Network resource scheduling method and device, equipment, storage medium and product

Abstract

The invention discloses a network resource scheduling method and device, equipment, a storage medium and a product, and the method comprises the steps: obtaining the network slicing demand information of a target network, carrying out the slicing operation of the target network according to the network slicing demand information, and obtaining a plurality of different types of network slicing demands; classifying network traffic of the target network according to business service quality requirements, slice priorities and traffic characteristics to obtain a traffic classification result of the target network; and performing resource scheduling on the target network according to the flow classification result and the network slicing requirement. Performing priority division of the flow based on QoS parameters such as the bandwidth requirement, the time delay requirement and the priority of the flow; according to different flow characteristics and business demand optimization classification rules, a resource allocation strategy is adjusted in real time in a dynamically changing network environment, it is ensured that high-priority flow is processed in time, and network load fluctuation and business demand changes can be coped with in real time.

Description

Technical Field

[0001] The present invention relates to the field of network scheduling technology, and in particular to a network resource scheduling method, device, equipment, storage medium and product. Background Art

[0002] With the rapid development of 5G technology, private network applications have gradually become an important communication method, especially in the fields of industry, transportation, and medical care, where the requirements for network reliability, low latency, high bandwidth and other performance are becoming more and more stringent. In order to solve the shortcomings of traditional network architecture in these high-demand scenarios, 5G networks have introduced network slicing technology, which divides the physical network into multiple virtual networks to provide customized services for different business needs. Network slicing can achieve efficient allocation of network resources, improve network performance, support the parallel operation of various business flows, and ensure that each slice can operate independently in the network according to the predetermined quality of service (QoS) requirements.

[0003] Existing network resource scheduling methods lack sufficient flexibility in the face of dynamically changing network environments, and most of them are static strategies based on priorities, which cannot respond to network load fluctuations and changes in business needs in real time. Summary of the invention

[0004] The present invention provides a network resource scheduling method, device, equipment, storage medium and product, which prioritize flows based on QoS parameters such as bandwidth requirements, delay requirements and priority of flows; optimize classification rules according to different traffic characteristics and business requirements, and adjust resource allocation strategies in real time in a dynamically changing network environment to ensure that high-priority flows are processed in a timely manner, and can respond to network load fluctuations and changes in business requirements in real time.

[0005] In order to achieve the above object, an embodiment of the present invention provides a network resource scheduling method, including:

[0006] Obtain network slicing requirement information of a target network, and perform a slicing operation on the target network according to the network slicing requirement information to obtain several different types of network slicing requirements;

[0007] Classify the network traffic of the target network according to the business service quality requirements, slice priority and traffic characteristics, and obtain the flow classification result of the target network;

[0008] According to the flow classification results and the network slicing requirements, resources are scheduled for the target network.

[0009] As an improvement of the above solution, the acquiring network slicing requirement information of the target network, performing a slicing operation on the target network according to the network slicing requirement information, and obtaining several different types of network slicing requirements, including:

[0010] Performing demand analysis on different 5G private network services of the target network to obtain network slicing demand information of the target network; wherein the network slicing demand information includes bandwidth demand, latency requirement, and service quality parameters of reliability;

[0011] According to the network slicing requirement information, a slicing operation is performed on the target network to obtain several different types of network slicing requirements.

[0012] As an improvement of the above solution, the network traffic of the target network is classified according to the business service quality requirements, slice priority and traffic characteristics to obtain the flow classification result of the target network, including:

[0013] Acquire network traffic data of the target network, and generate traffic characteristics of the target network according to the network traffic data; wherein the network traffic data includes bandwidth requirements, delay requirements, and dynamic changes of traffic;

[0014] Classify the network traffic of the target network according to the service quality requirements and slice priorities to obtain different service flows;

[0015] Priority classification is performed according to the delay sensitivity and importance of the service flow and the traffic characteristics, and the flow classification result of the target network.

[0016] As an improvement of the above solution, the resource scheduling of the target network according to the flow classification result and the network slicing requirement includes:

[0017] Generate a resource allocation strategy for the target network according to the flow classification result and the network slicing requirement;

[0018] According to the flow classification result, the priority and bandwidth requirement of each flow are determined, and according to the priority and bandwidth requirement and the resource allocation strategy, resources are scheduled for the target network.

[0019] As an improvement of the above solution, after performing resource scheduling on the target network, the method further includes:

[0020] The resource scheduling result is evaluated according to the service quality index, and the resource allocation strategy of the target network is adjusted according to the evaluation result.

[0021] As an improvement of the above solution, the objective function of the resource allocation strategy is:

[0022]

[0023] Where U is the overall utility function of the system, w i is the weight of flow i, indicating the priority of the flow; R i is the resource allocated to flow i; N is the total number of flows.

[0024] In order to achieve the above object, an embodiment of the present invention provides a network resource scheduling device, including:

[0025] A slicing requirement acquisition module, used to obtain network slicing requirement information of a target network, and perform a slicing operation on the target network according to the network slicing requirement information to obtain several different types of network slicing requirements;

[0026] A network traffic classification module is used to classify the network traffic of the target network according to the business service quality requirements, slice priority and traffic characteristics, and obtain the flow classification result of the target network;

[0027] A network resource scheduling module is used to schedule resources for the target network according to the flow classification results and the network slicing requirements.

[0028] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a network resource scheduling device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the above-mentioned network resource scheduling method when executing the computer program.

[0029] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned network resource scheduling method.

[0030] To achieve the above objective, an embodiment of the present invention further provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the steps of the above network resource scheduling method.

[0031] Compared with the prior art, the network resource scheduling method, device, equipment, storage medium and product disclosed in the embodiment of the present invention obtain network slicing demand information of the target network, and perform slicing operations on the target network according to the network slicing demand information to obtain several different types of network slicing requirements; classify the network traffic of the target network according to the business service quality requirements, slicing priority and traffic characteristics to obtain the flow classification result of the target network; and schedule resources for the target network according to the flow classification result and the network slicing requirements. Prioritize flows based on QoS parameters such as bandwidth requirements, latency requirements and priority of flows; optimize classification rules according to different traffic characteristics and business requirements, and adjust resource allocation strategies in real time in a dynamically changing network environment to ensure that high-priority flows are processed in a timely manner, and can respond to network load fluctuations and changes in business requirements in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a flowchart of a network resource scheduling method provided by an embodiment of the present invention;

[0033] Figure 2 It is a structural diagram of a network resource scheduling device provided by an embodiment of the present invention;

[0034] Figure 3 It is a structural block diagram of a network resource scheduling device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0036] It should be noted that the terms "comprises" and "specifically" and any variations of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0037] See also Figure 1 , Figure 1 1 is a flow chart of a network resource scheduling method provided by an embodiment of the present invention, the network resource scheduling method comprising:

[0038] S1, obtaining network slicing requirement information of a target network, and performing a slicing operation on the target network according to the network slicing requirement information to obtain several different types of network slicing requirements;

[0039] S2, classifying the network traffic of the target network according to the service quality requirements, slice priorities and traffic characteristics, and obtaining a traffic classification result of the target network;

[0040] S3: Perform resource scheduling on the target network according to the flow classification result and the network slicing requirement.

[0041] Exemplarily, the network resource scheduling method described in the embodiment of the present invention can be implemented by a network traffic server, which can exchange information with the target user. The network traffic server obtains the network slicing requirement information of the target network, and performs slicing operations on the target network according to the network slicing requirement information to obtain several different types of network slicing requirements; classifies the network traffic of the target network according to the business service quality requirements, slicing priorities and traffic characteristics to obtain the flow classification results of the target network; and performs resource scheduling for the target network according to the flow classification results and the network slicing requirements. Prioritize flows based on QoS parameters such as bandwidth requirements, latency requirements and priority of flows; optimize classification rules according to different traffic characteristics and business requirements, and adjust resource allocation strategies in real time in a dynamically changing network environment to ensure that high-priority flows are processed in a timely manner, and can respond to network load fluctuations and changes in business requirements in real time.

[0042] Specifically, the step S1 includes:

[0043] S11, performing demand analysis on different 5G private network services of the target network to obtain network slicing demand information of the target network; wherein the network slicing demand information includes bandwidth demand, latency requirement, and service quality parameters of reliability;

[0044] S12: Perform a slicing operation on the target network according to the network slicing requirement information to obtain several different types of network slicing requirements.

[0045] Exemplarily, by analyzing the needs of different 5G private network services, including bandwidth requirements, latency requirements, reliability and other QoS (quality of service) parameters, the characteristics of different service flows are identified, and network slice demand information is obtained. According to the network slice demand information, a centralized network resource pool is constructed. The resources in the resource pool include computing resources, storage resources, bandwidth resources, latency and network topology, etc. The resource pool is dynamically adjusted according to the needs of different slices. The resource pool has a dynamic adjustment function. When the network load changes and the service demand changes, the resource allocation in the resource pool is adjusted in time to ensure the efficient use of network slice resources. The embodiment of the present invention constructs a dynamically adjusted resource pool by analyzing the needs of different 5G private network services (such as QoS parameters such as bandwidth, latency, reliability, etc.) to optimize resource allocation and dynamic scheduling. This method of constructing a resource pool based on slice demand is more flexible and real-time than traditional static resource pool allocation.

[0046] Specifically, the step S2 includes:

[0047] S21, obtaining network traffic data of the target network, and generating traffic characteristics of the target network according to the network traffic data; wherein the network traffic data includes bandwidth requirements, delay requirements, and dynamic changes of traffic;

[0048] S22, classifying the network traffic of the target network according to the service quality requirements and the slice priority to obtain different service flows;

[0049] S23, performing priority classification according to the delay sensitivity and importance of the service flow and the traffic characteristics, and obtaining the flow classification result of the target network.

[0050] Exemplarily, network traffic data is collected in real time, including traffic bandwidth requirements, latency requirements, dynamic changes in traffic, etc. Traffic is classified according to the QoS requirements of each service flow and the priority of the network slice. For example, real-time traffic (such as voice, video conferencing, etc.) and non-real-time traffic (such as large data transmission, software updates, etc.) need to be treated differently. Priority classification is performed based on the latency sensitivity and importance of the service flow to ensure that high-priority flows (such as emergency medical care, industrial control, etc.) can be allocated resources first. For example, machine learning or deep learning technology is used to optimize and adjust flow classification rules based on historical data and network status to improve classification accuracy and efficiency. Alternatively, a traffic prediction model based on deep learning is used to improve the accuracy of flow classification, and more accurate flow classification and priority division are performed through an integrated learning method combined with traffic characteristics.

[0051] Assume that there are multiple flows in the network, and the bandwidth requirement of the i-th flow is B i , the delay requirement is D i ., priority is Pi , and the QoS requirements of each flow are described by parameters. In order to classify flows according to these parameters, we first define a flow classification function f(B, D, P), which will output the flow category based on the flow's bandwidth requirements, delay requirements, and priority. For each flow i, its classification result C i Determined by the following formula:

[0052] C i =f(B i ,D i ,P i )=1ifB i ≥B threshold andD i ≤D threshold P i =P high ,

[0053] C i =f(B i ,D i ,P i )=2ifB i ≥B threshold andD i ≤DthresholdandP i =P medium ,

[0054] C i =f(B i ,D i ,P i )=3ifB i <B thresholdand andD i >D threshold P i =P low ,

[0055] Among them, B threshold is the bandwidth threshold, D threshold is the delay threshold, P high , P medium and P low Representing the priority categories of high priority, medium priority and low priority flows respectively, the flow category is determined by comparing the actual bandwidth requirements, latency requirements and priority of each flow. The flow classification will be prioritized according to different business requirements, such as real-time flow, non-real-time flow and low priority flow. High priority flows will receive greater resource guarantees in terms of latency and bandwidth allocation, ensuring their priority processing in the network. This method makes it easy to clearly classify and assign priorities to different flows, thereby optimizing the efficiency of network resource allocation.

[0056] In order to optimize the flow classification process, especially how to classify flows more efficiently in large-scale networks, machine learning technology is used to further improve the accuracy of flow classification. In the flow classification process, the machine learning model helps to identify different types of flows and adjust the flow classification rules through optimization algorithms. Specifically, a deep neural network (DNN) model is used to fit the relationship between flow classification. Assume that we have N training samples, each sample is {B i ,D i ,P i}, where B i , D i and P i is the bandwidth, delay and priority of the i-th flow, and the goal is to predict the category of each flow through the model f(B,D,P).

[0057] To train this deep neural network model, the loss function LLL is defined as the error between the predicted value and the true value:

[0058]

[0059] in, is the flow category predicted by the neural network, For the actual category, the loss function optimizes the flow classification model by minimizing the prediction error.

[0060] During the network training process, the model parameters are optimized through the back propagation algorithm to minimize the loss function, thereby obtaining a model that can efficiently classify according to bandwidth, latency and priority. Through this model, the network can automatically adjust the classification rules according to historical traffic data and network status to adapt to the dynamically changing network environment and business needs. By using deep learning technology, the accuracy of flow classification can be further improved, especially in complex network environments, and large-scale traffic in the network can be better handled.

[0061] In addition, a key challenge in the flow classification process is how to dynamically optimize the classification rules based on the real-time network status and traffic characteristics. In order to meet this challenge, an ensemble learning method is introduced to improve the stability and accuracy of flow classification by combining multiple basic classifiers. Assume that there are multiple basic classifiers C1, C2, ..., C k , the prediction result of each classifier is Final flow classification result

[0062] The embodiments of the present invention can adjust the resource allocation strategy in real time in a dynamically changing network environment, ensuring that high-priority flows are processed in a timely manner, while avoiding the limitations of traditional methods in complex scenarios. Through this optimization solution, not only the utilization efficiency of network resources is improved, but also the overall performance of 5G private networks in different business scenarios is significantly improved, meeting the strict requirements for network reliability and low latency.

[0063] Specifically, the step S3 includes:

[0064] S31, generating a resource allocation strategy for the target network according to the flow classification result and the network slicing requirement;

[0065] S32, determining the priority and bandwidth requirement of each flow according to the flow classification result, and scheduling resources for the target network according to the priority and bandwidth requirement and the resource allocation strategy.

[0066] Exemplarily, the allocation of network resources is dynamically adjusted through the flow classification results. For example, for low-priority flows, they are scheduled when resources are abundant, while for high-priority flows, it is necessary to ensure that key resources such as latency and bandwidth are allocated first. Based on the real-time network status (such as traffic load, link quality, changes in slice resource requirements, etc.), the resource scheduling strategy is dynamically adjusted to ensure that high-priority flows are processed in a timely manner and avoid congestion. The reinforcement learning algorithm is introduced to allow the scheduling system to autonomously optimize and learn according to the network status and traffic changes, and continuously improve the scheduling efficiency. The load balancing algorithm is introduced during the scheduling process to ensure that the traffic load between different network slices is balanced to avoid overloading a certain slice. In addition, the delay control mechanism must ensure that key business flows can meet QoS requirements under any circumstances. Dynamic scheduling and resource allocation are the core of the entire solution. Its purpose is to achieve efficient and dynamic allocation of network resources based on the flow classification results and the needs of network slices, thereby ensuring that the QoS requirements of various types of flows are met. In order to achieve this goal, it is necessary to combine the real-time network load, traffic characteristics and slice requirements for accurate scheduling and resource allocation. Specifically, dynamic scheduling needs to be based on the flow classification results. and network slicing requirements R slice To adjust the allocation strategy of each network resource, determine the priority and bandwidth requirements of the flow according to the classification results of each flow, and dynamically adjust the allocation ratio of various resources in the network resource pool based on these priorities and bandwidth requirements.

[0067] Specifically, the objective function of the resource allocation strategy is:

[0068]

[0069] Where U is the overall utility function of the system, w iis the weight of flow i, indicating the priority of the flow; R i is the resource allocated to flow i; N is the total number of flows. By maximizing the overall utility function, it can be ensured that high-priority flows get more resources to meet their QoS requirements. At the same time, the dynamic adjustment of the resource pool can be achieved through the following constraints:

[0070]

[0071] Among them, R total is the total amount of resources in the network resource pool, ensuring that resource allocation does not exceed the total resources;

[0072] R i ≥QoS i ,

[0073] Among them, QoS i is the minimum QoS requirement of flow i, ensuring that the minimum requirement of each flow is met.

[0074] Further, after performing resource scheduling on the target network, the method further includes:

[0075] S4, evaluating the resource scheduling result according to the service quality index, and adjusting the resource allocation strategy of the target network according to the evaluation result.

[0076] For example, a traffic monitoring system is deployed to track the resource usage, traffic changes and network load of network slices in real time. The system needs to monitor the overall performance of the network, including bandwidth, latency, packet loss rate, etc.; evaluate the scheduling effect according to QoS indicators, including latency, bandwidth occupancy, packet loss, etc. If the QoS of some flows does not meet the standards, dynamic adjustments are required; according to the monitoring and evaluation results, the resource pool allocation strategy and flow classification rules are adjusted to form a closed-loop control mechanism to improve the system's adaptive capabilities.

[0077] A network resource scheduling method disclosed in an embodiment of the present invention obtains network slicing demand information of a target network, performs slicing operations on the target network according to the network slicing demand information, and obtains several different types of network slicing demands; classifies the network traffic of the target network according to the service quality requirements, slicing priorities, and traffic characteristics, and obtains the flow classification results of the target network; and performs resource scheduling on the target network according to the flow classification results and the network slicing demand. Prioritize flows based on QoS parameters such as flow bandwidth requirements, latency requirements, and priorities; optimize classification rules according to different traffic characteristics and business requirements, and adjust resource allocation strategies in real time in a dynamically changing network environment to ensure that high-priority flows are processed in a timely manner, and can respond to network load fluctuations and changes in business requirements in real time.

[0078] See also Figure 2 , Figure 2 1 is a schematic diagram of the structure of a network resource scheduling device 10 provided in an embodiment of the present invention. The network resource scheduling device 10 includes:

[0079] A slice requirement acquisition module 11 is used to obtain network slice requirement information of a target network, and perform a slice operation on the target network according to the network slice requirement information to obtain several different types of network slice requirements;

[0080] The network traffic classification module 12 is used to classify the network traffic of the target network according to the business service quality requirements, slice priority and traffic characteristics, and obtain the flow classification result of the target network;

[0081] The network resource scheduling module 13 is used to schedule resources for the target network according to the flow classification results and the network slicing requirements.

[0082] Furthermore, the network resource scheduling device 10 further includes:

[0083] The scheduling result evaluation module is used to evaluate the resource scheduling result according to the service quality index, and adjust the resource allocation strategy of the target network according to the evaluation result.

[0084] A network resource scheduling device 10 provided in an embodiment of the present invention can implement all processes of the network resource scheduling method of the above embodiment. The functions of each module in the device and the technical effects achieved are respectively the same as the functions and technical effects achieved by the network resource scheduling method of the above embodiment, and will not be repeated here.

[0085] See also Figure 3 , Figure 3 1 is a schematic diagram of the structure of a network resource scheduling device 20 provided in an embodiment of the present invention. The network resource scheduling device 20 of this embodiment includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned network resource scheduling method embodiment are implemented. Alternatively, when the processor 21 executes the computer program, the functions of each module in the above-mentioned network resource scheduling device embodiment are implemented.

[0086] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the network resource scheduling device 20.

[0087] The network resource scheduling device 20 may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The network resource scheduling device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art may understand that the schematic diagram is only an example of the network resource scheduling device 20 and does not constitute a limitation on the network resource scheduling device 20. The network resource scheduling device 20 may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the network resource scheduling device 20 may also include input and output devices, network access devices, buses, etc.

[0088] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the network resource scheduling device 20, and uses various interfaces and lines to connect various parts of the entire network resource scheduling device 20.

[0089] The memory 22 can be used to store the computer program and / or module. The processor 21 implements various functions of the network resource scheduling device 20 by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0090] Wherein, if the module integrated in the network resource scheduling device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 21, the steps of the above-mentioned various method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0091] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0092] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the network resource scheduling method as described in the above embodiment.

[0093] In addition, an embodiment of the present invention further provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the steps of the network resource scheduling method of the above embodiment.

[0094] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A network resource scheduling method, characterized in that: include: Obtain network slicing requirement information of a target network, and perform a slicing operation on the target network according to the network slicing requirement information to obtain several different types of network slicing requirements; Classify the network traffic of the target network according to the business service quality requirements, slice priority and traffic characteristics, and obtain the flow classification result of the target network; According to the flow classification results and the network slicing requirements, resources are scheduled for the target network.

2. The network resource scheduling method according to claim 1, characterized in that: The obtaining network slicing requirement information of the target network, and performing a slicing operation on the target network according to the network slicing requirement information to obtain several different types of network slicing requirements, including: Performing demand analysis on different 5G private network services of the target network to obtain network slicing demand information of the target network; wherein the network slicing demand information includes bandwidth demand, latency requirement, and service quality parameters of reliability; According to the network slicing requirement information, a slicing operation is performed on the target network to obtain several different types of network slicing requirements.

3. The network resource scheduling method according to claim 1, characterized in that: The classifying the network traffic of the target network according to the business service quality requirements, slice priorities, and traffic characteristics to obtain the flow classification result of the target network includes: Acquire network traffic data of the target network, and generate traffic characteristics of the target network according to the network traffic data; wherein the network traffic data includes bandwidth requirements, delay requirements, and dynamic changes of traffic; Classify the network traffic of the target network according to the service quality requirements and slice priorities to obtain different service flows; Priority classification is performed according to the delay sensitivity and importance of the service flow and the traffic characteristics, and the flow classification result of the target network.

4. The network resource scheduling method according to claim 1, characterized in that: The performing resource scheduling on the target network according to the flow classification result and the network slicing requirement includes: Generate a resource allocation strategy for the target network according to the flow classification result and the network slicing requirement; According to the flow classification result, the priority and bandwidth requirement of each flow are determined, and according to the priority and bandwidth requirement and the resource allocation strategy, resources are scheduled for the target network.

5. The network resource scheduling method according to claim 4, characterized in that: After performing resource scheduling on the target network, the method further includes: The resource scheduling result is evaluated according to the service quality index, and the resource allocation strategy of the target network is adjusted according to the evaluation result.

6. The network resource scheduling method according to claim 4, characterized in that: The objective function of the resource allocation strategy is: Where U is the overall utility function of the system, w i is the weight of flow i, indicating the priority of the flow; R i is the resource allocated to flow i; N is the total number of flows.

7. A network resource scheduling device, characterized in that: include: A slicing requirement acquisition module, used to obtain network slicing requirement information of a target network, and perform a slicing operation on the target network according to the network slicing requirement information to obtain several different types of network slicing requirements; A network traffic classification module is used to classify the network traffic of the target network according to the business service quality requirements, slice priority and traffic characteristics, and obtain the flow classification result of the target network; A network resource scheduling module is used to schedule resources for the target network according to the flow classification results and the network slicing requirements.

8. A network resource scheduling device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the network resource scheduling method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the network resource scheduling method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product is stored in a storage medium, and the program product is executed by at least one processor to implement the steps of the network resource scheduling method according to any one of claims 1 to 6.

Images