Resource energy saving method and device, vnfm and vfvo

Abstract

The application provides a resource energy-saving method, device and network element, the method comprises the following steps: a VNFM acquires a created and activated scaling-in policy; the scaling-in policy is a scaling-in policy of a network service (NS) instance or a scaling-in policy of a virtual network function (VNF) instance; and the VNFM triggers a scaling-in operation of the NS instance or a scaling-in operation of the VNF instance based on the scaling-in policy within the validity period of the scaling-in policy. According to the embodiment of the application, an automatic scaling-in policy is created in combination with service change characteristics, the number of idle VMs in the NS instance or the VNF instance is reduced through the automatic scaling-in operation of the NS instance or the VNF instance, more servers are in an idle state, and energy-saving is finally realized through a server power-off operation.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a resource-saving method, apparatus, VNFM, and VFVO. Background Technology

[0002] Traditional network equipment manufacturers customize equipment based on specific specifications and technical requirements, resulting in complex maintenance and upgrade processes and high operational costs for service deployment. To reduce the complexity and cost of network deployment and service promotion, hardware-software decoupling through a hardware platform can effectively reduce the cost of equipment upgrades and accelerate the deployment of new services. NFV (Network Function Virtualization) was proposed against this backdrop. NFV utilizes a MANO (Management and Orchestration) system and a network management system (Object Storage Service (OSS), Operation and Maintenance Center (OMC)) to implement the core cloud's management functions.

[0003] The MANO system comprises three main components: NFVO (Network Functions Virtualization Orchestrator), VNFM (Virtualized Network Function Manager), and VIM (Virtualized Infrastructure Manager). Its main functions include network element lifecycle management, creation of network element images, management of network element templates and software, and allocation and management of network resources.

[0004] With the introduction of SDN (Software-Defined Networking), virtual resources are deployed as NS (Network Service). Each NS instance contains one or more VNF (Virtual Network Function) instances, as well as virtual links (VLs) and network connectivity resources required for communication and interaction between VNF instances.

[0005] On the one hand, during the resource planning and design phase, due to network performance and stability considerations, each NS and network element in the existing network has a certain proportion of redundant resources. On the other hand, since various network services generally exhibit the characteristic of "higher service access volume during the day and lower service access volume at night," there are a certain number of idle VMs (virtual machines) in each NS / VNF instance at night. That is, the large number of idle VMs in the NS / VNF instance at night will lead to additional energy consumption.

[0006] On the other hand, in the current network, NS / VNF instances are deployed in batches according to the plan, with long intervals between different deployment batches. During these intervals, there may be temporary deployments of systems or applications. Therefore, it was not possible to design resources globally to achieve centralized deployment of virtual resources from the initial design stage, resulting in resource fragmentation. Consequently, due to resource fragmentation, VMs are distributed relatively widely across various servers, leading to more servers being in operation at any given time, resulting in higher energy consumption. Summary of the Invention

[0007] The purpose of this invention is to provide a resource-saving method, device, and network element to solve the problem of additional energy consumption caused by idle VMs or fragmented resource distribution within NS instances or VNF instances in the prior art.

[0008] To address the above problems, embodiments of the present invention provide a resource-saving method, comprising:

[0009] VNFM obtains the created and activated scaling-down policy; the scaling-down policy is the scaling-down policy of the Network Service NS instance or the scaling-down policy of the Virtual Network Function VNF instance.

[0010] During the validity period of the scaling-down policy, the VNFM triggers a scaling-down operation for either the NS instance or the VNF instance based on the scaling-down policy.

[0011] The shrinking operation of the NS instance includes:

[0012] Make resource changes to at least one first VNF ​​instance within the NS instance to reduce the number of virtual machines (VMs) within the first VNF ​​instance.

[0013] The shrinking operation of the VNF instance includes:

[0014] Make resource changes to the VNF instance to reduce the number of VMs within the VNF instance.

[0015] The method further includes, after triggering the NS instance based on the shrinkage strategy, the following:

[0016] Change the state of the NS instance to elastic scaling state; wherein, when the NS instance is in elastic scaling state, other VNF instances within the NS instance, except for the first VNF ​​instance, are prohibited from triggering scaling and related lifecycle operations.

[0017] VNFM retrieves created and activated scaling policies, including:

[0018] VNFM obtains the scaling-down strategy by accessing the creation strategy interface between VNFM and NFVO;

[0019] The VNFM feeds back the identifier of the scaling-down strategy to the NFVO; wherein the NFVO activates the scaling-down strategy by calling the activation strategy interface between the VNFM and the NFVO.

[0020] The creation strategy interface includes:

[0021] VNFM identifier;

[0022] NFVO identifier;

[0023] Strategy content;

[0024] Strategy identifier;

[0025] The creation strategy interface also includes at least one of the following:

[0026] The identifier of the instance to which the strategy applies;

[0027] The start time of the effective period of the scaling-down strategy;

[0028] The end date of the scaling-down strategy's validity period.

[0029] This invention also provides a resource-saving method, comprising:

[0030] NFVO creates a scaling-down strategy by calling the creation strategy interface between VNFM and NFVO and the preset scaling-down strategy template information; the scaling-down strategy is the scaling-down strategy of the Network Service NS instance or the scaling-down strategy of the Virtual Network Function VNF instance.

[0031] NFVO activates the scaling-down policy by calling the activation policy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down policy during the validity period of the scaling-down policy.

[0032] The creation strategy interface includes:

[0033] VNFM identifier;

[0034] NFVO identifier;

[0035] Strategy content;

[0036] Strategy identifier;

[0037] The creation strategy interface also includes at least one of the following:

[0038] The identifier of the instance to which the strategy applies;

[0039] The start time of the effective period of the scaling-down strategy;

[0040] The end date of the scaling-down strategy's validity period.

[0041] The method further includes:

[0042] After completing the scaling down operation of the NS instance or VNF instance, the NFVO obtains the resource utilization status of the server.

[0043] If there is an idle server that is not hosting a virtual machine (VM), the NFVO will power down or put the idle server into hibernation.

[0044] This invention also provides a resource-saving method, comprising:

[0045] NFVO determines VM optimization strategies based on the distribution of virtual machines (VMs) in NS instances or VNF instances, with the goal of reducing resource fragmentation.

[0046] The NFVO triggers a VM migration operation for the NS instance or VNF instance based on the VM optimization strategy.

[0047] The VM optimization strategy includes:

[0048] VM migration methods from high-fragmentation servers to low-fragmentation servers;

[0049] VM migration restrictions.

[0050] The VM migration restrictions include at least one of the following:

[0051] VM attribute limitations;

[0052] Are there sufficient unused resources on the server?

[0053] Affinity constraints of VMs;

[0054] Anti-affinity constraints on VMs.

[0055] Before the NFVO triggers the VM migration operation of the NS instance or VNF instance according to the VM optimization strategy, the method further includes:

[0056] Based on business needs, migrate the services hosted on the VMs to be migrated in the NS instance or VNF instance.

[0057] Wherein, after the NFVO triggers the VM migration operation of the NS instance or VNF instance according to the VM optimization strategy, the method further includes:

[0058] The NFVO obtains the server's resource utilization status;

[0059] If there is an idle server that is not hosting a virtual machine (VM), the NFVO will power down or put the idle server into hibernation.

[0060] This invention also provides a resource-saving device, comprising:

[0061] The first acquisition module is used to acquire the created and activated scaling-down strategy; the scaling-down strategy is the scaling-down strategy of the Network Service NS instance or the scaling-down strategy of the Virtual Network Function VNF instance.

[0062] The operation module is used to trigger a shrinkage operation of the NS instance or the VNF instance based on the shrinkage policy during the validity period of the shrinkage policy.

[0063] This invention also provides a VNFM, including a processor and a transceiver, wherein the transceiver receives and transmits data under the control of the processor, and the processor is configured to perform the following operations:

[0064] Obtain the created and activated scaling-down policy; the scaling-down policy is either the scaling-down policy of a Network Service (NS) instance or the scaling-down policy of a Virtual Network Function (VNF) instance.

[0065] During the validity period of the scaling-down policy, the scaling-down operation of the NS instance or the VNF instance is triggered based on the scaling-down policy.

[0066] The shrinking operation of the NS instance includes:

[0067] Make resource changes to at least one first VNF ​​instance within the NS instance to reduce the number of virtual machines (VMs) within the first VNF ​​instance.

[0068] The shrinking operation of the VNF instance includes:

[0069] Make resource changes to the VNF instance to reduce the number of VMs within the VNF instance.

[0070] The processor is also used to perform the following operations:

[0071] Change the state of the NS instance to elastic scaling state; wherein, when the NS instance is in elastic scaling state, other VNF instances within the NS instance, except for the first VNF ​​instance, are prohibited from triggering scaling and related lifecycle operations.

[0072] The processor is also used to perform the following operations:

[0073] The scaling-down strategy is obtained by accessing the creation strategy interface between VNFM and NFVO;

[0074] The identifier of the scaling-down strategy is fed back to the NFVO; wherein the scaling-down strategy is activated by the NFVO by calling the activation strategy interface between VNFM and NFVO.

[0075] The creation strategy interface includes:

[0076] VNFM identifier;

[0077] NFVO identifier;

[0078] Strategy content;

[0079] Strategy identifier;

[0080] The creation strategy interface also includes at least one of the following:

[0081] The identifier of the instance to which the strategy applies;

[0082] The start time of the effective period of the scaling-down strategy;

[0083] The end date of the scaling-down strategy's validity period.

[0084] This invention also provides a resource-saving device, comprising:

[0085] The creation module is used to create a scaling-down strategy by calling the creation strategy interface between VNFM and NFVO and the preset scaling-down strategy template information; the scaling-down strategy is the scaling-down strategy of the network service NS instance or the scaling-down strategy of the virtual network function VNF instance.

[0086] The activation module is used to activate the scaling-down strategy by calling the activation strategy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down strategy during the validity period of the scaling-down strategy.

[0087] This invention also provides an NFVO, including a processor and a transceiver, wherein the transceiver receives and transmits data under the control of the processor, and the processor is configured to perform the following operations:

[0088] A scaling-down strategy is created by calling the creation strategy interface between VNFM and NFVO and the preset scaling-down strategy template information; the scaling-down strategy is either the scaling-down strategy of a network service NS instance or the scaling-down strategy of a virtual network function VNF instance.

[0089] The scaling-down strategy is activated by calling the activation strategy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down strategy during the validity period of the scaling-down strategy.

[0090] The creation strategy interface includes:

[0091] VNFM identifier;

[0092] NFVO identifier;

[0093] Strategy content;

[0094] Strategy identifier;

[0095] The creation strategy interface also includes at least one of the following:

[0096] The identifier of the instance to which the strategy applies;

[0097] The start time of the effective period of the scaling-down strategy;

[0098] The end date of the scaling-down strategy's validity period.

[0099] The processor is also used to perform the following operations:

[0100] After completing the scaling down operation of the NS instance or VNF instance, obtain the server's resource utilization status.

[0101] If there is an idle server that is not hosting a virtual machine (VM), power down or put the idle server into hibernation mode.

[0102] This invention also provides a resource-saving device, comprising:

[0103] The strategy determination module is used to determine VM optimization strategies based on the distribution of virtual machines (VMs) in NS instances or VNF instances, with the goal of reducing resource fragmentation.

[0104] The migration module is used to trigger VM migration operations for NS instances or VNF instances according to the VM optimization strategy.

[0105] This invention also provides an NFVO, including a processor and a transceiver, wherein the transceiver receives and transmits data under the control of the processor, and the processor is configured to perform the following operations:

[0106] Based on the distribution of virtual machines (VMs) in NS instances or VNF instances, determine VM optimization strategies with the goal of reducing resource fragmentation.

[0107] Based on the VM optimization strategy, trigger VM migration operations for NS instances or VNF instances.

[0108] The VM optimization strategy includes:

[0109] VM migration methods from high-fragmentation servers to low-fragmentation servers;

[0110] VM migration restrictions.

[0111] The VM migration restrictions include at least one of the following:

[0112] VM attribute limitations;

[0113] Are there sufficient unused resources on the server?

[0114] Affinity constraints of VMs;

[0115] Anti-affinity constraints on VMs.

[0116] The processor is also used to perform the following operations:

[0117] Based on business needs, migrate the services hosted on the VMs to be migrated in the NS instance or VNF instance.

[0118] The processor is also used to perform the following operations:

[0119] Obtain information on server resource utilization;

[0120] If there is an idle server that is not hosting a virtual machine (VM), power down or put the idle server into hibernation mode.

[0121] This invention also provides a virtual network device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the resource-saving method described above.

[0122] This invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the resource-saving method described above.

[0123] The above-described technical solution of the present invention has at least the following beneficial effects:

[0124] In the resource-saving methods, devices, VNFMs, and NFVOs of this invention, an automatic scaling-down strategy is created based on the characteristics of business changes. Through the automatic scaling-down operation of NS instances or VNF instances, the number of idle VMs in NS instances or VNF instances is reduced, so that more servers are in an idle state. Ultimately, energy saving is achieved through the server power-down operation. Attached Figure Description

[0125] Figure 1A diagram illustrating the logical relationship between NS instances and VNF instances;

[0126] Figure 2 This represents one of the steps in the resource-saving method provided in this embodiment of the invention;

[0127] Figure 3 This diagram illustrates the creation and activation of a scaling-down strategy in the resource-saving method provided in this embodiment of the invention.

[0128] Figure 4 This is the second flowchart illustrating the steps of the resource-saving method provided in this embodiment of the invention.

[0129] Figure 5 This diagram illustrates the VNF scaling-down operation in the resource-saving method provided in this embodiment of the invention.

[0130] Figure 6 One of the example diagrams illustrates the resource-saving method provided in the embodiments of the present invention;

[0131] Figure 7 This is the third flowchart illustrating the steps of the resource-saving method provided in this embodiment of the invention.

[0132] Figure 8 This diagram illustrates VM migration in the resource-saving method provided in this embodiment of the invention.

[0133] Figure 9 The second example diagram illustrates the resource-saving method provided in this embodiment of the invention.

[0134] Figure 10 This is one of the structural schematic diagrams of the energy-saving device provided in the embodiments of the present invention;

[0135] Figure 11 This is a schematic diagram of the structure of VNFM provided in an embodiment of the present invention;

[0136] Figure 12 This is the second schematic diagram of the structure of the energy-saving device provided in the embodiment of the present invention;

[0137] Figure 13 This is one of the structural schematic diagrams of the NFVO provided in the embodiments of the present invention;

[0138] Figure 14 This is the third schematic diagram of the structure of the energy-saving device provided in the embodiment of the present invention;

[0139] Figure 15 This is the second schematic diagram of the structure of the NFVO provided in the embodiment of the present invention. Detailed Implementation

[0140] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0141] In this embodiment of the invention, after introducing SDN (Software-Defined Networking), virtual resources are deployed in the form of NS (Network Service). Each NS instance contains one or more VNF (Virtual Network Function) instances, such as... Figure 1 The diagram shows the logical relationship between NS instances and VNF instances.

[0142] like Figure 2 As shown, an embodiment of the present invention provides a resource-saving method, including:

[0143] Step 201: The Virtual Network Function Manager (VNFM) obtains the created and activated scaling-down policy; the scaling-down policy is either the scaling-down policy of the Network Service (NS) instance or the scaling-down policy of the Virtual Network Function (VNF) instance.

[0144] Step 202: During the validity period of the scaling-down policy, the VNFM triggers a scaling-down operation on the NS instance or the VNF instance based on the scaling-down policy. The validity period of the scaling-down policy can also be referred to as the execution time of the scaling-down policy.

[0145] It should be noted that NFVO creates and activates the scaling-down strategy based on business needs, according to the preset scaling-down strategy template information and the strategy management interface between VNFM and NFVO.

[0146] The policy management interface includes the CreatePolicy interface, UpdatePolicy interface, QueryPolicy interface, DeletePolicy interface, ActivePolicy interface, and DeActivePolicy interface.

[0147] For example, the parameters included in the preset scaling strategy module information are shown in Table 1.

[0148]

[0149]

[0150] Table 1

[0151] In at least one embodiment of the present invention, step 201 includes:

[0152] VNFM obtains the scaling-down strategy by accessing the creation strategy interface between VNFM and NFVO;

[0153] The VNFM feeds back the identifier of the scaling-down strategy to the NFVO; wherein the NFVO activates the scaling-down strategy by calling the activation strategy interface between the VNFM and the NFVO.

[0154] like Figure 3 As shown, the process of creating and activating a scaling-down strategy includes:

[0155] Step 31: NFVO calls the CreatePolicy interface to create an NS / VNF automatic scaling-down policy and specifies the validity period of the scaling-down policy;

[0156] Step 32, VNFM returns the Policy ID;

[0157] Step 33: NFVO calls the ActivePolicy interface to activate the scaling-down strategy.

[0158] As an optional embodiment, the creation strategy interface includes:

[0159] VNFM identifier;

[0160] NFVO identifier;

[0161] Strategy content;

[0162] Strategy identifier;

[0163] The creation strategy interface also includes at least one of the following:

[0164] The identifier of the instance to which the policy applies; for example, an NS instance identifier or a VNF instance identifier;

[0165] The start time of the effective period of the scaling-down strategy;

[0166] The end date of the scaling-down strategy's validity period.

[0167] For example, the parameters included in creating a strategy interface are shown in Table 2.

[0168]

[0169] Table 2

[0170] For example, the interface access method for "Creating Policy Interface" in Table 2 is: POST / v1 / {InstanceID} / policies.

[0171] Optionally, embodiments of the present invention further extend the following interfaces: update policy interface and activate policy interface. For example, the parameters of the extended update policy interface are shown in Table 3. The parameters of the extended activate policy interface are shown in Table 4.

[0172]

[0173] Table 3

[0174] For example, the interface access method for the "Update Policy Interface" in Table 3 is: PUT / v1 / {InstanceID} / policies / {policyID}.

[0175]

[0176]

[0177] Table 4

[0178] For example, the interface access method for the “Activation Policy Interface” in Table 4 is: PUT / v1 / {InstanceID} / policies / {policyID} / active.

[0179] In at least one embodiment of the present invention, the scaling-down operation of the NS instance includes:

[0180] Make resource changes to at least one first VNF ​​instance within the NS instance to reduce the number of virtual machines (VMs) within the first VNF ​​instance.

[0181] For example, VNFM continuously monitors the performance metrics (such as CPU utilization) of each VNF within the NS instance. Once the NS automatic scaling-down policy has been successfully created and activated, VNFM automatically triggers the VNF instance scaling-down operation based on the "effective time" set by the scaling-down policy, making resource changes to the VNF instances within the NS instance and reducing the number of VMs within the relevant VNF ​​instances.

[0182] Optionally, after triggering the NS instance based on the shrinkage strategy, the method further includes:

[0183] Change the state of the NS instance to automatic scaling state; wherein, when the NS instance is in automatic scaling state, other VNF instances within the NS instance, except for the first VNF ​​instance, are prohibited from triggering scaling and related lifecycle operations.

[0184] It should be noted that after a VNF instance within an NS instance triggers automatic scaling, the instance state changes to Auto_Scaling. While an NS instance is in the Auto_Scaling state, other VNF instances within that NS instance are not allowed to trigger automatic scaling or other lifecycle operations. After the NS instance's automatic scaling operation is completed, the instance state changes to active.

[0185] In at least one embodiment of the present invention, the shrinking operation of the VNF instance includes:

[0186] Make resource changes to the VNF instance to reduce the number of VMs within the VNF instance.

[0187] For example, VNFM continuously monitors VNF-related performance metrics (such as CPU utilization). Once the VNF automatic scaling-down strategy has been successfully created and activated, VNFM automatically triggers the VNF instance scaling-down operation based on the "valid time" set by the scaling-down strategy, completing resource changes and reducing the number of VMs within the VNF instance.

[0188] After a VNF instance triggers an automatic scaling operation, its state changes to Auto_Scaling. Once the automatic scaling operation is complete, the VNF instance state changes to active.

[0189] In summary, this embodiment of the invention extends the policy template, introduces fields such as VNF type, and constructs an NS / VNF scaling strategy model. Simultaneously, it extends the policy management interface (CreatePolicy, UpdatePolicy) to implement a "timed" function for policy activation. Based on the extended policy template and policy management interface, and combined with actual business characteristics, a reasonable NS / VNF scaling strategy is created, and corresponding effective time periods are set or updated. Through the automatic scaling down operation of NS instances or VNF instances, the number of idle VMs within NS instances or VNF instances is reduced, avoiding additional power consumption and allowing more servers to be in an idle state. Ultimately, energy saving is achieved through server power-down operations.

[0190] like Figure 4 As shown, this embodiment of the invention also provides a resource-saving method, including:

[0191] Step 401: NFVO creates a scaling-down strategy by calling the creation strategy interface between VNFM and NFVO and the preset scaling-down strategy template information; the scaling-down strategy is a scaling-down strategy for a network service NS instance or a scaling-down strategy for a virtual network function VNF instance.

[0192] Step 402: NFVO activates the scaling-down strategy by calling the activation strategy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down strategy during the validity period of the scaling-down strategy.

[0193] Based on business requirements, NFVO creates and activates the scaling-down policy according to the preset scaling-down policy template information and the policy management interface between VNFM and NFVO. The policy management interface includes CreatePolicy, UpdatePolicy, QueryPolicy, DeletePolicy, ActivePolicy, and DeActivePolicy.

[0194] like Figure 3 As shown, the process of creating and activating a scaling-down strategy includes:

[0195] Step 31: NFVO calls the CreatePolicy interface to create an NS / VNF automatic scaling-down policy and specifies the validity period of the scaling-down policy;

[0196] Step 32, VNFM returns the Policy ID;

[0197] Step 33: NFVO calls the ActivePolicy interface to activate the scaling-down strategy.

[0198] As an optional embodiment, the creation strategy interface includes:

[0199] VNFM identifier;

[0200] NFVO identifier;

[0201] Strategy content;

[0202] Strategy identifier;

[0203] The creation strategy interface also includes at least one of the following:

[0204] The identifier of the instance to which the policy applies; for example, an NS instance identifier or a VNF instance identifier;

[0205] The start time of the effective period of the scaling-down strategy;

[0206] The end date of the scaling-down strategy's validity period.

[0207] After an NS / VNF instance completes its automatic scaling-down operation, the number of VMs hosted by the server decreases. At this point, there may be idle servers hosting no VMs, such as... Figure 5 As shown. Accordingly, the method further includes:

[0208] After completing the scaling down operation of the NS instance or VNF instance, the NFVO obtains the resource utilization status of the server.

[0209] If there is an idle server that is not hosting a virtual machine (VM), the NFVO will power down or put the idle server into hibernation.

[0210] For example, an operator can use NFVO to invoke the VIM northbound interface HostOperation to power down the corresponding server. The parameters of the VIM northbound interface are shown in Table 5.

[0211]

[0212] Table 5

[0213] For example, the interface access method for the “VIM Northbound Interface” in Table 5 is: POST / v2 / hosts_action.

[0214] In summary, this embodiment of the invention extends the policy template, introduces fields such as VNF type, and constructs an NS / VNF scaling strategy model. Simultaneously, it extends the policy management interface (CreatePolicy, UpdatePolicy) to implement a "timed" function for policy activation. Based on the extended policy template and policy management interface, and combined with actual business characteristics, a reasonable NS / VNF scaling strategy is created, and corresponding effective time periods are set or updated. Through the automatic scaling down operation of NS instances or VNF instances, the number of idle VMs within NS instances or VNF instances is reduced, avoiding additional power consumption and allowing more servers to be in an idle state. Ultimately, energy saving is achieved through server power-down operations.

[0215] For example, Figure 6 The resource-saving methods shown include:

[0216] Step 1: Based on business requirements, NFVO formulates an automatic scaling-down strategy and sets the execution time.

[0217] Step 2: During off-peak hours, VNFM triggers automatic scaling down of NS / VNF based on the NS / VNF automatic scaling down strategy;

[0218] Step 3.1: NFVO calls the VIM northbound interface to obtain server resource utilization information;

[0219] Step 3.2, VIM returns the server resource utilization status;

[0220] Step 4: Power off / sleep the idle server.

[0221] like Figure 7 As shown, this embodiment of the invention also provides a resource-saving method, including:

[0222] Step 701: NFVO determines the VM optimization strategy based on the distribution of virtual machines (VMs) of NS instances or VNF instances, with the goal of reducing resource fragmentation.

[0223] Step 702: The NFVO triggers a VM migration operation for the NS instance or VNF instance according to the VM optimization strategy.

[0224] In this embodiment of the invention, NFVO is based on the distribution of VMs on the server in NS / VNF instances to form a VM optimization strategy. It completes resource fragmentation and consolidation through VM migration, centralizes virtual resources, forms idle servers, and finally achieves energy saving through server power-down operation.

[0225] As an optional embodiment, the VM optimization strategy includes:

[0226] VM migration methods from high-fragmentation servers to low-fragmentation servers;

[0227] VM migration restrictions.

[0228] The VM migration restrictions include at least one of the following:

[0229] VM attribute limitations;

[0230] Are there sufficient unused resources on the server?

[0231] Affinity constraints of VMs;

[0232] Anti-affinity constraints on VMs.

[0233] For example, NFVO obtains virtual resource information of NS / VNF instances and server CPU utilization in the resource pool. Based on the principle of "migrating VMs from high-fragmentation servers to low-fragmentation servers", it plans and designs VM optimization strategies in combination with various migration constraints, including VM AZ / HA attribute restrictions, whether the number of remaining CPUs and memory size of the server is sufficient, VM affinity and anti-affinity constraints, etc., in order to achieve resource deployment as centrally as possible.

[0234] Optionally, NFVO calls the VmOperation interface to trigger a VM migration operation. For example, the parameters of the VmOperation interface are shown in Table 6.

[0235]

[0236] Table 6

[0237] For example, the interface access method for the "VmOperation interface" in Table 6 is: PUT / v4 / vnfs / <vnfinstance id> / vms / operation.

[0238] In this embodiment of the invention, based on the VM optimization strategy, the VMs within the NS / VNF instance are migrated by calling the VmOperation interface, thereby centralizing virtual resources and forming an idle server, as shown in Table 7.

[0239]

[0240] Table 7

[0241] In at least one embodiment of the present invention, before the NFVO triggers the VM migration operation of the NS instance or VNF instance according to the VM optimization strategy, the method further includes:

[0242] Based on business needs, migrate the services hosted on the VMs to be migrated from the NS instance or VNF instance. For example, when using VM cold migration, for business reasons, the services on the VMs to be migrated need to be migrated in advance.

[0243] As another optional embodiment, after the NFVO triggers the VM migration operation of the NS instance or VNF instance according to the VM optimization strategy, the method further includes:

[0244] The NFVO obtains the server's resource utilization status;

[0245] If there is an idle server that is not hosting a virtual machine (VM), the NFVO will power down or put the idle server into hibernation.

[0246] For example, such as Figure 8 As shown, the operator uses NFVO to call the VIM northbound interface HostOperation to power down server 3.

[0247] For example, Figure 9 The resource-saving methods shown include:

[0248] Step 5: Based on the distribution of NS / VNF instance VMs, formulate a VM optimization strategy with the goal of minimizing resource fragmentation rate;

[0249] Step 6: Trigger NS / VNF instance maintenance operations based on VM optimization strategies, migrate VMs, and complete resource fragmentation defragmentation;

[0250] Step 7: Power off / sleep the idle server.

[0251] In summary, this embodiment of the invention, by combining the distribution of virtual resources and performing VM migration operations in NS / VNF instances, integrates resource fragments to achieve centralized deployment of virtual resources, allowing more servers to be in an idle state, and ultimately achieves energy saving through server power-down operations.

[0252] like Figure 10 As shown, this embodiment of the invention also provides a resource-saving device, comprising:

[0253] The first acquisition module 1001 is used to acquire the created and activated scaling-down strategy; the scaling-down strategy is the scaling-down strategy of a network service NS instance or a virtual network function VNF instance.

[0254] The operation module 1002 is used to trigger the shrinkage operation of the NS instance or the shrinkage operation of the VNF instance based on the shrinkage strategy during the validity period of the shrinkage strategy.

[0255] As an optional embodiment, the scaling down operation of the NS instance includes:

[0256] Make resource changes to at least one first VNF ​​instance within the NS instance to reduce the number of virtual machines (VMs) within the first VNF ​​instance.

[0257] As an optional embodiment, the shrinking operation of the VNF instance includes:

[0258] Make resource changes to the VNF instance to reduce the number of VMs within the VNF instance.

[0259] As an optional embodiment, the apparatus further includes:

[0260] The state change module is used to change the state of the NS instance to an elastic scaling state; wherein, when the NS instance is in an elastic scaling state, other VNF instances within the NS instance, except for the first VNF ​​instance, are prohibited from triggering scaling and related lifecycle operations.

[0261] As an optional embodiment, the first acquisition module includes:

[0262] The acquisition submodule is used to obtain the scaling strategy by accessing the creation strategy interface between VNFM and NFVO;

[0263] The feedback receiving submodule is used to send the identifier of the scaling-down strategy back to the NFVO; wherein the scaling-down strategy is activated by the NFVO by calling the activation strategy interface between the VNFM and the NFVO.

[0264] As an optional embodiment, the creation strategy interface includes at least one of the following parameters:

[0265] VNF instance identifier;

[0266] NS instance identifier;

[0267] The start time of the effective period of the scaling-down strategy;

[0268] The end date of the effective period of the scaling-down strategy;

[0269] VNFM identifier;

[0270] NFVO identifier;

[0271] Strategy information;

[0272] Strategy identifier.

[0273] This invention extends the policy template by introducing fields such as VNF type to construct an NS / VNF scaling strategy model. It also extends the policy management interface (CreatePolicy, UpdatePolicy) to implement a "timed" function for policy activation. Based on the extended policy template and policy management interface, and combined with actual business characteristics, a reasonable NS / VNF scaling strategy is created, and corresponding effective time periods are set or updated. Through automatic scaling down of NS or VNF instances, the number of idle VMs within NS or VNF instances is reduced, avoiding additional power consumption and allowing more servers to be in an idle state. Ultimately, energy saving is achieved through server power-down operations.

[0274] It should be noted that the resource-saving device provided in the embodiments of the present invention is a device capable of performing the above-described resource-saving method. Therefore, all embodiments of the above-described resource-saving method are applicable to this device and can achieve the same or similar beneficial effects.

[0275] like Figure 11 As shown, this embodiment of the invention also provides a VNFM, including a processor 1100 and a transceiver 1110. The transceiver 1110 receives and transmits data under the control of the processor 1100, and the processor 1100 is used to perform the following operations:

[0276] Obtain the created and activated scaling-down policy; the scaling-down policy is either the scaling-down policy of a Network Service (NS) instance or the scaling-down policy of a Virtual Network Function (VNF) instance.

[0277] During the validity period of the scaling-down policy, the scaling-down operation of the NS instance or the VNF instance is triggered based on the scaling-down policy.

[0278] As an optional embodiment, the scaling down operation of the NS instance includes:

[0279] Make resource changes to at least one first VNF ​​instance within the NS instance to reduce the number of virtual machines (VMs) within the first VNF ​​instance.

[0280] As an optional embodiment, the shrinking operation of the VNF instance includes:

[0281] Make resource changes to the VNF instance to reduce the number of VMs within the VNF instance.

[0282] As an optional embodiment, the processor is also configured to perform the following operations:

[0283] Change the state of the NS instance to automatic scaling state; wherein, when the NS instance is in automatic scaling state, other VNF instances within the NS instance, except for the first VNF ​​instance, are prohibited from triggering scaling and related lifecycle operations.

[0284] As an optional embodiment, the processor is also configured to perform the following operations:

[0285] The scaling-down strategy is obtained by accessing the creation strategy interface between VNFM and NFVO;

[0286] The identifier of the scaling-down strategy is fed back to the NFVO; wherein the scaling-down strategy is activated by the NFVO by calling the activation strategy interface between VNFM and NFVO.

[0287] As an optional embodiment, the creation strategy interface includes:

[0288] VNFM identifier;

[0289] NFVO identifier;

[0290] Strategy content;

[0291] Strategy identifier;

[0292] The creation strategy interface also includes at least one of the following:

[0293] The identifier of the instance to which the policy applies; for example, an NS instance identifier or a VNF instance identifier;

[0294] The start time of the effective period of the scaling-down strategy;

[0295] The end date of the scaling-down strategy's validity period.

[0296] This invention extends the policy template by introducing fields such as VNF type to construct an NS / VNF scaling strategy model. It also extends the policy management interface (CreatePolicy, UpdatePolicy) to implement a "timed" function for policy activation. Based on the extended policy template and policy management interface, and combined with actual business characteristics, a reasonable NS / VNF scaling strategy is created, and corresponding effective time periods are set or updated. Through automatic scaling down of NS or VNF instances, the number of idle VMs within NS or VNF instances is reduced, avoiding additional power consumption and allowing more servers to be in an idle state. Ultimately, energy saving is achieved through server power-down operations.

[0297] It should be noted that the network element provided in the embodiments of the present invention is a network element capable of executing the above-described resource-saving method. Therefore, all embodiments of the above-described resource-saving method are applicable to this network element and can achieve the same or similar beneficial effects.

[0298] like Figure 12 As shown, this embodiment of the invention also provides a resource-saving device, comprising:

[0299] The creation module 1201 is used to create a scaling-down strategy by calling the creation strategy interface between VNFM and NFVO and the preset scaling-down strategy template information; the scaling-down strategy is a scaling-down strategy for a network service NS instance or a scaling-down strategy for a virtual network function VNF instance.

[0300] The activation module 1202 is used to activate the scaling-down strategy by calling the activation strategy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down strategy during the validity period of the scaling-down strategy.

[0301] As an optional embodiment, the creation strategy interface includes:

[0302] VNFM identifier;

[0303] NFVO identifier;

[0304] Strategy content;

[0305] Strategy identifier;

[0306] The creation strategy interface also includes at least one of the following:

[0307] The identifier of the instance to which the policy applies; for example, an NS instance identifier or a VNF instance identifier;

[0308] The start time of the effective period of the scaling-down strategy;

[0309] The end date of the scaling-down strategy's validity period.

[0310] As an optional embodiment, the apparatus further includes:

[0311] The second acquisition module is used to acquire the server's resource utilization status after the NS instance or VNF instance is scaled down.

[0312] The energy-saving module is used to power down or put into hibernation operations on idle servers that are not hosting virtual machines (VMs).

[0313] This invention extends the policy template by introducing fields such as VNF type to construct an NS / VNF scaling strategy model. It also extends the policy management interface (CreatePolicy, UpdatePolicy) to implement a "timed" function for policy activation. Based on the extended policy template and policy management interface, and combined with actual business characteristics, a reasonable NS / VNF scaling strategy is created, and corresponding effective time periods are set or updated. Through automatic scaling down of NS or VNF instances, the number of idle VMs within NS or VNF instances is reduced, avoiding additional power consumption and allowing more servers to be in an idle state. Ultimately, energy saving is achieved through server power-down operations.

[0314] It should be noted that the resource-saving device provided in the embodiments of the present invention is a device capable of performing the above-described resource-saving method. Therefore, all embodiments of the above-described resource-saving method are applicable to this device and can achieve the same or similar beneficial effects.

[0315] like Figure 13 As shown, this embodiment of the invention also provides an NFVO, including a processor 1300 and a transceiver 1310. The transceiver 1310 receives and transmits data under the control of the processor 1300, and the processor 1300 is used to perform the following operations:

[0316] A scaling-down strategy is created by calling the creation strategy interface between VNFM and NFVO and the preset scaling-down strategy template information; the scaling-down strategy is either the scaling-down strategy of a network service NS instance or the scaling-down strategy of a virtual network function VNF instance.

[0317] The scaling-down strategy is activated by calling the activation strategy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down strategy during the validity period of the scaling-down strategy.

[0318] As an optional embodiment, the creation strategy interface includes at least one of the following parameters:

[0319] VNFM identifier;

[0320] NFVO identifier;

[0321] Strategy content;

[0322] Strategy identifier;

[0323] The creation strategy interface also includes at least one of the following:

[0324] The identifier of the instance to which the policy applies; for example, an NS instance identifier or a VNF instance identifier;

[0325] The start time of the effective period of the scaling-down strategy;

[0326] The end date of the scaling-down strategy's validity period.

[0327] As an optional embodiment, the processor is also configured to perform the following operations:

[0328] After completing the scaling down operation of the NS instance or VNF instance, obtain the server's resource utilization status.

[0329] If there is an idle server that is not hosting a virtual machine (VM), power down or put the idle server into hibernation mode.

[0330] This invention extends the policy template by introducing fields such as VNF type to construct an NS / VNF scaling strategy model. It also extends the policy management interface (CreatePolicy, UpdatePolicy) to implement a "timed" function for policy activation. Based on the extended policy template and policy management interface, and combined with actual business characteristics, a reasonable NS / VNF scaling strategy is created, and corresponding effective time periods are set or updated. Through automatic scaling down of NS or VNF instances, the number of idle VMs within NS or VNF instances is reduced, avoiding additional power consumption and allowing more servers to be in an idle state. Ultimately, energy saving is achieved through server power-down operations.

[0331] It should be noted that the network element provided in the embodiments of the present invention is a network element capable of executing the above-described resource-saving method. Therefore, all embodiments of the above-described resource-saving method are applicable to this network element and can achieve the same or similar beneficial effects.

[0332] like Figure 14 As shown, this embodiment of the invention also provides a resource-saving device, comprising:

[0333] The strategy determination module 1401 is used to determine the VM optimization strategy based on the distribution of virtual machines (VMs) of NS instances or VNF instances, with the goal of reducing resource fragmentation.

[0334] The migration module 1402 is used to trigger a VM migration operation for an NS instance or a VNF instance according to the VM optimization strategy.

[0335] As an optional embodiment, the VM optimization strategy includes:

[0336] VM migration methods from high-fragmentation servers to low-fragmentation servers;

[0337] VM migration restrictions.

[0338] As an optional embodiment, the VM migration constraints include at least one of the following:

[0339] VM attribute limitations;

[0340] Are there sufficient unused resources on the server?

[0341] Affinity constraints of VMs;

[0342] Anti-affinity constraints on VMs.

[0343] As an optional embodiment, the apparatus further includes:

[0344] The business migration module is used to migrate the services hosted on the VM to be migrated in the NS instance or VNF instance according to business needs.

[0345] As an optional embodiment, the apparatus further includes:

[0346] The third acquisition module is used to acquire information about the server's resource utilization.

[0347] The power-down module is used to power down or put the idle server to sleep if there is an idle server that is not hosting a virtual machine (VM).

[0348] This invention, in combination with the distribution of virtual resources, integrates resource fragments through VM migration operations in NS / VNF instances, achieving centralized deployment of virtual resources, keeping more servers in an idle state, and ultimately achieving energy saving through server power-down operations.

[0349] It should be noted that the resource-saving device provided in the embodiments of the present invention is a device capable of performing the above-described resource-saving method. Therefore, all embodiments of the above-described resource-saving method are applicable to this device and can achieve the same or similar beneficial effects.

[0350] like Figure 15 As shown, this embodiment of the invention also provides an NFVO, including a processor 1500 and a transceiver 1510. The transceiver 1510 receives and transmits data under the control of the processor 1500, and the processor 1500 is used to perform the following operations:

[0351] Based on the distribution of virtual machines (VMs) in NS instances or VNF instances, determine VM optimization strategies with the goal of reducing resource fragmentation.

[0352] Based on the VM optimization strategy, trigger VM migration operations for NS instances or VNF instances.

[0353] As an optional embodiment, the VM optimization strategy includes:

[0354] VM migration methods from high-fragmentation servers to low-fragmentation servers;

[0355] VM migration restrictions.

[0356] As an optional embodiment, the VM migration constraints include at least one of the following:

[0357] VM attribute limitations;

[0358] Are there sufficient unused resources on the server?

[0359] Affinity constraints of VMs;

[0360] Anti-affinity constraints on VMs.

[0361] As an optional embodiment, the processor is also configured to perform the following operations:

[0362] Based on business needs, migrate the services hosted on the VMs to be migrated in the NS instance or VNF instance.

[0363] As an optional embodiment, the processor is also configured to perform the following operations:

[0364] Obtain information on server resource utilization;

[0365] If there is an idle server that is not hosting a virtual machine (VM), power down or put the idle server into hibernation mode.

[0366] This invention, in combination with the distribution of virtual resources, integrates resource fragments through VM migration operations in NS / VNF instances, achieving centralized deployment of virtual resources, keeping more servers in an idle state, and ultimately achieving energy saving through server power-down operations.

[0367] It should be noted that the network element provided in the embodiments of the present invention is a network element capable of executing the above-described resource-saving method. Therefore, all embodiments of the above-described resource-saving method are applicable to this network element and can achieve the same or similar beneficial effects.

[0368] This invention also provides a virtual network device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the various processes in the resource-saving method embodiments described above and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0369] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, this program implements the various processes described above in the resource-saving method embodiments, achieving the same technical effects. To avoid repetition, further details are omitted here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0370] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0371] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 A device for one or more processes and / or the functions specified in one or more boxes.

[0372] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce a paper article including an instruction means, the instruction means being implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0373] These computer program instructions can also be loaded onto a computer or other programmable data processing equipment, causing the computer or other programmable equipment to perform a series of operational steps to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0374] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A resource-saving method, characterized in that, include: The Virtual Network Function Manager (VNFM) obtains the created and activated scaling-down policy; the scaling-down policy is either the scaling-down policy of the Network Service (NS) instance or the scaling-down policy of the Virtual Network Function (VNF) instance; the scaling-down policy is created by the Network Function Virtualization Orchestrator (NFVO) by calling the creation policy interface between VNFM and NFVO, the preset scaling-down policy template information, and the service situation. During the validity period of the scaling-down policy, VNFM triggers the scaling-down operation of the NS instance or the VNF instance based on the scaling-down policy.

2. The method according to claim 1, characterized in that, The scaling down operation of the NS instance includes: Make resource changes to at least one first VNF ​​instance within the NS instance to reduce the number of virtual machines (VMs) within the first VNF ​​instance.

3. The method according to claim 1, characterized in that, The shrinking operation of the VNF instance includes: Make resource changes to the VNF instance to reduce the number of VMs within the VNF instance.

4. The method according to claim 2, characterized in that, After triggering the NS instance based on the shrinkage strategy, the method further includes: Change the state of the NS instance to elastic scaling state; wherein, when the NS instance is in elastic scaling state, other VNF instances within the NS instance, except for the first VNF ​​instance, are prohibited from triggering scaling and related lifecycle operations.

5. The method according to claim 1, characterized in that, VNFM retrieves created and activated scaling policies, including: VNFM obtains the scaling down strategy by accessing the creation strategy interface between VNFM and the NFVO; The VNFM feeds back the identifier of the scaling-down strategy to the NFVO; wherein the NFVO activates the scaling-down strategy by calling the activation strategy interface between the VNFM and the NFVO.

6. The method according to claim 5, characterized in that, The creation strategy interface includes: VNFM identifier; NFVO identifier; Strategy content; Strategy identifier; The creation strategy interface also includes at least one of the following: The identifier of the instance to which the strategy applies; The start time of the effective period of the scaling-down strategy; The end date of the scaling-down strategy's validity period.

7. A resource-saving method, characterized in that, include: NFVO creates a scaling-down strategy by calling the creation strategy interface between VNFM and NFVO, the preset scaling-down strategy template information, and the business situation; The scaling-down strategy is either the scaling-down strategy for a Network Service (NS) instance or the scaling-down strategy for a Virtual Network Function (VNF) instance. NFVO activates the scaling-down policy by calling the activation policy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down policy during the validity period of the scaling-down policy.

8. The method according to claim 7, characterized in that, The creation strategy interface includes: VNFM identifier; NFVO identifier; Strategy content; Strategy identifier; The creation strategy interface also includes at least one of the following: The identifier of the instance to which the strategy applies; The start time of the effective period of the scaling-down strategy; The end date of the scaling-down strategy's validity period.

9. The method according to claim 7, characterized in that, The method further includes: After completing the scaling down operation of the NS instance or VNF instance, the NFVO obtains the resource utilization status of the server. If there is an idle server that is not hosting a virtual machine (VM), the NFVO will power down or put the idle server into hibernation.

10. A resource-saving method, characterized in that, include: NFVO determines VM optimization strategies based on the distribution of virtual machines (VMs) in NS instances or VNF instances, with the goal of reducing resource fragmentation. The NFVO triggers a VM migration operation for the NS instance or VNF instance based on the VM optimization strategy. The VM optimization strategy includes: VM migration methods from high-fragmentation servers to low-fragmentation servers; VM migration restrictions.

11. The method according to claim 10, characterized in that, The VM migration restrictions include at least one of the following: VM attribute limitations; Are there sufficient unused resources on the server? Affinity constraints of VMs; Anti-affinity constraints on VMs.

12. The method according to claim 10, characterized in that, Before the NFVO triggers the VM migration operation of the NS instance or VNF instance according to the VM optimization strategy, the method further includes: Based on business needs, migrate the services hosted on the VMs to be migrated in the NS instance or VNF instance.

13. The method according to claim 10, characterized in that, After the NFVO triggers the VM migration operation of the NS instance or VNF instance according to the VM optimization strategy, the method further includes: The NFVO obtains the server's resource utilization status; If there is an idle server that is not hosting a virtual machine (VM), the NFVO will power down or put the idle server into hibernation.

14. A resource-saving device, characterized in that, include: The first acquisition module is used to acquire the created and activated scaling-down strategy; the scaling-down strategy is the scaling-down strategy of the Network Service NS instance or the scaling-down strategy of the Virtual Network Function VNF instance; the scaling-down strategy is created by the Network Function Virtualization Orchestrator NFVO by calling the creation strategy interface between VNFM and NFVO, the preset scaling-down strategy template information, and the service situation. The operation module is used to trigger a shrinkage operation of the NS instance or the VNF instance based on the shrinkage policy during the validity period of the shrinkage policy.

15. A VNFM, comprising a processor and a transceiver, the transceiver receiving and transmitting data under the control of the processor, characterized in that, The processor is used to perform the following operations: Obtain the created and activated scaling-down policy; the scaling-down policy is the scaling-down policy of the Network Service NS instance or the scaling-down policy of the Virtual Network Function VNF instance; the scaling-down policy is created by the Network Function Virtualization Orchestrator NFVO by calling the creation policy interface between VNFM and NFVO, the preset scaling-down policy template information, and the service situation. During the validity period of the scaling-down policy, the scaling-down operation of the NS instance or the VNF instance is triggered based on the scaling-down policy.

16. The VNFM according to claim 15, characterized in that, The scaling down operation of the NS instance includes: Make resource changes to at least one first VNF ​​instance within the NS instance to reduce the number of virtual machines (VMs) within the first VNF ​​instance.

17. The VNFM according to claim 15, characterized in that, The shrinking operation of the VNF instance includes: Make resource changes to the VNF instance to reduce the number of VMs within the VNF instance.

18. The VNFM according to claim 16, characterized in that, The processor is also used to perform the following operations: Change the state of the NS instance to elastic scaling state; wherein, when the NS instance is in elastic scaling state, other VNF instances within the NS instance, except for the first VNF ​​instance, are prohibited from triggering scaling and related lifecycle operations.

19. The VNFM according to claim 15, characterized in that, The processor is also used to perform the following operations: The scaling-down strategy is obtained by accessing the creation strategy interface between VNFM and NFVO; The identifier of the scaling-down strategy is fed back to the NFVO; wherein the scaling-down strategy is activated by the NFVO by calling the activation strategy interface between VNFM and NFVO.

20. The VNFM according to claim 19, characterized in that, The creation strategy interface includes: VNFM identifier; NFVO identifier; Strategy content; Strategy identifier; The creation strategy interface also includes at least one of the following: The identifier of the instance to which the strategy applies; The start time of the effective period of the scaling-down strategy; The end date of the scaling-down strategy's validity period.

21. A resource-saving device, characterized in that, include: The creation module is used to create a scaling-down strategy by calling the creation strategy interface between VNFM and NFVO, the preset scaling-down strategy template information, and the service situation; the scaling-down strategy is the scaling-down strategy of the network service NS instance or the scaling-down strategy of the virtual network function VNF instance. The activation module is used to activate the scaling-down strategy by calling the activation strategy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down strategy during the validity period of the scaling-down strategy.

22. An NFVO comprising a processor and a transceiver, the transceiver receiving and transmitting data under the control of the processor, characterized in that, The processor is used to perform the following operations: A scaling-down strategy is created by calling the creation strategy interface between VNFM and NFVO, the preset scaling-down strategy template information, and the service situation; the scaling-down strategy is either the scaling-down strategy of a network service NS instance or the scaling-down strategy of a virtual network function VNF instance. The scaling-down strategy is activated by calling the activation strategy interface between VNFM and NFVO, so that VNFM can trigger the scaling-down operation of NS instance or VNF instance based on the scaling-down strategy during the validity period of the scaling-down strategy.

23. The NFVO according to claim 22, characterized in that, The creation strategy interface includes: VNFM identifier; NFVO identifier; Strategy content; Strategy identifier; The creation strategy interface also includes at least one of the following: The identifier of the instance to which the strategy applies; The start time of the effective period of the scaling-down strategy; The end date of the scaling-down strategy's validity period.

24. The NFVO according to claim 22, characterized in that, The processor is also used to perform the following operations: After completing the scaling down operation of the NS instance or VNF instance, obtain the server's resource utilization status. If there is an idle server that is not hosting a virtual machine (VM), power down or put the idle server into hibernation mode.

25. A resource-saving device, characterized in that, include: The strategy determination module is used to determine VM optimization strategies based on the distribution of virtual machines (VMs) in NS instances or VNF instances, with the goal of reducing resource fragmentation. The migration module is used to trigger VM migration operations for NS instances or VNF instances according to the VM optimization strategy. The VM optimization strategy includes: VM migration methods from high-fragmentation servers to low-fragmentation servers; VM migration restrictions.

26. An NFVO comprising a processor and a transceiver, the transceiver receiving and transmitting data under the control of the processor, characterized in that, The processor is used to perform the following operations: Based on the distribution of virtual machines (VMs) in NS instances or VNF instances, determine VM optimization strategies with the goal of reducing resource fragmentation. Based on the VM optimization strategy, trigger VM migration operations for NS instances or VNF instances; The VM optimization strategy includes: VM migration methods from high-fragmentation servers to low-fragmentation servers; VM migration restrictions.

27. The NFVO according to claim 26, characterized in that, The VM migration restrictions include at least one of the following: VM attribute limitations; Are there sufficient unused resources on the server? Affinity constraints of VMs; Anti-affinity constraints on VMs.

28. The NFVO according to claim 26, characterized in that, The processor is also used to perform the following operations: Based on business needs, migrate the services hosted on the VMs to be migrated in the NS instance or VNF instance.

29. The NFVO according to claim 26, characterized in that, The processor is also used to perform the following operations: Obtain information on server resource utilization; If there is an idle server that is not hosting a virtual machine (VM), power down or put the idle server into hibernation mode.

30. A virtual network device, comprising a memory, a processor, and a program stored in the memory and executable on the processor; characterized in that, When the processor executes the program, it implements the resource-saving method as described in any one of claims 1-6; or when the processor executes the program, it implements the resource-saving method as described in any one of claims 7-9; or when the processor executes the program, it implements the resource-saving method as described in any one of claims 10-13.

31. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the resource-saving method as described in any one of claims 1-6; or when the program is executed by the processor, it implements the steps of the resource-saving method as described in any one of claims 7-9; or when the program is executed by the processor, it implements the steps of the resource-saving method as described in any one of claims 10-13.

Images