CN115396929A

CN115396929A - Performance data prediction method, device and storage medium

Info

Publication number: CN115396929A
Application number: CN202210977289.7A
Authority: CN
Inventors: 刘凡栋; 尼松涛; 赵以爽; 何万县; 张奎; 刘扬; 巫峡; 岳向阳; 贺晓博; 李蓉
Original assignee: China United Network Communications Group Co Ltd; China Information Technology Designing and Consulting Institute Co Ltd
Current assignee: China United Network Communications Group Co Ltd; China Information Technology Designing and Consulting Institute Co Ltd
Priority date: 2022-08-15
Filing date: 2022-08-15
Publication date: 2022-11-25

Abstract

The application provides a method, a device and a storage medium for predicting performance data, relates to the field of communication, and is used for predicting the performance data of a plurality of network element devices. The method comprises the following steps: acquiring requirement change data of first network element equipment, wherein the requirement change data is data with a first performance index changed, the first performance index is any one performance index in the first network element equipment, and the first network element equipment is any one network element equipment in a plurality of network element equipment. And determining the prediction data of the second performance index according to the demand change data and the target relation map, wherein the target relation map is used for reflecting the influence degree of the change of the first performance index on the second performance index, and the second performance index comprises at least one performance index except the first performance index in the plurality of network element devices.

Description

Performance data prediction method, device and storage medium

Technical Field

The present application relates to the field of communications, and in particular, to a method, an apparatus, and a storage medium for predicting performance data.

Background

With the development of network technology, the service demand of users gradually increases, and the requirements of users on network quality are higher and higher. In order to guarantee the user experience, the operator needs to maintain and optimize the network element device to guarantee the normal operation of the network.

At present, operation and maintenance personnel can predict the performance index of a network element device according to service requirements and optimize the network element device. However, in the core network of the fifth Generation Mobile Communication technology (5 th Generation Mobile Communication technology,5 g), there are a large number of network elements, and adjusting only one network element may still cause the network to fail. Therefore, how to adjust the data of the performance indexes of other network element devices becomes a technical problem to be solved urgently.

Disclosure of Invention

The application provides a method and a device for predicting performance data and a storage medium, which are used for predicting the performance data of a plurality of network element devices.

In order to achieve the purpose, the following technical scheme is adopted in the application:

in a first aspect, the present application provides a method for predicting performance data. In the method, a performance data prediction device (may be referred to as a "prediction device" for short) obtains demand change data of a first network element device, where the demand change data is data of a first performance index change, the first performance index is any one of performance indexes of the first network element device, and the first network element device is any one of multiple network element devices. Then, the predicting device may determine the predicted data of the second performance index according to the demand change data and the target relationship map, where the target relationship map is used to reflect an influence degree of the change of the first performance index on the second performance index, and the second performance index includes at least one performance index of the plurality of network element devices except the first performance index.

Optionally, the method for determining the prediction data of the second performance index according to the demand change data and the target relationship map further includes: the prediction device may determine a second performance index according to the first performance index and the target relationship map, the second performance index being a performance index that is affected when the first performance index is changed. Then, the prediction means may acquire current data of the second performance index, the current data being data when the demand change data is acquired. The prediction means may determine the modified data of the second performance index based on the demand modification data and the target relationship map. The prediction means may then determine prediction data for the second performance indicator based on the modified data for the second performance indicator and the current data for the second performance indicator.

Optionally, the method further includes: in response to the current data for the second performance metric not reaching the predicted data for the second performance metric, the prediction apparatus may determine a target policy for adjusting the performance data for the second performance metric to the predicted data.

Optionally, the method further includes: the predicting means may obtain historical performance data of each of the plurality of network element devices. Then, the prediction device may input the historical performance data of each network element device into the trained core network service twin model to obtain a plurality of influence parameters, where the influence parameters are used to reflect the influence degree between any two performance indexes. The prediction means may construct the target relationship map from a plurality of influence parameters.

Optionally, the method further includes: in response to the actual data of the first performance level being demand alteration data, the prediction means may acquire actual data of a second performance level. The prediction means may determine a target similarity indicating a degree of similarity between the actual data of the second performance indicator and the predicted data of the second performance indicator. In response to the target similarity being less than the preset similarity threshold, the prediction device may update a plurality of influence parameters, the updated plurality of influence parameters including: the degree of influence between the first performance indicator and the second performance indicator. The prediction device may update the target relationship map based on the updated plurality of impact parameters.

In a second aspect, the present application provides an apparatus for predicting performance data, the apparatus comprising an obtaining module and a processing module.

An obtaining module, configured to obtain requirement change data of a first network element device, where the requirement change data is data with a changed first performance index, the first performance index is any one performance index of the first network element device, and the first network element device is any one network element device of multiple network element devices. And the processing module is used for determining the prediction data of the second performance index according to the demand change data and the target relation map, wherein the target relation map is used for reflecting the influence degree of the change of the first performance index on the second performance index, and the second performance index comprises at least one performance index except the first performance index in the plurality of network element devices.

Optionally, the processing module is specifically configured to determine a second performance index according to the first performance index and the target relationship map, where the second performance index is a performance index affected when the first performance index is changed. And the obtaining module is specifically used for obtaining the current data of the second performance index, wherein the current data is the data when the data is required to be changed. And the processing module is also used for determining the changed data of the second performance index according to the required changed data and the target relation map. And then, the processing module is further used for determining the prediction data of the second performance index according to the change data of the second performance index and the current data of the second performance index.

Optionally, the processing module is specifically configured to determine a target policy in response to predicted data that current data of the second performance index does not reach the second performance index, where the target policy is used to adjust the performance data of the second performance index to the predicted data.

Optionally, the obtaining module is specifically configured to obtain historical performance data of each network element device in the multiple network element devices. And the processing module is specifically used for inputting the historical performance data of each network element device into the trained core network service twin model to obtain a plurality of influence parameters, and the influence parameters are used for reflecting the influence degree between any two performance indexes. And then, the processing module is also used for constructing a target relation map according to the plurality of influence parameters.

Optionally, the obtaining module is specifically configured to obtain actual data of a second performance index in response to that the actual data of the first performance index is the demand change data. And the processing module is specifically used for determining a target similarity, and the target similarity is used for indicating the similarity between the actual data of the second performance index and the predicted data of the second performance index. Then, the processing module is further configured to update a plurality of influence parameters in response to the target similarity being smaller than a preset similarity threshold, where the updated plurality of influence parameters include: the degree of influence between the first performance indicator and the second performance indicator. And then, the processing module is further used for updating the target relation map according to the updated plurality of influence parameters.

In a third aspect, the present application provides an apparatus for predicting performance data, the apparatus comprising: a processor and a memory. A processor and a memory are coupled. The memory is used for storing one or more programs, the one or more programs comprising computer executable instructions, which when executed by the performance data prediction apparatus, are executed by the processor to implement the performance data prediction method as described in the first aspect and any one of the possible implementations of the first aspect.

In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and when the instructions are executed on a computer, the instructions cause the computer to perform the prediction method for performance data described in the first aspect and any one of the possible implementation manners of the first aspect.

In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, causes a computer to implement a method of predicting performance data as described in the first aspect and any one of the possible implementations of the first aspect.

In the foregoing solution, for technical problems that can be solved and technical effects that can be achieved by the performance data prediction apparatus, the computer device, the computer storage medium, or the computer program product, reference may be made to the technical problems and technical effects that are solved by the first aspect, and details are not described herein again.

The technical scheme provided by the application at least brings the following beneficial effects: the server may obtain requirement change data of the first network element device, where the requirement change data is data of a change of a first performance index, the first performance index is any one of the performance indexes of the first network element device, and the first network element device is any one of the multiple network element devices. Then, the server may determine the predicted data of the second performance index according to the demand change data and a target relationship map, where the target relationship map is used to reflect an influence degree of a change of the first performance index on the second performance index, and the second performance index includes at least one performance index of the plurality of network element devices except the first performance index. That is, the server may determine the prediction data for the second performance indicator based on the data of the first performance indicator change and the target relationship map. In this way, the server can predict data in which one performance index is changed from data in which another performance index is changed. Therefore, the server can maintain and optimize the plurality of network element devices according to the prediction data of the second performance index, and normal operation of the network is guaranteed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application and are not to be construed as limiting the application.

FIG. 1 is a schematic diagram illustrating the structure of a server in accordance with an exemplary embodiment;

FIG. 2 is a flow diagram illustrating a method of prediction of performance data in accordance with an exemplary embodiment;

FIG. 3 is a flow diagram illustrating another method of predicting performance data in accordance with an exemplary embodiment;

FIG. 4 is a schematic diagram illustrating a target relationship map, according to an exemplary embodiment;

FIG. 5 is a flow diagram illustrating another method of predicting performance data in accordance with an exemplary embodiment;

FIG. 6 is a schematic diagram illustrating another target relationship map, according to an exemplary embodiment;

FIG. 7 is a flow diagram illustrating another method of predicting performance data in accordance with an exemplary embodiment;

FIG. 8 is a block diagram illustrating an apparatus for predicting performance data in accordance with an exemplary embodiment;

FIG. 9 is a block diagram illustrating an apparatus for predicting performance data in accordance with an exemplary embodiment;

FIG. 10 is a conceptual partial view of a computer program product shown in accordance with an example embodiment.

Detailed Description

The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

The character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship. For example, A/B may be understood as either A or B.

The terms "first" and "second" in the description and claims of the present application are used for distinguishing between different objects and not for describing a particular order of the objects.

Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or modules is not limited to the listed steps or modules but may alternatively include other steps or modules not listed or inherent to such process, method, article, or apparatus.

In addition, in the embodiments of the present application, words such as "exemplary" or "for example" are used to mean serving as examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "such as" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "e.g.," is intended to present concepts in a concrete fashion.

Before describing the prediction method of performance data in the embodiment of the present application in detail, the implementation environment and the application scenario of the embodiment of the present application are described first.

At present, operation and maintenance personnel can predict the performance index of a network element device according to service requirements and optimize the network element device. However, a large number of network element devices exist in the 5G core network, and adjusting only one network element device may still cause a network failure. Therefore, how to adjust the data of the performance indexes of other network element devices becomes a technical problem to be solved urgently.

In order to solve the foregoing problem, an embodiment of the present application provides a method for predicting performance data, where a server may obtain data of a change of a first performance index of a first network element device, where the first performance index is any performance index of the first network element device, and the first network element device is any network element device of multiple network element devices. Then, the server may determine the prediction data of the second performance index according to the data of the first performance index change of the first network element device and the target relationship map. The target relation map is used for reflecting the influence degree of the change of the first performance index on a second performance index, and the second performance index comprises at least one performance index except the first performance index in the plurality of network element devices. In this way, in the embodiment of the present application, the server can predict data with changed performance indexes according to data with changed performance indexes. In this way, the server can maintain and optimize the plurality of network element devices according to the predicted data of the second performance index, thereby ensuring the normal operation of the network.

The following describes an implementation environment of embodiments of the present application.

Fig. 1 is a schematic diagram of a communication system according to an embodiment of the present disclosure. As shown in fig. 1, the communication system may include: a plurality of network devices (e.g., base stations, servers, network element devices, etc.), which may include: server 101, network element device 102, network element device 103, and network element device 104.

The base station may include various forms of base stations, such as: macro base stations, micro base stations (also known as small stations), relay stations, access points, etc. The method specifically comprises the following steps: the Access Point (AP) in a Wireless Local Area Network (WLAN), the Base Station (BTS) in a Global System for Mobile Communications (GSM) or Code Division Multiple Access (CDMA), the Base Station (NodeB, NB) in a Wideband Code Division Multiple Access (WCDMA), the Evolved Node B (Evolved Node B, eNB, or eNodeB) in LTE, or a relay Station or Access Point, or a Base Station in a vehicle-mounted device, a wearable device, and a Next Generation Node B (The Next Generation Node B, gbb) in a future 5G Network, or a Base Station in a future Evolved Public Land Mobile Network (PLMN) Network, and The like.

The core network mainly comprises the following key logic network elements: access and Mobility Management Function (AMF), session Management Function (SMF), user Plane Function (UPF), policy Control Function (Policy Control Function), unified Data Management (UDM), network element.

In a possible design, multiple network element devices (e.g., network element device 102, network element device 103, and network element device 104) may be network element devices of one core network service.

For example, the network element device 102 may be an Access and Mobility Management Function (AMF), and is mainly responsible for operations such as Access authentication of the terminal device, mobility Management, and signaling interaction between functional network elements, for example: and managing the registration state of the user, the connection state of the user, the user registration and network access, the tracking area updating, the cell switching user authentication, the key safety and the like. The network element device 103 may be a Session Management Function (SMF) network element, and is mainly used to implement a user plane transmission logic channel, for example: a session management function such as establishment, release, and modification of a Packet Data Unit (PDU) session or a multicast session. The network element device 104 may be a User Plane Function network element (User Plane Function, UPF), and may be used as an anchor point on a User Plane transmission logic channel, and is configured to complete functions such as routing and forwarding of User Plane data, for example: and a channel (namely a user plane transmission logic channel) is established between the network node and the terminal, and the channel forwards a data packet between the terminal and the DN and is responsible for filtering data messages of the terminal, forwarding data, controlling the rate and generating charging information.

The server can be a physical server or a cloud server. The server may communicate with a network device (e.g., a base station). For example, the server acquires information (e.g., factory information, network device setting information) of the network device. And, the server may process information of the network device. And, the server may also store information of the network devices.

The embodiments of the present application will be described in detail below with reference to the drawings attached to the specification.

As shown in fig. 2, a method for predicting performance data provided in an embodiment of the present application includes:

s201, the server obtains the requirement change data of the first network element device.

The requirement change data is data of a first performance index change, the first performance index is any one performance index in the first network element equipment, and the first network element equipment is any one network element equipment in the multiple network element equipment.

In one possible design, the data of the first performance indicator change may be a difference between the performance data of the first performance indicator before the change and the performance data of the first performance indicator after the change.

For example, if the performance data of the first performance index before being changed is 1000, and the performance data of the first performance index after being changed is 1500, the data of the first performance index after being changed is 500.

It should be noted that, in the embodiment of the present application, the plurality of network element devices are not limited. For example, the plurality of network element devices may be network element devices in a 5G core network. For example, the network element device may be a UPF network element. As another example, the network element device may be an SMF network element. In the embodiment of the present application, the performance index in the network element device is not limited. As another example, the network element device may be a Unified Data Management (UDM) network element.

Illustratively, as shown in table 1, the performance index of the UDM network element is shown. If the first network element device is a UDM network element, the first performance indicator may be a number of 5G active users.

Table 1 performance index of UDM network elements

In a possible implementation manner, the server may obtain the demand data information, where the demand data information includes the performance data of the changed first performance index of the first network element device. The server may obtain performance data of the first performance index of the first network element device before the change. The server may then determine the demand modification data based on the performance data for the first performance indicator before the modification and the performance data for the first performance indicator after the modification.

Exemplarily, if the first network element device is a UDM network element, the first performance index is 5G of the number of active users, and the data before the first performance index is changed is 10000. If the demand data of the first performance index is 15000, the demand change data is 5000.

In another possible implementation manner, the server may obtain historical performance data of the first performance index of the first network element device, where the historical performance data is historical data of the performance index. The server may then determine the demand change data based on the business prediction model.

It should be noted that, in the embodiment of the present application, a method for a server to obtain historical performance data of a first network element device is not limited. For example, the server may obtain B-domain data, which includes user data and service data. The server may obtain O-domain data, which includes network data.

Illustratively, suppose the historical performance data for the first performance metric comprises: 5000. 10000, 15000, the demand change data is 5000.

In the embodiment of the present application, the service prediction model is not limited. For example, the traffic prediction model may be a mobile translation model. As another example, the traffic prediction model may be an exponential smoothing model. As another example, the traffic prediction model may be a linear regression model.

S202, the server determines the prediction data of the second performance index according to the demand change data and the target relation map.

The target relation map is used for reflecting the influence degree of the change of the first performance index on the second performance index.

That is, in the embodiment of the present application, the second performance index is a performance index that is affected when the first performance index is changed.

In one possible design, the second performance indicator may include at least one performance indicator other than the first performance indicator in the plurality of network element devices. That is, the second performance indicator may include one performance indicator and may also include a plurality of performance indicators.

Exemplarily, if the plurality of network element devices include a UDM network element 1 and a UDM network element 2, the first network element device is the UDM network element 1, and the first performance index is a number of 5G active users. For example, the second performance indicator may be the number of authentication requests of the UDM network element 1. For another example, the second performance indicator may be the number of times of subscribing user data requests of the UDM network element 2. For another example, the second performance index may be the number of authentication requests of the UDM network element 1 and the number of subscription user data requests of the UDM network element 2.

In an embodiment of the present application, the influence of the first performance indicator on the second performance indicator includes: the first performance index and the second performance index are in positive correlation, and the first performance index and the second performance index are in negative correlation.

In the embodiment of the present application, a positive correlation means that the influence of the first performance index on the second performance index is a positive influence. That is, the first performance level altered data is increased, and the second performance level altered data is increased; the first performance level altered data is reduced and the second performance level altered data is reduced. Negative correlation means that the effect of the first performance indicator on the second performance indicator is negative. That is, the first performance level altered data increases and the second performance level altered data decreases; the first performance level altered data is decreased and the second performance level altered data is increased.

In one possible design, the target relationship graph may include at least one of: the influence degree between different performance indexes of the same network element equipment, the influence degree between the same performance indexes of different network element equipment, and the influence degree between different performance indexes of different network element equipment.

Illustratively, it is assumed that the plurality of network element devices include: the influence degree between different performance indexes of the same network element device may be an influence degree between the number of 5G active users of the UDM network element 1 and the number of authentication requests of the UDM network element 1, the influence degree between the same performance indexes of different network element devices may be an influence degree between the number of authentication requests of the UDM network element 1 and the number of authentication requests of the UDM network element 2, and the influence degree between different performance indexes of different network element devices may be an influence degree between the number of 5G active users of the UDM network element 1 and the number of authentication requests of the UDM network element 2.

In one possible implementation manner, a target relationship map is stored in the server, and the target relationship map includes a plurality of influence parameters. The impact parameter is used to reflect the degree of impact between any two performance indicators. The server may determine a target influence parameter according to the first performance index and the target relationship map, where the target influence parameter is used to indicate a degree of influence on the second performance index when the first performance index is changed. The server may then determine prediction data for the second performance indicator based on the target impact parameter and the demand alteration data.

In general, if the target influence parameter is positive, the first performance index and the second performance index are positively correlated. And if the target influence parameter is negative, the first performance index and the second performance index are in negative correlation. If the target impact parameter is 0, it indicates that the first performance index and the second performance index are not related.

Exemplarily, if the first network element device is a UDM network element 1, the first performance index is 5G active user number, the requirement change data is 10000, the second performance index is authentication request times, and the performance data of the authentication request times is 8000. If the target impact parameter is 0.5, which indicates that the first performance index and the second performance index are in positive correlation, the predicted data of the number of authentication requests is 13000. If the target impact parameter is-0.5, which indicates that the first performance indicator and the second performance indicator are negatively correlated, the prediction data of the number of authentication requests is 3000.

It can be understood that the server may obtain the requirement change data of the first network element device, where the requirement change data is data of a change of the first performance index, the first performance index is any one performance index of the first network element device, and the first network element device is any one network element device of the multiple network element devices. Then, the server may determine the predicted data of the second performance index according to the demand change data and a target relationship map, where the target relationship map is used to reflect an influence degree of a change of the first performance index on the second performance index, and the second performance index includes at least one performance index of the plurality of network element devices except the first performance index. That is, the server may determine the prediction data for the second performance indicator based on the data of the first performance indicator change and the target relationship map. In this way, the server can predict data with changed performance index from data with changed performance index. Therefore, the server can maintain and optimize the plurality of network element devices according to the prediction data of the second performance index, and normal operation of the network is guaranteed.

In some embodiments, as shown in FIG. 3, S202 may include S301-S304.

S301, the server determines a second performance index according to the first performance index and the target relation map.

In one possible design, the target relationship graph may include: and one incidence relation is used for reflecting the performance index influenced when one performance index is changed.

Exemplarily, if the plurality of network devices include the UDM network element 1 and the UDM network element 2, the first network element device is the UDM network element 1, the first performance index is the number of 5G active users, and the second performance index is the number of authentication requests of the UDM network element 1, the number of 5G active users of the UDM network element 2, and the number of subscription user data requests of the UDM network element 2. When the number of 5G active users changes, the performance indexes of the influence include: the number of authentication requests of the UDM network element 1, the number of 5G active users of the UDM network element 2 and the number of data requests of subscribed users of the UDM network element 2. The plurality of associations may include: the relation between the number of 5G active users of the UDM network element 1 and the number of authentication requests of the UDM network element 1, the relation between the number of 5G active users of the UDM network element 1 and the number of 5G active users of the UDM network element 2, and the relation between the number of 5G active users of the UDM network element 1 and the number of subscribed user data requests of the UDM network element 2.

In one possible implementation, the server may determine the first performance metric. The server may then determine a second performance metric based on the first performance metric and the plurality of associations.

Illustratively, as shown in fig. 4, suppose the target relationship map includes: the association relationship between the number of 5G active users of the UDM network element 1 and the number of authentication request times of the UDM network element 1, the association relationship between the number of 5G active users of the UDM network element 1 and the number of 5G active users of the UDM network element 2, the association relationship between the number of 5G active users of the UDM network element 1 and the number of authentication request times of the UDM network element 2, the association relationship between the number of authentication request times of the UDM network element 1 and the number of 5G active users of the UDM network element 2, the association relationship between the number of authentication request times of the UDM network element 1 and the number of authentication request times of the UDM network element 2, and the association relationship between the number of 5G active users of the UDM network element 2 and the number of authentication request times of the UDM network element 2. And if the first performance index is the number of 5G active users, when the first network element device is the UDM network element 1. The second performance metric may then include: the authentication request times of the UDM network element 1, the number of 5G active users of the UDM network element 2 and the authentication request times of the UDM network element 2. If the first performance level is the number of authentication requests. The second performance metric may then include: the number of the 5G active users of the UDM network element 1, the number of the 5G active users of the UDM network element 2 and the number of the authentication requests of the UDM network element 2. Similarly, for the case that the first network element device is the UDM network element 2, the case that the first network element device is the UDM network element 1 may be referred to.

S302, the server obtains the current data of the second performance index.

And the current data is data when the required change data is acquired.

Exemplarily, if the first network element device is the UDM network element 1, the first performance index is the number of 5G active users, and the second performance index is the number of authentication requests of the UDM network element 1. When the server obtains the data of the requirement change, if the data before the first performance index is changed is 10000, the authentication request times of the udm network element 1 is 8000. The server may then determine that the current data for the second performance metric is 8000.

In a possible implementation manner, an EMS (Element Management Systems) may obtain current data of a performance index of each network Element device in the plurality of network Element devices from a network Element side. Then, the EMS may send current data of the performance index of each of the plurality of network element devices to the server, and the server may receive the current data of the performance index of each of the plurality of network element devices.

In another possible implementation manner, the server stores current data of the performance index of each of the plurality of network element devices. The server may obtain current data of the second performance indicator from the stored plurality of network element devices.

S303, the server determines the changed data of the second performance index according to the required changed data and the target relation map.

In a possible implementation manner, the server may determine the target influence parameter according to the first performance index and the target relationship map. The server may then determine changed data for the second performance indicator based on the target impact parameter and the demand change data.

Exemplarily, if the first network element device is the UDM1, the first performance index is the number of 5G active users, and the influence degree of the number of 5G active users of the target relationship graph including the UDM network element 1 on the number of authentication request times of the UDM network element 1 is 0.5, the second performance index is the number of authentication request times of the UDM network element 1. If the demand change data is 500, the change data of the second performance level is 250.

S304, the server determines the prediction data of the second performance index according to the change data of the second performance index and the current data of the second performance index.

In a possible implementation manner, if the first performance index and the second performance index are positively correlated, the server may add the current data of the second performance index and the changed data of the second performance index to determine the predicted data of the second performance index.

Illustratively, if the modified data of the second performance indicator is 20, the current data of the second performance indicator is 50. If the first performance indicator is positively correlated with the second performance indicator, the predicted data for the second performance indicator is 70.

In another possible implementation manner, if the first performance index and the second performance index are negatively correlated, the server may subtract the current data of the second performance index and the changed data of the second performance index, and determine the predicted data of the second performance index.

Illustratively, if the modified data of the second performance indicator is 20, the current data of the second performance indicator is 50. If the first performance level and the second performance level are negatively correlated, the prediction data for the second performance level is 30.

It can be understood that the server may determine a second performance index according to the first performance index and the target relationship map, where the second performance index is a performance index affected when the first performance index is changed. Then, the server may obtain current data of the second performance index, where the current data is data when the demand change data is obtained. The server may determine the changed data of the second performance index based on the demand change data and the target relationship map. The server may then determine prediction data for the second performance indicator based on the change data for the second performance indicator and the current data for the second performance indicator. In this way, the server can maintain and optimize the plurality of network element devices according to the predicted data of the second performance index, thereby ensuring the normal operation of the network.

It should be noted that when the current data of the performance index of each of the plurality of network element devices is low, a network failure may occur.

In some embodiments, the server may determine whether the current data for the second performance metric meets the predicted data for the second performance metric based on the current data for the second performance metric and the predicted data for the second performance metric.

In one possible implementation, the server may compare the current data of the second performance indicator with the predicted data of the second performance indicator to determine whether the current data of the second performance indicator reaches the predicted data of the second performance indicator. If the current data of the second performance index is greater than or equal to the predicted data of the second performance index, the server may determine that the current data of the second performance index has reached the predicted data of the second performance index. If the current data of the second performance index is less than the predicted data of the second performance index, the server may determine that the current data of the second performance index does not reach the predicted data of the second performance index.

Illustratively, if the second performance indicator is the number of authentication requests, the current data of the number of authentication requests is 12000. If the prediction data of the authentication request times is 16000, the server may determine that the current data of the second performance index does not reach the prediction data of the second performance index. If the prediction data of the authentication request times is 10000, the server may determine that the current data of the second performance index has reached the prediction data of the second performance index.

In this embodiment, if the current data of the second performance index does not reach the predicted data of the second performance index, the server may determine a target policy, where the target policy is used to adjust the performance data of the second performance index to the predicted data.

Illustratively, suppose the second performance metric comprises: the number of authentication requests, the number of registration requests sent by the AMF to the SMF, the current data of the number of authentication requests is 12000, and the current data of the number of registration requests sent by the AMF to the SMF is 9000. If the current data of the number of authentication requests is 16000, the amf sends the SMF predicted data of the number of registration requests is 12000. The server may then adjust the number of authentication requests to 16000 and the AMF to send prediction of the number of registration requests to the SMF to 12000.

In some embodiments, the server may determine the target policy in response to the current data for the second performance metric failing to meet the predicted data for the second performance metric.

That is, in response to the current data for the second performance metric not reaching the predicted data for the second performance metric, the server may adjust the performance data for the second performance metric to the predicted data.

It will be appreciated that the server may determine whether the current data for the second performance metric meets the predicted data for the second performance metric based on the current data for the second performance metric and the predicted data for the second performance metric. If the current data of the second performance index does not reach the predicted data of the second performance index, the server may determine a target policy, where the target policy is used to adjust the performance data of the second performance index to the predicted data. In this way, when the performance data of the first performance index reaches the changed performance data, the server can ensure normal operation of the network because the second performance index is adjusted to the predicted data.

In some embodiments, as shown in fig. 5, before the server determines the predicted data of the second performance index according to the demand alteration data and the target relationship map, the performance data prediction method may further include S501-S503.

S501, the server obtains historical performance data of each network element device in the plurality of network element devices.

In a possible implementation manner, the EMS may obtain historical performance data of each network element device in the plurality of network element devices from the network element side. Thereafter, the EMS may send the historical performance data of each of the plurality of network element devices to the server, and the server may receive the historical performance data of each of the plurality of network element devices.

In another possible implementation manner, the server stores historical performance data of each of the plurality of network element devices. The server may obtain historical performance data for each network element device from the stored plurality of network element devices.

In one possible design, the historical performance data may include performance data for a plurality of historical time instants.

Exemplarily, as shown in table 2, it shows performance data of a 5G active user number of the UDM network element at three times of 800, 12, 00.

TABLE 2

	8:00	12:00	18:00
				Number of 5G active users	5000	7000	10000
Number of authentication requests	2000	6000	4000
				Number of times of subscribing user data requests	4000	3000	2000

S502, the server inputs the historical performance data of each network element device into the trained core network service twin model to obtain a plurality of influence parameters.

In one possible design, at least one correlation may exist for a performance metric. That is, one performance indicator corresponds to at least one impact parameter.

Illustratively, suppose the target relationship graph includes: the correlation between the performance index A and the performance index B, the correlation between the performance index A and the performance index C, and the correlation between the performance index A and the performance index D. Then the impact parameters corresponding to the performance index a include: the influence parameter of the performance index A on the performance index B, the influence parameter of the performance index A on the performance index C, and the influence parameter of the performance index A on the performance index D.

In the embodiments of the present application, the values of the influencing parameters are not limited. For example, in a typical case, the influence parameter has a value in the range of [ -1,1]. For another example, the impact parameter may have a value in the range of [ -2,2]. For another example, the impact parameter may have a value in the range of [ -3,3].

In one possible implementation, the server may input historical performance data of each network element device into the trained core network traffic twin model. The server may then determine a plurality of impact parameters according to a correlation coefficient algorithm.

It should be noted that, in the embodiment of the present application, the correlation coefficient algorithm is not limited. For example, the correlation coefficient algorithm may be a pearson (pearson) correlation coefficient algorithm. For another example, the correlation coefficient algorithm may be a kendall (kendall) rank correlation coefficient algorithm. For another example, the correlation coefficient algorithm may be a spearman (spearman) correlation coefficient algorithm.

In some embodiments, the server may obtain a plurality of impact parameters according to the first operation. Wherein the first operation may include:

the server may determine a plurality of first impact parameters based on a plurality of historical performance data for the first performance indicator and a plurality of historical performance data for the third performance indicator, one historical performance data for the first performance indicator corresponding to one historical performance data for the third performance indicator. The third performance index is any one of the performance indexes of the plurality of network element devices except the first performance index.

In one possible design, the first influencing parameter may be represented by formula one.

Wherein ρ _XY For representing the first influencing parameter. X is used to represent a historical performance data of the first performance level and Y is used to represent a historical performance data of the third performance level. Cov (X, Y) is used to represent the covariance of X and Y. D (X) is used for representing the variance of X, and D (Y) is used for representing the variance of Y.

The server may then process the plurality of first impact parameters to determine a second impact parameter, where the second impact parameter is used to reflect an impact degree between the first performance index and the third performance index.

For example, if the plurality of first impact parameters is 1000 impact parameters, the server may sort the plurality of first impact parameters according to a preset sorting manner (for example, a sorting manner from large to small). The server may then determine a second impact parameter via equation two.

Wherein f (x) is used to represent the second influencing parameter, n is used to represent the number of the first influencing parameters, a _n For representing the nth first influencing parameter.

It should be noted that, in the embodiment of the present application, for a plurality of impact parameters, the server may determine each impact parameter according to the first operation. That is, the server may perform the first operation on each of the plurality of influence parameters, determining each of the influence parameters.

S503, the server constructs a target relation map according to the plurality of influence parameters.

In a possible implementation manner, the server may construct the target relationship map according to the first performance index, the second performance index, and the plurality of influence parameters of the first network element.

Exemplarily, referring to fig. 4, as shown in fig. 6, if the plurality of network element devices include a UDM network element 1 and a UDM network element 2, the first performance index is a number of 5G active users, and the second performance index includes a number of authentication requests of the UDM network element 1, a number of 5G active users of the UDM network element 2, and a number of authentication requests of the UDM network element 2. The target relationship map includes: the influence parameter of the number of 5G active users of the UDM network element 1 on the number of authentication requests of the UDM network element 1 is 0.5, the influence parameter of the number of 5G active users of the UDM network element 1 and the number of 5G active users of the UDM network element 2 is 1, and the influence parameter of the number of 5G active users of the UDM network element 1 and the number of authentication requests of the UDM network element 2 is 0.3. Similarly, when the performance index of other network element devices is used as the first performance index, the number of 5G active users of the UDM network element 1 may be referred to.

It will be appreciated that the server may obtain historical performance data for each of the plurality of network element devices. Then, the server may input the historical performance data of each network element device into the trained core network service twin model to obtain a plurality of influence parameters, where the influence parameters are used to reflect the degree of influence between any two performance indexes. The server may then construct a target relationship graph from the plurality of impact parameters. Therefore, the server can obtain the target relation map according to the historical performance data, and the accuracy of the target relation map is improved.

In some embodiments, as shown in FIG. 7, a method of predicting performance data further comprises S701-S705.

And S701, when the actual data of the first performance index is the demand change data, acquiring the actual data of the second performance index.

In one possible design, the demand change data may be performance data after the first performance indicator is changed.

For example, the performance data of the first performance index before the change is 1000, and the performance data of the first performance index after the change is 2000, the demand change data is 2000.

In a possible implementation manner, after the server determines the predicted data of the second performance index, when the actual data of the first performance index is the demand change data, the EMS may obtain the actual data of the performance index of each network element device in the plurality of network element devices from the network element side. Then, the EMS may send actual data of the performance index of each of the plurality of network element devices to the server, and the server may receive the actual data of the performance index of each of the plurality of network element devices.

In another possible implementation manner, the server stores actual data of the performance data of each of the plurality of network element devices. When the actual data of the first performance index is the demand change data, the server may obtain the actual data of the second performance index from the multiple network element devices.

Exemplarily, if the plurality of network element devices include a UDM network element 1 and a UDM network element 2, the first network element device is the UDM network element 1, the first performance index is a number of 5G active users, and the second performance index includes a number of authentication requests of the UDM network element 1, a number of 5G active users of the UDM network element 2, and a number of registration requests sent by the AMF of the UDM network element 2 to the SMF. If the first performance index is 20000, the number of authentication requests of the UDM network element 1 is 16000, the number of 5G active users of the UDM network element 2 is 20000, and the number of registration requests sent by the AMF of the UDM network element 2 to the SMF is 12000. The actual data of the second performance level is 16000, 20000, 12000.

S702, the server determines the target similarity.

Wherein the target similarity is indicative of a degree of similarity between actual data of the second performance indicator and predicted data of the second performance indicator.

In one possible implementation, the server may determine the target similarity according to actual data of the second performance index and predicted data of the second performance index.

As an example, suppose the actual data of the second performance indicator is 50. If the predicted data of the second performance level is 50, the target similarity is 100%. If the predicted data of the second performance level is 30, the target similarity is 60%. If the predicted data of the second performance index is 0, the target similarity is 0.

In some embodiments, after the server determines the target similarity, the server may determine the target information according to the target similarity. The target information is used to reflect the degree of similarity between the actual data of the second performance indicator and the predicted data of the second performance indicator.

That is, the greater the degree of similarity between the actual data of the second performance indicator and the predicted data of the second performance indicator, the more accurate the target influence parameter in the target relationship map is. The smaller the degree of similarity between the actual data of the second performance index and the predicted data of the second performance index is, the more inaccurate the target influence parameter in the target relationship map is. Thus, the target information may be used to reflect the accuracy of the target impact parameter.

In one possible design, the target information may be 10 if the target similarity is 100%. If the target similarity is 90% -99%, the target information may be 9. If the target similarity is 80% to 89%, the target information may be 8. If the target similarity is 70% to 79%, the target information may be 7. If the target similarity is 60% to 69%, the target information may be 6. If the target similarity is 50% to 59%, the target information may be 5. If the target similarity is 40% -49%, the target information may be 4. If the target similarity is 30% to 39%, the target information may be 3. If the target similarity is 20% to 29%, the target information may be 2. If the target similarity is 10% to 19%, the target information may be 1. If the target similarity is 0 to 9%, the target information may be 0.

Illustratively, if the target similarity is 95%, the target information is 9. If the target similarity is 55%, the target information is 5. If the target similarity is 5%, the target information is 0.

S703, the server determines whether the target similarity is smaller than a preset similarity threshold.

In a possible implementation manner, the server may compare the target similarity with a preset similarity threshold, and determine whether the target similarity is smaller than the preset similarity threshold.

It should be noted that, in the embodiment of the present application, the preset similarity threshold is not limited. For example, the preset similarity threshold may be 50%. For another example, the preset similarity threshold may be 80%. For another example, the preset similarity threshold may be 30%.

Illustratively, suppose the preset similarity threshold is 50%. If the target similarity is 90%, the target similarity is greater than a preset similarity threshold. If the target similarity is 40%, the target similarity is smaller than a preset similarity threshold.

In some embodiments, if the target similarity is less than the preset similarity threshold, the server may perform S704-S705.

In some embodiments, the server may perform S704-S705 in response to the target similarity being less than a preset similarity threshold.

S704, the server updates a plurality of influence parameters.

Wherein the updated plurality of impact parameters include: the degree of influence between the first performance indicator and the second performance indicator.

In a possible implementation manner, the server may determine the updated plurality of impact parameters according to the actual data of the second performance index.

Illustratively, suppose the second performance level is any performance level of the plurality of devices other than the first performance level. If the data of the first performance level change is 500 and the target impact parameter is 0.5 before the impact parameter is updated, the data of the second performance level change is 250. If the actual changed data of the second performance index is 500, and the target similarity is smaller than the preset similarity threshold. The server may then determine that the target impact parameter is 1.

S705, the server updates the target relation map according to the updated plurality of influence parameters.

In one possible implementation, the server may determine actively adjusted data and passively adjusted data, the actively adjusted data including performance data of the first performance indicator, and the passively adjusted data may include: the performance data of the second performance index and the influence parameter corresponding to the second performance index. The server may then update the target relationship graph based on the actively-adjusted data and the passively-adjusted data.

Illustratively, suppose the first performance level changed data is 500. Before updating the impact parameters, assuming that the plurality of impact parameters includes: the influence parameter of the number of the 5G users of the UDM network element 1 on the number of the authentication requests of the UDM network element 1 is 0.5, and the influence parameter of the number of the 5G users of the UDM network element 1 on the number of the authentication requests of the UDM network element 2 is 0.4. After the impact parameters are updated, suppose the plurality of impact parameters includes: the influence parameter of the number of 5G active users of the UDM network element 1 on the number of authentication requests of the UDM network element 1 is 0.8, and the influence parameter of the number of 5G active users of the UDM network element 1 on the number of authentication requests of the UDM network element 2 is 0.2. The server may determine that the actively adjusted data is the performance data of the first performance index, and the passively adjusted data is the number of authentication requests of the UDM network element 1, the number of authentication requests of the UDM network element 2, an influence parameter of the number of 5G active users of the UDM network element 1 on the number of authentication requests of the UDM network element 1, and an influence parameter of the number of 5G users of the UDM network element 1 on the number of authentication requests of the UDM network element 2.

In some embodiments, in response to the actual data of the first performance indicator being demand change data, the server may perform S701-S705.

It can be understood that, when the actual data of the first performance index is the demand change data, the server may obtain the actual data of the second performance index. The server may then determine a target similarity indicating a degree of similarity between the actual data of the second performance metric and the predicted data of the second performance metric. If the target similarity is smaller than the preset similarity threshold, the server may update a plurality of influence parameters, where the updated plurality of influence parameters include: the degree of influence between the first performance indicator and the second performance indicator. Then, the server may update the target relationship map according to the updated plurality of influence parameters. Therefore, the server can update the target relation map, and the accuracy of the target influence parameters is improved.

In some embodiments, the server may obtain the requirement change data of the first network element device when the requirement change data is the performance data after the first performance index is changed. Then, the server may change the data and the target relationship map according to the demand, and determine the prediction data of the second performance index.

In a possible implementation manner, after the server obtains the requirement change data of the first network element device, the server may determine the second performance index according to the first performance index and the target relationship map. The server may then obtain current data for the second performance metric. The server may then determine the changed data for the second performance indicator based on the demand change data and the target relationship map. The server may determine prediction data for the second performance indicator.

Illustratively, it is assumed that the plurality of network element devices include: the network element equipment comprises a UDM network element 1 and a UDM network element 2, the first network element equipment is the UDM network element 1, the first performance index is the number of 5G active users, and the second performance index comprises: the authentication request times of the UDM network element 1, the number of 5G active users of the UDM network element 2 and the subscription user data request times of the UDM network element 2. If the first performance index before the change is 500, the number of authentication requests of the UDM network element 1 before the change is 250, the number of 5G active users of the UDM network element 2 before the change is 500, and the number of data requests of a subscription user of the UDM network element 2 before the change is 300. If the changed first performance index is 600, the prediction data of the authentication request times of the UDM network element 1 is 300, the prediction data of the 5G active user number of the UDM network element 2 is 600, and the prediction data of the subscription user data request times of the UDM network element 2 is 360.

The foregoing describes the solution provided by embodiments of the present application primarily from the perspective of a computer device. It will be appreciated that the computer device, in order to implement the above-described functions, comprises corresponding hardware structures and/or software modules for performing the respective functions. Those skilled in the art will readily appreciate that the exemplary performance data prediction method steps described in connection with the embodiments disclosed herein may be implemented in hardware or a combination of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The embodiment of the application also provides a device for predicting the performance data. The performance data prediction device may be a computer device, a CPU in the computer device, a processing module for predicting performance data in the computer device, or a client for predicting performance data in the computer device.

In the embodiment of the present application, the prediction of the performance data may be performed by dividing function modules or function units according to the above method examples, for example, each function module or function unit may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module may be implemented in a form of hardware, or may be implemented in a form of a software functional module or a functional unit. The division of the modules or units in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

Fig. 8 is a schematic structural diagram of a performance data predicting apparatus according to an embodiment of the present application. The performance data prediction apparatus is used to perform the performance data prediction method shown in fig. 2, 3, 5, and 7. The prediction means of the performance data may comprise an acquisition module 801 and a processing module 802.

An obtaining module 801, configured to obtain requirement change data of a first network element device, where the requirement change data is data of a change of a first performance index, the first performance index is any one performance index of the first network element device, and the first network element device is any one network element device of multiple network element devices. A processing module 802, configured to determine prediction data of a second performance index according to the demand change data and a target relationship map, where the target relationship map is used to reflect an influence degree of a change of the first performance index on the second performance index, and the second performance index includes at least one performance index, except the first performance index, in the multiple network element devices.

Optionally, the processing module 802 is specifically configured to determine a second performance index according to the first performance index and the target relationship map, where the second performance index is a performance index affected when the first performance index is changed. The obtaining module 801 is specifically configured to obtain current data of the second performance index, where the current data is data when the data is required to be changed. The processing module 802 is further configured to determine changed data of the second performance index according to the demand changed data and the target relationship map. Thereafter, the processing module 802 is further configured to determine prediction data of the second performance index according to the changed data of the second performance index and the current data of the second performance index.

Optionally, the processing module 802 is specifically configured to determine a target policy in response to that the current data of the second performance index does not reach the predicted data of the second performance index, where the target policy is used to adjust the performance data of the second performance index to the predicted data.

Optionally, the obtaining module 801 is specifically configured to obtain historical performance data of each network element device in the multiple network element devices. The processing module 802 is specifically configured to input the historical performance data of each network element device into the trained core network service twin model to obtain a plurality of influence parameters, where the influence parameters are used to reflect the degree of influence between any two performance indexes. Thereafter, the processing module 802 is further configured to construct a target relationship map according to the multiple influence parameters.

Optionally, the obtaining module 801 is specifically configured to obtain actual data of the second performance index in response to that the actual data of the first performance index is demand change data. The processing module 802 is specifically configured to determine a target similarity, where the target similarity is used to indicate a degree of similarity between actual data of the second performance index and predicted data of the second performance index. Then, the processing module 802 is further configured to update a plurality of influence parameters in response to the target similarity being smaller than the preset similarity threshold, where the updated plurality of influence parameters include: the degree of influence between the first performance indicator and the second performance indicator. Thereafter, the processing module 802 is further configured to update the target relationship map according to the updated plurality of influence parameters.

Fig. 9 is a diagram illustrating a hardware configuration of a performance data prediction apparatus according to an exemplary embodiment. The performance data prediction device may include a processor 901, and the processor 901 is configured to execute application program codes, so as to implement the performance data prediction method in the present application.

The processor 901 may be a Central Processing Unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more ics for controlling the execution of programs in accordance with the present disclosure.

As shown in fig. 9, the prediction device of performance data may further include a memory 902. The memory 902 is used for storing application program codes for executing the present application, and the processor 901 controls the execution.

The memory 902 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that may store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disk read-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory 902 may be separate and coupled to the processor 901 by a bus 904. The memory 902 may also be integrated with the processor 901.

As shown in fig. 9, the prediction device of performance data may further comprise a communication interface 903, wherein the processor 901, the memory 902, and the communication interface 903 may be coupled to each other, for example, via a bus 904. The communication interface 903 is used for information interaction with other devices, for example, information interaction between a prediction device supporting performance data and other devices.

It is noted that the device configuration shown in fig. 9 does not constitute a limitation of the predictive device of performance data, which may include more or less components than those shown in fig. 9, or some components in combination, or a different arrangement of components than those shown in fig. 9.

In actual implementation, the functions implemented by the processing module 802 can be implemented by the processor 901 shown in fig. 9 calling the program code in the memory 902.

The present application also provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor of a computer device, enable the computer to perform the prediction method of performance data provided by the above-described illustrative embodiments. For example, the computer-readable storage medium may be a memory 902 comprising instructions executable by a processor 901 of a computer device to perform the above-described method. Alternatively, the computer readable storage medium may be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium may be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Fig. 10 schematically illustrates a conceptual partial view of a computer program product comprising a computer program for executing a computer process on a computing device provided by an embodiment of the application.

In one embodiment, a computer program product is provided using signal bearing medium 1000. The signal bearing medium 1000 may include one or more program instructions that, when executed by one or more processors, may provide the functions or portions of the functions described above with respect to fig. 2, 3, 5, and 7. Thus, for example, referring to the embodiment shown in FIG. 2, one or more features of S201-S202 may be undertaken by one or more instructions associated with the signal bearing medium 1000. Further, the program instructions in FIG. 10 also describe example instructions.

In some examples, signal bearing medium 1000 may comprise a computer readable medium 1001 such as, but not limited to, a hard disk drive, a Compact Disc (CD), a Digital Video Disc (DVD), a digital tape, a memory, a read-only memory (ROM), a Random Access Memory (RAM), or the like.

In some implementations, the signal bearing medium 1000 may comprise a computer recordable medium 1002 such as, but not limited to, a memory, a read/write (R/W) CD, a R/W DVD, and the like.

In some implementations, the signal bearing medium 1000 may include a communication medium 1003 such as, but not limited to, a digital and/or analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communications link, a wireless communication link, etc.).

The signal bearing medium 1000 may be conveyed by a wireless form of communication medium 1003. The one or more program instructions may be, for example, computer-executable instructions or logic-implemented instructions.

In some examples, a predictive device of performance data, such as described with respect to fig. 8, may be configured to provide various operations, functions, or actions in response to one or more program instructions via the computer-readable medium 1001, the computer-recordable medium 1002, and/or the communication medium 1003.

It can be clearly understood by those skilled in the art from the foregoing description of the embodiments that, for convenience and simplicity of description, only the division of the functional modules is illustrated, and in practical applications, the above function allocation may be performed by different functional modules as needed, that is, the internal structure of the apparatus may be divided into different functional modules to perform the above-described whole classification part or part of the functions.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, a module or a unit may be divided into only one logic function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another apparatus, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed to a plurality of different places. The purpose of the scheme of the embodiment can be realized by selecting a part of or a whole classification part unit according to actual needs.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application, or portions thereof that substantially contribute to the prior art, or the whole classification part or portions thereof, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a device (which may be a single chip, a chip, etc.) or a processor (processor) to execute the whole classification part or some steps of the methods of the embodiments of the present application. The storage medium includes various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk.

The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for predicting performance data, the method comprising:

acquiring demand change data of first network element equipment, wherein the demand change data is data with a changed first performance index, the first performance index is any one performance index in the first network element equipment, and the first network element equipment is any one network element equipment in a plurality of network element equipment;

and determining prediction data of a second performance index according to the demand change data and a target relation map, wherein the target relation map is used for reflecting the influence degree of the change of the first performance index on the second performance index, and the second performance index comprises at least one performance index except the first performance index in the plurality of network element devices.

2. The method of claim 1, wherein determining the prediction data for the second performance metric based on the demand alteration data and the target relationship map comprises:

determining the second performance index according to the first performance index and the target relation map, wherein the second performance index is a performance index influenced when the first performance index is changed;

acquiring current data of the second performance index, wherein the current data is data when the demand change data is acquired;

determining the changed data of the second performance index according to the requirement changed data and the target relation map;

and determining the prediction data of the second performance index according to the change data of the second performance index and the current data of the second performance index.

3. The method of claim 2, further comprising:

in response to the current data of the second performance metric not reaching the predicted data of the second performance metric, determining a target policy, the target policy for adjusting the performance data of the second performance metric to the predicted data.

4. A method according to any of claims 1-3, wherein prior to said determining prediction data for a second performance indicator based on said demand alteration data and a target relationship graph, the method further comprises:

obtaining historical performance data of each network element device in the plurality of network element devices;

inputting the historical performance data of each network element device into the trained core network service twin model to obtain a plurality of influence parameters, wherein the influence parameters are used for reflecting the influence degree between any two performance indexes;

and constructing the target relation map according to the plurality of influence parameters.

5. The method of claim 4, further comprising:

responding to the actual data of the first performance index as the requirement change data, and acquiring the actual data of the second performance index;

determining a target similarity indicating a degree of similarity between the actual data of the second performance indicator and the predicted data of the second performance indicator;

in response to the target similarity being less than a preset similarity threshold, updating the plurality of influence parameters, the updated plurality of influence parameters including: a degree of influence between the first performance indicator and the second performance indicator;

and updating the target relation map according to the updated plurality of influence parameters.

6. An apparatus for predicting performance data, the apparatus comprising:

an obtaining module, configured to obtain requirement change data of a first network element device, where the requirement change data is data of a change of a first performance index, the first performance index is any one of the performance indexes of the first network element device, and the first network element device is any one of a plurality of network element devices;

a processing module, configured to determine prediction data of a second performance index according to the demand change data and a target relationship map, where the target relationship map is used to reflect an influence degree of a change of the first performance index on the second performance index, and the second performance index includes at least one performance index, except the first performance index, in the multiple network element devices.

7. The apparatus of claim 6,

the processing module is specifically configured to determine the second performance index according to the first performance index and the target relationship map, where the second performance index is a performance index affected when the first performance index is changed;

the obtaining module is specifically configured to obtain current data of the second performance index, where the current data is data obtained when the demand change data is obtained;

the processing module is further configured to determine change data of the second performance index according to the demand change data and the target relationship map;

the processing module is further configured to determine prediction data of the second performance indicator according to the change data of the second performance indicator and the current data of the second performance indicator.

8. The apparatus of claim 7,

the processing module is specifically configured to determine a target policy in response to that the current data of the second performance index does not reach the predicted data of the second performance index, where the target policy is used to adjust the performance data of the second performance index to the predicted data.

9. The apparatus according to any one of claims 6 to 8,

the obtaining module is specifically configured to obtain historical performance data of each network element device in the multiple network element devices;

the processing module is specifically configured to input the historical performance data of each network element device into the trained core network service twin model to obtain a plurality of influence parameters, where the influence parameters are used to reflect an influence degree between any two performance indexes;

the processing module is further configured to construct the target relationship map according to the plurality of influence parameters.

10. The apparatus of claim 9,

the obtaining module is specifically configured to obtain actual data of the second performance index in response to that the actual data of the first performance index is the demand change data;

the processing module is specifically configured to determine a target similarity, where the target similarity is used to indicate a degree of similarity between actual data of the second performance indicator and predicted data of the second performance indicator;

the processing module is further configured to update the plurality of influence parameters in response to the target similarity being smaller than a preset similarity threshold, where the updated plurality of influence parameters include: a degree of influence between the first performance indicator and the second performance indicator;

the processing module is further configured to update the target relationship map according to the updated plurality of influence parameters.

11. An apparatus for predicting performance data, comprising: a processor and a memory; the processor and the memory are coupled; the memory is configured to store one or more programs, the one or more programs including computer executable instructions that, when executed by the performance data prediction device, cause the performance data prediction device to perform the performance data prediction method of any of claims 1-5.

12. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a computer, cause the computer to perform the method of predicting performance data as set forth in any one of claims 1-5.

13. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the method of prediction of performance data according to any of the claims 1-5.