Network slice self-optimization method, base station and storage medium

Abstract

The application provides a network slice self-optimization method, a base station and a storage medium. The network slice self-optimization method is applied to a first base station, the first base station is connected with a server, the server is connected with a second base station, and the method comprises the following steps: obtaining optimization strategy information and an index threshold value sent by the server, wherein the optimization strategy information comprises first network slice resource configuration information and a parameter optimization model, and the first network slice resource configuration information and the parameter optimization model are both from the second base station; obtaining a service level agreement (SLA) index according to the first network slice resource configuration information and the parameter optimization model; and adjusting the first network slice resource configuration information when the SLA index does not satisfy the index threshold value, so that the SLA index satisfies the index threshold value. In this way, the application can realize the self-optimization function of the wireless network slice, reduce the manual optimization workload, and improve the network optimization efficiency.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a network slicing self-optimization method, a base station, and a storage medium. Background Technology

[0002] Currently, 5G (5th Generation) wireless communication technology is a hot topic in the industry. Because 5G network slicing technology allows for the selection of desired characteristics for each slice, such as low latency, high throughput, connection density, spectral efficiency, traffic capacity, and network efficiency, it helps improve the efficiency of product and service creation and enhance customer experience. 5G network slicing technology is mainly applied in various vertical industries with high network communication demands, such as connected vehicles, emergency communications, and the industrial internet. To ensure the normal operation of network slices, real-time optimization of each slice is required. However, in vertical industries, due to limited scale and the industry's lack of network operation and maintenance optimization capabilities, a large amount of manual work is required, resulting in high operation and maintenance costs. Summary of the Invention

[0003] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0004] This invention provides a network slicing self-optimization method, a base station, and a storage medium, which can realize the self-optimization function of wireless network slices, reduce the workload of manual optimization, and improve network optimization efficiency.

[0005] In a first aspect, embodiments of the present invention provide a network slicing self-optimization method, applied to a first base station, the first base station being connected to a server, and the server being connected to a second base station, the network slicing self-optimization method comprising:

[0006] Obtain the optimization strategy information and indicator threshold sent by the server, wherein the optimization strategy information includes first network slice resource configuration information and parameter optimization model, and both the first network slice resource configuration information and the parameter optimization model come from the second base station;

[0007] The Service Level Agreement (SLA) metrics are obtained based on the first network slice resource configuration information and the parameter optimization model.

[0008] When the SLA metric does not meet the metric threshold, the resource configuration information of the first network slice is adjusted so that the SLA metric meets the metric threshold.

[0009] Secondly, embodiments of the present invention provide a network slicing self-optimization method, applied to a second base station, wherein the second base station is connected to a server, and the server is connected to a first base station, the network slicing self-optimization method comprising:

[0010] Obtain the task threshold sent by the server;

[0011] Obtain local network slice resource configuration information and parameter optimization model;

[0012] The first network slice resource configuration information is obtained based on the task threshold, the local network slice resource configuration information, and the parameter optimization model.

[0013] The first network slice resource configuration information and the parameter optimization model are sent to the first base station through the server, so that the first base station obtains the Service Level Agreement (SLA) index based on the first network slice resource configuration information and the parameter optimization model, and adjusts the first network slice resource configuration information so that the SLA index meets the index threshold if the SLA index does not meet the index threshold.

[0014] Thirdly, embodiments of the present invention provide a base station, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the network slicing self-optimization method provided in embodiments of the present invention.

[0015] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the network slicing self-optimization method provided in embodiments of the present invention.

[0016] This invention includes: acquiring optimization strategy information and indicator thresholds sent by a server, wherein the optimization strategy information includes first network slice resource configuration information and parameter optimization model, both of which are derived from a second base station; obtaining a Service Level Agreement (SLA) indicator based on the first network slice resource configuration information and parameter optimization model; and adjusting the first network slice resource configuration information to meet the indicator threshold when the SLA indicator does not meet the indicator threshold. According to the solution provided by this invention, by acquiring the indicator thresholds, first network slice resource configuration information, and parameter optimization model through a server, and using the first network slice resource configuration information and parameter optimization model of the second base station to derive the Service Level Agreement (SLA) indicator, the SLA indicator can represent the performance of the current network slice and also the optimization effect of the current network slice. Therefore, by acquiring optimization strategy information from other base stations as data samples through a server, the local base station can be optimized, thereby expanding the data sample of the local base station and improving optimization efficiency and effect. The indicator threshold, as a task standard issued by the server, is used to judge the optimization effect of the current base station. When the SLA indicator does not meet the indicator threshold, it can be considered that the optimization effect of the current base station's network slice has not yet met the standard. Therefore, by adjusting the resource configuration information of the first network slice to make the SLA indicator meet the indicator threshold, the optimization effect of the current base station's network slice meets the requirements, and the optimization task is completed. Therefore, by adjusting the configuration parameters of the first base station through the indicator threshold issued by the server and the SLA indicator representing the performance of the current network slice, the self-optimization function of the wireless network slice is realized, reducing the workload of manual optimization and improving network optimization efficiency.

[0017] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0018] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0019] Figure 1 This is a schematic diagram of the structure of a network slice optimization system for performing a network slice self-optimization method provided in an embodiment of the present invention;

[0020] Figure 2 This is a flowchart illustrating a network slicing self-optimization method provided in an embodiment of the present invention;

[0021] Figure 3 yes Figure 2 A schematic diagram illustrating the specific implementation process of step S200;

[0022] Figure 4 yes Figure 2 A schematic diagram illustrating the specific implementation process of step S300;

[0023] Figure 5 yes Figure 2 A schematic diagram of a specific implementation process is also included after step S200;

[0024] Figure 6 This is a schematic diagram illustrating the specific process of forming optimization strategy information provided in the embodiments of the present invention;

[0025] Figure 7 This is a flowchart illustrating a network slicing self-optimization method provided in an embodiment of the present invention;

[0026] Figure 8 yes Figure 7 A schematic diagram illustrating the specific implementation process of step S900;

[0027] Figure 9 This is a schematic diagram of the structure of a base station provided in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0029] It should be noted that although functional modules are divided in the module diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the module diagram or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0030] This invention provides a network slicing self-optimization method. It obtains indicator thresholds and optimization strategy information from a second base station via a server. The optimization strategy information includes first network slice resource configuration information and parameter optimization models. This allows the method to derive Service Level Agreement (SLA) indicators using the first network slice resource configuration information and parameter optimization models from the second base station. The SLA indicator represents both the performance and optimization effect of the current network slice. Therefore, by obtaining optimization strategy information from other base stations as data samples, the method can optimize the local base station, thereby expanding the data sample and improving optimization efficiency and effectiveness. The indicator threshold, as a task standard issued by the server, is used to judge the optimization effect of the current base station. When the SLA indicator does not meet the indicator threshold, it can be considered that the optimization effect of the current base station's network slice has not yet met the standard and needs further optimization. Therefore, by adjusting the first network slice resource configuration information, the SLA indicator is made to meet the indicator threshold, thus ensuring that the optimization effect of the current base station's network slice meets the requirements and completing the optimization task. Therefore, by adjusting the configuration parameters of the first base station through the indicator thresholds issued by the server and the SLA indicators representing the current network slice performance, the self-optimization function of the wireless network slice is realized, reducing the workload of manual optimization and improving the efficiency of network optimization.

[0031] To facilitate understanding, the application scenarios of the network slicing self-optimization method provided in the embodiments of the present invention will be introduced below with reference to the accompanying drawings.

[0032] Figure 1 A network slice optimization system 100 for implementing a network slice self-optimization method is shown. The system 100 includes a server 110, a first base station 120, and a second base station 130, wherein the server 110 is connected to both the first base station 120 and the second base station 130. The server 110 can be a wireless sub-slice manager, which includes a wireless sub-slice management function (RAN-NSSMF). The RAN-NSSMF is responsible for resource allocation for wireless sub-slices and managing their lifecycle. The first base station 120 and the second base station 130 connected to the server 110 can be base stations within the coverage area of ​​the wireless sub-slice. The first base station 120 requires data from other base stations for self-optimization, while the second base station 130 can optimize independently of data from other base stations. Thus, under the coordination of the server 110, the first base station 120 can use the optimized data sent from the second base station 130 to the server 110 as input for machine learning, achieving horizontal federated learning and thus realizing base station self-optimization.

[0033] It should be noted that server 110 is also used to respond to instantiation information, determine the base stations to be optimized and the instantiation configuration data that need to be optimized by horizontal federated learning based on the instantiation information, and send the instantiation configuration data to the base stations to be optimized. Server 110 is also used to receive feedback results from the base stations to be optimized regarding the instantiation configuration data, and determine the base stations to be optimized that have completed instantiation based on the feedback results, so as to facilitate subsequent network slicing self-optimization processing of the base stations to be optimized.

[0034] It should be noted that server 110 can also connect to the Network Slice Management Function (NSMF), a third-party slice management system. The instantiation information can be initiated by NSMF or manually entered. The instantiation information is used by the server to issue instantiation operations to instantiate the network slice of the base station, so as to facilitate subsequent network slice optimization tasks.

[0035] It should be noted that server 110 can also receive externally input slice optimization task parameters and distribute them to designated base stations. For example, slice optimization task parameters can be data related to network slice configuration, including optimization algorithms, SLA task indicators, and optimization thresholds. Server 110 can also select base stations within its coverage area as the first base station 120 or the second base station 130 for distributing optimization tasks using a participant selection algorithm. In other words, server 110 can select a preferred base station as the second base station 130 from base stations within its coverage area based on parameters such as the quality and quantity of data samples. The data samples from the preferred base station can meet the task requirements of local network slice optimization, can operate independently of data samples from other base stations, and can maximize the satisfaction of other base stations' needs for expanding data samples to perform network slice optimization tasks. This means it can provide data samples for the first base station 120, improving the optimization effect and efficiency of the first base station 120.

[0036] The network slice optimization system 100 for performing the network slice self-optimization method described in this embodiment of the invention is for the purpose of more clearly illustrating the technical solutions of this embodiment of the invention, and does not constitute a limitation on the technical solutions provided by this embodiment of the invention. As those skilled in the art will know, with the evolution of the network slice optimization system 100 and the emergence of new application scenarios, the technical solutions provided by this embodiment of the invention are also applicable to similar technical problems.

[0037] It will be understood by those skilled in the art that Figure 1 The structure of the network slicing optimization system 100 shown does not constitute a limitation on the embodiments of the present invention. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0038] Based on the structure of the network slicing optimization system 100 described above, various embodiments of the network slicing self-optimization method of the present invention are proposed.

[0039] See Figure 2 , Figure 2 The flowchart illustrates a network slicing self-optimization method provided in an embodiment of the present invention. This network slicing self-optimization method can be applied to a first base station, for example... Figure 1 The first base station shown in the figure, the path acquisition method includes, but is not limited to, the following steps:

[0040] Step S100: Obtain the optimization strategy information and indicator threshold sent by the server, wherein the optimization strategy information includes first network slice resource configuration information and parameter optimization model, and both the first network slice resource configuration information and the parameter optimization model come from the second base station.

[0041] Understandably, the first base station obtains optimization strategy information and indicator thresholds from the server. These indicator thresholds serve as standard conditions for the base station to complete the optimization task. The optimization strategy information includes the first network slice resource configuration information and parameter optimization model. This optimization strategy information, i.e., the first network slice resource configuration information and parameter optimization model, comes from the second base station. Therefore, the first base station can utilize the second base station's first network slice resource configuration information and parameter optimization model for subsequent optimization processing, achieving horizontal federated learning between the first and second base stations. This expands the data sample for the first base station's network slice optimization processing, improving optimization effectiveness and efficiency. The first base station obtains the optimized strategy information (i.e., the first network slice resource configuration information and parameter optimization model) from the second base station through the server to optimize the network slice. Currently, due to the limited amount and poor quality of network slice data at some base stations, the optimization processing of network slices is not effective. It is necessary to set up a centralized point to obtain data from relevant base stations for network slice optimization processing. However, this may contain user privacy data, and the centralized point and base stations require a large amount of data interaction, increasing communication overhead and affecting network stability. The first base station uses the resource configuration information and parameter model of the first network slice after optimization by the second base station to perform subsequent optimization processing on the network slice. This realizes horizontal federated learning of the base station, eliminates the need to set up a central point to obtain data from relevant base stations, avoids a large amount of data interaction between the central point and the base station, thereby reducing the communication overhead between the server and the base station and improving the stability of the network.

[0042] Step S200: Obtain the Service Level Agreement (SLA) index based on the first network slice resource configuration information and the parameter optimization model;

[0043] Step S300: When the SLA metric does not meet the metric threshold, adjust the first network slice resource configuration information so that the SLA metric meets the metric threshold.

[0044] Understandably, by utilizing the resource configuration information and parameter optimization model of the first network slice from the second base station, the network slice is optimized to obtain the SLA (Service Level Agreement) index corresponding to the optimized network slice. The SLA index represents the performance of the current network slice, i.e., its availability. Before the first base station performs optimization, it obtains the index threshold issued by the server. The index threshold corresponds to the SLA index, representing the SLA index of the network slice that has successfully completed the optimization task, i.e., the optimization task objective. If the SLA index obtained by the network slice after optimization by the first base station does not meet the index threshold, it can be considered that the current network slice of the first base station has not reached the optimization task objective, and the first base station needs to continue optimizing the network slice. The first network slice resource configuration information is configuration data or policy data related to the network slice. By adjusting the first network slice resource configuration information, the network slice can be adjusted and optimized. The adjusted SLA (Service Level Agreement) is obtained using the adjusted first network slice resource configuration information and parameter optimization model. If the adjusted SLA still does not meet the threshold, further optimization of the network slice is required. This means the first network slice resource configuration information needs further adjustment to ensure the adjusted SLA meets the threshold, thus achieving the optimization goal. Therefore, by adjusting the first network slice resource configuration information to ensure the SLA meets the threshold, the optimization effect of the current base station's network slice meets the requirements, completing the optimization task. Thus, by using the threshold issued by the server and the SLA representing the current network slice performance, the first network slice resource configuration information from the second base station is adjusted for optimization. This achieves optimization of the wireless network slice using horizontal federated learning, reducing manual optimization workload and improving network optimization efficiency.

[0045] It should be noted that when the SLA metric does not meet the threshold, the first base station will continue to adjust the resource configuration information of the first network slice until the SLA metric meets the threshold. To avoid long optimization processing time and improve optimization efficiency, the number of SLA iterations can be limited by setting an upper limit on the number of adjustments. That is, the number of times the resource configuration information of the first network slice is adjusted is limited. When the number of adjustments to the resource configuration information of the first network slice reaches the upper limit, the resource configuration information of the first network slice after the last adjustment is retained, and the optimization process of the network slice is terminated using the resource configuration information of the first network slice after the last adjustment as the optimization result.

[0046] It should be noted that the first network slice resource configuration information may include at least one of a resource reservation policy, a quality of service (QoS) configuration policy, or a 5G QoS indicator. It may also be a set of parameters related to SLA metrics defined in the 3rd Generation Partnership Project (3GPP) specifications. This embodiment does not impose specific limitations on this. For example, the first network slice resource configuration information may be the maximum resource reservation ratio parameter in the resource reservation policy. By adjusting the maximum resource reservation ratio parameter, the network slice can be optimized to ensure that the SLA metrics meet the threshold. As another example, the first network slice resource configuration information may be a QoS configuration policy. By adjusting the network traffic priority in the QoS configuration policy, the network slice can be optimized to ensure that the SLA metrics meet the threshold.

[0047] It should be noted that when the SLA indicator does not meet the threshold, the first base station can adjust the first network slice resource configuration information based on the difference between the adjusted SLA indicator and the threshold. For example, the first network slice resource configuration information can be a maximum resource reservation ratio parameter. If increasing the maximum resource reservation ratio parameter results in an increased difference between the adjusted SLA and the threshold, then the maximum resource reservation ratio parameter can be adjusted in the opposite direction, i.e., decreased. Alternatively, if increasing the maximum resource reservation ratio parameter results in a decreased difference between the adjusted SLA indicator and the threshold, then the adjustment direction of the first network slice resource configuration information can be maintained, but the adjustment step size can be reduced, thereby improving the optimization efficiency of the first base station for network slices.

[0048] Reference Figure 3 , Figure 2 Step S200 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0049] Step S210: Input the first network slice resource configuration information into the parameter optimization model for optimization and prediction to obtain the Service Level Agreement (SLA) index.

[0050] It is understandable that the first network slice resource configuration information and parameter optimization model both come from the second base station. The first network slice resource configuration information and parameter optimization model are data after the second base station has completed the optimization process. The first base station uses the first network slice resource configuration information sent by the server as the input parameter of the parameter optimization model to perform network slice optimization prediction and obtain the SLA index. That is, by using the data sample after the second base station has completed the optimization process, the network slice is processed within the first base station, which increases the data sample for the first base station to perform optimization processing, improves the optimization effect of the first base station, and makes it easier for the SLA index corresponding to the adjusted network slice to reach the index threshold, complete the optimization task, and improve the optimization efficiency.

[0051] Reference Figure 4 , Figure 2 Step S300 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0052] Step S310: Obtain the local second network slice resource configuration information;

[0053] Step S320: Adjust the first network slice resource configuration information according to the second network slice resource configuration information.

[0054] Understandably, the first base station obtains the first network slice resource configuration information and parameter optimization model from the second base station through a server, and then uses the optimized first network slice resource configuration information and parameter optimization model from the second base station to optimize the network slice within the first base station. Since the environmental conditions of each base station are different, the content to be optimized may differ. By using data optimized by other base stations to expand its own data sample, optimization is performed. For example, using the first network slice resource configuration information as a reference, adjustments are also needed based on the base station's local network slice resource configuration information to ensure that the SLA indicators corresponding to the network slices within the base station's local environment meet the indicator thresholds. Therefore, the base station obtains the local second network slice resource configuration information, which corresponds to the first network slice resource configuration information. The first network slice resource configuration information is then adjusted based on the local second network slice resource configuration information to ensure that the local network slice optimization process conforms to the current environmental conditions of the base station, that the local base station's SLA indicators meet the indicator thresholds, thus completing the optimization task, improving the optimization effect and efficiency of the network slices, and enhancing network stability.

[0055] It should be noted that the second network slice resource configuration information local to the base station corresponds to the first network slice resource configuration information from the second base station. The second network slice resource configuration information may include at least one of resource reservation policy, quality of service configuration policy, or 5G quality of service indicator. It may also be a set of parameters related to SLA indicators defined in the 3rd Generation Partnership Project (3GPP) specification. The specific parameters of the second network slice resource configuration information are the same as the specific parameters of the first network slice resource configuration information. Since the specific parameters related to the first network slice resource configuration information have been described in the above embodiments, this embodiment will not describe them in detail to avoid redundancy.

[0056] Reference Figure 5 , Figure 2 Following step S200 in the illustrated embodiment, the following steps may also be included, but are not limited to:

[0057] Step S330: When the SLA indicator meets the indicator threshold, the first network slice resource configuration information and the parameter optimization model are reported to the server.

[0058] Understandably, SLA (Service Level Agreement) metrics can be obtained based on the first network slice resource configuration information and parameter optimization model. These metrics are then compared to threshold values ​​to determine whether optimizing the network slice using the current first network slice resource configuration information and parameter optimization model can meet the optimization task objectives issued by the server. When the SLA metrics meet the threshold values, it can be considered that the optimized network slice, after being optimized locally by the base station using the current first network slice resource configuration information and optimization model, achieves the optimization task objective; that is, the optimization task is completed, and the adjustment of the first network slice resource configuration information and the optimization of the network slice are terminated. The first network slice resource configuration information and parameter optimization model corresponding to the current threshold value are reported to the server, providing feedback on the optimization results. Therefore, this effectively reduces the interaction of large amounts of data between the base station and the server, reduces communication overhead, and improves optimization efficiency.

[0059] It should be noted that when the SLA index does not meet the index threshold, the first base station can also report the failure of optimization as an optimization result to the server, so that the server can understand the optimization progress of the first base station in a timely manner and improve the optimization efficiency.

[0060] It should be noted that if the SLA index obtained by the first base station based on the adjusted first network slice resource configuration information and parameter optimization model meets the index threshold, the first base station can broadcast the first network slice resource configuration information and parameter optimization model to other base stations through the server. This allows other base stations to supplement their own data samples with the adjusted first network slice resource configuration information and parameter optimization model from the first base station, thereby assisting other base stations in completing the network slice optimization task and improving the optimization efficiency and effect of the base stations.

[0061] It should be noted that the first base station can monitor its own SLA metrics. When the SLA metrics do not meet the threshold, even if the first base station's SLA metrics have met the threshold before, the first base station can report the information to the server to initiate self-optimization and adjust the current first network slice resource configuration information. This allows the first base station to obtain SLA metrics that meet the threshold based on the adjusted first network slice resource configuration information and parameter optimization model, thereby realizing the real-time self-optimization function of the first base station, reducing the workload of manual optimization and improving optimization efficiency.

[0062] Reference Figure 6 , Figure 6 The optimization strategy information is obtained through the following steps:

[0063] Step S610: Obtain the task threshold sent by the server;

[0064] Step S620: Obtain local network slice resource configuration information and the parameter optimization model;

[0065] Step S630: Obtain candidate SLA indicators based on the local network slice resource configuration information and the parameter optimization model;

[0066] Step S640: When the candidate SLA metric does not meet the task threshold, adjust the local network slice resource configuration information so that the candidate SLA metric meets the task threshold.

[0067] Step S650: If the candidate SLA metric meets the task threshold, the adjusted local network slice resource configuration information is determined as the first network slice resource configuration information.

[0068] Step S660: Obtain the optimization strategy information based on the first network slice resource configuration information and the parameter optimization model.

[0069] It is understandable that optimization strategy information can be obtained through base station processing. The base station acquires the task threshold sent by the server, as well as local network slice resource configuration information and parameter optimization models. The task threshold represents the optimization task objective that the SLA (Service Level Agreement) of the corresponding network slice needs to achieve. The base station uses the local network slice resource configuration information and parameter optimization model to obtain candidate SLA indicators, which represent the performance of the network slice after optimization based on the local network slice resource configuration information. When a candidate SLA indicator does not meet the task threshold, meaning the network slice optimized using the current local network slice resource configuration information has not achieved the optimization task objective, the candidate SLA indicator needs to be adjusted to meet the task threshold. Since the candidate SLA indicator is obtained from the local network slice resource configuration information and parameter optimization model, adjusting the local network slice resource configuration information and using the adjusted information to optimize the network slice ensures that the optimized candidate SLA indicator meets the task threshold. Therefore, the base station can complete the self-optimization task using its local data.

[0070] It is understandable that when the candidate SLA index meets the task threshold, that is, when the network slice obtained by using the adjusted local network slice resource configuration information and parameter optimization model can complete the optimization task objective, it can be considered that the optimization task is completed. The adjusted local network slice resource configuration information is determined as the first network slice resource configuration information, and the optimization strategy information is obtained based on the first network slice resource configuration information and parameter optimization model. In this way, the optimization results of the local base station, i.e. the optimization strategy information, can be shared with other base stations through the server, assisting other base stations in completing the optimization task, reducing the communication overhead between the server and the base station, increasing the data sample of other base stations, and improving the optimization effect and efficiency.

[0071] It should be noted that the specific parameters of the local network slice resource configuration information are the same as those of the first network slice resource configuration information. However, since the specific parameters related to the first network slice resource configuration information have been described in the above embodiments, this embodiment will not describe them in detail to avoid redundancy.

[0072] See Figure 7 , Figure 7 The flowchart illustrates a network slicing self-optimization method provided in an embodiment of the present invention. This network slicing self-optimization method can be applied to a second base station, for example... Figure 1 The second base station shown in the figure, the path acquisition method includes, but is not limited to, the following steps:

[0073] Step S700: Obtain the task threshold sent by the server;

[0074] Step S800: Obtain local network slice resource configuration information and parameter optimization model;

[0075] Step S900: Obtain the first network slice resource configuration information based on the task threshold, the local network slice resource configuration information, and the parameter optimization model;

[0076] Step S1000: The first network slice resource configuration information and the parameter optimization model are sent to the first base station through the server, so that the first base station obtains the Service Level Agreement (SLA) index based on the first network slice resource configuration information and the parameter optimization model, and adjusts the first network slice resource configuration information to make the SLA index meet the index threshold if the SLA index does not meet the index threshold.

[0077] Understandably, the second base station can determine the optimization task objective of the network slice by obtaining the task threshold from the server. It obtains the local network slice resource configuration information and parameter optimization model from the base station, optimizing the network slice without relying on data optimized by other base stations. The base station can perform optimization prediction based on the task threshold, local network slice resource configuration information, and parameter optimization model to obtain the optimized first network slice resource configuration information. This optimized first network slice resource configuration information and parameter optimization model are then sent to the first base station via the server. Thus, the first base station can derive the SLA index corresponding to the currently optimized network slice based on the optimized first network slice resource configuration information and parameter optimization model from the second base station. Furthermore, even if the SLA index does not meet the index threshold obtained from the server (i.e., the first base station's current optimization has not yet achieved the optimization task objective issued by the server), the first base station can adjust the first network slice resource configuration information to ensure the SLA index meets the index threshold, thereby completing the first base station's optimization task. The first network slice resource configuration information and parameter optimization model of the second base station can expand the data sample of the first base station for network slice optimization processing under the coordination of the server. This helps the first base station complete the self-optimization task of the wireless network slice, reduce the workload of manual optimization, and improve the optimization effect and efficiency.

[0078] Reference Figure 8 , Figure 8 Step S900 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0079] Step S910: Obtain candidate SLA indicators based on the local network slice resource configuration information and the parameter optimization model;

[0080] Step S920: When the candidate SLA metric does not meet the task threshold, adjust the local network slice resource configuration information so that the candidate SLA metric meets the task threshold.

[0081] Step S930: If the candidate SLA metric meets the task threshold, the adjusted local network slice resource configuration information is determined as the first network slice resource configuration information.

[0082] Understandably, network slices are optimized using local network slice resource configuration information and parameter optimization models. In other words, local network slice resource configuration information can be used as input parameters, fed into the parameter optimization model for optimization prediction, resulting in candidate SLA metrics for the optimized network slice. When the candidate SLA metrics do not meet the task threshold, it can be considered that the optimized network slice of the second base station has not achieved the server's optimization task objective, and the local network slice resource configuration information needs to be adjusted. Local network slice resource configuration information consists of configuration or policy data related to the network slice. By adjusting the local network slice resource configuration information, the network slice can be adjusted and optimized, improving its performance and its corresponding candidate SLA metrics. Based on the adjusted local network slice resource configuration information and parameter optimization model, the adjusted candidate SLA metrics are obtained. If the adjusted candidate SLA metrics still do not meet the task threshold, the local network slice resource configuration information needs to be further adjusted until the candidate SLA metrics meet the task threshold. That is, the network slice optimized based on the adjusted local network slice resource configuration information and parameter optimization model meets the server's optimization task objective, thus completing the optimization task. If a candidate SLA indicator meets the task threshold, the local network slice resource configuration information corresponding to that candidate SLA indicator, i.e., the adjusted local network slice resource configuration information, is determined as the first network slice resource configuration information. This information is then used by the server to assist the first base station in performing self-optimization of the network slice. Therefore, the second base station, using the task threshold issued by the server, optimizes the network slice using its local data, i.e., the local network slice resource configuration information and the parameter optimization model, until the optimized network slice meets the server's optimization task objective. The local network slice resource configuration information corresponding to the network slice that has achieved the optimization task objective is determined as the first network slice resource configuration information. This first network slice resource configuration information provides data samples for the first base station's network slice optimization, assisting the first base station in performing network slice self-optimization. This achieves horizontal federated learning, enabling self-optimization of the network slice, reducing manual optimization workload, and improving network optimization efficiency.

[0083] It should be noted that when the candidate SLA metric does not meet the task threshold, the second base station will continue to adjust the local network slice resource configuration information until the candidate SLA metric meets the task threshold. To avoid long optimization processing time and improve optimization efficiency, the number of iterations of the candidate SLA can be limited by setting an upper limit on the number of adjustments. That is, the number of times the local network slice resource configuration information can be adjusted is limited. When the number of adjustments to the local network slice resource configuration information reaches the upper limit, the local network slice resource configuration information after the last adjustment is retained, and the optimization process for the network slice is terminated using the local network slice resource configuration information after the last adjustment as the optimization result.

[0084] It should be noted that local network slice resource configuration information may include at least one of resource reservation policies, quality of service (QoS) configuration policies, or 5G QoS indicators. It can also be a set of parameters related to SLA metrics defined in the 3rd Generation Partnership Project (3GPP) specifications. This embodiment does not impose specific limitations on this. For example, local network slice resource configuration information may be the maximum resource reservation ratio parameter in the resource reservation policy. By adjusting the maximum resource reservation ratio parameter, the network slice can be optimized so that the adjusted QoS metrics meet the threshold. As another example, local network slice resource configuration information may be a QoS configuration policy. By adjusting the network traffic priority in the QoS configuration policy, the network slice can be optimized so that the adjusted QoS metrics meet the threshold.

[0085] It should be noted that when the candidate SLA indicator does not meet the task threshold, the first base station can adjust the local network slice resource configuration information based on the difference between the adjusted candidate SLA indicator and the task threshold. For example, the local network slice resource configuration information can be the maximum resource reservation ratio parameter. If reducing the maximum resource reservation ratio parameter results in an increase in the difference between the adjusted candidate SLA and the task threshold, then the maximum resource reservation ratio parameter can be adjusted in the opposite direction, i.e., increased. Alternatively, if reducing the maximum resource reservation ratio parameter results in a decrease in the difference between the adjusted candidate SLA indicator and the task threshold, then the adjustment direction of the local network slice resource configuration information can be maintained, but the adjustment step size can be reduced, thereby improving the optimization efficiency of the second base station for network slices.

[0086] See Figure 9 , Figure 9 This illustrates a base station 900 provided in an embodiment of the present invention. The base station 900 includes, but is not limited to:

[0087] Memory 910 is used to store programs;

[0088] The processor 920 is used to execute the program stored in the memory 910. When the processor 920 executes the computer program stored in the memory 910, the processor 920 is used to execute the network slicing self-optimization method described above.

[0089] The processor 920 and memory 910 can be connected via a bus or other means.

[0090] The memory 910, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the network slicing self-optimization method described in any embodiment of the present invention. The processor 920 implements the above-described network slicing self-optimization method by running the non-transitory software program and instructions stored in the memory 910.

[0091] The memory 910 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store the network slicing self-optimization method described above. Furthermore, the memory 910 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 910 may optionally include remote memories remotely located relative to the processor 920, which can be connected to the processor 920 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0092] The non-transient software program and instructions required to implement the above-described network slicing self-optimization method are stored in memory 910. When executed by one or more processors 920, the network slicing self-optimization method provided in any embodiment of the present invention is executed.

[0093] This invention also provides a storage medium storing computer-executable instructions for executing the above-described network slicing self-optimization method.

[0094] In one embodiment, the storage medium stores computer-executable instructions that are executed by one or more control processors, such as one processor in the network device, enabling the one or more processors to execute the network slicing self-optimization method provided in any embodiment of the present invention.

[0095] The embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0097] The foregoing detailed description of preferred embodiments of the present invention is not limited to the above-described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A network slicing self-optimization method, applied to a first base station, the first base station being connected to a server, the server being connected to a second base station, the network slicing self-optimization method comprising: Obtain the optimization strategy information and indicator threshold sent by the server, wherein the optimization strategy information includes first network slice resource configuration information and parameter optimization model, and both the first network slice resource configuration information and the parameter optimization model come from the second base station; The Service Level Agreement (SLA) metrics are obtained based on the first network slice resource configuration information and the parameter optimization model. When the SLA metric does not meet the metric threshold, the resource configuration information of the first network slice is adjusted so that the SLA metric meets the metric threshold.

2. The network slicing self-optimization method according to claim 1, characterized in that, The step of obtaining the Service Level Agreement (SLA) metrics based on the first network slice resource configuration information and the parameter optimization model includes: The resource configuration information of the first network slice is input into the parameter optimization model for optimization and prediction to obtain the Service Level Agreement (SLA) index.

3. The network slicing self-optimization method according to claim 1, characterized in that, The adjustment of the first network slice resource configuration information includes: Obtain local second network slice resource configuration information; Adjust the first network slice resource configuration information according to the second network slice resource configuration information.

4. The network slicing self-optimization method according to claim 1, characterized in that, After obtaining the Service Level Agreement (SLA) metrics based on the first network slice resource configuration information and the parameter optimization model, the network slice self-optimization method further includes: When the SLA metric meets the metric threshold, the first network slice resource configuration information and the parameter optimization model are reported to the server.

5. The network slicing self-optimization method according to claim 1, characterized in that, The optimization strategy information is obtained through the following steps: Obtain the task threshold sent by the server; Obtain local network slice resource configuration information and the parameter optimization model; Candidate SLA metrics are obtained based on the local network slice resource configuration information and the parameter optimization model. If the candidate SLA metric does not meet the task threshold, adjust the local network slice resource configuration information so that the candidate SLA metric meets the task threshold. If the candidate SLA metric meets the task threshold, the adjusted local network slice resource configuration information is determined as the first network slice resource configuration information. The optimization strategy information is obtained based on the first network slice resource configuration information and the parameter optimization model.

6. The network slicing self-optimization method according to any one of claims 1 to 5, characterized in that, The first network slice resource configuration information includes at least one of a resource reservation policy, a quality of service configuration policy, or a 5G quality of service indicator.

7. A network slicing self-optimization method, applied to a second base station, the second base station being connected to a server, the server being connected to a first base station, the network slicing self-optimization method comprising: Obtain the task threshold sent by the server; Obtain local network slice resource configuration information and parameter optimization model; The first network slice resource configuration information is obtained based on the task threshold, the local network slice resource configuration information, and the parameter optimization model. The first network slice resource configuration information and the parameter optimization model are sent to the first base station through the server, so that the first base station obtains the Service Level Agreement (SLA) index based on the first network slice resource configuration information and the parameter optimization model, and adjusts the first network slice resource configuration information so that the SLA index meets the index threshold if the SLA index does not meet the index threshold.

8. The network slicing self-optimization method according to claim 7, characterized in that, The step of obtaining the first network slice resource configuration information based on the task threshold, the local network slice resource configuration information, and the parameter optimization model includes: Candidate SLA metrics are obtained based on the local network slice resource configuration information and the parameter optimization model. If the candidate SLA metric does not meet the task threshold, adjust the local network slice resource configuration information so that the candidate SLA metric meets the task threshold. If the candidate SLA metric meets the task threshold, the adjusted local network slice resource configuration information is determined as the first network slice resource configuration information.

9. The network slicing self-optimization method according to claim 7 or 8, characterized in that, The local network slice resource configuration information includes at least one of the following: resource reservation policy, quality of service configuration policy, or 5G quality of service indicator.

10. A base station, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the network slicing self-optimization method as described in any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that, The device contains a computer program that, when executed by a processor, implements the network slicing self-optimization method as described in any one of claims 1 to 9.

Images