CN113535399A

CN113535399A - NFV resource scheduling method, device and system

Info

Publication number: CN113535399A
Application number: CN202110800472.5A
Authority: CN
Inventors: 吴立军; 李志圆
Original assignee: University of Electronic Science and Technology of China
Current assignee: University of Electronic Science and Technology of China
Priority date: 2021-07-15
Filing date: 2021-07-15
Publication date: 2021-10-22
Anticipated expiration: 2041-07-15
Also published as: CN113535399B

Abstract

The application discloses a method, a device and a system for NFV resource scheduling. The NFV resource scheduling method acquires original request data and dynamic network topology information; acquiring service request characteristics according to original request data; acquiring topological characteristics according to the dynamic network topological information; fusing the service request features and the topology features to form fused features; acquiring a trained resource allocation scheduling model; and inputting the fusion characteristics into a resource allocation scheduling model so as to obtain scheduling processing action information. The NFV resource scheduling method has the following advantages: in the problem of NFV resource allocation, the three sub-problems are solved by a coordinated scheme for the first time, and a new idea is provided for research of NFV-RA problems. In the NFV-RA problem, a graph convolutional neural network is used for the first time, improvement is carried out, feature extraction is carried out on the node and the link state at the same time, and topology change is effectively sensed.

Description

NFV resource scheduling method, device and system

Technical Field

The present application relates to the technical field of network function virtualization, and in particular, to an NFV resource scheduling method, an NFV resource scheduling apparatus, and an NFV resource scheduling system.

Background

Network Function Virtualization (NFV) software network functions via virtualization technology, separate from proprietary hardware devices, and can run on standard server virtualization software. Thanks to the flexibility of NFV, network operators can save a lot of costs while improving the network resource utilization. However, one important challenge to exploit the potential of NFV more deeply is the network resource allocation problem in NFV (NFV-RA).

NFV-RA may be classified as a VNFs chain component (VNFs-CC); VNF forwarding graph embedding (VNF-FGE); VNFs scheduling (VNFs-SCH) three phases. Designing a resource allocation algorithm for effectively and coordinately solving the three stages is the key for solving the NFV-RA problem. However, most current solutions only address a single phase, or solve the problem of more than one phase in a non-coordinated way, and do not consider the online arrival pattern of the service.

Accordingly, a technical solution is desired to overcome or at least alleviate at least one of the above-mentioned drawbacks of the prior art.

Disclosure of Invention

It is an object of the present invention to provide an NFV resource scheduling method to overcome or at least mitigate at least one of the above-mentioned drawbacks of the prior art.

One aspect of the present invention provides an NFV resource scheduling method, where the NFV resource scheduling method includes:

acquiring original request data and dynamic network topology information;

acquiring service request characteristics according to the original request data;

acquiring topological characteristics according to the dynamic network topological information;

fusing the service request feature and the topology feature to form a fused feature;

acquiring a trained resource allocation scheduling model;

and inputting the fusion characteristics into the resource allocation scheduling model so as to obtain scheduling processing action information.

Optionally, the obtaining the service request feature according to the original request data includes:

and acquiring the service request characteristics in the original request data through a multi-head self-attention mechanism.

Optionally, the obtaining of the topology characteristics according to the dynamic network topology information includes:

and acquiring topological features in the dynamic network topological information through the double-component graph convolutional neural network.

Optionally, after the inputting the fusion feature to the resource allocation scheduling model to obtain scheduling processing action information, the NFV resource scheduling method further includes:

and controlling the NFV resources to schedule the NFV environment according to the scheduling processing action information and acquiring evaluation information returned by the NFV environment after the scheduling processing action information is used for scheduling.

Optionally, the evaluation information includes an evaluation of the scheduling processing action information and index information.

Optionally, after obtaining evaluation information returned by the NFV environment after scheduling through the scheduling processing action information, the NFV resource scheduling method further includes:

and adjusting parameters in the resource allocation scheduling model according to the acquired evaluation information.

The present application further provides an NFV resource scheduling apparatus, including:

the system comprises an original request data acquisition module, a data processing module and a data processing module, wherein the original request data acquisition module is used for acquiring original request data;

the dynamic network topology information acquisition module is used for acquiring dynamic network topology information;

a service request characteristic obtaining module, configured to obtain a service request characteristic according to the original request data;

the topological characteristic acquisition module is used for acquiring topological characteristics according to the dynamic network topological information;

a fusion module for fusing the service request feature and the topology feature to form a fused feature;

the model acquisition module is used for acquiring a trained resource allocation scheduling model;

a model computation module for inputting the fusion characteristics to the resource allocation scheduling model to obtain scheduling processing action information.

The application also provides an NFV resource scheduling system, which comprises a plurality of NFV resource scheduling devices.

The present application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the NFV resource scheduling method as described above when executing the computer program.

The present application also provides a computer-readable storage medium storing a computer program, which when executed by a processor can implement the NFV resource scheduling method as described above.

Has the advantages that:

the NFV resource scheduling method has the following advantages:

1. in the problem of NFV resource allocation, the three sub-problems are solved by a coordinated scheme for the first time, and a new idea is provided for research of NFV-RA problems.

2. In the NFV-RA problem, a graph convolutional neural network is used for the first time, improvement is carried out, feature extraction is carried out on the node and the link state at the same time, and topology change is effectively sensed.

3. And a new reinforcement learning training algorithm is proposed for the NFV-RA problem and the inadaptability of the traditional deep reinforcement learning to the problem.

4. In the NFV-RA problem, a multi-NFV resource scheduling apparatus is used for the first time to perform online processing.

5. In the NFV-RA problem, a self-attention mechanism is used for the first time, a position code is added, and feature extraction is performed on a service request.

6. The NFV resource scheduling device adopts end-to-end training, and is convenient to deploy and debug.

Drawings

Fig. 1 is a flowchart illustrating an NFV resource scheduling method according to an embodiment of the present application.

Fig. 2 is an electronic device for implementing the NFV resource scheduling method shown in fig. 1.

Detailed Description

In order to make the implementation objects, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the drawings in the embodiments of the present application. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are a subset of the embodiments in the present application and not all embodiments in the present application. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application. Embodiments of the present application will be described in detail below with reference to the accompanying drawings.

It should be noted that the terms "first" and "second" in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

The NFV resource scheduling method shown in fig. 1 includes:

step 1, acquiring original request data and dynamic network topology information;

step 2, acquiring service request characteristics according to original request data;

step 3, acquiring topological characteristics according to the dynamic network topological information;

step 4, fusing the service request characteristics and the topology characteristics to form fused characteristics;

step 5, acquiring a trained resource allocation scheduling model;

and 6, inputting the fusion characteristics into a resource allocation scheduling model so as to obtain scheduling processing action information.

The NFV resource scheduling method has the following advantages:

1 in the problem of NFV resource allocation, the three sub-problems are solved by a coordinated scheme for the first time, and a new idea is provided for the research of the NFV-RA problem. In particular, the coordinated approach attempts to perform multiple phases as a whole in one step. The techniques in the past have employed non-coordinated approaches to solve one or both sub-problems. The non-coordinated way is to solve each problem in sequence, but does not consider the dependency relation among each problem, and the dependency relation, namely the output of one stage is the input of the next stage. The NFV resource allocation problem can be seen as a mapping: and mapping the directed graph representing the service request into an undirected graph representing the physical network, and performing scheduling execution. Therefore, after the obtained features are fused, the obtained action information is a subgraph of a physical network, wherein the subgraph comprises node information and link information. Thus we solve three sub-problems in a single step, i.e. in a coordinated way.

In this embodiment, obtaining the service request feature according to the original request data includes: and acquiring the service request characteristics in the original request data through a multi-head self-attention mechanism.

Specifically, the original request data is subjected to feature extraction by using a self-attention mechanism, and service request features of the original request data are fully mined. In NFV, service requests usually come in the form of Service Function Chains (SFC), where there is a dependency relationship between VNFs, and in order to link VNFs in different locations to compute a representation of a service request, the present algorithm introduces a location code in the self-attention mechanism. Meanwhile, in order to extract information of different representation subspaces, the method uses multi-head self-attention, projects the original request to different dimensions by using different linear mappings, respectively performs self-attention calculation, and finally performs multi-head series connection, thereby obtaining the final service request characteristic.

In the present embodiment, in natural language processing NLP, each word of an input character string is changed into a vector using the embedding algorithm. However, the present application is directed to NFV, and service requests in NFV have non-negligible characteristics, such as the number of modules, type, QoS requirement, time of arrival, requested data rate, etc., and besides encoding the service request, the present application also incorporates the above characteristics of the number of modules, type, QoS requirement, time of arrival, requested data rate, etc. as the input of the self-attention mechanism; in addition, in the present embodiment, position coding is introduced in the self-attention mechanism. In NLP, the position code represents the word order in the input sequence, however, the service request is not only simple order relation, but also parallel and segmentation modules exist, therefore, the position of the parallel and segmentation modules is specially coded on the basis of the position code.

In this embodiment, acquiring the topology characteristics according to the dynamic network topology information includes: and acquiring topological features in the dynamic network topological information through the double-component graph convolutional neural network.

Specifically, dynamic topological feature extraction is carried out, double-component graph convolution is introduced to explicitly model the correlation of nodes and links, and automatic feature extraction is carried out on the network topology of a non-Euclidean domain.

In this embodiment, after inputting the fusion feature to the resource allocation scheduling model to obtain scheduling processing action information, the NFV resource scheduling method further includes:

In this embodiment, the evaluation information includes two types: 1. because the scheduling processing action information is composed of a generation countermeasure network, the action generated by the generator is not necessarily a real physical network, and therefore a discriminator is needed to judge whether the action is a real physical network, so as to give first evaluation information; 2. in order to determine the quality of the generated action, an evaluation message is required for guidance. This assessment information is called Reward (Reward) in reinforcement learning and is returned after the execution of an action by the environment. The reward in the present invention is designed with the goals and constraints of the mathematical problem formalized by NFV resource allocation.

In the present embodiment, the evaluation information includes evaluation of scheduling processing operation information and index information.

In this embodiment, after obtaining evaluation information returned by the NFV environment after scheduling by the scheduling processing action information, the NFV resource scheduling method further includes:

In this embodiment, the resource allocation scheduling model is a generative countermeasure model composed of a generator and a discriminator, and the topology characteristics and the service request characteristics are input, and the real network sub-topology is used as a sample, and the input is used to generate the sub-topology. In particular, the generator takes samples from the prior distribution (i.e. the real network sub-topology) and generates a topology G with node and link information representing the topology. The node and edge of G respectively represent the node in which the VNF is to be embedded and the instance information and link bearer information in the node and traffic information. The discriminator extracts two samples from the data set and the generator and learns how to distinguish them. The generators and discriminators are trained using the modified WGAN, learning the generators to match the experience distribution, and finally outputting the effective topology.

In this embodiment, the multi-head self-attention mechanism, the dual-component graph convolutional neural network, and the resource allocation scheduling model form a single agent. According to the method, the multiple intelligent agents are adopted, and the number of the specific intelligent agents is determined by the probability distribution of service request arrival, so that zero-waiting processing can be basically guaranteed after the service request arrives. The use of multiple agents may allow for reduced latency of requests.

Because the model is unstable in early training and not easy to converge, the early training can be accelerated by using the data obtained by solving the simplified model by a solver, and therefore, a better strategy can be converged quickly by adopting a model assistance and simulation learning mode.

At the same time, it is considered that the intelligence will typically be slow to obtain experience from the environment, and the intelligence must wait for the environment to perform an operation before the training step. Second, the state and motion pairs in one trajectory are highly correlated, reducing the robustness and efficiency of the training process. We inspired by A3C to use parallel training to speed up the training process while enhancing its robustness. We use multiple worker agents to collect experiences from their own environment separately and send them to a central agent that is responsible for training and updating network parameters. For example, if parallel training is used in the single agent described above, the single agent acts as a central master agent, and then the agent is replicated several times as multiple worker agents; the same applies to the multi-agent, and the central master agent is the multi-agent.

The present application is described in further detail below by way of examples, it being understood that the examples do not constitute any limitation to the present application.

In the NFV resource scheduling method provided in this embodiment, a Dell Precision T7920 tower workstation is selected as a hardware platform, and is programmed using Python language.

Firstly, the resource scheduling system initializes the relevant interface, and starts the processing flow of the request after receiving the service request arriving in real time.

A service request parsing function request _ parser () extracts original request data from the DDR3 mounted under the workstation;

obtaining each sub-module in the analyzed request, and extracting the dependency relationship between the original features and each sub-module by using an initial feature extraction function init _ feature ();

then, the characteristic and the dependency relationship are used as the input of a self _ attribute () function to obtain the extracted characteristic of the service request, namely the service request characteristic;

meanwhile, performing feature extraction on the dynamic network topology by using a dual-component graph convolutional neural network to obtain topological features;

and fusing the obtained topological characteristic and the service request characteristic to be used as the input of a resource allocation scheduling model, and obtaining scheduling processing action information aiming at the request and considering the network state.

After the NFV environment processes the generated scheduling processing action information, the evaluation of the action and various indexes (such as success or failure, delay and the like) are returned, and the resource allocation scheduling model adjusts the neural network parameters according to the returned values. In particular, the parameters are adjusted according to the multi-agent reinforcement learning MADDPG algorithm.

The application also provides an NFV resource scheduling device, which comprises an original request data acquisition module, a dynamic network topology information acquisition module, a service request feature acquisition module, a topology feature acquisition module, a fusion module, a model acquisition module and a model calculation module, wherein the original request data acquisition module is used for acquiring original request data; the dynamic network topology information acquisition module is used for acquiring dynamic network topology information; the service request characteristic acquisition module is used for acquiring service request characteristics according to original request data; the topological characteristic acquisition module is used for acquiring topological characteristics according to the dynamic network topological information; the fusion module is used for fusing the service request features and the topological features to form fusion features; the model acquisition module is used for acquiring the trained resource allocation scheduling model; and the model calculation module is used for inputting the fusion characteristics to the resource allocation scheduling model so as to acquire scheduling processing action information.

The present application further provides an NFV resource scheduling system, where the NFV resource scheduling system includes a plurality of the NFV resource scheduling devices, and each NFV resource scheduling device is configured to implement the NFV resource scheduling method.

Similarly, when the NFV resource scheduling system of the present application is used, the NFV resource scheduling apparatuses cooperate with each other in addition to processing their respective requests, and increase the acceptance rate of request processing in consideration of their actions.

The above description of the method is equally applicable to the description of the apparatus and system.

Fig. 2 is an exemplary structural diagram of an electronic device capable of implementing the NFV resource scheduling method provided in an embodiment of the present application.

As shown in fig. 2, the electronic device includes an input device 501, an input interface 502, a central processor 503, a memory 504, an output interface 505, and an output device 506. The input interface 502, the central processing unit 503, the memory 504 and the output interface 505 are connected to each other through a bus 507, and the input device 501 and the output device 506 are connected to the bus 507 through the input interface 502 and the output interface 505, respectively, and further connected to other components of the electronic device. Specifically, the input device 501 receives input information from the outside and transmits the input information to the central processor 503 through the input interface 502; the central processor 503 processes input information based on computer-executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; the output device 506 outputs the output information to the outside of the electronic device for use by the user.

That is, the electronic device shown in fig. 2 may also be implemented to include: a memory storing computer-executable instructions; and one or more processors that when executing computer executable instructions may implement the NFV resource scheduling method described in connection with fig. 1.

In one embodiment, the electronic device shown in fig. 2 may be implemented to include: a memory 504 configured to store executable program code; one or more processors 503 configured to execute executable program code stored in the memory 504 to perform the NFV resource scheduling method in the above embodiments.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media include both non-transitory and non-transitory, removable and non-removable media that implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Furthermore, it will be obvious that the term "comprising" does not exclude other elements or steps. A plurality of units, modules or devices recited in the device claims may also be implemented by one unit or overall device by software or hardware. The terms first, second, etc. are used to identify names, but not any particular order.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks identified in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The Processor in this embodiment may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, and so on. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the apparatus/terminal device by running or executing the computer programs and/or modules stored in the memory, as well as by invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.

In this embodiment, the module/unit integrated with the apparatus/terminal device may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by hardware related to instructions of a computer program, which may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like.

It should be noted that the computer readable medium may contain content that is appropriately increased or decreased as required by legislation and patent practice in the jurisdiction. Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application.

Although the invention has been described in detail hereinabove with respect to a general description and specific embodiments thereof, it will be apparent to those skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.

Claims

1. An NFV resource scheduling method, the NFV resource scheduling method comprising:

acquiring original request data and dynamic network topology information;

acquiring a trained resource allocation scheduling model;

2. The NFV resource scheduling method of claim 1, wherein the obtaining the service request feature according to the original request data comprises:

3. The NFV resource scheduling method of claim 2, wherein the obtaining the topology characteristics according to the dynamic network topology information comprises:

4. The NFV resource scheduling method of claim 3, wherein after the inputting the fused feature to the resource allocation scheduling model to obtain scheduling processing action information, the NFV resource scheduling method further comprises:

5. The NFV resource scheduling method of claim 4, wherein the evaluation information comprises an evaluation of the scheduling processing action information and index information.

6. The NFV resource scheduling method according to claim 5, wherein after obtaining the evaluation information returned by the NFV environment after being scheduled by the scheduling processing action information, the NFV resource scheduling method further comprises:

7. An NFV resource scheduling apparatus, the NFV resource scheduling apparatus comprising:

8. An NFV resource scheduling system, comprising a plurality of NFV resource scheduling devices.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the NFV resource scheduling method of any of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, storing a computer program, the computer program, when being executed by a processor, being capable of implementing the NFV resource scheduling method according to any one of claims 1 to 6.