WO2016065858A1

WO2016065858A1 - Method and device for deploying virtual core network

Info

Publication number: WO2016065858A1
Application number: PCT/CN2015/076646
Authority: WO
Inventors: 巨满昌; 顾希
Original assignee: 中兴通讯股份有限公司
Priority date: 2014-10-30
Filing date: 2015-04-15
Publication date: 2016-05-06
Also published as: CN105610592A

Abstract

A method and device for deploying a virtual core network include: periodically predicting, according to the pre-acquired historical data representing the network element load of the core network, the data representing the network element load of the core network at a future time; when determining, according to the predicted data representing the network element load of the core network at a certain future time, that virtual machine capacity expansion or flexible virtual machine expansion needs to be performed at the future time, calculating a first newly-added virtual machine quantity according to the predicted data representing the network element load of the core network at the future time; and at a certain preset time point before the future time, notifying, by a Network Virtualisation Function Management (NVFM), a Network Virtualisation Function Orchestration (NVFO) to perform virtual machine capacity expansion, where the calculated first newly-added virtual machine quantity is also notified to the NVFO by the NVFM. The embodiments of the present invention can timely and effectively adjust the number of network virtual machines, and improve user experience.

Description

Method and device for deploying virtual core network

Technical field

This paper covers the field of communications and cloud computing, especially a method and device for deploying a virtual core network.

Background technique

Third Generation Partnership Project ^{(3GPP, 3 rd Generation Partnership Project} ) system architecture evolution (SAE) is the current mainstream technology evolution and development of the mobile network, it is widely used domestic and foreign operators and communications equipment business, its core network, also known as It is an evolved packet core network (EPC, Evolved Packet Core). The evolved packet core network (EPC) includes a Packet Data Network Gateway (PGW), a Serving-Gate Way (SGW), and a Mobility Management Entity (MME). In addition to the EPC, the core network includes a softswitch and an Internet Protocol (IP) multimedia subsystem (IMS, IP Multimedia Subsystem).

Cloud platforms refer to common cloud operating systems such as OpenStack, virtualization platforms (VmWare, vShpere), and cloud platform services (CloudStack). OpenStack is an infrastructure-as-a-service (IaaS) cloud computing solution. It is supported by many international companies with its full open source and is also concerned by the domestic industry.

The idea of Network Functions Virtualisation (NFV) is to use the virtualization technology to separate the business application from the underlying software architecture. The business runs on the virtual machine, and the virtual machine shields the underlying hardware, operating system, and storage. The differences at the network level form a relatively unified and simple operating environment. Operators can reduce equipment investment and reduce equipment costs and operation and maintenance costs.

Common virtualization systems include virtual systems (VmWare), Kernel-based Virtual Machine (KVM), and Xen. VmWare is a commercial virtualization tool that charges, functions stably, supports common underlying operating systems, and is not open source. KVM is a lightweight virtualization tool under Linux, open source. Xen is a virtualization tool implemented by the operating system's strong correlation mode. Virtualization The system can implement each core network element as a virtual machine deployed on the cloud platform. Similarly, softswitches and IMS devices can also be virtualized.

Through the capacity expansion or shrinkage deployment of the NE virtual machine, the processing capacity of the mobile core network element service is enhanced or weakened, energy consumption is reduced, and energy saving and emission reduction are realized.

Related art methods for deploying a virtual core network generally include:

Collecting data representing the current core network element load (such as one or more of a Packet Data Protocol (PDP), service traffic, number of users, and call volume), and characterizing the current core network element according to the collected Load data, when it is determined that the virtual machine needs to be expanded or expanded, the number of newly added virtual machines is calculated according to the collected data representing the current core network element load, and the virtualized management of the network function (VNFM, Virtualised) The Network Function Manager informs the Network Function Virtualised Orchestrator (NVFO) to expand or pop the virtual machine, and calculate the number of newly added virtual machines; when the current core network element is characterized according to the collected Load data, determine the current need to shrink the virtual machine or pop into the virtual machine, calculate the reduced number of virtual machines based on the collected data representing the current core network element load, and notify the NVFO of the virtual machine to shrink the volume through the VNFM. Or pop into the virtual machine, and calculate the number of reduced virtual machines.

In the method of deploying the virtual core network in the related art, the virtual machine is expanded or the virtual machine is ejected, which requires a certain processing time. As a result, the user migration and data synchronization take longer after the virtual machine is ejected, and the original virtual machine cannot be used. Handling services in a timely manner may further result in users being unable to access, and thus the user experience is degraded.

Summary of the invention

The embodiment of the invention provides a method and device for deploying a virtual core network, which can improve user experience.

In order to solve the above problem, the embodiment of the present invention provides a method for deploying a virtual core network, including:

Periodically predicting data representing the core network element load in the future time according to the pre-acquired historical data representing the core network element load;

When the data of the core network element load is predicted according to the predicted future time, and the virtual machine is required to be expanded at the future time, the first data of the core network element load is calculated according to the predicted future time. The number of new virtual machines added;

At a preset time point before the arrival of the future time, the network function virtualization management NVFM notifies the network function to virtualize the NVFO to expand the virtual machine and the number of the first newly added virtual machines.

Optionally, it also includes:

Real-time acquisition of data representing the core network element load;

Determining, according to the predicted data of the core network element load of the future time, that the virtual machine needs to be expanded at the future time, according to the preset time point before the arrival of the future time Characterizing the data of the core network element load, and calculating the number of the second newly added virtual machine;

At the preset time point before the arrival of the future time, the NVFO is notified by the NVFM to perform capacity expansion of the virtual machine, and the number of the first newly added virtual machine and the second newly added virtual machine The larger the number.

Optionally, the method further includes:

When the data of the core network element load is characterized according to the predicted future time, and the virtual machine is required to be reduced in the future time, the data of the core network element load is calculated according to the predicted future time. a reduced number of virtual machines;

At the future moment, the NVFO is notified by the NVFM to perform virtual machine shrinkage and the first reduced number of virtual machines.

Optionally, the method further includes:

The system flag is asserted during the time period from the preset time point to the future time, and the system flag is set to be invalid when the future time arrives.

Optionally, the method further includes:

Real-time acquisition of data representing the core network element load;

When it is determined that the virtual machine is required to be reduced according to the data of the core network element load obtained in real time, and the system is marked as invalid, the calculation is performed according to the obtained core network element load data. The number of reduced virtual machines;

Notifying the NVFO by the NVFM for virtual machine shrinkage and the second reduced number of virtual machines.

Optionally, the method further includes:

Real-time acquisition of data representing the core network element load;

Determining, according to the data of the core network element load obtained at the future time, that the virtual machine is required to be reduced at the future time, and the data of the core network element load is characterized according to the predicted future time, Determining that the virtual machine needs to be reduced in the future time, and calculating the third reduced number of virtual machines according to the data that is obtained at the future time and that represents the core network element load;

Notifying the NVFO by the NVFM at the future time to perform virtual machine shrinkage and the third reduced number of virtual machines.

An embodiment of the present invention further provides an apparatus for deploying a virtual core network, including:

Obtaining a module, configured to obtain historical data representing a core network element load;

The prediction module is configured to periodically predict, according to the acquired historical data representing the core network element load of the core network, data representing the core network element load at a future time;

The notification module is configured to: according to the predicted data of the core network element load of the future time, determine, when the virtual machine needs to be expanded at the future time, represent the data of the core network element load according to the predicted future time, Calculating the number of the first newly added virtual machines, and at a preset time point before the arrival of the future time, the NVFM is notified by the network function virtualization management network function to virtualize the NVFO for VM expansion and the first added virtual Number of machines.

Optionally, the obtaining module is further configured to:

Real-time acquisition of data representing the core network element load;

The notification module is further configured to:

Determining, according to the predicted data of the core network element load of the future time, that the virtual machine is required to be expanded at the future time, according to the characterization obtained at the preset time point before the arrival of the future time Data of the core network element load, calculating a second newly added number of virtual machines; and reporting, by the NVFM, the preset time point before the arrival of the future time The NVFO performs virtual machine expansion, and a larger value of the number of the first newly added virtual machines and the number of the second newly added virtual machines.

Optionally, the notification module is further configured to:

When the data of the core network element load is predicted according to the predicted future time, and the virtual machine is required to be reduced at the moment, the first data of the core network element load is calculated according to the predicted future time. The reduced number of virtual machines; at the future time, the NVFO is notified by the NVFM to perform virtual machine shrinkage and the first reduced number of virtual machines.

Optionally, the notification module is further configured to:

Optionally, the obtaining module is further configured to:

Real-time acquisition of data representing the core network element load;

The notification module is further configured to:

When it is determined that the virtual machine is required to be reduced in the future time according to the data of the core network element load obtained in the future time, and the system is marked as invalid, according to the obtained core network element load Data, calculating a second reduced number of virtual machines; notifying the NVFO of the virtual machine shrinking and the second reduced number of virtual machines by the NVFM.

Optionally, the obtaining module is further configured to:

Real-time acquisition of data representing the core network element load;

The notification module is further configured to:

Determining that the virtual machine needs to be reduced in the future time according to the predicted data of the core network element load in the future time, and determining, according to the data representing the core network element load obtained at the future time, When the virtual machine needs to be reduced in the future time; calculating the third reduced number of virtual machines according to the data that is obtained at the future time and representing the core network element load; and the NVFM notification station at the future time The NVFO performs virtual machine shrinkage and the third reduced number of virtual machines.

An embodiment of the present invention further provides a computer readable storage medium, where the storage medium stores The computer program includes program instructions that, when executed by a device deployed in the virtual core network, cause the device to perform the above-described method of deploying a virtual core network.

Compared with the related art, the embodiment of the present invention includes: periodically predicting, according to historical data representing the core network element load of the core network, the data representing the core network element load at a future time; according to a predicted future moment Determining the data of the core network element load, determining that the virtual machine needs to be expanded or expanded by the virtual machine at the future time, and calculating the first newly added virtual machine according to the predicted data of the core network element load at the future time. The number of the virtual machines is notified by the network function virtualization management NVFM and the number of the first newly added virtual machines. The solution of the embodiment of the present invention predicts, by using the historical data representing the core network element load of the core network, a data indicating the core network element load of the future time, so that a preset time before the arrival of the future time In the meantime, the NVFM is notified to expand the virtual machine or expand the virtual machine, and a sufficient time is reserved for the expansion of the virtual machine. The solution of the embodiment of the present invention may also be used to predict the result and before the arrival of the future time. The data of the core network element load that is acquired in real time at a preset time point is combined to determine the better virtual machine's capacity expansion or the number of virtual machine expansions, or the predicted result and/or the characterization obtained in real time at the future time. The data of the core network element load determines the shrinkage of the virtual machine or the number of virtual machines that are zoomed out to improve the user experience.

BRIEF abstract

The drawings in the following description of the embodiments of the present invention are intended to illustrate the invention, and are not intended to limit the scope of the invention.

1 is a flowchart of a method for deploying a virtual core network according to an embodiment of the present invention;

Figure 2 is an actual data collection diagram of the total number of PDPs operated on the existing network in a certain place;

FIG. 3 is a schematic structural diagram of an apparatus for deploying a virtual core network according to an embodiment of the present invention.

Preferred embodiment of the invention

In order to facilitate the understanding of those skilled in the art, the embodiments of the present invention are further described below with reference to the accompanying drawings. The description of the steps is not intended to limit the scope of the invention. It should be noted that the embodiments in the present application and the various manners in the embodiments may be combined with each other without conflict.

Referring to FIG. 1, an embodiment of the present invention provides a method for deploying a virtual core network, including:

Step 100: Periodically predict, according to historical data representing the core network element load of the core network, data representing the core network element load at a certain moment in the future.

In this step, the core network element may be an MME, or an SGW, or a PGW, or a softswitch device, or an IMS device.

In this step, the data representing the core network element load may be one or more of a PDP, or a call volume, or a number of users, or a service traffic. For softswitch devices and IMS devices, the call volume is typically used as data to characterize the core network element load.

In this step, after obtaining the data representing the core network element load, the data may be stored in the form of a table. Table 1 shows the data storage format for characterizing the core network element load. As shown in Table 1, the data type, the time of collecting data, and the collected data values are saved.

Table 1

In this step, the historical data representing the core network element load of the core network may be analyzed to obtain a change rule, and then the data representing the core network element load at a certain moment in the future may be predicted according to the obtained change rule. For example, Figure 2 is the actual data collection graph of the total number of PDPs operated on the existing network in a certain place. The total number of PDPs was collected according to the whole point. The total number of PDPs collected for 3 and a half days was collected. The total number of PDPs shows a regular change.

According to the variation rule presented in Fig. 2, the total number of PDPs is substantially the same at the same time every day. Therefore, the following two methods can be used to predict the total number of PDPs at a certain moment in the future:

First, the total number of PDPs at a certain time on the previous day is taken as the total number of PDPs at the same time of the day.

Second, the average of the total number of PDPs at a certain time in the previous days is taken as the total number of PDPs at the same time of the day.

On the other hand, there may be some differences in the total number of PDPs on weekdays and holidays. Therefore, the following two methods can be used to predict the total number of PDPs at a certain moment in the future:

First, if the day is a working day, the total number of PDPs at a certain time on the previous working day can be used as the total number of PDPs at the same time of the day; if the day is a holiday, the total number of PDPs at a certain time in the previous holiday can be the same as the same day. The total number of PDPs at the moment.

Second, if the day is a working day, the average of the total number of PDPs at a certain time on the first few working days can be used as the total number of PDPs at the same time of the day; if the day is a holiday, the previous few holidays can be used at a certain time. The average of the total number of PDPs is taken as the total number of PDPs at the same time of the day.

Step 101: According to the predicted data of the core network element load at a certain moment in the future, determine that the virtual machine is to be expanded or the virtual machine is expanded at the moment, and the core network element is characterized according to the predicted future moment. The data of the load is used to calculate the number of the first newly added virtual machines. At some time before the preset time before the arrival of the time, the NVFO is notified to the NVFO to expand or expand the virtual machine, and the first calculated. The number of new virtual machines added.

In this step, the preset time can be set according to experience. For example, it can be set to NVFO to complete the expansion of the virtual machine or the time required to expand the virtual machine, and the user migration caused by the expansion or expansion of the virtual machine. The sum of the time required to synchronize with the data. For example, the preset time may be set to half an hour or 15 minutes or the like according to system requirements. It is assumed that the preset time is half an hour, and the NVFO can be notified to the NVFO to expand or expand the virtual machine by using the NVFM, and the number of the first newly added virtual machines can be calculated. .

In this step, when it is determined according to the predicted data of the core network element load at a certain moment in the future, when it is determined that the virtual machine needs to be compressed or collapsed, the virtual machine according to the prediction may be Instantly characterizing the core network element load data to calculate the first reduced number of virtual machines; at this time, NVFM notifies NVFO to perform virtual machine shrinkage or scaling virtual machine, and the calculated first reduced virtual machine number.

The method also includes:

Obtaining data representing the core network element load in real time; determining, according to data representing the core network element load obtained at a certain moment in the future, that the virtual machine needs to be compressed or collapsed at a certain moment in the future, and According to the predicted data of the core network element load at a certain moment in the future, when it is determined that the virtual machine needs to be compressed or collapsed at a certain moment in the future, according to the characterization core obtained at a certain moment in the future. The data of the network element load calculates the number of the third reduced virtual machine; at some time in the future, the NVFO is notified by the NVFM to shrink or shrink the virtual machine, and the calculated number of the third reduced virtual machine is obtained. .

That is to say, if the data representing the core network element load obtained in real time at a certain moment in the future and the data of the core network element load according to the predicted future moment are determined, the need is determined at a certain moment in the future. The virtual machine is compressed or collapsed, and the number of the third reduced virtual machine is calculated based on the real-time data of the core network element load obtained at a certain moment in the future.

The method also includes:

Real-time acquisition of data representing the core network element load;

Determining the data of the core network element load obtained in real time at a certain time before the preset time before the arrival of a certain time in the future, and judging that when the virtual machine needs to be expanded or expanded, the virtual machine needs to be expanded at a certain moment in the future. Calculating the number of the second newly added virtual machine according to the data representing the core network element load obtained in real time at a certain time before the preset time before the arrival of the future time; the pre-arrival before the arrival of the future moment At some point before the time, NVFM is notified to the NVFO to expand or expand the virtual machine, and the number of the first newly added virtual machine and the number of the second newly added virtual machine are larger.

That is, if the data of the core network element load obtained in real time is obtained according to a certain time before the preset time before the arrival of a certain moment in the future, and the predicted core network element load according to the predicted future moment. Data, it is judged that the virtual machine needs to be expanded at a certain moment in the future. Or expanding the virtual machine, the larger value of the number of the first newly added virtual machine and the number of the second newly added virtual machine at a certain time before the preset time before the arrival of the future moment. The expansion of the virtual machine or the expansion of the virtual machine is permitted.

The method also includes:

The system flag is asserted for some preset time at some point in the future, and the system flag is deactivated after the future time arrives.

If the system is marked as valid, it indicates that the virtual machine needs to be expanded or expanded by the virtual machine within a preset time. If the virtual machine is determined according to other methods (such as data obtained by real-time characterization of the core network element load), the preset is determined. If the virtual machine is to be retracted or the virtual machine is to be retracted, the virtual machine will not be shrinked or the virtual machine will be collapsed. If the system ID is invalid, the virtual machine can be expanded according to other methods after the preset time. Or shrinkage.

The method also includes:

Obtaining data representing the core network element load in real time; determining, according to the data of the core network element load obtained in real time, that the virtual machine needs to be compressed or collapsed at a certain moment in the future; and the system marking is invalid. Calculating the number of the second reduced virtual machine according to the obtained data of the core network element load; notifying the NVFO of the virtual machine by the NVFM to shrink or shrink the virtual machine, and calculating the obtained number of the second reduced virtual machine.

Wherein, when it is determined that the system tag is valid, the virtual machine is not contracted or the virtual machine is collapsed.

Referring to FIG. 3, an embodiment of the present invention further provides an apparatus for deploying a virtual core network, including a processor and a program storage device, and further includes:

The obtaining module is configured to pre-acquire historical data representing the core network element load;

The prediction module is configured to periodically predict data representing the core network element load at a certain moment in the future according to a pre-acquired change rule of data representing the core network element load;

The notification module is adapted to represent the data of the core network element load according to the predicted future moment, and determine that the virtual machine is to be expanded or the virtual machine is expanded at the moment, and the core network is characterized according to the predicted future moment. The data of the network element load is used to calculate the number of the first newly added virtual machine. Before the preset time before the arrival of the time, the NVFM is notified by the network function virtualization management to notify the NVFO of the virtual machine to expand or expand the virtual machine, and calculate Get the first new virtual machine number.

In the apparatus of the embodiment of the present invention, the notification module is further applicable to:

According to the predicted data of the core network element load at a certain moment in the future, when it is determined that the virtual machine needs to be compressed or collapsed at the moment, the core network element load is characterized according to the predicted future moment. The data calculates the number of first reduced virtual machines; at this time, the NVFO is notified by the NVFM to shrink or shrink the virtual machine, and the calculated number of first reduced virtual machines.

The system flag is asserted for some preset time at some point in the future, and the system flag is deactivated when the future time arrives.

In the apparatus of the embodiment of the present invention, the obtaining module is further applicable to:

Real-time acquisition of data representing the core network element load;

The notification module also applies to:

According to the data of the core network element load obtained in real time, it is determined that the virtual machine needs to be compressed or collapsed at a certain moment in the future; the system is marked as invalid, and the data is calculated according to the obtained core network element load data. The number of reduced virtual machines; NVFM notifies NVFO to shrink or shrink the virtual machine, and calculate the number of second reduced virtual machines.

Real-time acquisition of data representing the core network element load;

The notification module is also applicable to;

According to the predicted data of the core network element load at a certain moment in the future, it is determined that the virtual machine needs to be compressed or collapsed by the virtual machine at the moment, and according to the current representation of the core network element obtained at a certain moment in the future. The data of the load is judged when the virtual machine needs to be compressed or collapsed at a certain moment in the future; the third reduced virtual machine is calculated according to the data representing the core network element load obtained at a certain moment in the future. The number; at some point in the future, the NVFO is notified by the NVFM to shrink or shrink the virtual machine, and the calculated number of the third reduced virtual machine.

Real-time acquisition of data representing the core network element load;

The notification module also applies to:

According to the data representing the core network element load obtained at a certain time before the preset time before the arrival of a certain time in the future, it is determined that when the virtual machine needs to be expanded or expanded by the virtual machine at a certain moment in the future, according to Calculating the number of the second newly added virtual machine obtained from the data of the core network element load obtained at a certain time before the preset time before the arrival of the future time; the preset time before the arrival of the future time At some point in the past, the NVFO notifies the NVFO to expand or expand the virtual machine, and the larger number of the first newly added virtual machine and the second newly added virtual machine.

It should be noted that the above-mentioned embodiments are only for the purpose of facilitating the understanding of those skilled in the art, and are not intended to limit the scope of the present invention, and those skilled in the art will Any obvious substitutions and improvements made by the invention are within the scope of the invention.

Industrial applicability

The technical solution of the embodiment of the present invention may predict, according to the periodically acquired historical data representing the core network element load of the core network, data representing the core network element load at a certain moment in the future, and the real-time obtained representation core network combined with the future moment. The data of the network element load, the NVFM is notified to expand the virtual machine at a preset time point before the arrival of the future time, or the virtual machine is reduced in the future time, and sufficient time is reserved for completing the expansion of the virtual machine. At the same time, the virtual machine can be reduced in time to improve the user experience.

Claims

A method of deploying a virtual core network includes:

Periodically predicting data representing the core network element load in the future time according to the pre-acquired historical data representing the core network element load;

When the data of the core network element load is predicted according to the predicted future time, and the virtual machine is required to be expanded at the future time, the first data of the core network element load is calculated according to the predicted future time. The number of new virtual machines added;

At a preset time point before the arrival of the future time, the network function virtualization management NVFM notifies the network function to virtualize the NVFO for VM expansion and the number of the first newly added virtual machines.
The method of claim 1 further comprising:

Real-time acquisition of data representing the core network element load;

Determining a characterization core obtained according to the preset time point before the arrival of the future time when determining, according to the predicted data of the core network element load of the future time, that the future time needs to be expanded by the virtual machine Data of the network element load, and calculate the number of the second newly added virtual machine;

At the preset time point before the arrival of the future time, the NVFO is notified by the NVFM to perform virtual machine expansion, and the number of the first newly added virtual machine and the number of the second newly added virtual machine The larger value.
The method of claim 1 further comprising:

When the data of the core network element load is characterized according to the predicted future time, and the virtual machine is required to be reduced in the future time, the data of the core network element load is calculated according to the predicted future time. a reduced number of virtual machines;

Notifying the NVFO by the NVFM at the future time to perform virtual machine shrinkage and the first reduced number of virtual machines.
The method of claim 1 further comprising:

Setting the system flag to be valid during the preset time point to the future time, in the The system flag is set to be invalid when the future time arrives.
The method of claim 4 further comprising:

Real-time acquisition of data representing the core network element load;

When it is determined that the virtual machine is required to be reduced according to the data of the core network element load obtained in real time, and the system is marked as invalid, the second reduced virtual is calculated according to the obtained core network element load data. Number of machines;

Notifying the NVFO by the NVFM for virtual machine shrinkage and the second reduced number of virtual machines.
The method of claim 1 further comprising:

Real-time acquisition of data representing the core network element load;

Determining, according to the data of the core network element load obtained at the future time, that the virtual machine is required to be reduced at the future time, and the data of the core network element load is characterized according to the predicted future time, When it is determined that the virtual machine needs to be reduced in the future time, the third reduced virtual machine number is calculated according to the data representing the core network element load obtained at the future time;

Notifying the NVFO by the NVFM at the future time to perform virtual machine shrinkage and the third reduced number of virtual machines.
A device for deploying a virtual core network, comprising:

Obtaining a module, configured to obtain historical data representing a core network element load;

The prediction module is configured to periodically predict, according to the acquired historical data representing the core network element load of the core network, data representing the core network element load at a future time;

The notification module is configured to: according to the predicted data of the core network element load of the future time, determine, when the virtual machine needs to be expanded at the future time, represent the data of the core network element load according to the predicted future time, Calculating the number of the first newly added virtual machines, and at a preset time point before the arrival of the future time, the NVFM is notified by the network function virtualization management network function to virtualize the NVFO for VM expansion and the first added virtual Number of machines.
The apparatus of claim 7, wherein the obtaining module is further configured to:

Real-time acquisition of data representing the core network element load;

The notification module is further configured to:

Determining, according to the predicted data of the core network element load of the future time, that the virtual machine needs to be expanded at the future time, according to the preset time point before the arrival of the future time Determining the data of the core network element load, and calculating the number of the second newly added virtual machine; the NVFO notifying the NVFO to perform virtual machine expansion by the NVFM at the preset time point before the arrival of the future time, and the The larger number of the first newly added virtual machine and the second newly added virtual machine.
The apparatus of claim 7, wherein the notification module is further configured to:

When the data of the core network element load is predicted according to the predicted future time, and the virtual machine is required to be reduced at the moment, the first data of the core network element load is calculated according to the predicted future time. The reduced number of virtual machines; at the future time, the NVFO is notified by the NVFM to perform virtual machine shrinkage and the first reduced number of virtual machines.
The apparatus of claim 7, wherein the notification module is further configured to:

The system flag is asserted during the time period from the preset time point to the future time, and the system flag is set to be invalid when the future time arrives.
The apparatus of claim 10, wherein the obtaining module is further configured to:

Real-time acquisition of data representing the core network element load;

The notification module is further configured to:

When it is determined that the virtual machine is required to be reduced in the future time according to the data of the core network element load obtained in the future time, and the system is marked as invalid, according to the obtained core network element load Data, calculating a number of second reduced virtual machines; notifying the NVFO by the NVFM for virtual machine shrinkage and the second reduced number of virtual machines.
The apparatus of claim 7, wherein the obtaining module is further configured to:

Real-time acquisition of data representing the core network element load;

The notification module is further configured to:

Determining that the virtual machine needs to be reduced in the future time according to the predicted data of the core network element load in the future time, and determining, according to the data representing the core network element load obtained at the future time, When the virtual machine needs to be reduced in the future time, the number of the third reduced virtual machine is calculated according to the data that is obtained at the future time and represents the core network element load; and the NVFM is notified at the future time. The NVFO performs virtual machine shrinkage and the third reduced number of virtual machines.
A computer readable storage medium storing a computer program, the computer program comprising program instructions, when the program instructions are executed by a device deployed in a virtual core network, enabling the device to perform any of claims 1-6 The method of the item.