CN116546518A - Data processing method and device - Google Patents

Abstract

The application discloses a data processing method and device, which can reduce invalid adjustment of network slice parameters and reduce waste of resources. The data processing method comprises the following steps: acquiring performance data of a network slice; predicting the first service level agreement SLA achievement level of the first duration according to the performance data; under the condition that the first SLA achievement level is smaller than a first threshold value, predicting a second SLA achievement level of a second duration according to the performance data, wherein the second duration is smaller than the first duration; and when the second SLA achievement level is smaller than a second threshold value, determining to adjust parameters of the network slice.

Description

Data processing method and device

Technical Field

The present application relates to the field of communications, and more particularly, to a data processing method and apparatus.

Background

The fifth generation (5th generation,5G) mobile communication system is required to meet diversified service demands, such as enhanced mobile broadband, large-scale machine-type communication, ultra-high reliability and low-delay communication, and the like. The network slicing technology logically abstracts a network into one or more mutually isolated network slices, wherein each network slice comprises a series of logic network functions, and the differentiated requirements of different services are purposefully met.

The management data analysis function (management data analysis function, MDAF) may analyze the performance data of the network slice to obtain actual and predicted values of the degree of achievement of the service level agreement (service level agreement, SLA) of the network slice. In the event that either the actual value or the predicted value of the SLA achievement level of the network slice is less than a threshold value, the MDAF may determine to adjust the parameters of the network slice.

Due to network fluctuations, the SLA of a network slice may not reach a threshold for a short period of time. After the parameters of the network slice are adjusted, the SLA achievement level of the network slice can be restored to be greater than the threshold value after a period of time. Therefore, the adjustment of the network slice parameters according to the actual and predicted values of the SLA achievement level may be redundant, resulting in waste of system resources.

Disclosure of Invention

The application provides a data processing method and device, which can reduce invalid adjustment of network slice parameters and reduce waste of resources.

In a first aspect, a data processing method is provided, including: acquiring performance data of a network slice; predicting a first service level agreement achievement level of a first duration according to the performance data; predicting a second SLA achievement level of a second duration according to the performance data, wherein the second duration is smaller than the first duration under the condition that the first service level agreement achievement level is smaller than a first threshold; and determining to adjust the parameters of the network slice under the condition that the second service level agreement achievement degree is smaller than a second threshold value.

By predicting the second SLA achievement level for a shorter time when the first SLA achievement level prediction result for a longer time is smaller than the first threshold value, frequent adjustment of network slicing parameters caused by fluctuation of the SLA achievement level can be avoided.

For example, the first duration may be greater than or equal to the intended-to-sustain duration. The intended duration of maintenance is used to represent the length of time required from determining adjustments to the network slice to stabilization of the network slice performance parameters. The intent-to-maintain duration may be a statistical value, i.e., the intent-to-maintain duration may be used to represent a trend in the data set for the length of time required for the network slice performance parameter to stabilize after each determination of an adjustment to the network slice.

With reference to the first aspect, in some possible implementations, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold; and in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

The smaller the first SLA achievement level, the longer the length of time that the real-time SLA achievement level is below the first threshold value may be in the first duration, or the greater the difference between the real-time SLA achievement level and the first threshold value may be in the first duration. Under the condition that the first SLA achievement level is smaller than a third threshold value, a plurality of second SLA achievement levels in the first duration are predicted by adopting a smaller step length, so that the adjustment of parameters of the network slice can be more timely.

With reference to the first aspect, in some possible implementations, the method further includes: determining the achievement degree of a real-time service level agreement according to the performance data; the predicting the first service level agreement achievement level of the first duration according to the performance data comprises: and predicting the first service level agreement achievement level according to the performance data if the real-time service level agreement achievement level is less than a fourth threshold, wherein the fourth threshold is greater than the second threshold.

And under the condition that the real-time SLA achievement level is smaller than a fourth threshold value, the first SLA achievement level is predicted, so that the prediction times can be reduced, and the occupation of resources is reduced.

With reference to the first aspect, in some possible implementations, the fourth threshold is associated with traffic of the network slice service.

And under the condition that the real-time SLA achievement level is smaller than a fourth threshold value, the first SLA achievement level is predicted, and the fourth threshold value is associated with the business of the network slicing service, so that the condition for predicting the first SLA achievement level meets business requirements more reasonably.

In a second aspect, a data processing method is provided, including: acquiring performance data of a network slice; determining the achievement degree of a real-time service level agreement according to the performance data; predicting a second service level agreement achievement level of a second duration according to the performance data when the real-time service level agreement achievement level is less than a fourth threshold; and under the condition that the second service level agreement achievement degree is smaller than a second threshold value, determining to adjust the parameters of the network slice, wherein the fourth threshold value is larger than the second threshold value.

With reference to the second aspect, in some possible implementations, the method includes: under the condition that the real-time service level agreement achievement level is smaller than a fourth threshold value, predicting a first service level agreement achievement level of a first duration according to the performance data; the predicting the second service level agreement achievement degree of the second duration according to the performance data comprises the following steps: and under the condition that the first service level agreement achievement level is smaller than a first threshold value, predicting the second service level agreement achievement level according to the performance data, wherein the second duration is smaller than the first duration.

With reference to the second aspect, in some possible implementations, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold; and in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

With reference to the second aspect, in some possible implementations, the fourth threshold is associated with traffic of the network slice service.

In a third aspect, there is provided a data processing apparatus comprising: the acquisition module is used for acquiring the performance data of the network slice; the processing module is used for predicting the first service level agreement achievement degree of the first duration according to the performance data; the processing module is further configured to predict, according to the performance data, a second service level agreement achievement level for a second duration, where the second duration is less than the first duration, if the first service level agreement achievement level is less than a first threshold; the processing module is further configured to determine to adjust a parameter of the network slice if the second service level agreement achievement level is less than a second threshold.

With reference to the third aspect, in some possible implementations, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold; and in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

With reference to the third aspect, in some possible implementations, the processing module is further configured to determine a real-time service level agreement achievement level according to the performance data; the processing module is further configured to predict the first service level agreement achievement level based on the performance data if the real-time service level agreement achievement level is less than a fourth threshold, where the fourth threshold is greater than the second threshold.

With reference to the third aspect, in some possible implementations, the fourth threshold is associated with traffic of the network slice service.

In a fourth aspect, there is provided a data processing apparatus comprising: the acquisition module is used for acquiring the performance data of the network slice; the processing module is used for determining the achievement degree of the real-time service level agreement according to the performance data; the processing module is further configured to predict a second service level agreement achievement level for a second duration according to the performance data if the real-time service level agreement achievement level is less than a fourth threshold; the processing module is further configured to determine to adjust a parameter of the network slice if the second service level agreement achievement level is less than a second threshold, and the fourth threshold is greater than the second threshold.

With reference to the fourth aspect, in some possible implementations, the processing module is further configured to predict, according to the performance data, a first service level agreement achievement level for a first duration if the real-time service level agreement achievement level is less than a fourth threshold; the processing module is further configured to predict, based on the performance data, the second service level agreement achievement level, the second duration being less than the first duration, if the first service level agreement achievement level is less than a first threshold.

With reference to the fourth aspect, in some possible implementations, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold; and in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

With reference to the fourth aspect, in some possible implementations, the fourth threshold is associated with traffic of the network slice service.

In a fifth aspect, there is provided a data processing apparatus comprising a memory for storing program instructions and a processor; the program instructions, when executed in the processor, are for performing the method of the first or second aspect.

In a sixth aspect, a computer readable medium is provided, the computer readable medium storing program code for execution by a device, the program code comprising instructions for performing the method in any one of the implementations of the first or second aspects.

In a seventh aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any one of the implementations of the first or second aspects described above.

In an eighth aspect, a chip is provided, the chip including a processor and a data interface, the processor reading instructions stored on a memory through the data interface, and performing the method in any implementation manner of the first aspect or the second aspect.

Optionally, as an implementation manner, the chip may further include a memory, where the memory stores instructions, and the processor is configured to execute the instructions stored on the memory, where the instructions, when executed, are configured to perform the method in any implementation manner of the first aspect or the second aspect.

The chip may be a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC).

It should be understood that, in this application, the method of the first aspect may specifically refer to the method of the first aspect and any implementation manner of the various implementation manners of the first aspect.

The technical effects that may be achieved by any one of the possible implementation manners of the second aspect to the eighth aspect may be correspondingly described with reference to the technical effects that may be achieved by any one of the possible implementation manners of the first aspect, and the descriptions will not be repeated.

Drawings

Fig. 1 is a schematic diagram of one possible network architecture according to an embodiment of the present application.

Fig. 2 is a schematic diagram of a network slice.

Fig. 3 is a schematic flow chart of a communication method.

Fig. 4 and 5 are schematic block diagrams of a communication system provided in an embodiment of the present application.

Fig. 6 is a schematic flow chart of a communication method.

FIG. 7 is a schematic diagram of SLA achievement level.

Fig. 8 is a schematic flow chart of a data processing method provided in an embodiment of the present application.

Fig. 9 is a schematic flow chart of another data processing method provided in an embodiment of the present application.

Fig. 10 is a schematic flow chart of yet another data processing method provided in an embodiment of the present application.

Fig. 11 is a schematic diagram of a prediction period, a prediction step number, and a second duration provided in an embodiment of the present application.

Fig. 12 is a schematic flow chart of yet another data processing method provided in an embodiment of the present application.

Fig. 13 is a schematic structural diagram of a data processing apparatus provided in an embodiment of the present application.

Fig. 14 is a schematic structural view of another data processing apparatus provided in an embodiment of the present application.

Detailed Description

The technical solutions in the present application will be described below with reference to the accompanying drawings.

The technical solution of the embodiment of the application can be applied to various communication systems, for example: global system for mobile communications (global system for mobile communications, GSM), code division multiple access (code division multiple access, CDMA) system, wideband code division multiple access (wideband code division multiple access, WCDMA) system, general packet radio service (general packet radio service, GPRS), long term evolution (long term evolution, LTE) system, LTE frequency division duplex (frequency division duplex, FDD) system, LTE time division duplex (time division duplex, TDD), universal mobile telecommunications system (universal mobile telecommunication system, UMTS), worldwide interoperability for microwave access (worldwide interoperability for microwave access, wiMAX) communication system, fifth generation (5th generation,5G) system, or New Radio (NR), and the like.

A terminal in an embodiment of the present application may refer to a User Equipment (UE), an access terminal, a subscriber unit, a subscriber station, a mobile station, a remote terminal, a mobile device, a user terminal, a wireless communication device, a user agent, or a user equipment. The terminal may also be a cellular telephone, a cordless telephone, a session initiation protocol (session initiation protocol, SIP) phone, a wireless local loop (wireless local loop, WLL) station, a personal digital assistant (personal digital assistant, PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal in a 5G network or a terminal in a future-evolving public land mobile communication network (public land mobile network, PLMN), etc., as the embodiments of the present application are not limited in this respect.

The access network device in this embodiment of the present application may be a device for communicating with a terminal, which may be a base station (base transceiver station, BTS) in a global system for mobile communications (global system for mobile communications, GSM) or code division multiple access (code division multiple access, CDMA), a base station (NodeB, NB) in a wideband code division multiple access (wideband code division multiple access, WCDMA) system, an evolved NodeB (eNB or eNodeB) in an LTE system, a radio controller in a cloud radio access network (cloud radio access network, CRAN) scenario, or an access network device may be a relay station, an access point, a vehicle device, a wearable device, and an access network device in a 5G network or an access network device in a future evolution PLMN network, one or a group (including a plurality of antenna panels) of base stations in a 5G system, or a network node that forms a gNB or a transmission point, such as a baseband unit, BBU, or a Distributed Unit (DU), or the embodiment of the present application is not limited.

In some deployments, the gNB may include a Centralized Unit (CU) and DUs. The gNB may also include an active antenna unit (active antenna unit, AAU). The CU implements part of the functionality of the gNB and the DU implements part of the functionality of the gNB. For example, the CU is responsible for handling non-real time protocols and services, implementing the functions of the radio resource control (radio resource control, RRC), packet data convergence layer protocol (packet data convergence protocol, PDCP) layer. The DUs are responsible for handling physical layer protocols and real-time services, implementing the functions of the radio link control (radio link control, RLC), medium access control (media access control, MAC) and Physical (PHY) layers. The AAU realizes part of physical layer processing function, radio frequency processing and related functions of the active antenna. Since the information of the RRC layer may eventually become information of the PHY layer or be converted from the information of the PHY layer, under this architecture, higher layer signaling, such as RRC layer signaling, may also be considered to be transmitted by the DU or by the du+aau. It is understood that the access network device may be a device comprising one or more of a CU node, a DU node, an AAU node. In addition, the CU may be divided into access network devices in an access network (radio access network, RAN), or may be divided into access network devices in a Core Network (CN), which is not limited in this application.

In the embodiment of the application, the terminal or the access network device comprises a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system layer. The hardware layer includes hardware such as a central processing unit (central processing unit, CPU), a memory management unit (memory management unit, MMU), and a memory (also referred to as a main memory). The operating system may be any one or more computer operating systems that implement business processes through processes (processes), such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a windows operating system. The application layer comprises applications such as a browser, an address book, word processing software, instant messaging software and the like. Further, the embodiment of the present application is not particularly limited to the specific structure of the execution body of the method provided in the embodiment of the present application, as long as the communication can be performed by the method provided in the embodiment of the present application by running the program recorded with the code of the method provided in the embodiment of the present application, and for example, the execution body of the method provided in the embodiment of the present application may be a terminal or an access network device, or a functional module in the terminal or the access network device that can call the program and execute the program.

Furthermore, various aspects or features of the present application may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. For example, computer-readable media may include, but are not limited to: magnetic storage devices (e.g., hard disk, floppy disk, or magnetic tape, etc.), optical disks (e.g., compact Disk (CD), digital versatile disk (digital versatile disc, DVD), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROM), cards, sticks, key drives, etc.). Additionally, various storage media described herein can represent one or more devices and/or other machine-readable media for storing information. The term "machine-readable medium" can include, without being limited to, wireless channels and various other media capable of storing, containing, and/or carrying instruction(s) and/or data.

Fig. 1 is a schematic diagram of one possible network architecture according to an embodiment of the present application. Taking a 5G network architecture as an example, the network architecture includes: terminal 101, (radio) access network equipment (radio access network, (R) AN) 102, user plane function (user plane function, UPF) network element 103, data Network (DN) network element 104, authentication server function (authentication server function, AUSF) network element 105, AMF network element 106, session management function (session management function, SMF) network element 107, network opening function (network exposure function, NEF) network element 108, network function library function (network repository function, NRF) network element 109, policy control function module (policy control function, PCF) network element 110, unified data management (udified data management, UDM) network element 111, and NSSF network element 112. The UPF network element 103, DN network element 104, AUSF network element 105, AMF network element 106, SMF network element 107, NEF network element 108, NRF network element 109, policy control function (policy control function, PCF) network element 110, UDM network element 111, NSSF network element 112 are abbreviated as UPF103, DN104, AUSF105, AMF106, SMF107, NEF108, NRF109, PCF110, UDM111, NSSF112.

The terminal 101 mainly accesses the 5G network through a wireless air interface and obtains services, and the terminal interacts with the RAN through the air interface and interacts with the AMF of the core network through non-access stratum (NAS). RAN102 is responsible for air interface resource scheduling and air interface connection management for terminal access networks. The UPF103 is responsible for forwarding and receiving user data in the terminal. For example, the UPF may receive user data from a data network and transmit the user data to a terminal through an access network device, and may also receive user data from the terminal through the access network device and forward the user data to the data network. The transmission resources and scheduling functions in the UPF103 that serve the terminal are managed and controlled by the SMF network element. The AUSF105 belongs to a core network control plane network element and is mainly responsible for authentication and authorization of a user to ensure that the user is a legal user. The AMF106 belongs to a core network element and is mainly responsible for signaling processing parts, such as: access control, mobility management, attach and detach, gateway selection, etc., and the AMF106 may also provide a storage resource of a control plane for a session in the terminal to store a session identifier, an SMF network element identifier associated with the session identifier, etc. in case of providing services for the session. SMF107 is responsible for user plane element selection, user plane element redirection, internet protocol (internet protocol, IP) address assignment, bearer establishment, modification and release, and quality of service (quality of service, qoS) control. The NEF108 belongs to a core network control plane network element for taking charge of the outward opening of mobile network capabilities. NRF109 belongs to a core network control plane network element for dynamic registration of service capabilities and network function discovery responsible for network functions. PCF110 is primarily responsible for providing a unified policy framework to control network behavior, providing policy rules to control layer network functions, and acquiring subscriber subscription information associated with policy decisions. The UDM111 belongs to a core network control plane network element, and belongs to a home subscriber server, and can be used for unified data management, and support functions such as 3GPP authentication, subscriber identity operation, authority grant, registration, mobility management, and the like. NSSF112 is used to perform network slice selection functions for the terminal. The NSSF112 belongs to a core network control plane entity for being responsible for the selection of the target NSI.

In the network architecture, nausf is a service-based interface displayed by AUSF105, namf is a service-based interface displayed by AMF106, nsmf is a service-based interface displayed by SMF107, nnef is a service-based interface displayed by NEF108, nnrf is a service-based interface displayed by NRF109, npcf is a service-based interface displayed by PCF110, nudm is a service-based interface displayed by UDM111, and Nnsf is a service-based interface displayed by NSSF 112. N1 is a reference point between the UE101 and the AMF106, N2 is a reference point between the (R) AN102 and the AMF106, and is used for sending non-access stratum (NAS) messages, etc.; n3 is a reference point between the (R) AN102 and the UPF103, for transmitting data of the user plane, etc.; n4 is a reference point between the SMF107 and the UPF103, and is used for transmitting information such as tunnel identification information of the N3 connection, data buffer indication information, and downlink data notification message; the N6 interface is a reference point between the UPF103 and the DN104, and is used for transmitting data of the user plane, etc.

The following description refers to the terminology involved in this application.

Network slice (network slice): refers to customizing different logical networks based on different service requirements, either on a physical or virtual network infrastructure. The network slice can be a complete end-to-end network comprising a terminal, an access network, a transmission network, a core network and an application server, can provide telecommunication services, and has certain network capability; the network slice may also be any combination of the above-mentioned terminals, access networks, transport networks, core networks and application servers, e.g. the network slice comprises only the access network and the core network.

Network-sliced subnetwork (network slice subnet, NSS): a network system consisting of connected, computing and storage resources, possibly including network functions and network management entities, forms a complete instantiated logical/physical network to support certain network and business features. The network slice subnetwork cannot be activated individually as a whole (end-to-end) network slice, and must be interconnected with other network slice subnetworks to form one network slice.

The functionality of a network slice may be implemented by one or more network slice instances. A network slice may include one or more network slice instances.

Network slice instance (Network slice instance, NSI): is a logic network which runs truly and can meet certain network characteristics or service requirements. One network slice instance may provide one or more services. Network slice instances may be created by a network management system, which may create multiple network slice instances and manage them at the same time, including performance monitoring and fault management during operation of the network slice instances, etc. When multiple network slice instances coexist, portions of network resources and network functions may be shared between the network slice instances. The network slice instance may or may not be created from a network slice template. A complete network slice instance is capable of providing complete end-to-end network services, and may be composed of network slice subnet instances (network slice subnet instance) and/or network functions. The network functions may include physical network functions and/or virtual network functions.

The functionality of the network chippings subnetwork may be implemented by one or more network chippings subnetwork instances. A network slice subnet may include one or more network slice subnet instances. The on-resource network-sliced subnetwork may be carried over one or more network-sliced subnetwork instances.

Network slice subnet instance (network slice subnet instance, NSSI): the network slicing subnet instance may not need to provide end-to-end complete network services, and may be a set of network functions of the same vendor in the network slicing instance, or may be a set of network functions divided by domains, for example, a core network slicing subnet instance, an access network slicing subnet instance, or may be a set formed by other means. Network slice subnet instances may be shared by multiple network slice instances. The network slicing subnet example is provided, and the management of a network management system can be facilitated. Each network slice instance is composed of several network functions and/or several network slice subnet instances, i.e. one network slice instance may be composed of several network slice subnet instances and network functions not divided into network slice subnet instances; it is also possible that one network slice instance consists of only a few network functions.

Network Function (NF): the network function is a processing function in the network, defines the functional behaviors and interfaces, and can be realized by special hardware, can be realized by running software on the special hardware, and can be realized in a virtual function form on a general hardware platform. Thus, from an implementation perspective, network functions may be divided into physical network functions and virtual network functions. From the point of view of use, the network functions may be divided into dedicated network functions and shared network functions, in particular, for multiple (sub) network slice instances, different network functions may be used independently, which are referred to as dedicated network functions, or may share the same network function, which is referred to as shared network functions.

Network slice subnet management function (network slice subnet management function, NSSMF): the method is used for slice management and design of the network slice subnetwork. The requirements for the network slice subnet instance are received from the NSMF, so that the lifecycle, performance, failure, etc. of the network slice subnet instance are managed (hereinafter, the lifecycle, performance, failure management is simply managed), and the composition of the network slice instance is organized. The NSSMF reports the capability of the network slicing subnet instance to the NSMF, and after receiving the deployment requirement of NSMF decomposition, the autonomous deployment and enabling in the network slicing subnet instance are realized. During operation, NSSMF is used to manage and monitor network slices of network slice subnet instances.

Service level agreement (service level agreement, SLA): is a contract (or a portion of a contract) between a service provider and a customer intended to establish a common understanding of services, priorities, responsibilities, etc. SLA index mainly includes user rate, end-to-end delay, packet reliability, positioning accuracy, clock synchronization. A plurality of 'slices' are cut from a physical network through a network slicing technology, and customized, differentiated and deterministic network service capability is provided for enterprise service (to business) business by taking business SLA as a center.

Fig. 2 shows a schematic diagram of a network slice. For example, network slice a includes NSI1, network slice B includes NSI1 and NSI 2, and network slice C includes NSI 3. Different network slices provide different services, such as internet surfing services, voice services, ultra-low latency services, or internet of things services.

Fig. 3 is a schematic flow chart of a communication method.

The communication method 300 includes S310 and S320 for implementing SLA guarantee of the network slice subnet.

At S310, intent management.

The intent management information sent by the receiving operator/user is translated to determine the analysis object as well as key performance indicators (key performance indicator, KPI) and other indicators that need to be monitored.

At S320, the KPIs and other metrics of the analysis object are perceived.

At S330, analysis is performed according to the KPI of the analysis object and the values of other performance data.

The SLA achievement degree of the analysis object can be determined according to the KPI of the analysis object and the values of other performance data.

At S340, a decision is made.

If the SLA achievement level is 100% or more, the process returns to S320.

And under the condition that the SLA achievement degree is less than 100%, root cause analysis is carried out, so that an SLA guarantee scheme is determined, and the SLA guarantee scheme is issued.

SLA achievement may be made 100% satisfied by the method 300.

Fig. 4 and 5 are schematic block diagrams of a communication system provided in an embodiment of the present application. Various steps in method 300 may be performed in communication system 400 or communication system 500.

The communication system 400 includes a network management system (network management system, NMS) and a network element management system (element management system, EMS). The NMS is responsible for the operation, management and maintenance of the network. The EMS is responsible for managing the network elements of a certain class, the EMS manages the functions and capacities of each network element, and the number of managed network elements may be one or more.

As shown in fig. 4, the NMS includes an intention driven management service (intent driven management service, IDMS) consumer (consumer), and the like. The EMS includes IDMF, management data analysis function (management data analysis function, MDAF), NSSMF, etc.

MDAF is used to provide management data analysis services for NF, NSSMF, NSSI and the like.

Alternatively, the IDMF may also be located in the NMS in the communication system 500 shown in fig. 5.

Fig. 6 is a schematic flow chart of a data processing method.

The method 600 is applied to the communication system 400 or the communication system 500 for implementing SLA provisioning of a network chippings subnet. The method 600 includes S601 to S609.

At S601, an IDMS user (consumer) transmits SLA guarantee intention information to an intention driver management function (intent driven management, IDMF).

SLA provisioning intent information may be carried in the intent creation message. The IDMS consumer may send an intent creation message to the IDMF.

Is intended to represent a desire for a system, including requirements, goals, constraints, and the like. The SLA assurance intent information may include information such as analysis objects, analysis indicators, limit values of the analysis indicators, and the like.

The SLA provisioning intent information may be, for example, network clip subnet configuration information (e.g., may be slicerp profile information).

The analysis object may be used to indicate a network slice, such as may be represented by a network slice identification. The network slice identity may be, for example, network slice selection assistance information (single network slice selection assistance information, S-NSSAI), etc.

The analysis index can be understood as an SLA performance parameter of the network slice subnet. The limit value of the analysis index is used to represent the range of the analysis index. For example, the analysis indicator may be a time delay, and the limit value of the analysis indicator may be 40 milliseconds (ms), indicating that the maximum time delay does not exceed 40ms.

At S602, IDMF performs intent translation on SLA guarantee intent information.

Intent translation may translate intent into executable commands, rules, flows of sub-intents, and the like.

The IDMF can determine information such as an analysis object, an analysis index, a limiting value of the analysis index and the like by performing intent translation on the SLA guarantee intent information, and determine a calculation formula according to the analysis index and the limiting value of the analysis index, wherein the calculation formula is used for representing the association relation between the detection value of the analysis index and the SLA achievement level.

At S603, the IDMF sends task creation information to the MDAF.

The task creation information may include all or part of the translated SLA provisioning intent information. The task creation information may include, for example, analysis objects and calculation formulas, and may also include information such as analysis periods.

The IDMF may determine the analysis period based on traffic or MDAF, etc.

At S604, the MDAF obtains performance data of the network slice subnet from the NSSMF according to the analysis object and the analysis period. The performance data is used to represent the detected value of the analysis index.

Each network slice may be used to provide services for a certain service. That is, network slices may be in one-to-one correspondence with traffic. One network slice may include a network slice subnet of multiple domains. For each domain, a network slice subnet in the domain that belongs to the network slice may be determined from the network slice indicated by the analysis object.

The MDAF may obtain, from each NSSMF, performance data of a network slice subnet corresponding to the NSSMF. The MDAF may obtain performance data of one or more network slice subnets in the network slice and perform subsequent processing. That is, method 600 may be performed with respect to SLAs of a network slice or with respect to SLAs of a sub-network of a network slice. Illustratively, an MDAF with cross-domain management functionality may obtain performance data for multiple network slice subnets in a network slice.

At S605, the MDAF determines the real-time SLA achievement level using a calculation formula from the performance data.

The MDAF can bring the detection value of the analysis index into a calculation formula to calculate the real-time SLA achievement degree.

If the real-time SLA achievement level is less than 100%, S606 is performed; in the case where the real-time SLA achievement level is 100% or more, S607 is performed.

At S606, the MDAF determines a predictive SLA achievement level from the performance data.

Determining the predicted SLA achievement level may also be understood as making a degradation prediction. The predicted SLA achievement level is used to represent the SLA achievement level within a predetermined time period in the future.

If the predicted SLA achievement level is 100% or more, the process returns to S605; if the real-time SLA achievement level is less than 100%, S607 is performed.

In S607, the MDAF determines an adjustment policy according to the performance data and configuration information, environment information, etc. of the network slice subnet.

At S608, the MDAF sends the adjustment policy to the IDMF.

In S609, the IDMF adjusts the parameters of the network slice subnet according to the adjustment policy.

The adjustment policy may be, for example, a resource allocation algorithm to adjust the network slice subnet, a cell coverage parameter, etc.

In particular, IDMF may evaluate the tuning policy to determine whether the tuning policy can bring the SLA to 100%. In the case where it is determined that the adjustment policy can bring the SLA to 100%, the IDMF may adjust the network slice subnet according to the adjustment policy.

The number of MDAF sending adjustment policies to IDMF may be multiple. The IDMF may determine a target adjustment policy having a smaller influence on other performance indexes (such as energy saving, network capacity, etc.) from among the plurality of adjustment policies, and adjust the network slice subnet according to the target adjustment policy.

The method 600 may further include S610.

At S610, the IDMF sends report information to the IDMS consumer.

The report message may be used to indicate real-time SLA achievement and/or predict SLA achievement. Illustratively, the IDMF may send the reporting information to the IDMS consumer periodically or aperiodically. Alternatively, reporting information may be sent to the IDMS consumer if the real-time SLA achievement level and the predicted SLA achievement level of the network slice are restored to above 100%.

Due to network fluctuations (e.g., channel degradation due to temporary occlusion, temporary preemption of resources by high priority traffic, etc.), the SLA may not reach 100% in a short period of time. As shown in fig. 7, the actual value of the SLA achievement level of the network slice subnet changes with time without adjustment according to the SLA achievement level. After time 2, the SLA achievement level of the network slice subnetwork drops below 100%; after time 6, the SLA achievement level of the network slice subnetwork is restored to above 100%.

In accordance with method 600, at time 2, the predicted SLA achievement level determined in S606 is less than 100%, and the predicted SLA achievement level (i.e., the predicted value in the graph) may be used to represent a predicted result of the SLA achievement level average for time 2 to time 3. Then S607 and S608 are performed after S606, an adjustment policy is determined, and the network elements in the network slice subnet are adjusted so that the SLA achievement level reaches 100%.

After the network elements in the network slicing sub-network are adjusted, the SLA achievement degree of the network slicing sub-network can be recovered to be more than 100% after a period of time. In the method 600, the predicted SLA achievement level determined from S606 is less than 100%, and the time period elapsed after the SLA achievement level is restored to 100% by performing S607-S609 may be referred to as the intention-to-maintain time period. If the time period is intended to be maintained longer than the time period between time 2 and time 6, the execution of S607 and S608 is redundant, resulting in waste of system resources.

In order to solve the above problems, embodiments of the present application provide a data processing method.

Fig. 8 is a schematic flow chart of a data processing method provided in an embodiment of the present application. The method 800 includes S810 to S840.

At S810, performance data for a network slice is acquired.

At S820, a first SLA achievement level for a first duration is predicted from the performance data.

In S830, if the first SLA achievement level is less than a first threshold, a second SLA achievement level of a second duration is predicted according to the performance data, where the second duration is less than the first duration.

In S840, if the second SLA achievement level is less than a second preset value, it is determined to adjust the parameters of the network slice.

The network slice may include a plurality of network slice subnets. Performance data for all or a portion of the network slice subnets in the network slice may be acquired at S810 and parameters for the all or a portion of the network slice subnets may be adjusted at S840.

The method 800 can avoid frequent adjustment of network slicing parameters caused by fluctuation of the SLA achievement level by predicting the second SLA achievement level for a shorter time if the first SLA achievement level prediction result for the longer time is smaller than the first threshold value.

The parameters of the network slice may include one or more of a maximum number of cell radio resource control (radio resource control, RRC) connected state users, a cell Resource Block (RB) availability, an RB resource control policy, a network element isolation, a computational storage resource, and the like. The maximum RRC connection state user number of the cell, the available cell RB and the RB resource control strategy are parameters of the access network slicing subnet, the network element isolation degree and the calculation storage resource are parameters of the core network slicing subnet.

The performance data of the network slice may be acquired periodically or aperiodically at S810. Thus, the first SLA achievement level may be predicted at S820 based on the newly acquired performance data; and may predict a second SLA achievement level based on the newly acquired performance data at S830.

Because S830 and S820 are not performed simultaneously, S830 is performed after S820 and the first SLA achievement level is less than the first threshold, the performance data used to calculate the second SLA achievement level in S830 may be the same as or different from the performance data used to calculate the first SLA achievement level in S820.

That is, in some embodiments, after S820, the network slice up-to-date performance data may be reacquired. In S830, a second SLA achievement level is predicted based on the latest performance data.

At S830, a second duration may be determined based on the magnitude of the first SLA achievement level, thereby predicting the second achievement level.

Specifically, in the case that the first SLA achievement level is smaller than a third threshold, the first step length may be taken as the second duration, and the third threshold is smaller than the second threshold; and when the first SLA achievement level is greater than or equal to the third threshold value, the second step length can be used as the second duration, and the first step length is smaller than the second step length.

In S830, in the case that the first SLA achievement level is less than the third threshold, a second SLA achievement level may be predicted according to the first step size; and under the condition that the first SLA achievement level is larger than or equal to a third threshold value, predicting a second SLA achievement level according to a second step length.

The step size is used for representing the predicted time length corresponding to the second SLA achievement level. In the case where the first SLA achievement level is less than the first threshold, the smaller the first SLA achievement level, the longer the time period during which the real-time SLA achievement level is less than the first threshold may be, or the greater the difference between the real-time SLA achievement level and the first threshold may be (i.e., the worse the real-time SLA achievement level) during the first time period. Under the condition that the first SLA achievement level is smaller than a third threshold value, a plurality of second SLA achievement levels in the first duration are predicted by adopting a smaller step length, so that the adjustment of parameters of the network slice can be more timely.

Illustratively, at S830, the prediction may be performed according to a prediction period, a prediction step number, and a second duration. The time interval between the prediction time points is equal to the prediction period. At each prediction time point, a prediction may be performed, and the number of obtained second SLA achievement levels is the same as the number of prediction steps, and each second SLA achievement level is used to represent SLA achievement levels of a plurality of continuous second durations after the prediction time point. The prediction period may be greater than, less than, or equal to the product of the number of prediction steps and the second duration.

The prediction period and the number of prediction steps may be preset, may be received, or may be determined according to the second duration. For example, different step sizes may correspond to different prediction periods, and different step sizes may correspond to different prediction steps.

In some embodiments, a plurality of predictions of second SLA achievement level may be made based on performance data obtained at the beginning of S830.

In other embodiments, the performance data may be obtained according to a prediction period, and the second SLA achievement level may be predicted according to the number of prediction steps and the second duration according to the performance data obtained for each prediction period.

As shown in fig. 11, at the prediction time point 1, performance data may be obtained, prediction may be performed according to the predicted step number and the second duration according to the performance data, and if the predicted step number is 5, 5 second SLA achievement levels may be obtained, where the 5 SLAs are respectively used to represent the SLA achievement levels of the network slice for 5 consecutive second durations after the prediction time point 1.

The time interval between the prediction time point 2 and the prediction time point 1 may be a prediction period. At the prediction time point 2, the performance data may be reacquired, and the prediction may be performed according to the number of prediction steps and the second duration based on the new performance data.

The prediction period may be greater than, less than, or equal to the product of the number of prediction steps and the second duration. For example, the prediction period may be equal to a positive integer multiple of the second duration.

In still other embodiments, performance data may be acquired periodically or aperiodically. And the second SLA achievement degree can be predicted according to the latest acquired performance data, the prediction period, the prediction step number and the second duration.

To reduce the number of predictions, a real-time SLA achievement level may be determined from the performance data prior to S820. In S820, if the real-time SLA achievement level is less than a fourth threshold, the first SLA achievement level is predicted from the performance data, the fourth threshold being greater than the second threshold.

The fourth threshold is associated with traffic of the network slice service.

At S820, the fourth threshold sent by the IDMF may be received. In some embodiments, the IDMF may obtain SLA provisioning intent creation information sent by the IDMS consumer. The SLA provisioning intent creation information may include a fourth threshold. The service corresponding to the IDMS consumer is a service of the network slice service, and the IDMS consumer can determine the fourth threshold according to the service requirement. Therefore, the fourth threshold has an association relationship with the traffic of the network slice service.

In other embodiments, the IDMF may determine the fourth threshold based on received SLA provisioning intent creation information or other information related to traffic of the network slicing service.

Fig. 9 is a schematic flow chart of a data processing method provided in an embodiment of the present application. The method 900 includes S901 to S912.

At S901, the IDMS consumer sends SLA provisioning intent information and a first predictive trigger threshold to an intent driver management function (intent driven management, IDMF).

The IDMS consumer may determine SLA provisioning intent information and a first predictive trigger threshold based on the traffic. SLA provisioning intent information may be used to indicate information such as analysis objects and computational formulas.

The analysis object may include all or a portion of a network slice subnet in the network slice that serves the IDMS consumer.

The calculation formula is used for expressing the relation between the performance parameters of the analysis object and the SLA achievement degree. The performance parameters of the analysis object may include key performance indicators (key performance indicator, KPI), such as Bao Yanshi (packet delay), throughput (throughput), etc. For example, the SLA assurance intent information may include an analysis indicator and a limit value for the analysis indicator. Based on the analysis index and the limit value of the analysis index, the IDMF can determine a calculation formula. The number of analysis indicators in the SLA provisioning intent information may be one or more. Each analysis index can also be understood as a performance parameter.

Illustratively, according to a calculation formula, the SLA achievement level may be a mean, median, maximum, minimum, mode of the achievement levels of the plurality of analysis indicators. That is, the SLA achievement level may be used to represent a data set trend of multiple analysis index achievement levels.

Each analysis indicator achievement level may be expressed as a difference between a detected value of the analysis indicator and a limit value of the analysis indicator. For example, the indicator achievement level of the average delay may be expressed as 1+ (τ0- τ)/τ0, τ0 being used to represent the average delay threshold and τ being used to represent the average delay (i.e., the detected value of the average delay) calculated using the collected performance data.

The first predictive trigger threshold may be greater than 100%, for example, may be 120%, 130%, etc.

At S902, IDMF performs intent translation on SLA provisioning intent information, the first predictive trigger threshold.

At S903, the IDMF sends the translated SLA provisioning intent information and the first predictive trigger threshold to the MDAF.

At S904, the MDAF obtains performance data of the network slice subnet corresponding to the NSSMF from the NSSMF according to the analysis object.

It should be appreciated that different NSSMFs may correspond to different network slice subnets. The MDAF may obtain performance data from one or more NSSMFs. That is, the performance data acquired by the MDAF may include values of performance parameters of one or more network slice subnets.

At S905, the MDAF determines the real-time SLA achievement level according to the performance data using a calculation formula.

The MDAF may acquire performance data periodically or aperiodically, and perform S905 after each acquisition of performance data. That is, the MDAF may calculate the real-time SLA achievement level periodically or aperiodically.

The period during which the MDAF acquires performance data may also be referred to as an analysis period. The analysis period may be preset in the MDAF, may be determined by the MDAF according to parameters such as the computing capability, or may be transmitted to the MDAF by the IDMF. Illustratively, the IDMF receives the analysis period sent by the IDMS consumer and forwards it to the MDAF.

At S906, the MDAF determines whether the real-time SLA achievement level is greater than or equal to a first predictive trigger threshold.

In the case where the real-time SLA achievement level is greater than or equal to the first predictive trigger threshold, the steps S904, S905 and subsequent steps are performed back.

In the case that the real-time SLA achievement level is less than the first predictive trigger threshold, S907 is performed.

In S907, the MDAF predicts a first SLA achievement level for the first duration according to the performance data.

The first duration may be greater than or equal to the intended maintenance duration. The intended duration of maintenance may be understood as the length of time required from the MDAF determination to meet the network slice adjustment condition until the adjusted network slice performance parameter stabilizes. The network slice adjustment condition may be that the first SLA achievement level or the second SLA achievement level is less than a second predictive trigger threshold.

The first duration may be equal to a positive integer multiple of the analysis period. Illustratively, the analysis period may be 1 minute (min), and the first duration may be 30 minutes (min).

The first SLA achievement level for the first duration may be determined by the MDAF based on the predicted value type and the SLA achievement levels for the plurality of time points in the first duration. The predictor type may be used to indicate a maximum, minimum, average, etc.

The type of the predicted value may be preset in the MDAF, may be preset in the IDMF and sent to the MDAF, or may be sent to the IDMF by the IDMF consumer and sent to the MDAF by the IDMF translation.

The first SLA achievement level may be predicted according to the first number of prediction steps. The first prediction step number may be a positive integer. That is, in the case where the first prediction step number is greater than 1, a plurality of second SLA achievement levels may be obtained each time the prediction of S907 is performed, and the number of obtained second SLA achievement levels is the same as the first prediction step number. The plurality of first SLA achievement levels are used to represent a plurality of consecutive first-time-period SLA achievement levels after the time point at which S907 is performed, respectively.

At S908, the MDAF determines whether the first SLA achievement level is greater than or equal to a second predictive trigger threshold.

The second prediction trigger threshold may be preset in the MDAF or IDMF, may be sent to the IDMF by the IDMS consumer and sent to the MDAF via IDMF translation, or may be determined by the MDAF or IDMF.

The second predictive trigger threshold may be less than or equal to the first predictive trigger threshold. Illustratively, the adjustment trigger threshold may be 100%.

In the case where the first SLA achievement level is greater than or equal to the second prediction trigger threshold, S907 and S908 are executed back until the number of times of the first SLA achievement level prediction reaches the first prediction number of times.

That is, after S906, the number of times the first SLA achievement level may be predicted, that is, the number of times S907 is performed, may be at most the first predicted number of times. When the number of executions of S907 reaches the first predicted number, if the first SLA achievement level is still greater than or equal to the second predicted trigger threshold, S904 and S905 and the subsequent steps may be returned to be executed.

The execution of S907 may be periodic or aperiodic. The repetition period of S907 may be greater than, equal to, or less than the product of the first number of predicted steps and the first time period.

The first prediction frequency may be preset in the MDAF, or may be sent by the IDMF to the MDAF, which is not limited in the embodiment of the present application. The preset first prediction step number in MDAF may be, for example, 1.

If the first SLA achievement level is smaller than the second prediction trigger threshold, S909 is performed.

In S909, the MDAF determines the second duration according to the magnitude relation between the first SLA achievement level and the parameter threshold.

And under the condition that the first SLA achievement level is smaller than the parameter threshold value, the second duration is the first step length.

And under the condition that the first SLA achievement level is greater than or equal to the parameter threshold value, the second duration is a second step length. The first step size is smaller than the second step size.

The first step size and the second step size can be preset in the MDAF or can be sent to the MDAF by the IDMF.

At S910, a second SLA achievement level is predicted according to a second duration.

The second duration is less than the first duration. That is, the first step length and the second step length are smaller than the first duration. The second time period may be, for example, 1min, 2min, 5min, or the like.

When the prediction of the second SLA achievement level is performed according to the first step size, the second prediction step number may be a first step number corresponding to the first step size. When the prediction of the second SLA achievement level is performed according to the second step size, the second prediction step number may be a second step number corresponding to the second step size. That is, each time the prediction in S910 is performed, a plurality of second SLA achievement levels may be obtained, at least one second SLA achievement level is obtained, and the number of obtained second SLA achievement levels is the same as the second prediction step number. The plurality of second SLA achievement levels are used to represent the SLA achievement levels for a plurality of consecutive second durations after the point in time at which S910 is performed, respectively.

The first step number corresponding to the first step length and the second step number corresponding to the second step length can be equal or unequal.

The first step size, the second step size, the first step number corresponding to the first step size, and the second step number corresponding to the second step size may be preset in the MDAF, or may be sent to the IDMF by the IDMS consumer, and then sent to the MDAF through the IDMF translation.

In S911, the relationship between the second SLA achievement level and the adjustment trigger threshold is determined.

The adjustment trigger threshold may be preset in the MDAF, or may be sent by the IDMS consumer to the IDMF and translated by the IDMF to the MDAF.

The adjustment trigger threshold may be greater than, less than, or equal to the second predictive trigger threshold. Illustratively, the adjustment trigger threshold may be 100%.

If the second SLA achievement level is greater than or equal to the adjustment trigger threshold, the process returns to S910 and S911.

S910 may be performed according to a second prediction period, which may be greater than, less than, or equal to a product of the second number of predicted steps and a second duration.

For example, in the case where the second SLA achievement level is less than 80%, the second duration is equal to 1 minute for the first step, the second prediction step number may be 5, and the second prediction period may be 5 minutes; in the case where the second SLA achievement level is between 80% and 100%, the second duration is equal to 5 minutes for the second step size, the second predicted number of steps may be 1, and the second prediction period may be 5 minutes.

After S909, a second SLA achievement level prediction may be performed at most a second prediction number. That is, after each execution of S909, the number of executions of S910 is at most the second prediction number. When the number of executions of S910 reaches the second predicted number, if the second SLA achievement level is still greater than or equal to the adjustment trigger threshold, S904 and S905 and the subsequent steps may be performed back.

The second prediction number may be preset in the MDAF, may be transmitted by the IDMF, or may be determined according to the first duration, the second prediction period, or the like. For example, the second number of predictions may be a product of a quotient of the first time period divided by the second prediction period.

If the second SLA achievement level is smaller than the adjustment trigger threshold, S912 is performed.

It should be understood that, in the case where the second prediction step number is greater than 1, that is, the number of second SLA achievement levels obtained in S910 is a plurality, S912 may be performed in the case where any one of the plurality of second SLA achievement levels is less than the adjustment trigger threshold.

At S912, parameters of the network slice are adjusted.

Specifically, in the case where the second SLA achievement level is less than the adjustment trigger threshold, the MDAF may send indication information to the IDMF to indicate that the IDMF determines the adjustment policy. After the IDMF determines the adjustment policy, parameters of each network element in the network slice subnet may be adjusted according to the adjustment policy.

Alternatively, in the event that the second SLA achievement level is less than the adjustment trigger threshold, the MDAF may determine an adjustment policy, and send the adjustment policy to the IDMF.

In some embodiments, S912 may also be performed if S908 determines that the first SLA achievement level is less than the second predictive trigger threshold.

Fig. 10 is a schematic flow chart of a data processing method provided in an embodiment of the present application. The method 1000 includes S901 to S912, and S1001 to S1003 in the method 900.

The IDMF may also send the first prediction parameter to the MDAF at S903.

The first prediction parameter may include one or more of a first number of prediction steps, a first prediction period, a first duration.

After S903, the MDAF may establish an analysis instance according to the SLA guarantee intention information, and proceed to S1001.

In S1001, the MDAF transmits response information to the IDMF. The response information may include an instance identification indicating the analysis instance.

After S903, the MDAF may perform S904 to S908 using the analysis instance.

In the case where S908 determines that the first SLA achievement level is greater than or equal to the second predictive trigger threshold, S904 and S905 are performed back.

If it is determined in S908 that the first SLA achievement level is smaller than the second predictive trigger threshold, S1002 is performed.

At S1002, the MDAF sends the first SLA achievement level to the IDMF. The reporting information may include a first SLA achievement level and an instance identification.

After receiving the report information, the IDMF may proceed to S909.

In S909, the IDMF determines a prediction step according to the first SLA achievement level.

In the case where the first SLA achievement level is less than the parameter threshold, the IDMF may determine the prediction step size to be the first step size.

In the case where the first SLA achievement level is greater than or equal to the parameter threshold, the IDMF may determine the prediction step size to be the second step size. The first step size is smaller than the second step size.

After S909, S1003 may be performed.

At S1003, the IDMF sends the second prediction parameter and the instance identification to the MDAF.

The second prediction parameters may include one or more of a second prediction step size, a second prediction period, a second duration, and the like.

After S1003, the MDAF may proceed with S910 and S911 according to the second prediction parameter. If the second SLA achievement level is smaller than the adjustment trigger threshold, S912 is performed.

In S912, parameters of the network slice subnetwork are adjusted.

It should be appreciated that, in comparison to method 1000, the determination of the first prediction parameter, the second prediction parameter may be performed by the MDAF in method 900, thereby reducing signaling overhead between the MDAF and the IDMF.

Fig. 12 is a schematic flow chart of a data processing method provided in an embodiment of the present application. The method 1200 includes S1210 to S1240.

At S1210, performance data of the network slice is acquired.

At S1220, a real-time service level agreement achievement level is determined from the performance data.

In S1230, if the real-time service level agreement achievement level is less than the fourth threshold, a second service level agreement achievement level for a second duration is predicted from the performance data.

In S1240, if the second service level agreement achievement level is less than a second threshold, it is determined to adjust a parameter of the network slice, the fourth threshold being greater than the second threshold.

By means of the method 1200, when the real-time SLA achievement level is smaller than the fourth threshold, the second SLA achievement level is predicted, so that the number of predictions can be reduced, and occupation of resources can be reduced.

Alternatively, the first service level agreement achievement level for the first duration may be predicted from the performance data if the real-time service level agreement achievement level is less than a fourth threshold.

In S1230, the second service level agreement achievement level may be predicted from the performance data, the second duration being less than the first duration, if the first service level agreement achievement level is less than a first threshold.

By predicting the second SLA achievement level for a shorter time when the first SLA achievement level prediction result for a longer time is smaller than the first threshold value, frequent adjustment of network slicing parameters caused by fluctuation of the SLA achievement level can be avoided.

For example, the first duration may be greater than or equal to the intended-to-sustain duration. The intended duration of maintenance is used to represent the length of time required from determining adjustments to the network slice to stabilization of the network slice performance parameters. The intent-to-maintain duration may be a statistical value, i.e., the intent-to-maintain duration may be used to represent a trend in the data set for the length of time required for the network slice performance parameter to stabilize after each determination of an adjustment to the network slice.

Optionally, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold; and in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

The smaller the first SLA achievement level, the longer the length of time that the real-time SLA achievement level is below the first threshold value may be in the first duration, or the greater the difference between the real-time SLA achievement level and the first threshold value may be in the first duration. Under the condition that the first SLA achievement level is smaller than a third threshold value, a plurality of second SLA achievement levels in the first duration are predicted by adopting a smaller step length, so that the adjustment of parameters of the network slice can be more timely.

Optionally, the fourth threshold is associated with traffic of the network slice service.

And under the condition that the real-time SLA achievement level is smaller than a fourth threshold value, the first SLA achievement level is predicted, and the fourth threshold value is associated with the business of the network slicing service, so that the condition for predicting the first SLA achievement level meets business requirements more reasonably.

Method embodiments of the present application are described above in connection with fig. 1-12, and apparatus embodiments of the present application are described below in connection with fig. 13-14. It is to be understood that the description of the method embodiments corresponds to the description of the device embodiments, and that parts not described in detail can therefore be seen in the preceding method embodiments.

Fig. 13 is a schematic structural diagram of a data processing apparatus provided in an embodiment of the present application.

The data processing apparatus 2000 includes an acquisition module 2010 and a processing module 2020.

In some embodiments, the acquiring module 2010 is used to acquire performance data of the network slice.

The processing module 2020 is configured to predict a first service level agreement achievement level for a first duration based on the performance data.

The processing module 2020 is further configured to predict, based on the performance data, a second service level agreement achievement level for a second duration, where the second duration is less than the first duration, if the first service level agreement achievement level is less than a first threshold;

The processing module 2020 is further configured to determine to adjust a parameter of the network slice if the second service level agreement achievement level is less than a second threshold.

Optionally, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold.

And in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

Optionally, the processing module 2020 is further configured to determine a real-time service level agreement achievement level based on the performance data.

The processing module 2020 is specifically configured to predict the first service level agreement achievement level according to the performance data, where the real-time service level agreement achievement level is less than a fourth threshold, and the fourth threshold is greater than the second threshold.

Optionally, the fourth threshold is associated with traffic of the network slice service.

In other embodiments, the acquiring module 2010 is configured to acquire performance data of the network slice.

The processing module 2020 is configured to determine a real-time service level agreement achievement level according to the performance data.

The processing module 2020 is further configured to predict a second service level agreement achievement level for a second duration based on the performance data if the real-time service level agreement achievement level is less than a fourth threshold.

The processing module 2020 is further configured to determine to adjust a parameter of the network slice if the second service level agreement achievement level is less than a second threshold, and the fourth threshold is greater than the second threshold.

Optionally, the processing module 2020 is further configured to predict, based on the performance data, a first service level agreement achievement level for a first duration if the real-time service level agreement achievement level is less than a fourth threshold.

The processing module 2020 is specifically configured to predict, according to the performance data, the second service level agreement achievement level, where the second duration is less than the first duration, when the first service level agreement achievement level is less than a first threshold.

Optionally, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold.

And in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

Optionally, the fourth threshold is associated with traffic of the network slice service.

Fig. 14 is a schematic structural diagram of a data processing apparatus provided in an embodiment of the present application.

The data processing apparatus 3000 includes a memory 3010 and a processor 3020.

Memory 3010 is used to store program instructions.

The processor 3020 is configured to perform the methods described above when the program instructions are executed in the processor 3020.

Specifically, in some embodiments, processor 3020 is used to obtain performance data for a network slice.

Processor 3020 is further configured to predict a first service level agreement achievement level for the first duration based on the performance data.

Processor 3020 is further configured to predict a second service level agreement achievement level for a second duration based on the performance data if the first service level agreement achievement level is less than a first threshold, the second duration being less than the first duration.

Processor 3020 is further configured to determine to adjust the parameter of the network slice if the second service level agreement achievement level is less than a second threshold.

Optionally, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold.

And in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

Optionally, the processor 3020 is further configured to determine a real-time service level agreement achievement level based on the performance data.

Processor 3020 is further configured to predict the first service level agreement achievement level based on the performance data if the real-time service level agreement achievement level is less than a fourth threshold, the fourth threshold being greater than the second threshold.

Optionally, the fourth threshold is associated with traffic of the network slice service. In other embodiments, processor 3020 is used to obtain performance data for a network slice.

Processor 3020 is also configured to determine a real-time service level agreement achievement level based on the performance data.

Processor 3020 is further configured to predict a second service level agreement achievement level for a second duration based on the performance data if the real-time service level agreement achievement level is less than a fourth threshold.

Processor 3020 is further configured to determine to adjust the parameter of the network slice if the second service level agreement achievement level is less than a second threshold, the fourth threshold being greater than the second threshold.

Optionally, the processor 3020 is further configured to predict, based on the performance data, a first service level agreement achievement level for a first duration if the real-time service level agreement achievement level is less than a fourth threshold.

Processor 3020 is further configured to predict the second service level agreement achievement level based on the performance data if the first service level agreement achievement level is less than a first threshold, the second duration being less than the first duration.

Optionally, in a case where the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold.

And in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

Optionally, the fourth threshold is associated with traffic of the network slice service.

Furthermore, the units in the above apparatus may be integrated together in whole or in part, or may be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SOC). The SOC may include at least one processor for implementing any of the methods above or for implementing the functions of the units of the apparatus, where the at least one processor may be of different types, including, for example, a CPU and FPGA, a CPU and artificial intelligence processor, a CPU and graphics processor (graphics processing unit, GPU), etc.

The embodiments of the present application also provide a computer program storage medium, characterized in that the computer program storage medium has program instructions which, when executed, cause the method in the foregoing to be performed.

Embodiments of the present application also provide a chip system, wherein the chip system includes at least one processor, and program instructions, when executed in the at least one processor, cause the method in the foregoing to be performed.

The present embodiments also provide a program product comprising program instructions which, when executed in a computer device, cause the foregoing data processing method to be performed.

It should be appreciated that the processor in embodiments of the present application may be a central processing unit (central processing unit, CPU), but may also be other general purpose processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), off-the-shelf programmable gate arrays (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It should also be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example but not limitation, many forms of random access memory (random access memory, RAM) are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.

It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.

In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.

In the embodiment of the present application, prefix words such as "first" and "second" are used merely to distinguish different description objects, and there is no limitation on the location, order, priority, number, content, or the like of the described objects. For example, the described object is "duration", and ordinal words preceding the "duration" in the "first duration" and the "second duration" do not limit the position or order or priority between the "durations"; for another example, the object being described is a "step size", and the ordinal words preceding the "step size" in the "first step size" and the "second step size" do not limit the position or order or priority between the "step sizes".

It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software 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.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by 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 (20)

1. A method of data processing, comprising:

acquiring performance data of a network slice;

predicting a first service level agreement achievement level of a first duration according to the performance data;

predicting a second SLA achievement level of a second duration according to the performance data, wherein the second duration is smaller than the first duration under the condition that the first service level agreement achievement level is smaller than a first threshold;

and determining to adjust the parameters of the network slice under the condition that the second service level agreement achievement degree is smaller than a second threshold value.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

in the case that the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold;

And in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

3. The method according to claim 1 or 2, characterized in that the method further comprises:

determining the achievement degree of a real-time service level agreement according to the performance data;

the predicting the first service level agreement achievement level of the first duration according to the performance data comprises: and predicting the first service level agreement achievement level according to the performance data if the real-time service level agreement achievement level is less than a fourth threshold, wherein the fourth threshold is greater than the second threshold.

4. The method of claim 3, wherein the fourth threshold is associated with traffic of the network slice service.

5. A method of data processing, comprising:

acquiring performance data of a network slice;

determining the achievement degree of a real-time service level agreement according to the performance data;

predicting a second service level agreement achievement level of a second duration according to the performance data when the real-time service level agreement achievement level is less than a fourth threshold;

And under the condition that the second service level agreement achievement degree is smaller than a second threshold value, determining to adjust the parameters of the network slice, wherein the fourth threshold value is larger than the second threshold value.

6. The method of claim 5, wherein the step of determining the position of the probe is performed,

the method comprises the following steps: under the condition that the real-time service level agreement achievement level is smaller than a fourth threshold value, predicting a first service level agreement achievement level of a first duration according to the performance data;

the predicting the second service level agreement achievement degree of the second duration according to the performance data comprises the following steps: and under the condition that the first service level agreement achievement level is smaller than a first threshold value, predicting the second service level agreement achievement level according to the performance data, wherein the second duration is smaller than the first duration.

7. The method of claim 6, wherein the step of providing the first layer comprises,

in the case that the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold;

and in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

8. The method of any of claims 5-7, wherein the fourth threshold is associated with traffic of the network slice service.

9. A data processing apparatus, comprising:

the acquisition module is used for acquiring the performance data of the network slice;

the processing module is used for predicting the first service level agreement achievement degree of the first duration according to the performance data;

the processing module is further configured to predict, according to the performance data, a second service level agreement achievement level for a second duration, where the second duration is less than the first duration, if the first service level agreement achievement level is less than a first threshold;

the processing module is further configured to determine to adjust a parameter of the network slice if the second service level agreement achievement level is less than a second threshold.

10. The apparatus of claim 9, wherein the device comprises a plurality of sensors,

in the case that the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold;

and in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

11. The device according to claim 9 or 10, wherein,

the processing module is further used for determining the achievement degree of the real-time service level agreement according to the performance data;

the processing module is further configured to predict the first service level agreement achievement level based on the performance data if the real-time service level agreement achievement level is less than a fourth threshold, where the fourth threshold is greater than the second threshold.

12. The apparatus of claim 11, wherein the fourth threshold is associated with traffic of the network slice service.

13. A data processing apparatus, comprising:

the acquisition module is used for acquiring the performance data of the network slice;

the processing module is used for determining the achievement degree of the real-time service level agreement according to the performance data;

the processing module is further configured to predict a second service level agreement achievement level for a second duration according to the performance data if the real-time service level agreement achievement level is less than a fourth threshold;

the processing module is further configured to determine to adjust a parameter of the network slice if the second service level agreement achievement level is less than a second threshold, and the fourth threshold is greater than the second threshold.

14. The apparatus of claim 13, wherein the device comprises a plurality of sensors,

the processing module is further configured to predict, according to the performance data, a first service level agreement achievement level for a first duration if the real-time service level agreement achievement level is less than a fourth threshold;

the processing module is further configured to predict, based on the performance data, the second service level agreement achievement level, the second duration being less than the first duration, if the first service level agreement achievement level is less than a first threshold.

15. The apparatus of claim 14, wherein the device comprises a plurality of sensors,

in the case that the first service level agreement achievement level is less than a third threshold, the second duration is equal to a first step size, and the third threshold is less than the second threshold;

and in the case that the achievement level of the first service level agreement is greater than or equal to the third threshold value, the second duration is equal to a second step length, and the first step length is smaller than the second step length.

16. The apparatus of any of claims 13-15, wherein the fourth threshold is associated with traffic of the network slice service.

17. A data processing apparatus comprising a memory for storing a program and a processor for executing the program to perform the method of any of claims 1-8.

18. A computer program product comprising program instructions which, when executed, perform the method of any of claims 1 to 8.

19. A computer readable storage medium storing program code for execution by a device, the program instructions when executed being such that the method of any one of claims 1 to 8 is performed.

20. A chip comprising at least one processor, wherein program instructions, when executed in the at least one processor, cause the method of any one of claims 1 to 8 to be performed.