CN118070850B - Data center network traffic generation method, device, medium and computer program - Google Patents
Data center network traffic generation method, device, medium and computer program Download PDFInfo
- Publication number
- CN118070850B CN118070850B CN202410466658.5A CN202410466658A CN118070850B CN 118070850 B CN118070850 B CN 118070850B CN 202410466658 A CN202410466658 A CN 202410466658A CN 118070850 B CN118070850 B CN 118070850B
- Authority
- CN
- China
- Prior art keywords
- rule
- network traffic
- generation rule
- vector
- generation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004590 computer program Methods 0.000 title claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 58
- 239000011159 matrix material Substances 0.000 claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 5
- 239000013598 vector Substances 0.000 claims description 51
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000003491 array Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a data center network flow generation method, a device, a medium and a computer program, wherein the method comprises the following steps: acquiring a training data set, and training a generator model by using the training data set, wherein the generator model is used for generating a similarity matrix of each generation rule and corresponding network traffic; and inputting the target generation rule into a trained generator model, outputting a similarity matrix of the target generation rule by the generator model, and generating network traffic corresponding to the target generation rule by using the similarity matrix of the target generation rule. Therefore, the problems that in the related technology, by configuring the generation rule on the network equipment and collecting the traffic conforming to the rule, the rule is only applicable to users who can issue the rule and can operate network equipment such as a switch, and the rule needs to be redeployed and collected each time the traffic is acquired are solved, and the operation is complex and the applicability is low are solved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a medium, and a computer program for generating network traffic of a data center.
Background
With the rapid development of technologies such as cloud computing, big data analysis and artificial intelligence, a data center plays a vital role in modern society, and not only flexible computing and storage resources are provided for enterprises, but also support is provided for development of innovative application programs and services. While the size and complexity of data centers is also continually increasing to meet the ever-increasing data demands and technical challenges.
Network traffic is often used to assist in completing various tasks such as network monitoring, and some rules to be adhered to are set according to the application or user requirements, and the network traffic generation method, whether based on a mathematical statistics method or a deep learning method, can only acquire the characteristics of traffic from the existing traffic and generate traffic conforming to the characteristics according to the characteristics. Essentially, network messages are generated from network messages.
In real scenes, however, users often expect to acquire traffic with certain characteristics. For example, the user may wish to detect a packet sent by a particular server (e.g., a particular ip), or the user may only be interested in a particular protocol (e.g., UDP (User Datagram Protocol, user datagram protocol)), etc. Configuring ACL (access control list ) rules on a network device and collecting traffic that meets the rules is a common method in the related art. However, this method is only suitable for users who can issue rules and can operate network devices such as switches to collect traffic, which often means that users need to have managers of network clusters, and in order to cope with complex and changeable traffic demands, users need to confirm ACL rules corresponding to the required traffic, and then deploy and collect the ACL rules in an actual network environment.
Disclosure of Invention
The invention provides a data center network flow generation method, a device, electronic equipment, a medium and a computer program, which are used for solving the problems that in the related art, by configuring ACL rules on network equipment and collecting flows conforming to the rules, the method is only suitable for users who can issue the rules and can operate network equipment such as a switch, and the rules are required to be redeployed and collected each time the flows are acquired, and the problems of complex operation, low applicability and the like exist.
An embodiment of a first aspect of the present invention provides a method for generating network traffic, including the following steps: acquiring a training data set, wherein the training data set comprises a plurality of generation rules and network traffic corresponding to each generation rule; training a generator model by using the training data set, wherein the generator model is used for generating a similarity matrix of each generation rule and corresponding network traffic; and inputting the target generation rule into a trained generator model, outputting a similarity matrix of the target generation rule by the generator model, and generating network traffic corresponding to the target generation rule by using the similarity matrix of the target generation rule.
Optionally, in one embodiment of the present invention, training the generator model with the training data set includes: converting a plurality of generation rules to obtain a rule vector set, and encoding network traffic corresponding to each generation rule to obtain a traffic vector set; associating a rule vector corresponding to each generation rule with network traffic corresponding to each generation rule to obtain a plurality of rule-traffic pairs; training the generator model using the plurality of rule-flow pairs until a preset condition is met.
Optionally, in one embodiment of the present invention, generating network traffic corresponding to the target generation rule using the similarity matrix of the target generation rule includes: encoding the target generation rule into a first vector; determining a second vector from the first vector and the similarity matrix; and decoding the second vector to obtain the network flow corresponding to the target generation rule.
Optionally, in one embodiment of the present invention, each generation rule and the format of the network traffic corresponding to each generation rule are the same in the high-dimensional space.
An embodiment of a second aspect of the present invention provides a data center network traffic generating device, including: the acquisition module is used for acquiring a training data set, wherein the training data set comprises a plurality of generation rules and network traffic corresponding to each generation rule; the training module is used for training a generator model by utilizing the training data set, wherein the generator model is used for generating a similarity matrix of each generation rule and corresponding network traffic; the generating module is used for inputting the target generating rule into the trained generator model, outputting a similarity matrix of the target generating rule by the generator model, and generating the network traffic corresponding to the target generating rule by using the similarity matrix of the target generating rule.
Optionally, in one embodiment of the present invention, the training module is further configured to: converting a plurality of generation rules to obtain a rule vector set, and encoding network traffic corresponding to each generation rule to obtain a traffic vector set; associating a rule vector corresponding to each generation rule with network traffic corresponding to each generation rule to obtain a plurality of rule-traffic pairs; training the generator model using the plurality of rule-flow pairs until a preset condition is met.
Optionally, in one embodiment of the present invention, the generating module is further configured to: encoding the target generation rule into a first vector; determining a second vector from the first vector and the similarity matrix; and decoding the second vector to obtain the network flow corresponding to the target generation rule.
Optionally, in one embodiment of the present invention, each generation rule and the format of the network traffic corresponding to each generation rule are the same in the high-dimensional space.
An embodiment of a third aspect of the present invention provides an electronic device, including: the data center network traffic generation method of the above embodiment is implemented by a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the program.
An embodiment of a fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program that is executed by a processor for implementing the data center network traffic generation method of the above-described embodiment.
An embodiment of a fifth aspect of the present invention provides a computer program, which when executed, is configured to implement the data center network traffic generation method of the above embodiment.
Therefore, the invention has at least the following beneficial effects:
According to the embodiment of the invention, the flow rules are associated with corresponding flows through training the generator model, the association is stored through the similarity matrix, the target generation rules are input into the trained generator model after training is completed, the generator model outputs the similarity matrix of the target generation rules, the network flow corresponding to the target generation rules can be generated by utilizing the similarity matrix, and a user does not have the management authority of the network cluster and can acquire complex and diverse network flows. Therefore, the problems that in the related technology, by configuring the generation rule on the network equipment and collecting the traffic conforming to the rule, the rule is only applicable to users who can issue the rule and can operate network equipment such as a switch, and the rule needs to be redeployed and collected each time the traffic is acquired are solved, and the operation is complex and the applicability is low are solved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flowchart of a data center network traffic generation method according to an embodiment of the present invention;
FIG. 2 is a pre-training model of rule-flow pairs provided in accordance with one embodiment of the present invention;
FIG. 3 is a block diagram of a traffic and rule encoder provided in accordance with one embodiment of the present invention;
fig. 4 is an exemplary diagram of a data center network traffic generation apparatus provided according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The following describes a data center network traffic generation method, apparatus, electronic device, storage medium, and computer program according to an embodiment of the present invention with reference to the accompanying drawings. In order to solve the problems mentioned in the background art, the invention provides a network traffic generation method, in the method, a generator model is trained, traffic rules are associated with corresponding traffic, the association is stored through a similarity matrix, a target generation rule is input into the trained generator model after training is completed, the generator model outputs the similarity matrix of the target generation rule, network traffic corresponding to the target generation rule can be generated by utilizing the similarity matrix, a user does not have management authority of a network cluster, and complex and various network traffic can be acquired. Therefore, the problems that in the related technology, by configuring the generation rule on the network equipment and collecting the traffic conforming to the rule, the rule is only applicable to users who can issue the rule and can operate network equipment such as a switch, and the rule needs to be redeployed and collected each time the traffic is acquired are solved, and the operation is complex and the applicability is low are solved.
Specifically, fig. 1 is a schematic flow chart of a data center network traffic generation method according to an embodiment of the present invention.
As shown in fig. 1, the data center network traffic generation method includes the following steps:
In step S101, a training data set is acquired.
The training data set includes a plurality of generation rules and network traffic corresponding to each generation rule, and in the embodiment of the present invention, the plurality of rules may be defined rules according to a writing format of ACL rules, and each rule corresponds to a corresponding network traffic, for example: wide area network traffic and data center traffic with application information, internet of things device traffic, traffic including network attacks, and the like. In the actual implementation process, the embodiment of the invention can process the original pcap data by using specific network traffic rules and generate the network traffic conforming to the rules.
In step S102, a generator model is trained using the training data set, wherein the generator model is used to generate a similarity matrix for each generation rule and corresponding network traffic.
It can be appreciated that the embodiment of the invention can be used for associating the flow rule with the corresponding flow through a generator training model and storing the association of the flow rule with the corresponding flow through a similarity matrix. Wherein, each generation rule and the format of the network traffic corresponding to each generation rule in the high-dimensional space are the same.
In one embodiment of the invention, training a generator model with a training data set includes: converting a plurality of generation rules to obtain a rule vector set, and encoding network traffic corresponding to each generation rule to obtain a traffic vector set; associating a rule vector corresponding to each generation rule with network traffic corresponding to each generation rule to obtain a plurality of rule-traffic pairs; training the generator model using the plurality of rule-flow pairs until a preset condition is met.
The network traffic generation method of the network traffic generation rule according to the embodiment of the present invention may be structurally divided into two blocks: a traffic and rule encoder module, and a rule-traffic pair model, wherein the traffic and rule encoder module is configured to vectorize network traffic generation rules (ACL rules) and network traffic and to create a unified format in a high-dimensional space; rule-traffic pair modules use CLIP (Contrastive Language-Image Pre-training, a Pre-trained model of contrast text-Image pairs) to establish the association of ACL rules with data sequence packet vectors, the model itself being an nxn matrix, as shown in fig. 2.
Specifically, the traffic and rules encoder module structure of the present embodiment is a common linear layer as a word segmentation device, and an encoder. As shown in fig. 3, the rules and traffic are each generated using a respective linear layer segmenter and transducer encoder. Two transformers-based encoders have 63M parameters, and rules and traffic after word segmentation and conversion respectively generate sets of rule vectorsAnd a set of flow vectorsAnd map them to the same subspace, wherein N can be set by those skilled in the art according to practical situations, such as 256, without specific limitation.
Further, the embodiment of the invention can correlate the rule vector corresponding to each generation rule with the network flow corresponding to each generation rule to obtain a plurality of rule-flow pairs, train the generator model by utilizing the plurality of rule-flow pairs until the preset condition is met, stop training, input the plurality of encoded rule-flow pairs into the similarity matrix, and continuously update the matrix parameters. Wherein the preset condition can be thatAnd/>The cosine similarity of (c) reaches a minimum.
For example, in using an open source traffic data set training model, embodiments of the present invention may link the traffic set after removing TCP ((Transmission Control Protocol, transmission control protocol) traffic with ACL rules meaning "Deny TCP". First, traffic and ACL rules go through respective segmenters, the words are segmented according to the occurrence frequencies of the respective fields, multiple common fields in the ACL rules may be trained to be intermediate representations that can be represented using fewer words (training process of the segmenters). After that the intermediate representations will enter the encoder to generateOr/>Vector. Finally, since the flow and the rule are input into the generator model in pairs, the/> can be found in the similarity matrixAnd/>Cosine similarity between the features of each dimension of the two. With the input of multiple rounds of rule-flow pairs, this cosine similarity matrix finds the lowest total deviation value over all training sets.
In step S103, the target generation rule is input into the trained generator model, the generator model outputs a similarity matrix of the target generation rule, and the network traffic corresponding to the target generation rule is generated by using the similarity matrix of the target generation rule.
Unlike the existing traffic generation method, which has the key point of learning the characteristics of the input traffic and outputting the network traffic with similar characteristics, the embodiment of the invention can directly train the relevance between the rule and the traffic under the constraint of the rule. Since the rule is a description that resembles natural language, and the network traffic is a sequence of numbers that satisfy the protocol format. Therefore, the embodiment of the invention can form the unification of the formats in the high-dimensional space after the two are segmented and coded respectively, and save the association of the two by using the similarity matrix. When the user wants to output the network traffic under the constraint of the target rule, the user only needs to input the target generation rule into the trained generator model, and the network traffic corresponding to the target generation rule can be output.
In the actual execution process, the embodiment of the invention can collect ACL rules and corresponding traffic in the network environment, respectively substitute the ACL rules and the corresponding traffic into the encoders of the rules and the traffic, train the similarity matrix which is more in line with the scene of the traffic, and give the ACL rules in the subsequent use, thereby generating the traffic corresponding to the ACL rules.
As another possible implementation manner, the embodiment of the present invention may use a traffic super-resolution model to generate a data packet sequence, where a user converts constraint conditions of a data packet into ACL rules and inputs the ACL rules into a generator model, so as to obtain corresponding network traffic. Wherein, the tree super-resolution model is a tree model composed of individual GTT models.
In one embodiment of the present invention, generating network traffic corresponding to a target generation rule using a similarity matrix of the target generation rule includes: encoding the target generation rule into a first vector; determining a second vector from the first vector and the similarity matrix; and decoding the second vector to obtain the network flow corresponding to the target generation rule.
It can be understood that, in the embodiment of the invention, the encoder is used for encoding the target generation rule into the first vector, the similarity matrix is used for converting the first vector into the second vector to represent, and the decoder is used for decoding the second vector to obtain the network traffic corresponding to the target generation rule.
According to the data center network flow generation method provided by the embodiment of the invention, the flow rules are associated with the corresponding flows through training the generator model, the association is stored through the similarity matrix, the target generation rules are input into the trained generator model after training is completed, the generator model outputs the similarity matrix of the target generation rules, the network flow corresponding to the target generation rules can be generated by utilizing the similarity matrix, and a user does not have the management authority of the network cluster and can acquire complex and diverse network flows. Therefore, the problems that in the related technology, by configuring the generation rule on the network equipment and collecting the traffic conforming to the rule, the rule is only applicable to users who can issue the rule and can operate network equipment such as a switch, and the rule needs to be redeployed and collected each time the traffic is acquired are solved, and the operation is complex and the applicability is low are solved.
The data center network traffic generating device according to the embodiment of the present invention will be described next with reference to the accompanying drawings.
Fig. 4 is a block schematic diagram of a data center network traffic generating device 10 according to an embodiment of the present invention.
As shown in fig. 4, the data center network traffic generation apparatus 10 includes: an acquisition module 100, a training module 200, and a generation module 300.
The acquiring module 100 is configured to acquire a training data set, where the training data set includes a plurality of generation rules and network traffic corresponding to each generation rule; the training module 200 is configured to train a generator model using the training data set, where the generator model is configured to generate a similarity matrix of each generation rule and the corresponding network traffic; the generating module 300 is configured to input the target generating rule into a trained generator model, and the generator model outputs a similarity matrix of the target generating rule, and generates the network traffic corresponding to the target generating rule by using the similarity matrix of the target generating rule.
In one embodiment of the present invention, training module 200 is further configured to: converting a plurality of generation rules to obtain a rule vector set, and encoding network traffic corresponding to each generation rule to obtain a traffic vector set; associating a rule vector corresponding to each generation rule with network traffic corresponding to each generation rule to obtain a plurality of rule-traffic pairs; training the generator model using the plurality of rule-flow pairs until a preset condition is met.
In one embodiment of the present invention, the generating module 300 is further configured to: encoding the target generation rule into a first vector; determining a second vector from the first vector and the similarity matrix; and decoding the second vector to obtain the network flow corresponding to the target generation rule.
In one embodiment of the present invention, each generation rule and the format of the network traffic corresponding to each generation rule are the same in the high-dimensional space.
It should be noted that the foregoing explanation of the embodiment of the data center network traffic generation method is also applicable to the data center network traffic generation device of this embodiment, and will not be repeated herein.
According to the data center network flow generating device provided by the embodiment of the invention, the flow rules are associated with corresponding flows through training the generator model, the association is stored through the similarity matrix, the target generating rules are input into the trained generator model after training is completed, the generator model outputs the similarity matrix of the target generating rules, the network flow corresponding to the target generating rules can be generated by utilizing the similarity matrix, and a user does not have the management authority of a network cluster and can acquire complex and diverse network flows. Therefore, the problems that in the related technology, by configuring the generation rule on the network equipment and collecting the traffic conforming to the rule, the rule is only applicable to users who can issue the rule and can operate network equipment such as a switch, and the rule needs to be redeployed and collected each time the traffic is acquired are solved, and the operation is complex and the applicability is low are solved.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device may include:
memory 501, processor 502, and a computer program stored on memory 501 and executable on processor 502.
The processor 502 implements the data center network traffic generation method provided in the above embodiment when executing a program.
Further, the electronic device further includes:
a communication interface 503 for communication between the memory 501 and the processor 502.
Memory 501 for storing a computer program executable on processor 502.
The memory 501 may include high-speed RAM (Random Access Memory ) memory, and may also include non-volatile memory, such as at least one disk memory.
If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 may be connected to each other via a bus and perform communication with each other. The bus may be an ISA (Industry Standard Architecture ) bus, a PCI (PERIPHERAL COMPONENT, external device interconnect) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 5, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a chip, the memory 501, the processor 502, and the communication interface 503 may perform communication with each other through internal interfaces.
The processor 502 may be a CPU (Central Processing Unit ) or an ASIC (Application SPECIFIC INTEGRATED Circuit, application specific integrated Circuit) or one or more integrated circuits configured to implement embodiments of the present invention.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the data center network traffic generation method as above.
The embodiment of the invention also provides a computer program which is used for realizing the data center network traffic generation method according to the embodiment when being executed.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, those skilled in the art may combine and combine the different embodiments or examples and features of the different embodiments or examples described in this specification without contradiction
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable gate arrays, field programmable gate arrays, and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (6)
1. A data center network traffic generation method, comprising the steps of:
Acquiring a training data set, wherein the training data set comprises a plurality of generation rules and network traffic corresponding to each generation rule;
Training a generator model by using the training data set, wherein the generator model is used for generating a similarity matrix of each generation rule and corresponding network traffic;
Inputting a target generation rule into a trained generator model, outputting a similarity matrix of the target generation rule by the generator model, and generating network traffic corresponding to the target generation rule by using the similarity matrix of the target generation rule;
The training of the generator model using the training data set comprises: converting the multiple generation rules to obtain a rule vector set, and encoding network traffic corresponding to each generation rule to obtain a traffic vector set; associating the rule vector corresponding to each generation rule with the network traffic corresponding to each generation rule to obtain a plurality of rule-traffic pairs; training the generator model using the plurality of rule-flow pairs until a preset condition is met;
The generating the network traffic corresponding to the target generation rule by using the similarity matrix of the target generation rule includes: encoding the target generation rule as a first vector; determining a second vector from the first vector and the similarity matrix; and decoding the second vector to obtain the network flow corresponding to the target generation rule.
2. The data center network traffic generation method according to claim 1, wherein each generation rule and the network traffic corresponding to each generation rule have the same format in a high-dimensional space.
3. A data center network traffic generating device, comprising:
The system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a training data set, wherein the training data set comprises a plurality of generation rules and network traffic corresponding to each generation rule;
the training module is used for training a generator model by utilizing the training data set, wherein the generator model is used for generating a similarity matrix of each generation rule and corresponding network traffic;
The generation module is used for inputting the target generation rule into a trained generator model, outputting a similarity matrix of the target generation rule by the generator model, and generating network traffic corresponding to the target generation rule by using the similarity matrix of the target generation rule;
The training module is further configured to: converting the multiple generation rules to obtain a rule vector set, and encoding network traffic corresponding to each generation rule to obtain a traffic vector set; associating the rule vector corresponding to each generation rule with the network traffic corresponding to each generation rule to obtain a plurality of rule-traffic pairs; training the generator model using the plurality of rule-flow pairs until a preset condition is met;
the generating module is further configured to: encoding the target generation rule as a first vector; determining a second vector from the first vector and the similarity matrix; and decoding the second vector to obtain the network flow corresponding to the target generation rule.
4. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the data center network traffic generation method of claim 1 or 2.
5. A computer-readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor for implementing the data center network traffic generating method according to claim 1 or 2.
6. A computer program product comprising a computer program, characterized in that the computer program, when executed, is adapted to carry out the data center network traffic generating method of claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410466658.5A CN118070850B (en) | 2024-04-18 | 2024-04-18 | Data center network traffic generation method, device, medium and computer program |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410466658.5A CN118070850B (en) | 2024-04-18 | 2024-04-18 | Data center network traffic generation method, device, medium and computer program |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118070850A CN118070850A (en) | 2024-05-24 |
| CN118070850B true CN118070850B (en) | 2024-06-18 |
Family
ID=91102453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410466658.5A Active CN118070850B (en) | 2024-04-18 | 2024-04-18 | Data center network traffic generation method, device, medium and computer program |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118070850B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113726545A (en) * | 2021-06-23 | 2021-11-30 | 清华大学 | Network traffic generation method and device for generating countermeasure network based on knowledge enhancement |
| CN113905391A (en) * | 2021-09-27 | 2022-01-07 | 湖北工业大学 | Ensemble learning network traffic prediction method, system, device, terminal, and medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105340311B (en) * | 2014-06-05 | 2019-06-28 | 华为技术有限公司 | The network equipment, network service prediction meanss and method |
| CN105022960B (en) * | 2015-08-10 | 2017-11-21 | 济南大学 | Multiple features mobile terminal from malicious software detecting method and system based on network traffics |
| US11696153B2 (en) * | 2020-08-13 | 2023-07-04 | Samsung Electronics Co., Ltd. | Transfer learning of network traffic prediction model among cellular base stations |
| CN113364752B (en) * | 2021-05-27 | 2023-04-18 | 鹏城实验室 | Flow abnormity detection method, detection equipment and computer readable storage medium |
| US20220385635A1 (en) * | 2021-05-27 | 2022-12-01 | Palo Alto Networks, Inc. | Combined machine learning and formal techniques for network traffic analysis |
| CN114362988B (en) * | 2021-09-29 | 2023-06-20 | 中国科学院计算机网络信息中心 | Network traffic identification method and device |
| CN114006870A (en) * | 2021-10-29 | 2022-02-01 | 西安热工研究院有限公司 | Network flow identification method based on self-supervision convolution subspace clustering network |
| CN114666162B (en) * | 2022-04-29 | 2023-05-05 | 北京火山引擎科技有限公司 | Flow detection method, device, equipment and storage medium |
| CN116743635B (en) * | 2023-08-14 | 2023-11-07 | 北京大学深圳研究生院 | Network prediction and regulation method and network regulation system |
-
2024
- 2024-04-18 CN CN202410466658.5A patent/CN118070850B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113726545A (en) * | 2021-06-23 | 2021-11-30 | 清华大学 | Network traffic generation method and device for generating countermeasure network based on knowledge enhancement |
| CN113905391A (en) * | 2021-09-27 | 2022-01-07 | 湖北工业大学 | Ensemble learning network traffic prediction method, system, device, terminal, and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118070850A (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3992976A1 (en) | Compound property prediction method and apparatus, and computer device and readable storage medium | |
| CN111324696A (en) | Entity extraction method, entity extraction model training method, device and equipment | |
| CN113222150A (en) | Quantum state transformation method and device | |
| CN111222046A (en) | Service configuration method, client for service configuration, equipment and electronic equipment | |
| CN109697083B (en) | Fixed-point acceleration method and device for data, electronic equipment and storage medium | |
| JP2022103136A (en) | Method, device, and computer readable storage medium for image processing | |
| CN112765481B (en) | Data processing method, device, computer and readable storage medium | |
| CN118070850B (en) | Data center network traffic generation method, device, medium and computer program | |
| CN116668351A (en) | Quality of service prediction method, device, computer equipment and storage medium | |
| CN113222151A (en) | Quantum state transformation method and device | |
| CN112948582B (en) | Data processing method, device, equipment and readable medium | |
| CN114462592A (en) | Model training method and device, electronic equipment and computer readable storage medium | |
| CN114299517A (en) | Image processing method, apparatus, device, storage medium, and computer program product | |
| CN112149426A (en) | Reading task processing method and related equipment | |
| CN115861605A (en) | Image data processing method, computer equipment and readable storage medium | |
| CN110517335B (en) | Dynamic texture video generation method, device, server and storage medium | |
| CN114528893A (en) | Machine learning model training method, electronic device and storage medium | |
| CN114584476A (en) | Traffic prediction method, network training device and electronic equipment | |
| CN118095358B (en) | Method, device and program for generating super-resolution of network traffic of data center | |
| CN111597211B (en) | Data flow graph processing method, device, equipment and readable storage medium | |
| US11789894B2 (en) | Acceleration system and dynamic configuration method thereof | |
| CN113836438B (en) | Method, electronic device, and storage medium for post recommendation | |
| EP4328807A1 (en) | Method and apparatus for adaptating to quantum computing platform, and quantum computer operating system | |
| Ghedass et al. | Modeling Big Data-centric Services using Knowledge Graphs | |
| CN117830935A (en) | Crowd counting model training method and device based on self-adaptive region selection module |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |