CN116055360A - Packet loss control method based on reinforcement learning and computer equipment - Google Patents
Packet loss control method based on reinforcement learning and computer equipment Download PDFInfo
- Publication number
- CN116055360A CN116055360A CN202310109335.6A CN202310109335A CN116055360A CN 116055360 A CN116055360 A CN 116055360A CN 202310109335 A CN202310109335 A CN 202310109335A CN 116055360 A CN116055360 A CN 116055360A
- Authority
- CN
- China
- Prior art keywords
- packet loss
- data
- file
- network
- processing program
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000002787 reinforcement Effects 0.000 title claims abstract description 14
- 230000007613 environmental effect Effects 0.000 claims abstract description 12
- 238000007405 data analysis Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000011835 investigation Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
- H04L43/0829—Packet loss
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/12—Arrangements for detecting or preventing errors in the information received by using return channel
- H04L1/16—Arrangements for detecting or preventing errors in the information received by using return channel in which the return channel carries supervisory signals, e.g. repetition request signals
- H04L1/18—Automatic repetition systems, e.g. Van Duuren systems
- H04L1/1809—Selective-repeat protocols
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a packet loss control method and computer equipment based on reinforcement learning, which relate to the technical field of computer equipment and comprise the following steps: step one: initializing a data analysis environment; step two: receiving data; step three: analyzing the data; step four: analyzing data, comparing the locally analyzed file with a network cloud file, and analyzing whether the analyzed file has a packet loss condition or not; step five: if the local file does not have the packet loss condition, acquiring environmental rewards and outputting data; step six: if the local file has the packet loss condition, the processing program performs the packet loss problem investigation; step seven: and after the local setting is modified, repeating the second step to the fourth step. The invention can analyze a single data packet by single operation, avoids the calculation resources required by simultaneous analysis and comparison of a plurality of data packets, and ensures the high-speed operation of computer equipment.
Description
Technical Field
The invention relates to the technical field of computer equipment, in particular to a packet loss control method based on reinforcement learning and the computer equipment.
Background
Reinforcement learning is one of a paradigm and a methodology of machine learning, and is used for describing and solving a problem that an agent achieves maximization of return or achieves a specific target through a learning strategy in an interaction process with an environment, causes of network packet loss are various, and in life and industrial production, the assistance of computer equipment is not separated, so that cooperation among a plurality of computer equipment is achieved through a network.
In the prior art, the situation of packet loss is more, and the situation of packet loss is possibly caused by software and hardware, but the existing packet loss control method mostly adopts repeated file reception for many times, and compares the files to avoid the situation of packet loss, so that computing resources of computer equipment are tense.
Disclosure of Invention
The invention aims to provide a packet loss control method and computer equipment based on reinforcement learning so as to solve the technical problems in the prior art.
The invention provides a packet loss control method based on reinforcement learning, which comprises the following steps:
step one: initializing a data analysis environment;
step two: receiving data, and receiving the data into a local storage module in a network transmission form;
step three: analyzing the data, analyzing the received local file, and analyzing the local file;
step four: analyzing data, comparing the locally analyzed file with a network cloud file, and analyzing whether the analyzed file has a packet loss condition or not;
step five: if the local file does not have the packet loss condition, acquiring environmental rewards and outputting data;
step six: if the local file has the packet loss condition, the processing program performs the packet loss problem check and correspondingly modifies the local setting;
step seven: and after the local setting is modified, repeating the second step to the fourth step.
Preferably, the processing program is used for detecting the packet loss problem, and the processing program comprises hardware detection and software detection.
Preferably, the processing program includes the steps of:
step one: the processing program performs hardware detection and software detection;
step two: carrying out packet loss detection of the hardware network card, inputting buffer data into a buffer area of hardware equipment to be detected, and detecting whether the buffer data overflows or not;
step three: if overflow occurs, pushing a prompt to remind the computer that the network card equipment performance of the computer equipment is poor, and acquiring environmental rewards;
step four: if the network IP layer packet loss detection is carried out, the router packet loss is detected, and if the router packet loss is carried out, the reminding router is pushed to have poor hardware performance, and environmental rewards are obtained;
step five: if the hardware detection is passed, performing software detection, firstly detecting packet loss of a firewall, and if the firewall is set incorrectly, pushing a prompting firewall setting problem, and acquiring environmental rewards;
step six: if the firewall is set correctly, detecting packet loss of an Ethernet link layer, checking the Ethernet link state, and if the Ethernet link is wrong, pushing a prompt to remind a user to plug an Ethernet plug and pick up environmental rewards;
step seven: if the Ethernet link is correct, detecting the network card drive packet loss, firstly carrying out network card packet loss statistics by a processing program, and if the network card packet loss statistics is abnormal, checking the network card configuration state;
step eight: if the network card configuration state is normal, the processing program checks the flow control statistics, and if the flow control statistics are abnormal, the network flow control configuration is checked.
In another aspect, the present invention provides a computer device, including a host, a router, an operating system, and a display, where the host is configured to implement a packet loss control method based on reinforcement learning.
Preferably, the display is used for displaying the content of the push prompt.
Preferably, the operating system is used for changing network card configuration, network flow control configuration and firewall setting in the host.
Preferably, the router is configured to provide network support to the host.
Compared with the prior art, the invention has the beneficial effects that:
according to the method and the device, after detection, analysis and judgment, whether the cloud file is received again is selected, so that a single data packet is analyzed through single operation in the use process of the computer equipment, the calculation resources required by simultaneous analysis and comparison of a plurality of data packets are avoided, and the high-speed operation of the computer equipment is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a training process of the present invention;
FIG. 2 is a flow chart of the process of the present invention;
FIG. 3 is a schematic diagram of a computer device of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown.
The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention.
Referring to fig. 1 to 3, an aspect of the present invention provides a packet loss control method based on reinforcement learning, which includes the following steps:
step one: initializing a data analysis environment;
step two: receiving data, and receiving the data into a local storage module in a network transmission form;
step three: analyzing the data, analyzing the received local file, and analyzing the local file;
step four: analyzing data, comparing the locally analyzed file with a network cloud file, and analyzing whether the analyzed file has a packet loss condition or not;
step five: if the local file does not have the packet loss condition, acquiring environmental rewards and outputting data;
step six: if the local file has the packet loss condition, the processing program performs the packet loss problem check and correspondingly modifies the local setting;
step seven: and after the local setting is modified, repeating the second step to the fourth step.
Only one file packet is analyzed at a time, the file can be analyzed more quickly and accurately under the condition of limited computing resources, so that the control efficiency of packet loss is ensured, and meanwhile, when the file has the packet loss, the data lost by the packet loss can be compensated locally by receiving the data again for analysis, and the packet loss condition is further controlled.
Further, the processing program is used for detecting the packet loss problem, and the processing program comprises hardware detection and software detection.
Further, the processing program comprises the following steps:
step one: the processing program performs hardware detection and software detection;
step two: carrying out packet loss detection of the hardware network card, inputting buffer data into a buffer area of hardware equipment to be detected, and detecting whether the buffer data overflows or not;
step three: if overflow occurs, pushing a prompt to remind the computer that the network card equipment performance of the computer equipment is poor, and acquiring environmental rewards;
step four: if the network IP layer packet loss detection is carried out, the router packet loss is detected, and if the router packet loss is carried out, the reminding router is pushed to have poor hardware performance, and environmental rewards are obtained;
step five: if the hardware detection is passed, performing software detection, firstly detecting packet loss of a firewall, and if the firewall is set incorrectly, pushing a prompting firewall setting problem, and acquiring environmental rewards;
step six: if the firewall is set correctly, detecting packet loss of an Ethernet link layer, checking the Ethernet link state, and if the Ethernet link is wrong, pushing a prompt to remind a user to plug an Ethernet plug and pick up environmental rewards;
step seven: if the Ethernet link is correct, detecting the network card drive packet loss, firstly carrying out network card packet loss statistics by a processing program, and if the network card packet loss statistics is abnormal, checking the network card configuration state;
step eight: if the network card configuration state is normal, the processing program checks the flow control statistics, and if the flow control statistics are abnormal, the network flow control configuration is checked.
Through the omnibearing detection of software and hardware, the packet loss condition generated by the problem of the local equipment can be effectively avoided, and the packet loss probability of the local equipment in the subsequent use process is further effectively reduced.
In another aspect, the embodiment of the invention provides a computer device, which includes a host, a router, an operating system and a display, and is characterized in that the host is used for implementing a packet loss control method based on reinforcement learning.
Further, the display is used for displaying the content of the push prompt.
The display timely displays the hardware state and the software configuration of the local equipment, so that a user can timely adjust the hardware state and set the software, and further the phenomenon of frequent packet loss caused by the hardware and the software is avoided.
Furthermore, the operating system is used for changing network card configuration, network flow control configuration and firewall setting in the host.
The network card configuration, the network flow control configuration and the firewall setting are carried out by the operating system, so that the packet loss condition can be timely adjusted.
Further, the router is configured to provide network support to the host.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (7)
1. The packet loss control method based on reinforcement learning is characterized by comprising the following steps:
step one: initializing a data analysis environment;
step two: receiving data, and receiving the data into a local storage module in a network transmission form;
step three: analyzing the data, analyzing the received local file, and analyzing the local file;
step four: analyzing data, comparing the locally analyzed file with a network cloud file, and analyzing whether the analyzed file has a packet loss condition or not;
step five: if the local file does not have the packet loss condition, acquiring environmental rewards and outputting data;
step six: if the local file has the packet loss condition, the processing program performs the packet loss problem check and correspondingly modifies the local setting;
step seven: and after the local setting is modified, repeating the second step to the fourth step.
2. The method for controlling packet loss based on reinforcement learning according to claim 1, wherein the processing program is used for detecting a packet loss problem, and the processing program comprises hardware detection and software detection.
3. The packet loss control method based on reinforcement learning according to claim 2, wherein the processing program comprises the steps of:
step one: the processing program performs hardware detection and software detection;
step two: carrying out packet loss detection of the hardware network card, inputting buffer data into a buffer area of hardware equipment to be detected, and detecting whether the buffer data overflows or not;
step three: if overflow occurs, pushing a prompt to remind the computer that the network card equipment performance is poor;
step four: if the packet is not overflowed, detecting packet loss of the network IP layer, detecting packet loss of the router, and if the packet loss of the router is detected, pushing the reminding router to have poor hardware performance;
step five: if the hardware detection is passed, performing software detection, firstly detecting packet loss of the firewall, and if the firewall is set incorrectly, pushing a prompting firewall setting problem;
step six: if the firewall is set correctly, detecting packet loss of an Ethernet link layer, checking the Ethernet link state, and if the Ethernet link is wrong, pushing a prompt to remind a user of plugging an Ethernet plug;
step seven: if the Ethernet link is correct, detecting the network card drive packet loss, firstly carrying out network card packet loss statistics by a processing program, and if the network card packet loss statistics is abnormal, checking the network card configuration state;
step eight: if the network card configuration state is normal, the processing program checks the flow control statistics, and if the flow control statistics are abnormal, the network flow control configuration is checked.
4. A computer device comprising a host, a router, an operating system, and a display, wherein the host is configured to perform the reinforcement learning-based packet loss control method of any of claims 1-3.
5. The computer device of claim 4, wherein the display is configured to display push prompt content.
6. The computer device of claim 5, wherein the operating system is configured to alter network card configuration, network flow control configuration, firewall settings in the host.
7. A computer device according to claim 6, wherein the router is configured to provide network support to a host.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310109335.6A CN116055360B (en) | 2023-02-14 | 2023-02-14 | Packet loss control method based on reinforcement learning and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310109335.6A CN116055360B (en) | 2023-02-14 | 2023-02-14 | Packet loss control method based on reinforcement learning and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116055360A true CN116055360A (en) | 2023-05-02 |
| CN116055360B CN116055360B (en) | 2024-07-05 |
Family
ID=86119978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310109335.6A Active CN116055360B (en) | 2023-02-14 | 2023-02-14 | Packet loss control method based on reinforcement learning and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116055360B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949827A (en) * | 2019-03-15 | 2019-06-28 | 上海师范大学 | A kind of room acoustics Activity recognition method based on deep learning and intensified learning |
| CN113079044A (en) * | 2021-03-26 | 2021-07-06 | 武汉大学 | Packet loss control method based on reinforcement learning and computer equipment |
| WO2022135542A1 (en) * | 2020-12-23 | 2022-06-30 | 苏州盛科通信股份有限公司 | Psn-based rdma network packet loss detection method and apparatus |
-
2023
- 2023-02-14 CN CN202310109335.6A patent/CN116055360B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949827A (en) * | 2019-03-15 | 2019-06-28 | 上海师范大学 | A kind of room acoustics Activity recognition method based on deep learning and intensified learning |
| WO2022135542A1 (en) * | 2020-12-23 | 2022-06-30 | 苏州盛科通信股份有限公司 | Psn-based rdma network packet loss detection method and apparatus |
| CN113079044A (en) * | 2021-03-26 | 2021-07-06 | 武汉大学 | Packet loss control method based on reinforcement learning and computer equipment |
Non-Patent Citations (4)
| Title |
|---|
| JIFENG HUANG: "Tensor Dictionary Manifold Learning for Channel Estimation and Interference Elimination of Multi-User Millimeter-Wave Massive MIMO Systems", 《IEEE ACCESS 》, 17 November 2021 (2021-11-17) * |
| 刘明;黄继风;高海;: "一种基于深度强化学习的室内声学行为识别方法", 上海师范大学学报(自然科学版), no. 01, 15 February 2020 (2020-02-15) * |
| 蒋红娜;艾波;: "一种网络化机载测试系统丢包检测算法实现", 中国科技信息, no. 13, 1 July 2017 (2017-07-01) * |
| 黄继风: "深度学习在音频信号处理中的研究探析", 《信息通信》, 15 March 2020 (2020-03-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116055360B (en) | 2024-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105205003A (en) | Automated testing method and device based on clustering system | |
| CN103684898A (en) | Method and device for monitoring operation of user request in distributed system | |
| CN109981715B (en) | Session management method and device | |
| US20220360516A1 (en) | Generation of test traffic configuration based on real-world traffic | |
| CN116055360B (en) | Packet loss control method based on reinforcement learning and computer equipment | |
| CN112463432A (en) | Inspection method, device and system based on index data | |
| CN116170203A (en) | Prediction method and system for security risk event | |
| CN110730112A (en) | Method, system, equipment and storage medium for testing network running speed | |
| US10613963B2 (en) | Intelligent packet analyzer circuits, systems, and methods | |
| CN106571975A (en) | Fault tolerance method of communication data and apparatus thereof | |
| CN113518019A (en) | System identification method based on survival port | |
| CN112532447A (en) | RDMA parameter configuration method, device and storage medium | |
| US7697428B2 (en) | Analyzing network traffic using an improved markov modulated poisson process model with two barrier states | |
| CN107579871B (en) | Method and system for generating distributed test script based on model detection | |
| CN115396142A (en) | Information access method and device based on zero trust, computer equipment and medium | |
| CN115037651A (en) | RDMA bandwidth transmission testing method, system and storage medium | |
| CN114598547A (en) | Data analysis method applied to network attack recognition and electronic equipment | |
| CN109981394B (en) | Communication method and device based on enhanced CAN bus protocol analyzer | |
| CN112181618A (en) | Data transmission method and device, computer equipment and storage medium | |
| Wanyan et al. | NCMFuzzer: Using non-critical field mutation and test case combination to improve the efficiency of ICS protocol fuzzing | |
| CN112035283B (en) | Queuing and executing method and system based on distributed quantum computing service | |
| CN115296973B (en) | Method, device and application for collecting and sending front-end journals in batches | |
| CN112565271B (en) | Web attack detection method and device | |
| CN114124754B (en) | Method for processing media data packets in a multimedia network and related products | |
| CN117439904A (en) | Conformal prediction-based network anomaly detection method, system, equipment and medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240614 Address after: Room 406, 4th Floor, Building 3, No. 168 Hangqian Road, Guali Town, Xiaoshan District, Hangzhou City, Zhejiang Province, 311200 (self division) Applicant after: Hangzhou Xincai Intelligent Technology Co.,Ltd. Country or region after: China Address before: 201418 Shanghai Normal University Applicant before: SHANGHAI NORMAL University Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |