CN114339858B - Terminal packet sending parameter adjusting method and device and related equipment - Google Patents
Terminal packet sending parameter adjusting method and device and related equipment Download PDFInfo
- Publication number
- CN114339858B CN114339858B CN202111654336.6A CN202111654336A CN114339858B CN 114339858 B CN114339858 B CN 114339858B CN 202111654336 A CN202111654336 A CN 202111654336A CN 114339858 B CN114339858 B CN 114339858B
- Authority
- CN
- China
- Prior art keywords
- value
- congestion
- parameter value
- packet sending
- parameter
- 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 33
- 239000013598 vector Substances 0.000 claims abstract description 26
- 230000006870 function Effects 0.000 claims description 27
- 230000005540 biological transmission Effects 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 230000003750 conditioning effect Effects 0.000 claims 2
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The application discloses a method, a device and related components for adjusting terminal packet sending parameters, wherein the method comprises the following steps: continuously obtaining a congestion parameter value of a current network according to a fixed frequency, and combining the congestion parameter value with a current packet sending parameter value to obtain an input vector; inputting the input vector into a pre-trained LSTM model, and predicting a congestion parameter value of a network congestion state at a target moment to obtain a congestion predicted value at the target moment; calculating the difference value between the current network congestion parameter value and the congestion predicted value, calculating the adjustment value of the packet sending parameter value according to the difference value and a preset adjustment function, and adjusting the packet sending parameter value according to the adjustment value. The application enables the terminal to autonomously adjust the packet sending parameter value according to the congestion prediction value and send packets according to the packet sending parameter value, thereby reducing the possibility that the terminal is easy to generate network congestion due to the fixed packet sending parameter value distributed by the base station.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for adjusting a terminal packet sending parameter, and related components.
Background
The internet of things is based on the idea that everything can access the internet to realize everything interconnection as a final target. With this goal, with the rapid development of networking intelligence, we are in the stage of exponential development of the internet of things (IoT). As the number of connectable internet of things devices increases, the internet of things will continue to evolve by providing connectivity and interaction between the physical and network worlds. Unlike traditional networking devices such as smartphones and personal computers, however, such internet of things devices typically transmit data that has been collected in bursts or communicate with a base station at a steady rate.
However, as the number of terminal devices changes, a single communication base station is prone to network congestion due to limited capacity. In addition, most of the existing communication modes adopt a preemption mode or a fixed time-sharing mode, and the terminal ignores network demands of other terminal devices in the network for the efficiency and smoothness of data transmission. The existing network conditions gradually deteriorate.
Disclosure of Invention
The embodiment of the application provides a method, a device and a related component for adjusting a terminal packet sending parameter, which aim to solve the problem that network congestion is caused when terminal equipment reports data in a competing manner in the prior art.
In a first aspect, an embodiment of the present application provides a method for adjusting a terminal packet sending parameter, including:
continuously obtaining a congestion parameter value of a current network according to a fixed frequency, and combining the congestion parameter value with a current packet sending parameter value to obtain an input vector;
inputting the input vector into a pre-trained LSTM model, and predicting a congestion parameter value of a network congestion state at a target moment to obtain a congestion predicted value at the target moment;
calculating the difference value between the current network congestion parameter value and the congestion predicted value, calculating the adjustment value of the packet sending parameter value according to the difference value and a preset adjustment function, and adjusting the packet sending parameter value according to the adjustment value.
In a second aspect, an embodiment of the present application provides a device for adjusting a terminal packet sending parameter, including:
the combination module is used for continuously acquiring the congestion parameter value of the current network according to the fixed frequency, and combining the congestion parameter value with the current packet sending parameter value to obtain an input vector;
the prediction module is used for inputting the input vector into a pre-trained LSTM model to predict the congestion parameter value of the network congestion state at the target moment to obtain a congestion prediction value at the target moment;
the adjusting module is used for calculating the difference value between the congestion parameter value of the current network and the congestion predicted value, calculating the adjusting value of the packet sending parameter value according to the difference value and a preset adjusting function, and adjusting the packet sending parameter value according to the adjusting value.
In a third aspect, an embodiment of the present application provides a computer 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 method for adjusting a terminal packet sending parameter according to the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, where the computer program when executed by a processor implements the method for adjusting a terminal packet sending parameter according to the first aspect.
The embodiment of the application provides a method and a device for adjusting a terminal packet sending parameter and related components, wherein the method comprises the following steps: continuously obtaining a congestion parameter value of a current network according to a fixed frequency, and combining the congestion parameter value with a current packet sending parameter value to obtain an input vector; inputting the input vector into a pre-trained LSTM model, and predicting a congestion parameter value of a network congestion state at a target moment to obtain a congestion predicted value at the target moment; calculating the difference value between the current network congestion parameter value and the congestion predicted value, calculating the adjustment value of the packet sending parameter value according to the difference value and a preset adjustment function, and adjusting the packet sending parameter value according to the adjustment value. According to the embodiment of the application, the congestion parameter value at the target moment is predicted by configuring the pre-trained LSTM model, the congestion parameter value of the current network and the packet sending parameter value of the terminal are used as input vectors of the LSTM model, the congestion predicted value of the network at the target moment is obtained through the LSTM model, and finally the packet sending parameter value is regulated according to the difference value of the congestion parameter value and the congestion predicted value of the network, so that the terminal can autonomously regulate the packet sending parameter value according to the congestion predicted value and send packets according to the packet sending parameter value, and the possibility that the network congestion is easy to occur due to the fixed packet sending parameter value distributed by the base station by the terminal is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an embodiment of a method for adjusting a terminal packet sending parameter according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a pre-training process of an LSTM model in a method for adjusting a packet sending parameter of a terminal according to an embodiment of the present application;
fig. 3 is a schematic diagram of a sub-example of an embodiment of a method for adjusting a terminal packet sending parameter according to an embodiment of the present application;
fig. 4 is a schematic block diagram of a device for adjusting a terminal packet sending parameter according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1, fig. 1 is a flow chart of a method for adjusting a terminal packet sending parameter according to an embodiment of the present application, which specifically includes: steps S101 to S105.
Step S101, continuously obtaining a congestion parameter value of a current network according to a fixed frequency, and combining the congestion parameter value with the current packet sending parameter value to obtain an input vector;
in this embodiment, since the terminal does not have any prior information, in an initialized state, the terminal initiates a congestion parameter value acquisition request to the base station according to an initialized fixed frequency, to obtain a congestion parameter value of a current network, including: the statistics of simple parameters such as link establishment times/failure times, average time delay, retransmission times, sector utilization rate and the like can not occupy the load of base station hardware. The congestion parameter value obtained from the base station and parameters such as the packet sending time slot, the packet sending frequency, the packet sending time delay random value of the current terminal are used as input vectors. It should be noted that the random value of packet sending delay is a strategy for preventing the channel congestion caused by simultaneous packet sending of multiple terminals in the same time slot, so that multiple terminals will not contend for the channel in the initialization stage.
Step S102, inputting the input vector into a pre-trained LSTM model, and predicting a congestion parameter value of a network congestion state at a target moment to obtain a congestion predicted value at the target moment;
in this embodiment, a pre-trained LSTM model is used to predict congestion parameter values of network congestion states at target moments. Because the performance of the bearing environment terminal of the model is insufficient, the lstm model with simpler structure and fewer parameters is adopted for prediction, and online learning capability is provided. Thereby achieving the effect of reducing the load of the base station. An LSTM model is defined, with 50 neurons in its first hidden layer and 1 neuron in the output layer for predicting congestion parameter values of the network. The dimensions of the incoming data will be 1 time (the duration is defined by the network administrator), congestion parameter values and packet-sending parameter values. Training with the real congestion index at the next moment, optimizing using a Mean Absolute Error (MAE) loss function and Adam optimizer. And inputting the input vector into the pre-trained LSTM model to obtain the network predicted value of the network congestion state at the target moment.
As shown in fig. 2, in an embodiment, the pre-training process of the LSTM model includes:
step S201, acquiring a history parameter value of a history network and a history packet sending value of a corresponding time terminal, and forming a training vector by the history parameter value and the history packet sending value;
step S202, inputting the training vector into an initial LSTM model to predict congestion parameter values of a historical network, so as to obtain a historical predicted value of the historical network;
and step 203, calculating a parameter loss value by adopting a preset loss function based on the historical parameter value and the historical predicted value, and optimizing the initial LSTM model according to the parameter loss value to obtain the LSTM model.
In this embodiment, a historical parameter value of a network congestion state at a historical moment and a historical packet sending value corresponding to a terminal at the historical moment are obtained, and the historical parameter value and the historical packet sending value form a training vector; then inputting the training vector into an initial LSTM model to predict the congestion parameter value of the historical network to obtain a historical predicted value of the historical network; based on the historical parameter values and the historical predicted values, calculating parameter loss values by adopting a Mean Absolute Error (MAE) loss function, and optimizing model parameters of the initial LSTM model according to the parameter loss values and an Adam optimizer to obtain the LSTM model. In addition, the prediction performance of the LSTM model is judged by using Root Mean Square Error (RMSE), and when the root mean square error is less than 10%, the self-adaptive data transmission frequency adjustment can be started, and meanwhile, the LSTM model is updated online.
Step S103, calculating the difference value between the congestion parameter value of the current network and the congestion predicted value, calculating the adjustment value of the packet sending parameter value according to the difference value and a preset adjustment function, and adjusting the packet sending parameter value according to the adjustment value.
In this embodiment, a difference value between a congestion parameter value and a congestion prediction value of a current network is calculated, an adjustment value of a packet sending parameter value is calculated according to the difference value and a preset adjustment function, and the packet sending parameter value is adjusted according to the adjustment value, wherein the adjustment function is as follows:
f 1 ＝(f max -f 0 )·Δ+f 0 ，
rand((1/f 1 )/ts)，
dt 1 ＝(ts-dt 0 )·Δ+dt 0 ，
wherein f 1 The packet sending frequency of the target moment is represented; f (f) max Representing the maximum frequency of single terminal sending packets which are set in an initializing mode; delta represents the difference between the current network congestion parameter value and the congestion prediction value; rand represents a random function; ts represents the duration of a single packet-sending time slot, which is determined by different transmission protocols; dt (dt) 1 A random value of packet delay representing a target moment; dt (dt) 0 And the random value of the packet sending delay of the target moment is represented.
As shown in fig. 3, in an embodiment, after step S103, the method further includes:
step S301, obtaining the actual congestion value of the network at the target moment, and calculating the predicted congestion value and the loss of the actual congestion value according to a preset loss function to obtain predicted loss;
and step S302, back-propagating model parameters of the LSTM model according to the prediction loss, and optimizing the LSTM model.
In this embodiment, after performing packet transmission according to the adjusted packet transmission parameter value, the terminal continues to acquire the congestion parameter value of the network from the base station according to the fixed frequency, calculates a prediction loss by adopting a Mean Absolute Error (MAE) loss function based on the congestion actual value and the congestion predicted value of the network at the target moment, and performs back propagation on the model of the LSTM model according to the prediction loss to update the LSTM model so as to implement online update of the LSTM model parameter. In addition, in order to increase the efficiency of network data transmission, when an analysis end needs to extract and analyze terminal data in the network, an analysis section can adopt a compressed sensing technology to perform high-frequency reduction on the terminal data which are unevenly sampled. The method has good effect on the multi-terminal network environment in NB-IoT scenes and loRa scenes.
According to the embodiment of the application, the congestion parameter value at the target moment is predicted by configuring the pre-trained LSTM model, the congestion parameter value of the current network and the packet sending parameter value of the terminal are used as input vectors of the LSTM model, the congestion predicted value of the network at the target moment is obtained through the LSTM model, and finally the packet sending parameter value is regulated according to the difference value of the congestion parameter value and the congestion predicted value of the network, so that the terminal can autonomously regulate the packet sending parameter value according to the congestion predicted value and send packets according to the packet sending parameter value, and the possibility that the network congestion is easy to occur due to the fixed packet sending parameter value distributed by the base station by the terminal is reduced.
The embodiment of the application also provides a terminal packet sending parameter adjusting device which is used for executing any embodiment of the method for adjusting the terminal packet sending parameter. Specifically, referring to fig. 4, fig. 4 is a schematic block diagram of a terminal packet sending parameter adjusting apparatus according to an embodiment of the present application. The terminal packet sending parameter adjusting apparatus 100 may be configured in a server node.
As shown in fig. 4, the terminal packet transmission parameter adjustment device 100 includes a combination module 110, a prediction module 120, and an adjustment module 130.
A combination module 110, configured to continuously obtain a congestion parameter value of a current network according to a fixed frequency, and combine the congestion parameter value with a current packet sending parameter value to obtain an input vector;
the prediction module 120 is configured to input the input vector into a pre-trained LSTM model to predict a congestion parameter value of a network congestion state at a target time, so as to obtain a congestion prediction value at the target time;
the adjusting module 130 is configured to calculate a difference between the congestion parameter value of the current network and the congestion prediction value, calculate an adjustment value of the packet sending parameter value according to the difference and a preset adjusting function, and adjust the packet sending parameter value according to the adjustment value.
In an embodiment, the terminal packet sending parameter adjusting apparatus 100 further includes:
the loss calculation module is used for obtaining the actual congestion value of the network at the target moment, and calculating the predicted congestion value and the loss of the actual congestion value according to a preset loss function to obtain predicted loss;
and the optimization module is used for carrying out back propagation on the model parameters of the LSTM model according to the prediction loss and optimizing the LSTM model.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus, device and unit described above may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein. Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the units is merely a logical function division, there may be another division manner in actual implementation, or units having the same function may be integrated into one unit, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present application.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units may be stored in a storage medium if implemented in the form of software functional units and sold or used as stand-alone products. Based on such understanding, the technical solution of the present application may be essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server node, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (9)
1. The method for adjusting the terminal packet sending parameters is characterized by comprising the following steps:
continuously obtaining a congestion parameter value of a current network according to a fixed frequency, and combining the congestion parameter value with a current packet sending parameter value to obtain an input vector;
inputting the input vector into a pre-trained LSTM model, and predicting a congestion parameter value of a network congestion state at a target moment to obtain a congestion predicted value at the target moment;
calculating the difference value between the current network congestion parameter value and the congestion predicted value, calculating the adjustment value of the packet sending parameter value according to the difference value and a preset adjustment function, and adjusting the packet sending parameter value according to the adjustment value;
the conditioning function includes:
f 1 = (f max -f 0 )·Δ + f 0 ，
rand(（1/f 1 ）/ts)，
dt 1 = (ts-dt 0 )·Δ + dt 0 ，
wherein f 1 The packet sending frequency of the target moment is represented; f (f) max Representing initialization settingsMaximum frequency of single terminal packet; delta represents the difference between the current network congestion parameter value and the congestion prediction value; rand is a random function representing the packet sending time slot; ts represents the duration of a single packet-sending time slot, which is determined by different transmission protocols; dt (dt) 1 And the random value of the packet sending delay of the target moment is represented.
2. The method for adjusting the parameters of the terminal packet according to claim 1, wherein the pre-training process of the LSTM model includes:
acquiring a historical parameter value of a historical network and a historical packet sending value of a corresponding time terminal, and forming a training vector by the historical parameter value and the historical packet sending value;
inputting the training vector into an initial LSTM model to predict congestion parameter values of the historical network, so as to obtain historical predicted values of the historical network;
and calculating a parameter loss value by adopting a preset loss function based on the historical parameter value and the historical predicted value, and optimizing the initial LSTM model according to the parameter loss value to obtain the LSTM model.
3. The method for adjusting a terminal packet sending parameter according to claim 1, wherein the congestion parameter value includes a link establishment number/failure number, an average delay, a retransmission number, and a sector utilization of the network.
4. The method for adjusting a packet transmission parameter of a terminal according to claim 1, wherein the packet transmission parameter value includes a packet transmission time slot, a packet transmission frequency, and a packet transmission delay random value of the terminal.
5. The method for adjusting a packet sending parameter of a terminal according to claim 1, wherein after calculating a difference between a congestion parameter value of a current network and the congestion prediction value, calculating an adjustment value of the packet sending parameter value according to the difference and a preset adjustment function, and adjusting the packet sending parameter value according to the adjustment value, further comprises:
acquiring a congestion actual value of a network at a target moment, and calculating the congestion predicted value and the loss of the congestion actual value according to a preset loss function to obtain a predicted loss;
and carrying out back propagation on model parameters of the LSTM model according to the prediction loss, and optimizing the LSTM model.
6. A terminal packet-issuing parameter adjusting device, comprising:
the combination module is used for continuously acquiring the congestion parameter value of the current network according to the fixed frequency, and combining the congestion parameter value with the current packet sending parameter value to obtain an input vector;
the prediction module is used for inputting the input vector into a pre-trained LSTM model to predict the congestion parameter value of the network congestion state at the target moment to obtain a congestion prediction value at the target moment;
the adjusting module is used for calculating the difference value between the congestion parameter value of the current network and the congestion predicted value, calculating an adjusting value of the packet sending parameter value according to the difference value and a preset adjusting function, and adjusting the packet sending parameter value according to the adjusting value;
the conditioning function includes:
f 1 = (f max -f 0 )·Δ + f 0 ，
rand(（1/f 1 ）/ts)，
dt 1 = (ts-dt 0 )·Δ + dt 0 ，
wherein f 1 The packet sending frequency of the target moment is represented; f (f) max Representing the maximum frequency of single terminal sending packets which are set in an initializing mode; delta represents the difference between the current network congestion parameter value and the congestion prediction value; rand is a random function representing the packet sending time slot; ts represents the duration of a single packet-sending time slot, which is determined by different transmission protocols; dt (dt) 1 And the random value of the packet sending delay of the target moment is represented.
7. The terminal packet transmission parameter adjustment device according to claim 6, further comprising:
the loss calculation module is used for obtaining the actual congestion value of the network at the target moment, and calculating the predicted congestion value and the loss of the actual congestion value according to a preset loss function to obtain predicted loss;
and the optimization module is used for carrying out back propagation on the model parameters of the LSTM model according to the prediction loss and optimizing the LSTM model.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a terminal packet-issuing parameter adjustment method according to any of claims 1 to 5 when the computer program is executed by the processor.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the terminal packet transmission parameter adjustment method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111654336.6A CN114339858B (en) | 2021-12-30 | 2021-12-30 | Terminal packet sending parameter adjusting method and device and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111654336.6A CN114339858B (en) | 2021-12-30 | 2021-12-30 | Terminal packet sending parameter adjusting method and device and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114339858A CN114339858A (en) | 2022-04-12 |
| CN114339858B true CN114339858B (en) | 2023-12-05 |
Family
ID=81019650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111654336.6A Active CN114339858B (en) | 2021-12-30 | 2021-12-30 | Terminal packet sending parameter adjusting method and device and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114339858B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104320809A (en) * | 2014-11-05 | 2015-01-28 | 四川九洲电器集团有限责任公司 | Wireless multi-hop network congestion control method and system based on RTT |
| CN106713055A (en) * | 2017-02-27 | 2017-05-24 | 电子科技大学 | Energy-saving deployment method of virtual CDN |
| CN108900546A (en) * | 2018-08-13 | 2018-11-27 | 杭州安恒信息技术股份有限公司 | The method and apparatus of time series Network anomaly detection based on LSTM |
| CN111132190A (en) * | 2019-11-28 | 2020-05-08 | 中通服建设有限公司 | Base station load early warning method and device |
| WO2020221224A1 (en) * | 2019-04-30 | 2020-11-05 | 华为技术有限公司 | Congestion information acquisition method and system, related device and computer storage medium |
| CN111970163A (en) * | 2020-06-30 | 2020-11-20 | 网络通信与安全紫金山实验室 | Network flow prediction method of LSTM model based on attention mechanism |
| WO2021026509A1 (en) * | 2019-08-08 | 2021-02-11 | Intel Corporation | Link performance prediction and media streaming technologies |
| CN112532409A (en) * | 2019-09-17 | 2021-03-19 | 华为技术有限公司 | Network parameter configuration method and device, computer equipment and storage medium |
| CN113079104A (en) * | 2021-03-22 | 2021-07-06 | 新华三技术有限公司 | Network congestion control method, device and equipment |
| CN113141318A (en) * | 2021-03-29 | 2021-07-20 | 重庆邮电大学 | Improved TFRC congestion control system and method based on video traffic prediction model |
| CN113259255A (en) * | 2021-06-03 | 2021-08-13 | 鹏城实验室 | Network congestion control method, device, terminal and storage medium |
| CN113283179A (en) * | 2021-06-17 | 2021-08-20 | 湘潭大学 | Short-term load prediction method based on multi-target LSTM integrated network |
| CN113825171A (en) * | 2021-09-30 | 2021-12-21 | 新华三技术有限公司 | Network congestion control method, device, equipment and medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100748187B1 (en) * | 2007-06-01 | 2007-08-10 | 인하대학교 산학협력단 | Node availability prediction-based grid network congestion control device and method therefor |
| US10855550B2 (en) * | 2016-11-16 | 2020-12-01 | Cisco Technology, Inc. | Network traffic prediction using long short term memory neural networks |
| CN107070805A (en) * | 2017-03-22 | 2017-08-18 | 上海华为技术有限公司 | The method and node of a kind of flow control |
-
2021
- 2021-12-30 CN CN202111654336.6A patent/CN114339858B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104320809A (en) * | 2014-11-05 | 2015-01-28 | 四川九洲电器集团有限责任公司 | Wireless multi-hop network congestion control method and system based on RTT |
| CN106713055A (en) * | 2017-02-27 | 2017-05-24 | 电子科技大学 | Energy-saving deployment method of virtual CDN |
| CN108900546A (en) * | 2018-08-13 | 2018-11-27 | 杭州安恒信息技术股份有限公司 | The method and apparatus of time series Network anomaly detection based on LSTM |
| WO2020221224A1 (en) * | 2019-04-30 | 2020-11-05 | 华为技术有限公司 | Congestion information acquisition method and system, related device and computer storage medium |
| WO2021026509A1 (en) * | 2019-08-08 | 2021-02-11 | Intel Corporation | Link performance prediction and media streaming technologies |
| CN112532409A (en) * | 2019-09-17 | 2021-03-19 | 华为技术有限公司 | Network parameter configuration method and device, computer equipment and storage medium |
| CN111132190A (en) * | 2019-11-28 | 2020-05-08 | 中通服建设有限公司 | Base station load early warning method and device |
| CN111970163A (en) * | 2020-06-30 | 2020-11-20 | 网络通信与安全紫金山实验室 | Network flow prediction method of LSTM model based on attention mechanism |
| CN113079104A (en) * | 2021-03-22 | 2021-07-06 | 新华三技术有限公司 | Network congestion control method, device and equipment |
| CN113141318A (en) * | 2021-03-29 | 2021-07-20 | 重庆邮电大学 | Improved TFRC congestion control system and method based on video traffic prediction model |
| CN113259255A (en) * | 2021-06-03 | 2021-08-13 | 鹏城实验室 | Network congestion control method, device, terminal and storage medium |
| CN113283179A (en) * | 2021-06-17 | 2021-08-20 | 湘潭大学 | Short-term load prediction method based on multi-target LSTM integrated network |
| CN113825171A (en) * | 2021-09-30 | 2021-12-21 | 新华三技术有限公司 | Network congestion control method, device, equipment and medium |
Non-Patent Citations (3)
| Title |
|---|
| Analyzing the Cascading Effect of Traffic Congestion Using LSTM Networks;Sanchita Basak et al.;《2019 IEEE International Conference on Big Data (Big Data)》;全文 * |
| 复杂网络下具有预测与自我调节能力的拥塞控制算法;邱泽敏 等;《计算机工程》(12);全文 * |
| 视频传输QoS优化方案研究;周鹏;《中国优秀硕士学位论文全文数据库 信息科技辑》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114339858A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111092823B (en) | Method and system for adaptively adjusting congestion control initial window | |
| CN110809306B (en) | Terminal access selection method based on deep reinforcement learning | |
| CN109862610B (en) | D2D user resource allocation method based on deep reinforcement learning DDPG algorithm | |
| CN111919423B (en) | Congestion control in network communications | |
| CN110971706A (en) | Approximate optimization and reinforcement learning-based task unloading method in MEC | |
| CN114340016B (en) | Power grid edge calculation unloading distribution method and system | |
| CN110336620B (en) | QL-UACW backoff method based on MAC layer fair access | |
| CN113595923A (en) | Network congestion control method and device | |
| CN113438315B (en) | Internet of things information freshness optimization method based on double-network deep reinforcement learning | |
| CN113507328B (en) | Time slot MAC protocol method, system, device and medium for underwater acoustic network | |
| CN113590232B (en) | Relay edge network task unloading method based on digital twinning | |
| CN116489712B (en) | Mobile edge computing task unloading method based on deep reinforcement learning | |
| CN113568727A (en) | Mobile edge calculation task allocation method based on deep reinforcement learning | |
| CN115277689A (en) | Yun Bianwang network communication optimization method and system based on distributed federal learning | |
| CN116260871A (en) | Independent task unloading method based on local and edge collaborative caching | |
| CN114281718A (en) | Industrial Internet edge service cache decision method and system | |
| CN114339858B (en) | Terminal packet sending parameter adjusting method and device and related equipment | |
| JP7259978B2 (en) | Controller, method and system | |
| CN116567651A (en) | Decision method and system for MEC task unloading and migration based on particle swarm | |
| CN115904533A (en) | Edge calculation task unloading method based on deep reinforcement learning | |
| CN111741050A (en) | Data distribution method and system based on roadside unit | |
| CN117891613B (en) | Computing unloading and resource allocation method and system based on Internet of vehicles | |
| CN114745337B (en) | Real-time congestion control method based on deep reinforcement learning | |
| CN110233762B (en) | Method for improving throughput of full-duplex CSMA network by using MAB | |
| CN117114113B (en) | Collaborative reasoning acceleration method based on queuing theory |
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 |