Core network resource optimization method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of communication, and discloses a core network resource optimization method and device, computer equipment and a storage medium. The method is applied to a management and orchestration MANO platform, a network data analysis function NWDAF entity is deployed on the management and orchestration MANO platform, and the method comprises the following steps: collecting network element index data of each network element through the network data analysis function NWDAF entity; the network element index data comprises instantiation information of a virtualized network function VNF; inputting the network element index data of each network element into a pre-trained analysis and prediction model to obtain a resource prediction result corresponding to each network element; determining a resource adjustment strategy corresponding to each network element according to the resource prediction result corresponding to each network element; and executing the resource adjustment strategy corresponding to each network element through the management and orchestration MANO platform. According to the technical scheme, resource waste can be effectively avoided, and the resource utilization rate is increased.

Description

Technical Field

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

[0002] With the rapid development of 5G core network, the number of infrastructure equipment has increased significantly. According to a study and analysis of 31 operators around the world, wireless network energy consumption is the largest at 73%, followed by core network energy consumption at 13%, of which core network network element energy consumption accounts for the largest proportion of 62%. For countries or regions with more 5G infrastructure equipment, core network network element energy consumption is relatively large.

[0003] In order to reduce energy consumption, the current resource scheduling for the core network usually adopts a static balanced allocation method. Specifically, it relies on manual setting of a corresponding fixed weight for each network element in the core network according to the initial performance and capacity of each network element, and then performs resource scheduling for the core network based on the corresponding fixed weight of each network element. However, this static balanced allocation method relies on human experience and is highly subjective, resulting in low resource scheduling efficiency and unreasonable resource allocation. Summary of the invention

[0004] Therefore, the technical problem to be solved by the present invention is to overcome the problems of low resource scheduling efficiency and unreasonable resource allocation in the related art.

[0005] In order to solve the above technical problems, the present invention provides a core network resource optimization method, which is applied to a management and orchestration (MANO) platform, on which a network data analysis function (NWDAF) entity is deployed. The core network resource optimization method includes:

[0006] Collecting network element indicator data of each network element through a network data analysis function NWDAF entity; the network element indicator data includes instantiation information of a virtualized network function (VNF);

[0007] Inputting the network element indicator data of each network element into a pre-trained analysis and prediction model to obtain resource prediction results corresponding to each network element;

[0008] Determine the resource adjustment strategy corresponding to each network element according to the resource prediction results corresponding to each network element;

[0009] The resource adjustment strategy corresponding to each network element is executed through the management and orchestration MANO platform.

[0010] In an optional implementation, executing the resource adjustment strategy corresponding to each network element through the management and orchestration MANO platform includes:

[0011] The network data analysis function NWDAF entity calls the communication interface corresponding to each network element on the management and orchestration MANO platform;

[0012] The resource adjustment strategy corresponding to each network element is executed through the communication interface corresponding to each network element on the management and orchestration MANO platform.

[0013] In an optional implementation, before inputting the network element indicator data of each network element into a pre-trained analysis and prediction model to obtain the resource prediction results corresponding to each network element, the core network resource optimization method also includes: preprocessing the network element indicator data of each network element.

[0014] In an optional implementation, after executing the resource adjustment strategy through the management and orchestration MANO platform, the core network resource optimization method further includes:

[0015] Collect preset performance data;

[0016] The impact of the resource adjustment strategy on network performance is evaluated according to the preset performance data to obtain an evaluation result.

[0017] In an optional implementation, after obtaining the evaluation result, the core network resource optimization method further includes:

[0018] The management and orchestration MANO platform feeds back the evaluation result to the network data analysis function NWDAF entity, and the network data analysis function NWDAF entity adjusts the resource adjustment strategy or the prediction model according to the evaluation result.

[0019] In a second aspect, the present invention provides a core network resource optimization device, which is applied to a management and orchestration MANO platform, wherein a network data analysis function NWDAF entity is deployed on the management and orchestration MANO platform, and the core network resource optimization device includes:

[0020] The first processing module is used to collect network element indicator data of each network element through the network data analysis function NWDAF entity; the network element indicator data includes instantiation information of the virtualized network function VNF;

[0021] The second processing module is used to input the network element indicator data of each network element into a pre-trained analysis and prediction model to obtain a resource prediction result corresponding to each network element;

[0022] The third processing module is used to determine the resource adjustment strategy corresponding to each network element according to the resource prediction result corresponding to each network element;

[0023] The fourth processing module is used to execute the resource adjustment strategy corresponding to each network element through the management and orchestration MANO platform.

[0024] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the core network resource optimization method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0025] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a single computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the core network resource optimization method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0026] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the core network resource optimization method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0027] The technical solution provided by the present invention has the following technical effects:

[0028] The technical solution of the present invention is applied to a management and orchestration MANO platform, on which a network data analysis function NWDAF entity is deployed. The network data analysis function NWDAF entity can collect instantiation information of virtualized network functions VNFs of each network element, and analyze the instantiation information of virtualized network functions VNFs through a pre-trained analysis and prediction model to obtain resource prediction results corresponding to each network element. The analysis and prediction model predicts the resource requirements of each network element according to the network element indicator data of each network element, thereby improving the efficiency of resource requirement prediction. The resource adjustment strategy corresponding to each network element can be determined according to the resource prediction results corresponding to each network element, thereby improving the rationality of resource allocation. The resource adjustment strategy corresponding to each network element is executed by the management and orchestration MANO platform, and the management and orchestration MANO platform performs resource scheduling according to the resource adjustment strategy corresponding to each network element, thereby improving the efficiency of resource scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1is a flow chart of a core network resource optimization method according to an embodiment of the present invention;

[0031] Figure 2 is a schematic diagram of a data processing flow according to an embodiment of the present invention;

[0032] Figure 3 is a structural diagram of a core network resource optimization device according to an embodiment of the present invention;

[0033] Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0035] Taking into account that there are many core network infrastructure equipment, resulting in a large proportion of core network element energy consumption, and the current 3GPP standard protocol has no corresponding energy-saving solution to reduce the core network element energy consumption. Therefore, the embodiments of the present invention provide a core network resource optimization method, device, computer equipment and storage medium to solve the problems of low resource scheduling efficiency and unreasonable resource allocation in related technologies.

[0036] According to an embodiment of the present invention, an embodiment of a core network resource optimization method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer device such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] Figure 1 It is a flowchart of a core network resource optimization method according to an embodiment of the present invention.

[0038] like Figure 1 As shown, a core network resource optimization method provided in an embodiment of the present invention is applied to a management and orchestration MANO platform, and a network data analysis function NWDAF entity is deployed on the management and orchestration MANO platform. The core network resource optimization method includes:

[0039] S101: Collect network element indicator data of each network element through the network data analysis function NWDAF entity.

[0040] In this embodiment, the network element indicator data includes instantiation information of a virtualized network function VNF. The core network includes at least one network element, and each network element in the core network corresponds to a different service type.

[0041] In this embodiment, the analysis and prediction model may be a machine learning (ML) model.

[0042] In this embodiment, S101 collects network element indicator data of each network element through the network data analysis function NWDAF entity, specifically including: receiving the instantiation information of the virtualized network function VNF reported by each network element through the network data analysis function NWDAF entity. The network element indicator data (the instantiation information of the virtualized network function VNF) may include data such as traffic load, delay, and VNF performance indicators. In this embodiment, the network element indicator data of each network element may be collected regularly or periodically through the network data analysis function NWDAF entity.

[0043] S102: Inputting the network element indicator data of each network element into a pre-trained analysis and prediction model to obtain resource prediction results corresponding to each network element.

[0044] In this embodiment, it is also necessary to collect the platform resource data of the management and orchestration MANO platform through the network data analysis function NWDAF entity. The network data analysis function NWDAF entity receives the platform resource data reported by the management and orchestration MANO platform, and can input the network element indicator data and platform resource data of each network element into a pre-trained analysis and prediction model to obtain the resource prediction results corresponding to each network element, thereby realizing the allocation of platform resource data.

[0045] In this embodiment, the network element indicator data of each network element is input into a pre-trained analysis and prediction model, and the resource prediction results corresponding to each network element in the future can be predicted, for example, traffic demand and resource usage.

[0046] In this embodiment, before the network element indicator data of each network element is input into the pre-trained analysis and prediction model in S102 and the resource prediction results corresponding to each network element are obtained, the analysis and prediction model needs to be constructed and trained. In this embodiment, the collected network element indicator data of each network element or the previously collected network element indicator data (historical data) of each network element can be used as training data to train the analysis and prediction model. The collected network element indicator data of each network element can also verify the resource prediction results of the analysis and prediction model at the current moment. If the previous resource prediction results do not match the actual traffic demand and resource usage or the error is greater than the preset error, it means that the prediction error is large, and it is necessary to update the analysis and prediction model or adjust the resource adjustment strategy to improve the accuracy of resource allocation.

[0047] In this embodiment, the analysis and prediction model can adopt various types of neural networks to adapt to different data characteristics and prediction tasks, including but not limited to: back propagation neural network, convolutional neural network, long short-term memory network, deep residual network, etc. As an example, when the analysis and prediction model includes a back propagation neural network, constructing and training the analysis and prediction model includes: initializing the parameters of the back propagation neural network, and adjusting the parameters of the back propagation neural network until the parameters of the back propagation neural network meet the preset conditions to obtain a trained back propagation neural network. The parameters of the back propagation neural network include the weights and thresholds from the input layer to the hidden layer, and the weights and biases from the hidden layer to the output layer. The analysis and prediction model corresponding to each network element can be constructed and trained according to the service type corresponding to each network element.

[0048] As an example, when the analysis and prediction model includes a back propagation neural network, S102 inputs the network element indicator data of each network element into the pre-trained analysis and prediction model to obtain the resource prediction results corresponding to each network element, specifically including: inputting the network element indicator data of each network element into the back propagation neural network corresponding to each network element. The output of the back propagation neural network corresponding to the network element can be used as the resource prediction result corresponding to the network element. As an example, the resource prediction result can include the traffic peak value and traffic valley value of the traffic demand within the prediction period.

[0049] In this embodiment, before inputting the network element indicator data of each network element into the pre-trained analysis and prediction model in S102 to obtain the resource prediction results corresponding to each network element, the core network resource optimization method further includes: pre-processing the network element indicator data of each network element. For example, data cleaning, data integration, data conversion, outlier detection and processing, data dimensionality reduction, etc., to obtain data that meets the input of the analysis and prediction model.

[0050] In this embodiment, the network data analysis function NWDAF entity pre-processes the network element indicator data of each network element, which may include at least one of the following: cleaning invalid data in the network element indicator data of each network element and processing missing data, storing the network element indicator data of each network element in a data warehouse, converting the network element indicator data of each network element into a standard format, and normalizing, standardizing or discretizing it.

[0051] As an example, the network data analysis function NWDAF entity performs at least one of the following preprocessing on the network element indicator data of each network element: data cleaning, data integration and data conversion, wherein data cleaning refers to the network data analysis function NWDAF entity removing invalid data from the network element indicator data of each network element collected, such as network element indicator data whose duration from the current time exceeds a certain threshold, repeated and erroneous network element indicator data, etc. Missing data in the network element indicator data of each network element can also be processed, such as using the average, median, mode, etc. to fill in missing data. By performing data cleaning on the invalid data in the network element indicator data of each network element, the influence of invalid data on resource prediction results can be avoided and the error can be reduced. Data integration refers to combining network element indicator data from multiple network elements and storing them uniformly to establish a data warehouse. The collected network element indicator data, for example, includes: the collection time or time period of network element indicator data, business type, business volume, time characteristics, traffic, etc., and extracting data that can be used for modeling or training or that meets the input of the analysis and prediction model and storing it in the data warehouse. Data conversion refers to converting network element indicator data into a standard format and normalizing the network element indicator data, such as scaling the network element indicator data so that it falls into a relatively small specific interval [0, 1] to obtain data suitable for modeling or training or in line with the input of the analysis and prediction model. Through preprocessing, the quality of the input data of the analysis and prediction model is improved, and the accuracy of the prediction is improved.

[0052] S103: Determine the resource adjustment strategy corresponding to each network element according to the resource prediction result corresponding to each network element.

[0053] In this embodiment, the resource adjustment strategy may include a dynamic expansion strategy, a dynamic reduction strategy, a migration strategy, etc. As an example, the dynamic expansion strategy or the dynamic reduction strategy includes: adjusting the computing resources (CPU, memory, storage, etc.) of the network element VNF. Power on and off: shut down unnecessary network element VNFs, or start them when needed. The migration strategy includes: migrating the network element VNF ​​from one node to another node.

[0054] In this embodiment, taking the resource prediction results corresponding to each network element including the traffic peak value and traffic valley value of the traffic demand corresponding to each network element within the prediction period as an example, the above 103 is specifically as follows: determine the resource adjustment strategy corresponding to each network element according to the traffic peak value and traffic valley value of the traffic demand corresponding to each network element within the prediction period. When the traffic peak value of the traffic demand corresponding to a single network element within the prediction period is less than the preset reduction threshold, the resource adjustment strategy corresponding to the network element is determined as follows: reduce the resource allocation of the network element. When the traffic valley value of the traffic demand corresponding to a single network element within the prediction period is greater than or equal to the preset expansion threshold, the resource adjustment strategy corresponding to the network element is determined as follows: increase the resource allocation of the network element. When the traffic peak value of the traffic demand corresponding to a single network element within the prediction period belongs to the first preset range, and the traffic valley value belongs to the second preset range, the resources of the network element may not be adjusted. In this embodiment, the preset reduction threshold, the preset expansion threshold, the first preset range, and the second preset range can be set and modified according to actual needs.

[0055] In this embodiment, when the traffic demand is low, not so many resources are needed to process the traffic, and reducing resource allocation can improve resource utilization and save costs. When the traffic demand is high, more resources are needed to ensure service quality and response time, and resource allocation needs to be increased. When the traffic peak value belongs to the first preset range and the traffic valley value belongs to the second preset range, it means that the current resource allocation can already meet the change in traffic demand, and no additional resource adjustment is required.

[0056] S104: Execute the resource adjustment strategy corresponding to each network element through the management and orchestration MANO platform.

[0057] In this embodiment, S104 executes the resource adjustment policy corresponding to each network element through the management and orchestration MANO platform, specifically including: calling the communication interface corresponding to each network element on the management and orchestration MANO platform through the network data analysis function NWDAF entity, and executing the resource adjustment policy corresponding to each network element through the communication interface corresponding to each network element on the management and orchestration MANO platform. For a single network element, the resource adjustment policy corresponding to the network element can be executed through the communication interface corresponding to the network element on the management and orchestration MANO platform.

[0058] In the present invention, multiple network elements with similar service types can be determined as a network element group, and the network element indicator data of a single network element group can be input into the pre-built analysis and prediction model corresponding to the network element group to obtain the resource prediction result corresponding to the network element group, and the resource adjustment strategy corresponding to each network element group can be determined according to the resource prediction result corresponding to each network element group, and the resource adjustment strategy corresponding to each network element group can be executed through the management and orchestration MANO platform. For details, refer to the relevant description of S102-S104 above, which will not be repeated here.

[0059] This embodiment uses the AI ​​characteristics of the network data analysis function NWDAF entity to formulate a plan, dynamically adjust the energy consumption of each core network element deployed by the management and orchestration MANO platform, so as to reduce carbon emissions and achieve intelligent green energy saving. The network data analysis function NWDAF entity can be an NWDAF entity introduced by the 3GPP standard, which can conduct AI analysis of the platform's network traffic, user behavior, network KPI, and experience requirements through machine learning models, and assist the management and orchestration MANO platform in formulating and changing the resource adjustment strategy of the network element, thereby performing vertical expansion and contraction, adjusting CPU overhead and memory usage overhead, and reducing the energy consumption of the core network elements.

[0060] The management and orchestration MANO platform in the present invention may include a (Cloud Information Model, CIM) communication interface CIM, a virtualized infrastructure manager (Virtualized Infrastructure Manager, VIM), a 5G core network, each network element of the 5G core network, and a network data analysis function NWDAF entity. The network data analysis function NWDAF entity is deployed on the management and orchestration MANO platform, and collects instantiation information of the virtualized network function VNF of each network element, such as network performance, specific area service load, user behavior and other information, and inputs the network element indicator data of each network element into a pre-built analysis and prediction model, and evaluates and analyzes different types of services through the pre-built analysis and prediction model, builds a business portrait, determines the business model and user habits, and assists the management and orchestration MANO platform in formulating resource adjustment strategies (for example, vertical expansion and contraction strategies) corresponding to each network element, adjusts VNF, adjusts CPU overhead and memory usage overhead, avoids resource waste and reduces resource loss.

[0061] The data processing flow diagram of the present invention is as follows Figure 2 As shown, each network element (OtherVNF) reports its network element indicator data to the management and orchestration MANO platform. The network data analysis function NWDAF entity on the management and orchestration MANO platform receives the network element indicator data of each network element and the platform resource data of the management and orchestration MANO platform, pre-processes the network element indicator data of each network element and the platform resource data, analyzes the pre-processed data through the analysis and prediction model, determines the resource prediction result corresponding to each network element, determines the resource adjustment strategy corresponding to each network element according to the resource prediction result corresponding to each network element, calls the communication interface corresponding to each network element on the management and orchestration MANO platform through the network data analysis function NWDAF entity, and executes the resource adjustment strategy corresponding to each network element through the communication interface corresponding to each network element on the management and orchestration MANO platform.

[0062] In the present invention, in order to achieve continuous optimization of core network resources, in an optional implementation, after the resource adjustment strategy is executed by the management and orchestration MANO platform in S014, the core network resource optimization method further includes: collecting preset performance data, evaluating the impact of the resource adjustment strategy on network performance according to the preset performance data, and obtaining an evaluation result. The impact of the resource adjustment strategy on network performance can be evaluated according to the preset performance data, and an evaluation report can be generated. In an optional implementation, after obtaining the evaluation result, the core network resource optimization method further includes: the management and orchestration MANO platform feeds back the evaluation result to the network data analysis function NWDAF entity, and the network data analysis function NWDAF entity adjusts the resource adjustment strategy or prediction model according to the evaluation result.

[0063] In this embodiment, the preset performance data may include VNF performance data, network performance data, energy consumption data, etc. After the network data analysis function NWDAF entity executes the resource adjustment strategy corresponding to each network element through the management and orchestration MANO platform and adjusts the resource requirements of each network element, the management and orchestration MANO platform can continuously monitor the effect of the resource adjustment strategy (preset performance data), including but not limited to VNF performance data, network performance data, and energy consumption data, to ensure the effectiveness of the resource adjustment strategy. Then, the effect analysis is performed on the monitoring results, and the impact of the resource adjustment strategy on energy consumption and network performance is evaluated based on indicators such as energy efficiency ratio and performance change to determine the effectiveness of the resource adjustment strategy. Finally, there is the feedback mechanism. After obtaining the evaluation results, the management and orchestration MANO platform can feed back the evaluation results to the network data analysis function NWDAF entity and provide it to the AI ​​component for optimization and improvement of subsequent resource adjustment strategies. The network data analysis function NWDAF entity improves the analysis and prediction model or optimizes the resource adjustment strategy based on the output, thereby continuously improving the core network resources.

[0064] Based on the technical solution of the present invention, a corresponding core network resource optimization system can be constructed. The present invention optimizes the allocation of resources by managing and arranging the MANO platform in combination with the network data analysis function NWDAF entity, which can achieve efficient resource management, thereby reducing energy consumption and reducing resource waste. The technical solution of the present invention ensures the efficient use of network resources while maintaining the stability and reliability of network performance. The AI ​​component in the network data analysis function NWDAF entity can predict future resource requirements and realize intelligent allocation, thereby increasing the availability of hardware resources. After executing the resource adjustment strategy through the management and arrangement MANO platform, the impact of the resource adjustment strategy on network performance can also be evaluated according to the preset performance data, thereby obtaining the evaluation result, and the evaluation result is fed back to the network data analysis function NWDAF entity. The AI ​​component in the network data analysis function NWDAF entity can adjust the resource adjustment strategy or the analysis prediction model according to the evaluation result. Through the continuous learning of the AI ​​component, not only the effectiveness of the resource adjustment strategy can be ensured, but also the analysis prediction model and the resource adjustment strategy can be continuously optimized and improved, which can ensure the stability of the core network resource optimization system.

[0065] It should be noted that the contents not described in detail in the specification of the present invention belong to the common knowledge of those skilled in the art.

[0066] In this embodiment, a core network resource optimization device is also provided. A single device is used to implement the above-mentioned embodiment and optional implementation methods. The descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0067] Figure 3 It is a structural diagram of a core network resource optimization device according to an embodiment of the present invention.

[0068] The present invention provides a core network resource optimization device, which is applied to a management and arrangement MANO platform, wherein a network data analysis function NWDAF entity is deployed on the management and arrangement MANO platform, such as Figure 3 As shown, the core network resource optimization device includes:

[0069] The first processing module 11 is used to collect network element indicator data of each network element through the network data analysis function NWDAF entity. The network element indicator data includes instantiation information of the virtualized network function VNF.

[0070] The second processing module 12 is used to input the network element indicator data of each network element into a pre-built analysis and prediction model to obtain the resource prediction result corresponding to each network element.

[0071] The third processing module 13 is used to determine the resource adjustment strategy corresponding to each network element according to the resource prediction result corresponding to each network element.

[0072] The fourth processing module 14 is used to execute the resource adjustment strategy corresponding to each network element through the management and orchestration MANO platform.

[0073] In an optional implementation, the fourth processing module 14 is specifically configured to call the communication interface corresponding to each network element on the management and orchestration MANO platform through the network data analysis function NWDAF entity, and execute the resource adjustment strategy corresponding to each network element through the communication interface corresponding to each network element on the management and orchestration MANO platform.

[0074] In an optional implementation, the core network resource optimization device further includes: a preprocessing module.

[0075] The preprocessing module is used to preprocess the network element indicator data of each network element before inputting the network element indicator data of each network element into a pre-trained analysis and prediction model to obtain the resource prediction results corresponding to each network element.

[0076] In an optional implementation, the core network resource optimization device further includes: a monitoring and evaluation module.

[0077] The monitoring feedback module is used to collect preset performance data after the resource adjustment strategy is executed through the management and orchestration MANO platform, and evaluate the impact of the resource adjustment strategy on network performance according to the preset performance data to obtain an evaluation result.

[0078] In an optional implementation, the core network resource optimization device further includes: a feedback module.

[0079] The feedback module is used to enable the management and orchestration MANO platform to feed back the evaluation results to the network data analysis function NWDAF entity after obtaining the evaluation results, and the network data analysis function NWDAF entity adjusts the resource adjustment strategy or prediction model according to the evaluation results.

[0080] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0081] The core network resource optimization device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0082] The embodiment of the present invention also provides a computer device having the above Figure 3The core network resource optimization device shown.

[0083] See also Figure 4 , Figure 4 Schematic diagram of the hardware structure of the computer device according to the embodiment of the present invention. Figure 4 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In an optional embodiment, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor device). Figure 4 A processor 10 is taken as an example.

[0084] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0085] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0086] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating device, an application required for at least one function. The data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In an optional embodiment, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0087] The memory 20 may include a volatile memory, such as a random access memory. The memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive. The memory 20 may also include a combination of the above types of memory.

[0088] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0089] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0090] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0091] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A core network resource optimization method is applied to a management and orchestration MANO platform, wherein a network data analysis function NWDAF entity is deployed on the management and orchestration MANO platform, characterized in that: The method comprises: The network element indicator data of each network element is collected through the network data analysis function NWDAF entity; the network element indicator data includes instantiation information of the virtualized network function VNF; Inputting the network element indicator data of each network element into a pre-trained analysis and prediction model to obtain resource prediction results corresponding to each network element; Determine the resource adjustment strategy corresponding to each network element according to the resource prediction results corresponding to each network element; The resource adjustment strategy corresponding to each network element is executed through the management and orchestration MANO platform.

2. The method according to claim 1, characterized in that The executing of the resource adjustment strategy corresponding to each network element through the management and orchestration MANO platform includes: The network data analysis function NWDAF entity calls the communication interface corresponding to each network element on the management and orchestration MANO platform; The resource adjustment strategy corresponding to each network element is executed through the communication interface corresponding to each network element on the management and orchestration MANO platform.

3. The method according to claim 1, characterized in that Before inputting the network element indicator data of each network element into a pre-trained analysis and prediction model to obtain the resource prediction results corresponding to each network element, the method further includes: pre-processing the network element indicator data of each network element.

4. The method according to claim 1, characterized in that: After executing the resource adjustment strategy through the management and orchestration MANO platform, the method further includes: Collect preset performance data; The impact of the resource adjustment strategy on network performance is evaluated according to the preset performance data to obtain an evaluation result.

5. The method according to claim 4, characterized in that After obtaining the evaluation result, the method further includes: The management and orchestration MANO platform feeds back the evaluation result to the network data analysis function NWDAF entity, and the network data analysis function NWDAF entity adjusts the resource adjustment strategy or the prediction model according to the evaluation result.

6. A core network resource optimization device, applied to a management and orchestration MANO platform, wherein a network data analysis function NWDAF entity is deployed on the management and orchestration MANO platform, characterized in that: The device comprises: The first processing module is used to collect network element indicator data of each network element through the network data analysis function NWDAF entity; the network element indicator data includes instantiation information of the virtualized network function VNF; The second processing module is used to input the network element indicator data of each network element into a pre-trained analysis and prediction model to obtain a resource prediction result corresponding to each network element; The third processing module is used to determine the resource adjustment strategy corresponding to each network element according to the resource prediction result corresponding to each network element; The fourth processing module is used to execute the resource adjustment strategy corresponding to each network element through the management and orchestration MANO platform.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the core network resource optimization method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the core network resource optimization method according to any one of claims 1 to 5.

Images