variety of initial task scheduling sequences of all tasks in the task pool to be scheduled, the multi-initialized particle swarm-genetic hybrid optimization algorithm can be iterated based on the initial population to determine the global optimal individual, that is, the optimal task scheduling sequence of the tasks in the task pool to be scheduled, and the optimal task scheduling sequence is determined as the task scheduling sequence.

[0111] In the embodiment of the present application, by combining a diversified initialization strategy, the diversity of the initial population is enriched, and the probability of the algorithm finding the global optimal solution is improved. This comprehensive method effectively combines the advantages of different strategies, enriching the initial population while increasing the probability of finding the global optimal solution, thereby improving resource scheduling efficiency.

[0112] In an exemplary embodiment, Figure 6 As shown, according to the initial population, the multi-initialized particle swarm-genetic hybrid optimization algorithm is iterated to obtain the task scheduling sequence, including the following steps:

[0113] S601, calculating the fitness values ​​of multiple individuals according to the initial population.

[0114] The objective function and corresponding constraints are pre-constructed in the multi-initialized particle swarm-genetic hybrid optimization algorithm. The initial scheduling strategy corresponding to the individuals in the initial population and the required resources for the task corresponding to the task request can be substituted into the objective function to obtain the objective function value, that is, the fitness value of the individual.

[0115] Optionally, each task can correspond to a weight, and the weight is related to the resources required for the task. For example, the higher the resources required for the task, the greater the weight. The sum of the products of all the task scheduling orders in the initial scheduling strategy and the weights of the corresponding tasks is determined as the objective function. In this way, taking an individual as an example, the corresponding initial scheduling strategy can be directly substituted into the objective function to obtain the fitness value of the corresponding individual.

[0116] S602, sorting the multiple fitness values, and according to the fitness value sorting result, using the particle swarm algorithm to process the individuals with a preset proportion of higher fitness, and using the genetic algorithm to process the remaining individuals with lower fitness, to obtain an updated population.

[0117] After obtaining the fitness values ​​of all individuals in the initial population, all fitness values ​​can be sorted, and then individual optimization and selection can be performed based on the fitness value sorting results.

[0118] Specifically, the preset ratio may be 50%. Accordingly, the first 50% of individuals with higher fitness may be optimized using a particle swarm algorithm, and the remaining 50% of individuals with lower fitness may be optimized using a genetic algorithm.

[0119] Among them, the way to use the particle swarm algorithm to process the first 50% of individuals with higher fitness can be to update the individual scheduling strategy using the speed and position update method in the particle swarm algorithm; the way to use the genetic algorithm to process the remaining 50% of individuals with lower fitness can be to update the individual scheduling strategy in sequence using the selection operation, crossover operation, mutation operation and correction operation in the genetic algorithm.

[0120] It can be understood that updating the population is to update the scheduling strategy corresponding to the individuals in the population, and the value of the preset ratio is not limited and can be set according to demand.

[0121] S603: Determine a task scheduling sequence according to the updated population.

[0122] In one embodiment, a task scheduling sequence is determined based on an updated population, including: if the multi-initialized particle swarm-genetic hybrid optimization algorithm does not meet the iteration termination condition, then performing the step of iterating the multi-initialized particle swarm-genetic hybrid optimization algorithm through the updated population; if the multi-initialized particle swarm-genetic hybrid optimization algorithm meets the preset iteration termination condition, then outputting the optimal individual in the updated population; and then determining the scheduling strategy corresponding to the optimal individual as the task scheduling strategy.

[0123] After obtaining the updated population, check whether the algorithm meets the iteration termination condition. If the multi-initialized particle swarm-genetic hybrid optimization algorithm meets the iteration termination condition, the algorithm terminates and outputs the optimal individual of the current population, that is, the scheduling strategy corresponding to the optimal individual is determined as the task scheduling strategy; if the multi-initialized particle swarm-genetic hybrid optimization algorithm does not meet the iteration termination condition, the multi-initialized particle swarm-genetic hybrid optimization algorithm is iterated through the updated population until the algorithm meets the iteration termination condition.

[0124] Optionally, the iterative termination condition of the multi-initialized particle swarm-genetic hybrid optimization algorithm may be that the number of algorithm iterations reaches a preset number of iterations, for example, 500 iterations of the multi-initialized particle swarm-genetic hybrid optimization algorithm are the iterative termination condition; the iterative termination condition of the multi-initialized particle swarm-genetic hybrid optimization algorithm may also be that the objective function of the multi-initialized particle swarm-genetic hybrid optimization algorithm reaches a preset threshold.

[0125] In one embodiment, Figure 7 As shown, Figure 7 Flowchart of the multi-initialized particle swarm-genetic hybrid optimization algorithm.

[0126] like Figure 8 As shown, Figure 8 The satellite distance education task delivery and scheduling model is mainly divided into four stages. The first stage: the task submission stage, users submit tasks to the teaching center to form a task pool, and concentrate the tasks waiting for scheduling and execution. The second stage: the same request merging stage, the same requests from different users are merged into a unit request. The third stage: the task scheduling optimization processing stage, the teaching center uses a multi-initialized particle swarm-genetic hybrid optimization method to optimize the task scheduling problem, and appropriately classify and sort the merged task sequence. The fourth stage: the task execution stage, resources are allocated according to the task scheduling sequence, tasks are executed, and the results are fed back to the user after the task is completed.

[0127] The present application aims to solve the key problems of uneven resource allocation, low scheduling efficiency, lack of dynamic adjustment capability and low resource utilization in the existing satellite distance education network resource scheduling. By introducing advanced resource scheduling optimization algorithms and dynamic adjustment mechanisms, satellite communication resources can be flexibly allocated and adjusted according to changes in education needs and network environment, significantly improving the resource utilization efficiency and task processing speed of the system. The present application has significant advantages in the following aspects: (1) Improving resource utilization efficiency: By optimizing the resource scheduling algorithm, satellite communication resources are utilized to the maximum extent, resource waste is avoided, and appropriate resource support is ensured for each task. (2) Improving scheduling response speed: The present invention can quickly respond to changes in task requirements and improve the service quality of the distance education system. (3) Enhancing dynamic adaptability: The present invention has dynamic adjustment capabilities and can adjust resource allocation strategies according to real-time network status and task requirements to ensure that the system can operate efficiently in complex environments. (4) Supporting a wide range of application scenarios: The present invention is not only applicable to distance education systems in remote areas, but can also be extended to other application scenarios that rely on satellite communications, such as emergency communications, public service platforms, etc., and has broad application prospects.

[0128] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0129] Based on the same inventive concept, the embodiment of the present application also provides a resource scheduling device for implementing the resource scheduling method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more resource scheduling device embodiments provided below can refer to the limitations on the resource scheduling method above, and will not be repeated here.

[0130] In an exemplary embodiment, Fig. 9 As shown, a resource scheduling device 900 is provided, comprising: a receiving module 901, a solving module 902 and a resource allocation module 903, wherein:

[0131] The receiving module 901 is used to receive task requests sent by multiple users, and merge the same requests in the task requests into one task request to obtain a task pool to be scheduled.

[0132] The solving module 902 is used to solve the tasks in the task pool to be scheduled by using a multi-initialization intelligent optimization algorithm to obtain a task scheduling sequence.

[0133] The resource allocation module 903 is used to allocate resources to tasks according to the task scheduling sequence to execute the corresponding tasks.

[0134] In an exemplary embodiment, the receiving module 901 is specifically used to obtain the bandwidth size of each task request; and classify the task requests according to the bandwidth size of each task request to obtain sorting queues with multiple different bandwidths; then merge the task requests for the same resources in each sorting queue into one task request; integrate the merged sorting queues to obtain a pool of tasks to be scheduled.

[0135] In an exemplary embodiment, the receiving module 901 is specifically used to allocate the task request to a low bandwidth queue if the bandwidth of the task request is less than or equal to a first preset threshold; allocate the task request to a medium bandwidth queue if the bandwidth of the task request is greater than the first preset threshold and less than or equal to a second preset threshold; allocate the task request to a high bandwidth queue if the bandwidth of the task request is greater than the second preset threshold and less than or equal to a third preset threshold; and allocate the task request to an ultra-high bandwidth queue if the bandwidth of the task request exceeds the third preset threshold.

[0136] In an exemplary embodiment, the multivariate initialization intelligent optimization algorithm is a multivariate initialization particle swarm-genetic hybrid optimization algorithm; the solution module 902 is specifically used to generate an initial population through a diversified initial strategy; the initial population includes multiple individuals, each individual corresponds to an initial scheduling strategy for tasks in the task pool to be scheduled; and based on the initial population, the multivariate initialization particle swarm-genetic hybrid optimization algorithm is iterated to obtain a task scheduling sequence.

[0137] In an exemplary embodiment, the solution module 902 is specifically used to: generate a first population according to a random initialization method; generate a second population according to crossover and mutation operations in a genetic algorithm; generate a third population based on an initialization method based on specific rules; and finally determine the first population, the second population, and the third population as initial populations.

[0138] In an exemplary embodiment, the solution module 902 is further configured to determine the third group by sorting the tasks according to their urgency, and to determine the third group based on the sorting method of the tasks for bandwidth requirements.

[0139] In an exemplary embodiment, the solution module 902 is specifically used to calculate the fitness values ​​of multiple individuals based on the initial population; then sort the multiple fitness values, and according to the fitness value sorting results, use the particle swarm algorithm to process the individuals with a preset proportion of higher fitness, and use the genetic algorithm to process the remaining individuals with lower fitness, to obtain an updated population; finally, determine the task scheduling sequence based on the updated population.

[0140] In an exemplary embodiment, the solution module 902 is specifically used to, if the multi-initialized particle swarm-genetic hybrid optimization algorithm does not meet the iteration termination condition, perform the step of iterating the multi-initialized particle swarm-genetic hybrid optimization algorithm through the updated population; if the multi-initialized particle swarm-genetic hybrid optimization algorithm meets the preset iteration termination condition, output the optimal individual in the updated population; and determine the scheduling strategy corresponding to the optimal individual as the task scheduling strategy.

[0141] In an exemplary embodiment, the apparatus 900 further includes:

[0142] The feedback module is used to feed back the execution result of the task to the corresponding user after the task is completed.

[0143] In an exemplary embodiment, the apparatus 900 further includes:

[0144] The analysis module is used to conduct a comprehensive analysis of the execution effects of multiple tasks after the tasks are completed to obtain evaluation results;

[0145] The optimization module is used to iteratively optimize the multi-initialization intelligent optimization algorithm according to the evaluation results and update the multi-initialization intelligent optimization algorithm.

[0146] Each module in the resource scheduling device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0147] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.10As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store resource scheduling data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a resource scheduling method is implemented.

[0148] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0149] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0150] The implementation principles and technical effects of each step implemented by the processor in this embodiment are similar to the principles of the above-mentioned resource scheduling method, and will not be repeated here.

[0151] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0152] The implementation principles and technical effects of the steps implemented when the computer program in this embodiment is executed by the processor are similar to the principles of the above-mentioned resource scheduling method, and will not be repeated here.

[0153] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0154] The implementation principles and technical effects of the steps implemented when the computer program in this embodiment is executed by the processor are similar to the principles of the above-mentioned resource scheduling method, and will not be repeated here.

[0155] It should be noted that the data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties.

[0156] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processors involved in each embodiment provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., but are not limited thereto.

[0157] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A resource scheduling method, characterized in that: The method comprises: Receive task requests sent by multiple users, and merge the same requests in the task requests into one task request to obtain a task pool to be scheduled; Solving the tasks in the task pool to be scheduled by a multi-element initialization intelligent optimization algorithm to obtain a task scheduling sequence; Resources are allocated to the tasks according to the task scheduling sequence to execute the corresponding tasks.

2. The method according to claim 1, characterized in that The step of merging the same requests in the task requests into one task request to obtain a task pool to be scheduled includes: Get the bandwidth size requested by each task; Classifying the task requests according to the bandwidth size of each task request to obtain a plurality of sorting queues with different bandwidths; Merge the task requests for the same resources in each sorting queue into one task request; The merged sorting queues are integrated to obtain the task pool to be scheduled.

3. The method according to claim 2, characterized in that The classifying the task requests according to the bandwidth size of each task request includes: If the bandwidth of the task request is less than or equal to a first preset threshold, allocating the task request to a low bandwidth queue; If the bandwidth of the task request is greater than a first preset threshold and less than or equal to a second preset threshold, the task request is allocated to a medium bandwidth queue; If the bandwidth of the task request is greater than the second preset threshold and less than or equal to the third preset threshold, the task request is allocated to the high bandwidth queue; If the bandwidth of the task request exceeds a third preset threshold, the task request is allocated to an ultra-high bandwidth queue.

4. The method according to any one of claims 1 to 3, characterized in that: The multivariate initialization intelligent optimization algorithm is a multivariate initialization particle swarm-genetic hybrid optimization algorithm; the multivariate initialization intelligent optimization algorithm is used to solve the tasks in the task pool to be scheduled to obtain a task scheduling sequence, including: Generate an initial population through a diversified initial strategy; the initial population includes a plurality of individuals, each individual corresponds to an initial scheduling strategy for tasks in the task pool to be scheduled; According to the initial population, the multivariate initialized particle swarm-genetic hybrid optimization algorithm is iterated to obtain the task scheduling sequence.

5. The method according to claim 4, characterized in that The generating of the initial population by using a diversified initial strategy includes: Generate the first population by random initialization; Generate a second population according to the crossover and mutation operations in the genetic algorithm; Based on the initialization method of specific rules, the third population is generated; The first population, the second population and the third population are determined as the initial populations.

6. The method according to claim 5, characterized in that The initialization method based on specific rules determines the third population, including: The third group is determined by sorting the tasks according to their urgency, and the third group is determined based on the sorting method of the tasks for bandwidth requirements.

7. The method according to claim 4, characterized in that The step of iterating the multivariate initialized particle swarm-genetic hybrid optimization algorithm according to the initial population to obtain the task scheduling sequence includes: Calculating the fitness values ​​of the multiple individuals according to the initial population; Sort multiple fitness values, and according to the fitness value sorting results, use the particle swarm algorithm to process the individuals with higher fitness and the preset proportion, and use the genetic algorithm to process the remaining individuals with lower fitness, to obtain an updated population; The task scheduling sequence is determined according to the updated population.

8. The method according to claim 7, characterized in that Determining the task scheduling sequence according to the updated population includes: If the multi-initialized particle swarm-genetic hybrid optimization algorithm does not satisfy the iteration termination condition, performing a step of iterating the multi-initialized particle swarm-genetic hybrid optimization algorithm through the updated population; If the multi-initialized particle swarm-genetic hybrid optimization algorithm meets the preset iteration termination condition, the optimal individual in the updated population is output; The scheduling strategy corresponding to the optimal individual is determined as the task scheduling strategy.

9. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: After the task is executed, the execution result of the task is fed back to the corresponding user.

10. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: After executing the tasks, a comprehensive analysis is performed on the execution effects of multiple tasks to obtain evaluation results; According to the evaluation result, the multi-initialization intelligent optimization algorithm is iteratively optimized to update the multi-initialization intelligent optimization algorithm.

Images