Virtual network element capacity expansion and contraction method, device, equipment, medium and program product
By acquiring and aggregating load data in virtual network elements, generating scaling strategies, and automatically adjusting resources, the problem of inefficiency in traditional virtual network elements is solved, and dynamic optimization and efficient utilization of resources are achieved.
Patent Information
- Application Number
- CN202411096840.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-12-06
AI Technical Summary
Traditional virtual network element capacity management relies on manual intervention, is inefficient and error-prone, and cannot automatically adjust resources dynamically according to business loads, and cannot effectively meet changing business needs.
By obtaining the aggregate load data of the target virtual network element in the current time window, a capacity expansion or reduction strategy is generated, including increasing or decreasing the number of virtual network element instances and resources, data aggregation is used using arithmetic average or weighted average algorithm, and according to presets The threshold automatically determines the scaling operation.
It realizes automatic adjustment and optimized configuration of resources, improves resource utilization, reduces manual intervention and human errors, improves operation and maintenance efficiency, and can quickly respond to load changes, avoid performance problems caused by insufficient or oversupply of resources.
Smart Images

Figure CN119094336A_ABST
Abstract
Description
Background Art
[0002] In the field of modern network communications and information technology, with the explosive growth of data traffic, the demand for network services is also increasing. Traditional network equipment (such as hardware firewalls, routers, etc.) can no longer meet this rapidly growing demand. In order to solve this problem, Network Function Virtualization (NFV) technology came into being.
[0003] NFV technology realizes the softwareization of network functions by transferring network functions (such as firewalls, load balancers, intrusion detection systems, vBRAS (Virtual Broadband Remote Access Server), 5GC (5th Generation Core Network), etc.) from dedicated hardware devices to virtual machines or servers. This not only reduces costs, but also improves flexibility and scalability. However, with the development of virtual network elements, how to effectively manage the capacity of virtual network elements to meet changing business needs has become a challenge. The change of traditional virtual network element capacity usually relies on manual intervention, which is not only inefficient but also prone to errors. Therefore, how to propose a method to automatically manage the capacity of virtual network elements and ensure that virtual network elements can dynamically adjust resources according to business load is a technical problem that needs to be solved urgently.
[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention
[0005] The present disclosure provides a method, device, equipment, medium and program product for scaling up and down a virtual network element, which at least to a certain extent overcomes the problem that the related technology cannot automatically manage the capacity of the virtual network element.
[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.
[0007] According to one aspect of the present disclosure, a method for scaling up and down a virtual network element is provided, including: obtaining aggregated load data of a target virtual network element within a current time window, the target virtual network element including at least one virtual network element instance; the current time window is a time period located before and immediately adjacent to the current moment, and the aggregated load data is an aggregation result of business load data of each virtual network element instance in the target virtual network element; based on the aggregated load data of the target virtual network element within the current time window, generating an expansion strategy or a reduction strategy for the target virtual network element at the current moment, the expansion strategy being to increase the number of virtual network element instances in the target virtual network element or to increase the resources of each virtual network element instance in the target virtual network element, and the reduction strategy being to reduce the number of virtual network element instances in the target virtual network element or to reduce the resources of each virtual network element instance in the target virtual network element.
[0008] In some embodiments, before obtaining the aggregate load data of the target virtual network element in the current time window, the method also includes: determining a collection period for the business load data of each virtual network element instance in the target virtual network element; determining a collection time point according to the collection period; and collecting the business load data of each virtual network element instance in the target virtual network element at the collection time point.
[0009] In some embodiments, before obtaining the aggregate load data of the target virtual network element within the current time window, the method also includes: obtaining the business load data of each virtual network element instance collected by the target virtual network element within the current time window; and obtaining the aggregate load data based on the business load data of each virtual network element instance collected within the current time window.
[0010] In some embodiments, aggregate load data is obtained based on the business load data of each virtual network element instance collected within the current time window, including: using an aggregation algorithm to calculate the aggregate load from the business load data of each virtual network element instance collected within the current time window, and the aggregation algorithm includes: arithmetic average algorithm and weighted average algorithm.
[0011] In some embodiments, based on the aggregated load data of the target virtual network element in the current time window, a capacity expansion strategy or a capacity reduction strategy of the target virtual network element at the current moment is generated, including: determining the upper threshold and / or lower threshold of the target virtual network element; comparing the aggregated load data of the target virtual network element in the current time window with the upper threshold and / or the lower threshold, if the aggregated load data is greater than the upper threshold, generating a capacity expansion strategy for the target virtual network element at the current moment, if the aggregated load data is less than the lower threshold, generating a capacity reduction strategy for the target virtual network element at the current moment.
[0012] In some embodiments, the capacity expansion strategy includes one or more of the following: restoring a created virtual network element instance, creating and configuring a virtual network element instance; the capacity reduction strategy includes one or more of the following: migrating the load of the virtual network element instance, shutting down the virtual network element instance, and reclaiming resources.
[0013] According to another aspect of the present disclosure, a virtual network element expansion and contraction device is also provided, including: a data acquisition module, used to obtain the aggregated load data of the target virtual network element within the current time window, the target virtual network element includes at least one virtual network element instance; the current time window is a time period located before and immediately adjacent to the current moment, and the aggregated load data is the aggregation result of the business load data of each virtual network element instance in the target virtual network element; a expansion and contraction execution module, used to generate an expansion strategy or a contraction strategy of the target virtual network element at the current moment according to the aggregated load data of the target virtual network element within the current time window, the expansion strategy is to increase the number of virtual network element instances in the target virtual network element or to increase the resources of each virtual network element instance in the target virtual network element, and the contraction strategy is to reduce the number of virtual network element instances in the target virtual network element or to reduce the resources of each virtual network element instance in the target virtual network element.
[0014] According to another aspect of the present disclosure, an electronic device is also provided, which includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned virtual network element expansion and contraction methods by executing the executable instructions.
[0015] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for scaling up and down a virtual network element described in any one of the above is implemented.
[0016] According to another aspect of the present disclosure, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for scaling up and down virtual network elements.
[0017] The virtual network element expansion and contraction method, device, equipment, medium and program product provided in the embodiments of the present disclosure obtains the aggregated load data of the target virtual network element in the current time window, and the target virtual network element includes at least one virtual network element instance; the current time window is a time period before and immediately adjacent to the current moment, and the aggregated load data is the aggregated result of the business load data of each virtual network element instance in the target virtual network element; based on the aggregated load data of the target virtual network element in the current time window, the expansion strategy or contraction strategy of the target virtual network element at the current moment is generated, and resource adjustment is automatically completed, thereby realizing optimal resource configuration and improving resource utilization. Through real-time monitoring and analysis of aggregated load data, resources can be dynamically adjusted to adapt to changing business needs. Through automated expansion and contraction decision-making and execution, the need for manual intervention is reduced, the possibility of human error is reduced, and operation and maintenance efficiency is improved.
[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.
[0020] Figure 1 A schematic diagram of a virtual network element in an embodiment of the present disclosure is shown;
[0021] Figure 2 A flow chart of a method for scaling up and down a virtual network element in an embodiment of the present disclosure is shown;
[0022] Figure 3 A flow chart of another method for scaling capacity of a virtual network element in an embodiment of the present disclosure is shown;
[0023] Figure 4 A flow chart of another method for scaling capacity of a virtual network element in an embodiment of the present disclosure is shown;
[0024] Figure 5 A flow chart of another method for scaling capacity of a virtual network element in an embodiment of the present disclosure is shown;
[0025] Figure 6 A schematic diagram of a scenario of virtual network element expansion and contraction based on a sliding time window in an embodiment of the present disclosure is shown;
[0026] Figure 7 An overall flow chart of a method for scaling up and down a virtual network element in an embodiment of the present disclosure is shown;
[0027] Figure 8 A flow chart of a method for collecting virtual network element load data in an embodiment of the present disclosure is shown;
[0028] Fig. 9 A flow chart of capacity expansion and contraction decision-making based on a sliding time window in an embodiment of the present disclosure is shown;
[0029] Fig.10 A flow chart of generating a scaling strategy in an embodiment of the present disclosure is shown;
[0030] Fig.11 A schematic diagram of a capacity expansion and contraction process in an embodiment of the present disclosure is shown;
[0031] Fig.12 A schematic diagram of a capacity expansion and contraction device in an embodiment of the present disclosure is shown;
[0032] Fig.13 A schematic diagram of a device for scaling up and down a virtual network element in an embodiment of the present disclosure is shown;
[0033] Fig.14 A structural block diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0034] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0035] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.
[0036] For ease of understanding, before introducing the embodiments of the present disclosure, several terms involved in the embodiments of the present disclosure are first explained as follows:
[0037] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.
[0038] Figure 1 FIG. 2 shows a schematic diagram of a virtual network element to which the present disclosure can be applied. Figure 1 As shown, the virtual network element 101 includes one or more virtual network element instances 102 .
[0039] Virtual Network Function (VNF) 101 refers to a software application that runs on a general-purpose hardware platform after virtualizing the functions of traditional network devices. It decouples network functions (such as routing, firewalls, load balancing, etc.) from dedicated hardware and runs them in a virtual machine or container in the form of software. Virtual network elements can flexibly deploy and adjust network functions as needed to meet the needs of different scenarios. Virtual network elements can quickly expand network capacity to adapt to business growth. Virtual network elements use general-purpose hardware platforms to reduce equipment costs and maintenance costs. Virtual network elements can automatically deploy, manage, and maintain network functions through software.
[0040] The types of virtual network elements 101 may include multiple types, such as access-type virtual network elements vBRAS (virtual Broadband Remote Access Server), vBNG (virtual Broadband Network Gateway), and vCPE (virtual Customer Premises Equipment); transmission-type virtual network elements such as vRouter (virtual Router), vSwitch (virtual Switch), etc.; control-type virtual network elements vSMF (virtual Session Management Function), vAMF (virtual Access and Mobility Management Function), etc.; security-type virtual network elements such as vFW (virtual Firewall) and vIPS (virtual Intrusion Prevention System).
[0041] Application scenarios of the virtual network element 101 may include: NFV (Network Function Virtualization) is an emerging network architecture that virtualizes network functions to achieve flexible deployment, management and expansion of the network. SDN (Software-Defined Networking) is a network architecture that separates the network control layer from the data layer and centrally manages network traffic through a network controller. Virtual network elements can be combined with cloud computing platforms to provide more flexible and scalable network services.
[0042] A virtual network element instance 102 (Virtual Network Function Instance, VNF Instance) is a specific running instance of a virtual network element. Each virtual network element instance represents a running entity of a virtual network element on a specific hardware platform and can independently perform network functions. Each virtual network element instance runs independently and does not interfere with each other. The composition of a virtual network element instance may include a VNF software image; virtualized resources: including virtual machines, containers, etc.
[0043] In the above-mentioned virtual network element schematic scenario, a method for scaling up and down a virtual network element is provided in an embodiment of the present disclosure. The method can be executed by any electronic device with computing and processing capabilities.
[0044] Figure 2 A flow chart of a method for scaling virtual network elements in an embodiment of the present disclosure is shown as follows: Figure 2 As shown, the method for scaling up and down a virtual network element provided in the embodiment of the present disclosure includes the following steps:
[0045] S202, obtain the aggregated load data of the target virtual network element in the current time window, the target virtual network element includes at least one virtual network element instance; the current time window is a time period before the current moment and adjacent to the current moment, and the aggregated load data is the aggregation result of the business load data of each virtual network element instance in the target virtual network element.
[0046] It should be noted that the target virtual network element can be any virtual network element that needs to be expanded or reduced, wherein the target virtual network element includes at least one virtual network element instance, and the target virtual network element is not a single entity, but a collection of one or more virtual network element instances. Each virtual network element instance is a running copy of the target virtual network element and can independently perform network functions.
[0047] The current time window is a time period that is before the current moment and is adjacent to the current moment. The time length of the current time window can be adjusted according to actual needs. It should be noted that the current time window of the embodiment of the present disclosure can be the current time window in the sliding time window. The sliding time window is a time period of fixed length that can be slid on the time axis, with a certain step length each time. The purpose of the sliding time window is to continuously analyze data and observe the changing trend of data over time by sliding the time window. The current time window can be regarded as a time period from the sliding time window sliding to the current moment and adjacent to the current moment.
[0048] The business load data of a virtual network element instance refers to the data reflecting the workload and resource usage of a specific virtual network element instance when performing its business functions. Business load data is a key indicator for measuring the performance and health of a virtual network element instance, and can usually include data such as the throughput, bandwidth utilization, vCPU (Virtual Central Processing Unit) utilization, and memory utilization of the virtual network element instance.
[0049] The service load data comes from each virtual network element instance in the target virtual network element. The aggregated load data refers to the data that is aggregated and integrated from the service load data of each virtual network element instance in the target virtual network element. By aggregating the service load data, the overall performance of the entire target virtual network element can be monitored. Aggregated load data can provide a comprehensive understanding of the performance of the entire virtual network element, not just a single instance. Aggregated load data provides data support for resource allocation and adjustment, making expansion and contraction decisions more scientific and reasonable.
[0050] S204, based on the aggregated load data of the target virtual network element in the current time window, generates an expansion strategy or a reduction strategy for the target virtual network element at the current moment, wherein the expansion strategy is to increase the number of virtual network element instances in the target virtual network element or to increase the resources of each virtual network element instance in the target virtual network element, and the reduction strategy is to reduce the number of virtual network element instances in the target virtual network element or to reduce the resources of each virtual network element instance in the target virtual network element.
[0051] It should be noted that the service load data collected and summarized from all instances of the target virtual network element reflects the overall workload and resource usage of the target virtual network element when performing service functions. Based on the analysis results of the aggregated load data, the system will generate corresponding expansion and contraction strategies, including expansion strategy and contraction strategy.
[0052] In some embodiments, when the aggregated load data indicates that the resource usage of the target virtual network element is close to or has reached the capacity limit, and the business demand continues to grow, the system will generate a capacity expansion strategy. The capacity expansion strategy can be achieved by increasing the number of virtual network element instances and adding resources, such as deploying more virtual network element instances to share the load and improve the overall processing capacity; or increasing the resource quota of the existing virtual network element instances, such as increasing CPU, memory or storage resources.
[0053] In other embodiments, when the aggregated load data shows that the resource usage of the target virtual network element is far below the capacity and the business demand decreases, the system will generate a reduction strategy. The reduction strategy can achieve reduction by reducing the number of instances and reducing resources, such as shutting down some virtual network element instances to reduce resource consumption and reduce operating costs; or reducing the resource quota of existing virtual network element instances to save resources.
[0054] The disclosed embodiments can dynamically adjust resources to adapt to changing business needs by analyzing the aggregated load data in the current time window in real time. The implementation of the expansion strategy can ensure that the virtual network element maintains good performance during peak hours, while the reduction strategy helps save resources and avoid waste while maintaining service availability. Ensuring that the virtual network element can automatically adjust resources according to the actual load helps maintain or improve the quality of the service, reduces the need for manual intervention, reduces the possibility of human error, and improves operation and maintenance efficiency. Since the disclosed embodiments make decisions based on the data in the current time window, they can quickly respond to load changes and adjust resources in a timely manner, avoiding performance problems caused by insufficient resources or waste problems caused by excess resources.
[0055] In some embodiments of the present disclosure, Figure 3 As shown, before obtaining the aggregated load data of the target virtual network element in the current time window, the following steps are also included:
[0056] S302, determining a collection period for service load data of each virtual network element instance in the target virtual network element;
[0057] S304, determining a collection time point according to a collection cycle;
[0058] S306, collecting business load data of each virtual network element instance in the target virtual network element at the collection time point.
[0059] It should be noted that before obtaining the aggregated load data, it is necessary to collect the business load data within the current time window. The collection process first needs to determine a collection period for the business load data of each virtual network element instance in the target virtual network element. The collection period refers to the frequency or interval of data collection, that is, how often the data is collected. This period can be set based on factors such as business needs and system performance requirements. According to the determined collection period, the specific collection time point is calculated. The collection time point refers to the data collection at a specific moment to ensure the continuity and consistency of the data.
[0060] At the set collection time point, the business load data of each virtual network element instance in the target virtual network element will be collected. This data may include throughput, vCPU utilization, memory usage, network traffic, response time, etc. By determining a fixed collection cycle and time point, the accuracy and consistency of the data can be ensured, providing a reliable basis for subsequent data analysis and decision-making. In addition, the collection cycle can be adjusted according to different business needs and environmental changes to adapt to different monitoring and management requirements. Reasonable setting of the collection cycle can avoid excessive data collection, save system resources, and also capture key performance indicators in a timely manner. The collected data is more accurate and systematic, which helps to generate more effective expansion or reduction strategies.
[0061] In some embodiments of the present disclosure, Figure 4 As shown, before obtaining the aggregated load data of the target virtual network element in the current time window, the following steps are also included:
[0062] S402, obtaining service load data of each virtual network element instance collected by the target virtual network element within the current time window;
[0063] S404: Obtain aggregated load data according to the service load data of each virtual network element instance collected in the current time window.
[0064] It should be noted that the collection process only collects business load data, including but not limited to throughput, vCPU utilization, memory utilization, etc. After collecting the business load data of each virtual network element instance, aggregate load data is generated based on these data. The aggregation process may include calculating statistical indicators such as average, sum, maximum, minimum, etc. to obtain the overall performance and resource usage of the entire target virtual network element in the current time window. In some embodiments, the aggregate load data is obtained based on the business load data of each virtual network element instance collected in the current time window, including: using an aggregation algorithm to calculate the aggregate load from the business load data of each virtual network element instance collected in the current time window, and the aggregation algorithm includes: arithmetic average algorithm, weighted average algorithm.
[0065] The disclosed embodiments require the use of a specific aggregation algorithm to calculate the aggregated load. The role of the aggregation algorithm is to merge multiple data points into a value that represents the overall performance. Among them, the arithmetic average algorithm obtains the arithmetic mean by adding the business load data of all virtual network element instances and then dividing it by the number of virtual network element instances. It is suitable for the case where it is assumed that all virtual network element instances contribute equally to the overall performance. The weighted average algorithm is different from the arithmetic average algorithm. The weighted average algorithm takes into account the different contributions of different virtual network element instances to the overall performance. The business load data of each virtual network element instance will be multiplied by a weight factor and then summed, which is more suitable for situations where the importance or resource distribution between instances is uneven.
[0066] By adopting arithmetic average or weighted average algorithm, more accurate and representative aggregated load data can be obtained, thus providing a more reliable basis for scaling decisions. By aggregating the service load data of each virtual network element instance, more comprehensive data can be obtained to better understand the performance status of the entire virtual network element. The process from data collection to aggregation is clarified, making the method clearer and easier to implement and verify. The generated aggregated load data provides direct data support for the formulation of expansion or reduction strategies, making the strategy more based on actual conditions.
[0067] In some embodiments of the present disclosure, Figure 5 As shown, according to the aggregated load data of the target virtual network element in the current time window, generating a capacity expansion strategy or a capacity reduction strategy of the target virtual network element at the current moment, further comprising the following steps:
[0068] S502, determining an upper threshold and / or a lower threshold of a target virtual network element;
[0069] S504, compare the aggregate load data of the target virtual network element in the current time window with the upper threshold and / or the lower threshold. If the aggregate load data is greater than the upper threshold, generate a capacity expansion strategy for the target virtual network element at the current moment. If the aggregate load data is less than the lower threshold, generate a capacity reduction strategy for the target virtual network element at the current moment.
[0070] It should be noted that an upper threshold and / or a lower threshold are set for the target virtual network element. The upper and lower thresholds are standards for determining whether capacity expansion or contraction is required, and the upper and lower thresholds can usually be determined based on historical data, performance targets, resource constraints, and other factors.
[0071] The upper threshold refers to the maximum load that the virtual network element can bear. If the aggregate load data exceeds this value, it indicates that the resources of the virtual network element may not be sufficient to meet the current business needs, and you need to consider expanding the capacity. The lower threshold refers to the minimum load that the virtual network element can maintain normal service operation. If the aggregate load data is lower than this value, it indicates that the resources of the virtual network element may be excessive, and you can consider reducing the capacity to save resources.
[0072] Compare the aggregate load data of the target virtual network element in the current time window with the preset upper threshold and / or lower threshold. If the aggregate load data is greater than the upper threshold, it indicates that the current load is too high, and a capacity expansion strategy will be generated. The capacity expansion strategy may include increasing the number of virtual network element instances or increasing the resources of existing instances. If the aggregate load data is less than the lower threshold, it indicates that the current load is too low, and a capacity reduction strategy will be generated. The capacity reduction strategy may include reducing the number of virtual network element instances or reducing the resources of existing instances.
[0073] Through the preset thresholds, it is possible to automatically determine when to expand or reduce capacity, reducing the need for manual intervention. Through the upper and lower thresholds, actions can be taken before resources are insufficient or excessive, preventing potential performance problems or resource waste. It should be noted that the thresholds can be adjusted according to different business needs and environmental changes, making the method more flexible and customizable.
[0074] In the embodiments of the present disclosure, the capacity expansion strategy may specifically include the following operations:
[0075] Restore created virtual network element instances: If you previously created virtual network element instances but later shut them down, you can restart these virtual network element instances to increase processing capacity.
[0076] Create and configure virtual network element instances: If the existing virtual network element instances are not sufficient to cope with the current load, you can create new virtual network element instances and configure them as needed to provide additional resources.
[0077] In the embodiment of the present disclosure, the scaling-down strategy may specifically include the following operations:
[0078] Migrate the load of virtual network element instances: If the load of a virtual network element instance is too high, you can transfer part of the load to other instances to balance resource usage.
[0079] Shut down a virtual network element instance: If the load on a virtual network element instance is too low, you can temporarily shut down the instance to save resources.
[0080] Reclaim resources: If the loads of multiple virtual network element instances are very low, you can reclaim the unused resources in these virtual network element instances so that they can be reallocated when needed elsewhere.
[0081] Through operations such as restoring, creating, migrating, shutting down, and reclaiming resources, you can manage the resources of virtual network elements more flexibly. By adjusting the number of instances and resource allocation, you can allocate resources more effectively and avoid resource waste. By migrating loads and shutting down low-load instances, you can prevent performance bottlenecks and over-allocation of resources. Based on real-time load data and preset thresholds, you can dynamically adjust the number of instances and resources to adapt to changes in business needs.
[0082] In some embodiments of the present disclosure, Figure 6-Figure 12 Taking the example, the method for scaling the virtual network element provided by the embodiment of the present disclosure is specifically described, which is applicable to the scenario where the virtual network element carries services and scales the capacity according to the service load.
[0083] Virtual network elements are widely used in public clouds, private clouds (such as vRouter, vGW, etc.) and NFV scenarios (such as vBRAS / vCPE, AMF / SMF, etc.). As the load fluctuates, virtual network elements need to be continuously expanded or reduced. When the load of virtual network elements continues to increase and reaches a certain threshold, expanding the capacity of virtual network elements can reduce the resource utilization of virtual network elements and ensure service quality; when the load of virtual network elements continues to decrease and reaches a certain threshold, reducing the capacity of virtual network elements can reduce the resources occupied by virtual network elements while meeting service quality, and reduce energy consumption, thereby saving costs.
[0084] The traditional scaling method of virtual network elements is difficult to adapt to the fluctuations of virtual network cloud load in an uncertain period of time, and leads to inaccurate scaling and even misoperation. The problems faced include: The scaling of virtual network elements based on the ETSI (European Telecommunications Standard Institute) NFV architecture is usually based on peak load. The decision-making method predicts the business volume and load demand in a certain period of time in the future. There are problems such as long prediction cycle, long decision-making process, inaccurate prediction, and need for manual participation, which leads to long-term low resource utilization, resource waste and high energy consumption. Virtual network elements based on ETSI NFV usually lack the ability to dynamically scale up and down, including the lack of a closed loop from load to scaling up and down, and the process is not perfect. The elastic scaling of traditional cloud resources usually focuses on resources such as virtual machines and containers, supports the resource requirements of hot events and emergencies, and is usually difficult to adapt to the dynamic scaling of virtual network elements and maintain the global configuration and strategy of virtual network elements such as routing strategies, address pools, and network topologies.
[0085] The target virtual network element of the disclosed embodiment runs based on cloud resources such as virtual machines and containers. When the business load increases, the virtual network element instance is expanded on demand, and the expanded virtual network element instance and the original network element instance jointly carry the business; when the business load drops to a certain level, the virtual network element instance is reduced, and the number of virtual network element instances to be reduced should be no less than 2. Virtual network element expansion includes expanding the number of virtual network element instances and expanding the computing resources for running virtual network elements, such as virtual machines, containers / Pods, bare metal, etc. The virtual network element instance group uses virtual machines or containers of the same specifications, including but not limited to 4C8G or 8C16G virtual machines, etc. The expansion method of the virtual network element instance includes but is not limited to expansion and reduction based on ETSI MANO, or elastic expansion or reduction based on the cloud platform.
[0086] A virtual network element uses a group of virtual network element instances to carry services together. Each virtual network element instance uses load balancing or n+1, n:1, n+m, n:m, group pool and other mechanisms. Scaling a virtual network element instance includes increasing the number of virtual network element instances, modifying the configuration, adding the virtual network element to the instance group, supporting load balancing or master-slave between virtual network element instances, and carrying network element services together. Scaling a virtual network element instance includes shutting down a virtual network element instance, deleting a virtual network element instance from an instance group, migrating service loads, and releasing occupied virtual resources.
[0087] The current time window of the embodiment of the present disclosure can apply the specific concept of sliding time window, which consists of two parts: time window and sliding mechanism. The time window specifies the size of the window. Figure 6 A schematic diagram of a virtual network element expansion and contraction scenario based on a sliding time window in an embodiment of the present disclosure is shown. Figure 6 The window size N shown in the figure is as follows; the sliding mechanism refers to the sliding progressive form, sliding from the previous time window to the next time window, and the sliding step size can be set to m. Figure 6 As shown, from the time window at the current time t, slide to the time window at time t+m. The window size N should be larger than the load data collection period of the virtual network element, including but not limited to one or more collected load data in the time window. Two consecutive time windows are allowed to have intersections of data sets.
[0088] By adopting the concept of sliding time window, the sliding time window algorithm is used to process real-time data. Among them, time t is the current time, and the business load data of the virtual network element in the current time window is composed of Loadgw(tN), ..., Loadgw(t). The aggregated load data of the time window at time t is generated by the merge algorithm. By comparing the aggregated load data with the upper threshold and the lower threshold, the virtual network element expansion and contraction strategy at time t is determined.
[0089] Time t+m: Slide to the next window time, re-aggregate and process the data in the next window and generate the expansion and contraction strategy. At time t+m, the business load data of the virtual network element in the current time is composed of Loadgw(t+mN), ..., Loadgw(t+m). The merge algorithm is used to generate the fused load data of the time window at time t+m, and the aggregated load data is compared with the upper and lower thresholds to determine the expansion and contraction strategy of the virtual network element at time t+m.
[0090] Sliding step m: When the sliding step m is smaller than the window size, the load data sets of the virtual network elements in the two consecutive windows have intersections, and some data are reused for aggregation processing and generation strategies; when the sliding step m is larger than the window size, the data sets of the two consecutive windows have no intersections.
[0091] Merge algorithm: including but not limited to averaging, weighted averaging and other algorithms.
[0092] Specifically, the embodiments of the present disclosure are all composed of a capacity expansion and contraction device. The capacity expansion and contraction device includes: a collection module, a decision module, and an execution module, wherein the collection module: periodically collects parameters such as the business load of the virtual network element; the decision module: uses the virtual network element load data obtained by the collection module, and adopts a sliding time window algorithm to calculate the aggregate load of the virtual network element in the current time window, and generates a capacity expansion and contraction strategy for the virtual network element; the execution module: executes the capacity expansion and contraction operations of the virtual network element instance, including the capacity expansion and contraction of the virtual network element instance, and the capacity expansion and contraction of the cloud resources running the virtual network element. The overall process of the capacity expansion and contraction method is as follows: Figure 7 As shown, including:
[0093] S702: Obtain load data of the virtual network element.
[0094] S704: Generate a capacity expansion and contraction strategy within the virtual network element time window.
[0095] S706: Execute the expansion and contraction strategy.
[0096] The data of the virtual network element instance is collected, updated and maintained by the collection module. The collection process is as follows: Figure 8 As shown, the following steps are also included:
[0097] S802, setting a collection period T and a data type of a service load of a virtual network element.
[0098] S804, determine whether the current time point is a collection time point. If not, return; if yes, go to step S806; the collection time point can be described as t0+iT, t=0, 1, .... Among them, t0 represents the time point of initial collection, and data is collected once every time period T. The current time point is not a collection time point, and the system waits until the collection time point.
[0099] S806, obtain the service load data of the virtual network element. The virtual network elements of the collected object include but are not limited to single or multiple virtual network element instances. The load data of each network element instance should be collected at each collection time point. For a virtual network element composed of S virtual network element instances, the virtual network element load data set to be collected is required to be: Loadgw(s,t0+iT), s=1,…,S, i=0,1,2,…, s represents the sequence number of the virtual network element instance, and T is the time period.
[0100] S808, reporting and storing the service load data of the virtual network element. The acquisition module is responsible for saving, updating and maintaining the reported and stored load data of the virtual network element, including writing, deleting, updating and writing to the database after deduplication.
[0101] The service load data of the virtual network element includes but is not limited to data types describing the VNF load, such as the throughput and bandwidth utilization of the virtual network element. When replaced by cloud resource data, the load data of the virtual network element includes but is not limited to the vCPU utilization and memory utilization of the virtual machine running the virtual network element. The collection period T of the load data of the virtual network element describes the time interval for collecting the load data of the virtual network element, which is manually specified or sent by the collection module.
[0102] The overall process of generating the expansion and contraction strategy of the target virtual network element in the current time window is as follows: Fig. 9 As shown, the following steps are included:
[0103] S902. Set the length N of the sliding time window and the threshold. Setting the length N of the sliding time window and the threshold includes, but is not limited to, initializing the sliding time window parameters and the threshold parameters. Among them, the length N of the sliding time window describes the size of the time window where the current moment is located, and the value range includes, but is not limited to, 0, 1, …, and must be a non - negative integer. When N = 0, the data in the time window is only the data at the current moment t; when N = 1, the data in the time window includes Loadgw(t - 1), Loadgw(t), and so on. The length N of the sliding time window should be not less than the virtual network element load data collection period T to ensure that there is at least one virtual network element's load data in each sliding time window. The threshold parameter refers to the upper threshold and the lower threshold of the virtual network element load. The length N of the sliding time window and the threshold include, but are not limited to, manual specification or system configuration.
[0104] S904. Determine whether it is the current moment of the sliding time window. If so, go to step S906; if not, return. The current moment of the time window refers to each time point generated when the sliding time window slides with a step size m starting from the initial moment t0, which can be described as t0 + km, k = 0, 1, …. The determination of whether it is the current moment of the sliding time window refers to judging whether the current time point is one of the current moments of the sliding time window. If not, do nothing and return; if so, go to step S906, process the virtual network element load data in the time window and determine whether scaling is required. Among them, the sliding time step size m includes, but is not limited to, integer values and time lengths.
[0105] S906. Obtain the service load data of the virtual network element instances in the time window. The virtual network element load data in the time window includes, but is not limited to, data such as the throughput, bandwidth utilization rate, vCPU utilization rate, and memory utilization rate of the virtual network element.
[0106] The virtual network element load data in the time window refers to all the network element load data of the virtual network element in the time window where the current moment t is located, including, but not limited to, the load data of a single virtual network element: Loadgw(t - N), …, Loadgw(t), t >= t0, representing the virtual network element load data set in the time period [t - N, t], which is composed of R virtual network element load data collected in the time period [t - N, t]. Or: Loadgw(t0 + km - N), …, Loadgw(t0 + km), k = 0, 1, … represents the virtual network element service load data set in the current moment set [t0 + km - N, …, t0 + km], which is composed of R virtual network element load data collected in [t0 + km - N, …, t0 + km]. For each moment before the current moment t0, represented by x, when t0 - N <= x < t0, the value of Loadgw(x) is 0.
[0107] The virtual network element load data within the time window includes, but is not limited to, the load data of multiple virtual network element instances. For the load data of S virtual network elements within the current time window, it includes, but is not limited to: Loadgw(s,t-N), …, Loadgw(s,t), s = 1, …, S, t >= t0, representing the load data sets of S virtual network elements within the time period [t-N,t], where each virtual network element collects R load data samples. Or: Loadgw(s,t0+km-N), …, Loadgw(s,t0+km), s = 1, …, S, k = 0,1, … representing the load data sets of S virtual network elements within the current moment set [t0+km-N, …, t0+km], where each virtual network element collects R load data samples. For each moment x before the current moment t0, when t0-N <= x < t0, the value of Loadgw(s,x) is 0.
[0108] S908, calculate the aggregated load of the virtual network element within the time window.
[0109] The aggregated load of the virtual network element within the time window refers to the aggregated load data of the target virtual network element obtained by using an aggregation algorithm merge on the service load data set of a single virtual network element instance within the current time window. The merge algorithm includes, but is not limited to, algorithms such as arithmetic mean and weighted mean:
[0110] Arithmetic mean:
[0111] Weighted mean:
[0112] Among them, R represents that there are R virtual network element load data in each time window. α x represents the weight of the x-th data.
[0113] The virtual network element load data within the time window includes, but is not limited to, the load data of multiple virtual network element instances, including:
[0114] For the throughput of S virtual network element instances within the current time window, the merge algorithm includes, but is not limited to, algorithms such as arithmetic mean and weighted mean:
[0115] Arithmetic mean:
[0116] Weighted mean:
[0117] Among them, R represents that each virtual network element instance has R load data in each time window.
[0118] α x represents the weight of the x-th data.
[0119] For the link utilization, vCPU utilization, memory utilization, etc. of the S virtual network elements in the current time window, the merge algorithm includes but is not limited to: arithmetic average, weighted average and other algorithms:
[0120] Arithmetic mean:
[0121] Weighted Average:
[0122] Among them, R means that each virtual network element instance has R load data in each time window. x Represents the weight of the x-th data.
[0123] S910, generate and return the expansion and contraction strategy of the virtual network element within the time window. The expansion strategy is described by the expansion identifier, and the contraction identifier is described by the contraction identifier. The expansion identifier and the contraction identifier may include but are not limited to information such as name, scheduling strategy, expansion identifier, or contraction identifier. The returned expansion and contraction strategy is created, updated, deleted, etc. by the decision module.
[0124] S912, set the next current time t of the sliding time window, and go to step S904. Set the next current time of the sliding time window, the system waits until the next current time, and repeats steps S904 to S912. Through continuous cycles, the system automatically updates the aggregated load data of the virtual network element, and generates, updates, and maintains the corresponding expansion and contraction strategies, and executes expansion and contraction operations, expanding when the load increases and contracting when the load decreases.
[0125] The process of generating and returning the expansion and contraction strategy of the virtual network element in the current time window is as follows: Fig.10 As shown, including:
[0126] S1002, obtaining the aggregated load data Loadgw(t) and the threshold value in the time window. The calculation method of the aggregated load data is as shown in the above step S908, which will not be repeated here.
[0127] S1004, compare the aggregate load Loadgw(t) with the threshold and select different operations. If the aggregate load Loadgw(t) is greater than the upper threshold THRmax, go to step S1006; if the aggregate load Loadgw(t) is less than the lower threshold THRmin, go to step S1008. Otherwise, return.
[0128] S1006: Generate and return a virtual network element expansion strategy. The expansion strategy includes but is not limited to an expansion identifier, a name, a scheduling strategy, etc., and returns the expansion strategy described by the expansion identifier.
[0129] S1008: Generate and return a virtual network element reduction policy. The reduction policy includes but is not limited to a reduction identifier, a name, etc., and returns the reduction policy described by the reduction identifier.
[0130] like Fig.11 As shown in the figure, the process of scaling up and down the virtual network element includes the following steps:
[0131] S1102, obtaining the capacity expansion and contraction strategy of the virtual network element. The capacity expansion and contraction strategy includes a name, an identifier, and a scheduling strategy. The capacity expansion and contraction strategy of the virtual network element is updated and maintained by the decision module at each current moment of the sliding time window, and is obtained by the execution module and performs capacity expansion and contraction operations on the virtual network element.
[0132] S1104, parse the expansion and contraction strategy and determine the expansion and contraction mark. When the mark is expansion, go to step S1106; when it is contraction, go to step S1108; the execution module parses the expansion and contraction strategy and determines whether expansion or contraction is required. When expansion is required, the expansion operation is performed; when contraction is required, the contraction operation is performed.
[0133] S1106, execute capacity expansion operations, including but not limited to expanding resources and virtual network element instances. The execution module executes capacity expansion operations. According to the capacity expansion strategy, the execution module is responsible for recovering, creating and configuring resource types and virtual network element instances for running virtual network elements. The resource types required to run virtual network elements include but are not limited to virtual machines, containers, virtual machine containers, etc., and their resource models (including vCPU, memory, storage) include but are not limited to models consistent with existing models of virtual network element instances. The execution module selects the target host for creating virtual resources and virtual network elements according to the expansion and contraction strategy.
[0134] Executing capacity expansion operations includes but is not limited to restoring created virtual network element instances, creating and configuring virtual network element instances. Restoring created virtual network elements refers to virtual network elements that were closed during the last capacity reduction but whose hard disk resources were not reclaimed, and the global configuration parameters are retained. The restored virtual network element instances can directly participate in carrying virtual network element services. Creating virtual network element instances includes but is not limited to creating and running virtual network element instances based on images, virtual machine templates, etc. Configuring virtual network element instances requires completing global and local configuration of virtual network elements, including IP addresses, configuring routes, routing policies, etc. The expanded virtual network element instances carry services together with the online virtual network element instances, including the use of reliable mechanisms such as load balancing or master-slave.
[0135] S1108, execute the capacity reduction operation, including but not limited to migrating the load of the virtual network element instance, shutting down the virtual network element instance, and reclaiming resources. Among them, the load of the migrated virtual network element instance refers to the business traffic originally carried by the network element instance to be shrunk being carried by other virtual network element instances that continue to run, including but not limited to exiting the virtual gateway instance group, configuring the diversion strategy, and directly shutting down. After the migration, the virtual network element instance to be shrunk no longer carries business traffic, and you can choose to reclaim or not reclaim the resources occupied by the virtual network element instance to be shrunk. When the resources of the virtual network element instance are reclaimed, new resources and virtual network element instances and configurations need to be recreated the next time the capacity is expanded; when not reclaimed, the hard disk resources and global configuration parameters occupied by the virtual network element instance are retained, and the virtual network element instance can be powered on and restored the next time the capacity is expanded.
[0136] In some embodiments of the present disclosure, the above method steps are all completed by a capacity expansion and contraction device, such as Fig.12 As shown, the expansion and contraction device includes a collection module, a decision module, and an execution module.
[0137] The collection module periodically collects data such as the service load of virtual network elements, including but not limited to the throughput, bandwidth utilization, vCPU utilization, memory utilization and other data of the virtual network elements.
[0138] Decision module: Calculates and generates the aggregate load of virtual network elements at the current moment of each sliding time window, and generates, updates and maintains the expansion and contraction strategy based on the aggregate load. The aggregate load of virtual network elements is generated based on the merge algorithm based on the load data of virtual network elements in the time window at the current moment.
[0139] Execution module: parses the expansion and contraction strategies of virtual network elements and executes expansion and contraction operations, including restoring virtual network element instances, expanding virtual network element instances, running cloud resources of virtual network elements, and shrinking virtual network elements.
[0140] The disclosed embodiments support flexible selection of sliding time windows to more accurately reflect changes in virtual network element loads within a certain period of time and avoid misoperation. Data on virtual network element loads can be judged based on sliding time windows to achieve the effect of "peak shaving and valley flattening" and avoid misjudgment and misoperation caused by sudden loads. It supports scenarios where the load of virtual network elements fluctuates periodically or has no regular fluctuations, and timely performs capacity expansion or reduction to ensure service quality and control resource utilization and energy consumption.
[0141] Based on the same inventive concept, the embodiment of the present disclosure also provides a virtual network element expansion and contraction device, as described in the following embodiment. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.
[0142] Fig.13 A schematic diagram of a virtual network element expansion and contraction device in an embodiment of the present disclosure is shown. Fig.13 As shown, the device comprises:
[0143] The data acquisition module 1301 is used to acquire the aggregated load data of the target virtual network element in the current time window, where the target virtual network element includes at least one virtual network element instance; the current time window is a time period before and immediately adjacent to the current moment, and the aggregated load data is an aggregated result of the service load data of each virtual network element instance in the target virtual network element;
[0144] The expansion and contraction execution module 1302 is used to generate an expansion strategy or a contraction strategy for the target virtual network element at the current moment according to the aggregated load data of the target virtual network element in the current time window. The expansion strategy is to increase the number of virtual network element instances in the target virtual network element or to increase the resources of each virtual network element instance in the target virtual network element. The contraction strategy is to reduce the number of virtual network element instances in the target virtual network element or to reduce the resources of each virtual network element instance in the target virtual network element.
[0145] In some embodiments of the present disclosure, the above-mentioned data acquisition module 1301 is also used to determine the collection period of business load data of each virtual network element instance in the target virtual network element; determine the collection time point according to the collection period; and collect the business load data of each virtual network element instance in the target virtual network element at the collection time point.
[0146] In some embodiments of the present disclosure, the above-mentioned data acquisition module 1301 is also used to obtain the business load data of each virtual network element instance collected by the target virtual network element within the current time window; and obtain aggregated load data based on the business load data of each virtual network element instance collected within the current time window.
[0147] In some embodiments of the present disclosure, the data acquisition module 1301 is further used to calculate the aggregated load from the service load data of each virtual network element instance collected in the current time window using an aggregation algorithm, and the aggregation algorithm includes: arithmetic average algorithm and weighted average algorithm.
[0148] In some embodiments of the present disclosure, the above-mentioned expansion and contraction execution module 1302 is also used to determine the upper threshold and / or lower threshold of the target virtual network element; compare the aggregated load data of the target virtual network element in the current time window with the upper threshold and / or lower threshold, if the aggregated load data is greater than the upper threshold, generate an expansion strategy for the target virtual network element at the current moment, if the aggregated load data is less than the lower threshold, generate a reduction strategy for the target virtual network element at the current moment.
[0149] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above method embodiments. It should be noted that the above modules as part of the device can be executed in a computer system such as a set of computer executable instructions.
[0150] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".
[0151] Refer to the following Fig.14 1400 according to this embodiment of the present disclosure is described. Fig.14 The electronic device 1400 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0152] like Fig.14 As shown, the electronic device 1400 is in the form of a general computing device. The components of the electronic device 1400 may include but are not limited to: at least one processing unit 1410, at least one storage unit 1420, and a bus 1430 connecting different system components (including the storage unit 1420 and the processing unit 1410).
[0153] The storage unit stores a program code, and the program code can be executed by the processing unit 1410, so that the processing unit 1410 executes the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 1410 can execute the following steps of the above method embodiment: obtaining the aggregated load data of the target virtual network element in the current time window, the target virtual network element includes at least one virtual network element instance; the current time window is a time period before the current moment and immediately adjacent to the current moment, and the aggregated load data is the aggregated result of the service load data of each virtual network element instance in the target virtual network element; according to the aggregated load data of the target virtual network element in the current time window, generating an expansion strategy or a reduction strategy of the target virtual network element at the current moment, the expansion strategy is to increase the number of virtual network element instances in the target virtual network element or increase the resources of each virtual network element instance in the target virtual network element, and the reduction strategy is to reduce the number of virtual network element instances in the target virtual network element or reduce the resources of each virtual network element instance in the target virtual network element.
[0154] The storage unit 1420 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 14201 and / or a cache storage unit 14202 , and may further include a read-only storage unit (ROM) 14203 .
[0155] The storage unit 1420 may also include a program / utility 14204 having a set (at least one) of program modules 14205, such program modules 14205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
[0156] Bus 1430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
[0157] The electronic device 1400 may also communicate with one or more external devices 1440 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1400, and / or communicate with any device that enables the electronic device 1400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1450. Furthermore, the electronic device 1400 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 1460. As shown, the network adapter 1460 communicates with other modules of the electronic device 1400 via a bus 1430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0158] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.
[0159] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer program product, which includes: a computer program, which implements the method in the above embodiment when executed by a processor.
[0160] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.
[0161] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0162] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0163] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.
[0164] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).
[0165] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.
[0166] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.
[0167] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.
[0168] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.
Claims
1. A method for expanding and contracting a virtual network element, characterized in that: include: Acquire aggregated load data of a target virtual network element within a current time window, wherein the target virtual network element includes at least one virtual network element instance; the current time window is a time period before a current moment and immediately adjacent to the current moment; the aggregated load data is an aggregated result of service load data of each virtual network element instance in the target virtual network element; Based on the aggregated load data of the target virtual network element in the current time window, an expansion strategy or a reduction strategy of the target virtual network element at the current moment is generated, wherein the expansion strategy is to increase the number of virtual network element instances in the target virtual network element or to increase the resources of each virtual network element instance in the target virtual network element, and the reduction strategy is to reduce the number of virtual network element instances in the target virtual network element or to reduce the resources of each virtual network element instance in the target virtual network element.
2. The method for expanding and contracting a virtual network element according to claim 1, characterized in that: The current time window includes a sliding time window.
3. The method for expanding and contracting virtual network elements according to claim 1, characterized in that: Before obtaining the aggregated load data of the target virtual network element in the current time window, the method further includes: Determining a collection period for service load data of each virtual network element instance in the target virtual network element; Determine a collection time point according to the collection cycle; The business load data of each virtual network element instance in the target virtual network element at the collection time point is collected.
4. The method for expanding and contracting virtual network elements according to claim 3, characterized in that: Before obtaining the aggregated load data of the target virtual network element in the current time window, the method further includes: Obtaining service load data of each virtual network element instance collected by the target virtual network element within the current time window; Aggregate load data is obtained according to the service load data of each virtual network element instance collected in the current time window.
5. The method for expanding and contracting virtual network elements according to claim 4, characterized in that: The aggregated load data is obtained according to the business load data of each virtual network element instance collected in the current time window, including: using an aggregation algorithm to calculate the aggregated load from the business load data of each virtual network element instance collected in the current time window, and the aggregation algorithm includes: an arithmetic average algorithm and a weighted average algorithm.
6. The method for expanding and contracting virtual network elements according to claim 1, characterized in that: Generating a capacity expansion strategy or a capacity reduction strategy of the target virtual network element at a current moment according to the aggregated load data of the target virtual network element in a current time window, including: Determining an upper threshold and / or a lower threshold of the target virtual network element; Compare the aggregate load data of the target virtual network element in the current time window with the upper threshold and / or the lower threshold. If the aggregate load data is greater than the upper threshold, generate a capacity expansion strategy for the target virtual network element at the current moment. If the aggregate load data is less than the lower threshold, generate a capacity reduction strategy for the target virtual network element at the current moment.
7. The method for expanding and contracting virtual network elements according to claim 1, characterized in that: The capacity expansion strategy includes one or more of the following: restoring the created virtual network element instance, creating and configuring the virtual network element instance; the capacity reduction strategy includes one or more of the following: migrating the load of the virtual network element instance, shutting down the virtual network element instance, and recovering resources.
8. A virtual network element expansion and contraction device, characterized in that: include: A data acquisition module, used to acquire aggregated load data of a target virtual network element within a current time window, wherein the target virtual network element includes at least one virtual network element instance; the current time window is a time period before and immediately adjacent to a current moment, and the aggregated load data is an aggregated result of service load data of each virtual network element instance in the target virtual network element; The expansion and contraction execution module is used to generate an expansion strategy or a contraction strategy for the target virtual network element at the current moment according to the aggregated load data of the target virtual network element in the current time window. The expansion strategy is to increase the number of virtual network element instances in the target virtual network element or to increase the resources of each virtual network element instance in the target virtual network element. The contraction strategy is to reduce the number of virtual network element instances in the target virtual network element or to reduce the resources of each virtual network element instance in the target virtual network element.
9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the method for scaling up and down a virtual network element as described in any one of claims 1 to 7 by executing the executable instructions.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for scaling up and down a virtual network element as claimed in any one of claims 1 to 7 is implemented.
11. A computer program product comprising: A computer program or instruction, characterized in that when the computer program or instruction is executed by a processor, it implements the method for scaling up and down a virtual network element as described in any one of claims 1 to 7.
Citation Information
Cited By
Dynamic resource scheduling method and device under NFV architecture, electronic equipment and storage medium
CN121334085A
