A dynamic optimization device response method based on a local area network in a distribution network process

Abstract

The application relates to a dynamic optimization device response method based on a local area network in a network distribution process, which comprises the following steps: after a device accesses the local area network, the device sends a multicast packet to a service end in the local area network to declare that the device accesses the local area network; the service end sends a response request to each device in the local area network through a UDP multicast; the network state parameter data of each device in the local area network is monitored in real time; a response delay time window prediction model is constructed, the network state parameter data of each device is input into the response delay time window prediction model, and the response delay of each device is obtained; when the device receives the response request, the device waits according to the predicted response delay and then responds; after the service end receives the response, the service end sends an ACK to the corresponding device; if the device does not receive the ACK within a preset time, a retransmission process is executed until the device receives the ACK within the preset time or reaches a preset maximum retransmission number.

Description

TECHNICAL FIELD

[0001] The application relates to a dynamic optimization device response method based on a local area network in a network configuration process and belongs to the technical field of network communication. BACKGROUND

[0002] In the network configuration process of an intelligent device, after the device is connected to a Wi-Fi local area network through the network configuration mode of an app via an AP (Access Point), the device needs to feed back the network configuration state and the network configuration result to the app. However, the existing response mechanism has the following problems:

[0003] 1. Response conflict: when multiple devices simultaneously feed back the state to the app, data packet conflict or information loss is prone to occur.

[0004] 2. Low discovery efficiency: the communication between the device and the app depends on broadcast, which is easily affected by local area network isolation or network configuration, resulting in low device discovery efficiency.

[0005] 3. Insufficient reliability: the reliability and repeatability of device response cannot be fully guaranteed, which may lead to the app receiving incomplete device state or result.

[0006] 4. Limitation of static delay mechanism: the traditional random delay response mechanism lacks the dynamic adaptation ability to the network state and is difficult to cope with the complex local area network scene of multiple device concurrency.

[0007] 5. Un-timely detection of response failure: in a high-delay or high-packet-loss network, device response may frequently fail or be delayed, affecting system stability and failing to timely warn or take corresponding measures. SUMMARY

[0008] In order to solve the problems existing in the prior art, the application provides a dynamic optimization device response method based on a local area network in a network configuration process.

[0009] The technical scheme of the application is as follows:

[0010] On the one hand, the application provides a dynamic optimization device response method based on a local area network in a network configuration process, comprising the following steps:

[0011] After the device is connected to the local area network, the device sends a multicast packet to the server in the local area network to declare that the device is connected to the local area network, and the server sends a response request to each device in the local area network through UDP multicast;

[0012] Real-time monitoring of network state parameter data of each device in the local area network;

[0013] A response delay time window prediction model is constructed, and the response delay of each device is obtained by inputting the network status parameter data of each device into the response delay time window prediction model.

[0014] When the device receives a response request, it waits for the predicted response delay before responding.

[0015] After receiving the response, the server sends an ACK to the corresponding device. If the device does not receive the ACK within a preset time, the retransmission process is executed until the device receives the ACK within the preset time or the preset maximum number of retransmissions is reached.

[0016] In a preferred embodiment of the present invention, the network status parameter data of the device includes latency and packet loss rate.

[0017] In a preferred embodiment of the present invention, the response delay time window prediction model is constructed based on the random forest model.

[0018] As a preferred embodiment of the present invention, network state parameter data derived features are constructed, and the derived features specifically include moving average features, standard deviation, and range.

[0019] The moving average feature The calculation formula is:

[0020]

[0021] in: Indicates the first One data sampling point; Indicates the size of the sampling window; Indicates the first Network status parameter data;

[0022] The standard deviation The calculation formula is:

[0023]

[0024] The range The calculation formula is:

[0025]

[0026] The network state parameter data and its derived features are input into the response delay time window prediction model for training.

[0027] In a preferred embodiment of the present invention, after optimizing the parameters of the response delay time window prediction model using a grid search algorithm, K-fold cross-validation is used to evaluate the model performance. When the evaluation result reaches a preset threshold, training is stopped.

[0028] As a preferred embodiment of the present application, the response request sent by the server comprises a unique identifier of the target device, and the device responds through the unique identifier.

[0029] As a preferred embodiment of the present application, the response delay time window prediction model and the device failure prediction model are respectively constructed based on a hierarchical random forest model.

[0030] The ACK reception rate, hardware state and communication module state of the device are collected and combined with the network state parameter data of the device to form a failure prediction data set.

[0031] The failure prediction data set is input into the device failure prediction model to predict the failure condition of the device, and corresponding measures are taken according to the failure condition of the device.

[0032] As a preferred embodiment of the present application, the measures specifically include prolonging the response delay, increasing the maximum number of retransmissions, and sending warning information.

[0033] On the other hand, the present application also provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method according to any one of the embodiments of the present application when executing the program.

[0034] In another aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method according to any one of the embodiments of the present application.

[0035] The present application has the following advantages:

[0036] 1. After receiving the response request, the device responds according to the optimal delay time predicted by the random forest model, effectively avoiding data packet collision caused by multiple devices sending responses at the same time.

[0037] 2. The present application can identify potential high packet loss or high delay risk in advance by analyzing network behavior data and operation logs in real time according to the random forest model, and take preventive measures such as prolonging the response delay or actively retrying. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 The present application is a method flowchart. DETAILED DESCRIPTION

[0039] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0040] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0041] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0042] The terms "comprise" and "include" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0043] The term "and / or" means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0044] Embodiment one:

[0045] Referring to Figure 1 A dynamic optimization device response method based on a local area network in a network configuration process, comprising the following steps:

[0046] After the device accesses the WI-FI local area network through the AP, the device sends a multicast packet to the server in the local area network to declare its access to the local area network, and the server (in this embodiment, the server is an APP) sends a response request to each device in the local area network through UDP multicast (multicast can reduce repeated sending of requests and improve network utilization);

[0047] Real-time monitoring of network state parameter data of each device in the local area network;

[0048] Constructing a response delay time window prediction model, inputting the network state parameter data of each device into the response delay time window prediction model to obtain the response delay of each device;

[0049] When the device receives the response request, it waits for a response according to the predicted response delay;

[0050] After receiving the response, the server sends an ACK (Acknowledgement, which is used to confirm that the data packet has been successfully received) to the corresponding device. If the device does not receive the ACK within a preset time, the retransmission process is executed until the device receives the ACK within the preset time or the preset maximum number of retransmissions is reached.

[0051] In a preferred embodiment of this invention, the network status parameter data of the device includes latency and packet loss rate.

[0052] In a preferred embodiment of this invention, the response delay time window prediction model is constructed based on a random forest model.

[0053] As a preferred embodiment of this example, network state parameter data derived features are constructed, and the derived features specifically include moving average features, standard deviation, and range.

[0054] The moving average feature The calculation formula is:

[0055]

[0056] in: Indicates the first One data sampling point; Indicates the first In this embodiment, network status parameter data, latency and packet loss rate are calculated separately;

[0057] The standard deviation The calculation formula is:

[0058]

[0059] The range The calculation formula is:

[0060]

[0061] The network state parameter data and its derived features are input into the response delay time window prediction model for training.

[0062] In a preferred embodiment of this invention, after optimizing the parameters of the response delay time window prediction model using a grid search algorithm or a Bayesian optimization algorithm, K-fold cross-validation is used to evaluate the model performance. When the evaluation result reaches a preset threshold, training is stopped.

[0063] In a preferred embodiment of this invention, the response request sent by the server includes a unique identifier of the target device (such as a MAC address or UUID). The device responds using the unique identifier to avoid interference from unrelated devices.

[0064] As a preferred embodiment of the present embodiment, a response delay time window prediction model and a device failure prediction model are respectively constructed based on a hierarchical random forest model;

[0065] The ACK reception rate, hardware state and communication module state of the device are collected and combined with the network state parameter data of the device to form a failure prediction data set;

[0066] The failure prediction data set is input into the device failure prediction model to predict the failure condition of the device, and corresponding measures are taken according to the failure condition of the device.

[0067] As a preferred embodiment of the present embodiment, the measures specifically include: prolonging the response delay, increasing the maximum number of retransmissions, and sending warning information.

[0068] In the present embodiment, the device periodically reports state information in batch to the server through multicast or broadcast mode, for example: device identifier, network distribution state, IP address, running state, etc., for subsequent operation and maintenance management.

[0069] Embodiment two:

[0070] The present embodiment proposes an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method according to any embodiment of the present application when executing the program.

[0071] Embodiment three:

[0072] The present embodiment proposes a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the method according to any embodiment of the present application.

[0073] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship between the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the cases of A alone, A and B together, and B alone. Wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, and c can be single or multiple.

[0074] Those skilled in the art can clearly understand that the units and algorithm steps described in the embodiments disclosed herein can be realized by electronic hardware, computer software and a combination of electronic hardware and computer software. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0076] In several embodiments provided in the present application, any function realized in the form of a software function unit and sold or used as an independent product can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part of the prior art or the part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory; hereinafter referred to as: ROM), a random access memory (Random Access Memory; hereinafter referred to as: RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0077] The above is only an embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, based on the content of the specification and drawings of the present application, are also included in the patent protection scope of the present application.

Claims

1. A method for dynamically optimizing device response based on a local area network in a network configuration process, characterized in that, The method comprises the following steps: After the device accesses the local area network, the device sends a multicast packet to a server in the local area network to declare that the device accesses the local area network, and the server sends a response request to each device in the local area network through a UDP multicast; Real-time monitoring of network state parameter data of each device in the local area network; A response delay time window prediction model is constructed, and the network state parameter data of each device is input into the response delay time window prediction model to obtain the response delay of each device; When the device receives the response request, the device waits for a period of time according to the predicted response delay and then responds; After the server receives the response, the server sends an ACK to the corresponding device, and if the device does not receive the ACK within a preset time, the device performs a retransmission process until the device receives the ACK within the preset time or reaches a preset maximum retransmission number.

2. The method of claim 1, wherein the method is a method of dynamically optimizing device response in a network configuration process based on a local area network, characterized in that, The network state parameter data of the device includes delay and packet loss rate.

3. The method of claim 2, wherein the method further comprises: The response delay time window prediction model is constructed based on a random forest model.

4. The method of claim 3, wherein the method further comprises: Network state parameter data derivative features are constructed, and the derivative features specifically include a moving average feature, a standard deviation, and a range; The moving average feature The calculation formula is: wherein: represents the th data sample point; represents the th network state parameter data; The standard deviation The formula for calculating the standard deviation is: The range The formula for calculating the range is: The network state parameter data and the derivative features are input into the response delay time window prediction model for training.

5. The method of claim 3, wherein the method further comprises: After the parameters of the response delay time window prediction model are optimized through a grid search algorithm, the performance of the model is evaluated using K-fold cross-validation, and when the evaluation result reaches a preset threshold, the training is stopped.

6. The method of claim 1, wherein the method is a method of dynamic optimization of device response in a network configuration process based on a local area network. The response request sent by the server includes a unique identifier of the target device, and the device responds through the unique identifier.

7. The method of claim 3, wherein the method further comprises: A hierarchical random forest model is used to construct a response delay time window prediction model and a device failure prediction model; The ACK reception rate, hardware state, and communication module state of the device are collected and combined with the network state parameter data of the device to form a failure prediction data set; The failure prediction data set is input into the device failure prediction model to predict the failure condition of the device, and corresponding measures are taken according to the failure condition of the device.

8. The method of claim 7, wherein the method further comprises: The measures specifically include extending the response delay, increasing the maximum retransmission number, and sending a warning message.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the method of any one of claims 1 to 8.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1 to 8.

Images