Adaptive method and device for communication mode in Internet of Things system
By preprocessing and machine learning prediction of the environment parameters and channel state data of the Internet of Things system, dynamically adjusting the communication methods and parameters, the stability and reliability problems of traditional Internet of Things communication in extreme environments are solved, and more efficient data transmission is achieved.
Patent Information
- Application Number
- CN202510063348.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-15
- Publication Date
- 2025-05-06
AI Technical Summary
Traditional IoT communication methods are difficult to ensure the stability and reliability of data transmission in complex and changeable extreme environments, and are limited by factors such as signal attenuation, electromagnetic interference, physical obstacles and environmental changes.
By preprocessing the environmental parameter data and channel status data monitored by the Internet of Things system, outliers and noise are removed, characteristic values are extracted, and input them into the preset machine learning model for prediction, and dynamically adjust the communication method and communication parameters according to the prediction results to achieve the preset performance level.
Ensure that the IoT system always maintains the best working state under different environmental conditions, improves the stability and reliability of data transmission, and enhances the robustness and adaptability of the system.
Smart Images
Figure CN119946088A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet of Things, and specifically to a method and device for adaptively controlling communication modes in an Internet of Things system. Background Art
[0002] With the rapid development of IoT technology, its application scope has expanded from daily life to industrial production, environmental protection, urban governance and other fields. In extreme environments such as polar regions, deep sea or space, the IoT system has an increasing demand for data collection, environmental monitoring and remote control. However, these special environments are often accompanied by complex geographical conditions and extreme environmental climates, which poses great challenges to traditional IoT communication methods.
[0003] Traditional IoT communication methods usually use a single communication method, such as Wi-Fi, Bluetooth or ZigBee. These technologies perform well in ordinary environments, but are incapable of doing so in complex and changeable extreme environments. For example, Wi-Fi suffers from severe signal attenuation during long-distance transmission, while ZigBee is prone to data packet loss when the network is congested. In addition, factors such as electromagnetic interference, physical obstacles and temperature changes in extreme environments can seriously affect the quality of communication. Using only one communication method makes it difficult to ensure the stability and reliability of data transmission in complex and changeable extreme environments. Summary of the invention
[0004] The present application provides an adaptive method and device for a communication mode in an Internet of Things system, which can dynamically adjust the communication mode in the Internet of Things system according to environmental parameter data and channel status data to ensure the stability and reliability of data transmission.
[0005] In a first aspect, an embodiment of the present application provides an adaptive method for a communication mode in an Internet of Things system, the method comprising:
[0006] Preprocessing the environmental parameter data and channel status data monitored by the IoT system, removing abnormal values and noise in the environmental parameter data and channel status data, and extracting characteristic values from the processed environmental parameter data and channel status data; the environmental parameter data includes temperature and humidity; the channel status data includes signal strength and channel noise;
[0007] Inputting the characteristic value into a preset machine learning model, predicting the data transmission situation of the Internet of Things system through the preset machine learning model, and obtaining a prediction result;
[0008] The communication mode and communication parameters of the Internet of Things system are adjusted according to the prediction results so that the Internet of Things system reaches a preset performance level.
[0009] In combination with the first aspect, in one implementation, adjusting the communication mode and communication parameters of the Internet of Things system according to the prediction result so that the Internet of Things system reaches a preset performance level includes:
[0010] adjusting the communication mode of the IoT system according to the prediction result;
[0011] Selecting preset communication parameters corresponding to the adjusted communication mode from a preset communication parameter library;
[0012] The preset communication parameters are adjusted according to the channel status data monitored by the Internet of Things system so that the Internet of Things system reaches a preset performance level; the preset communication parameters include signal power, signal frequency and signal modulation method.
[0013] In combination with the first aspect, in one embodiment, the preset machine learning model is one of linear regression, decision tree, random forest and neural network.
[0014] In combination with the first aspect, in one implementation, after extracting the characteristic value from the processed environmental parameter data and channel state data, the method further includes:
[0015] Construct a network topology diagram based on the location and connection relationship of network nodes in the IoT system;
[0016] When a faulty network node is detected in the network topology map, a network path that cannot transmit data due to the faulty network node is replanned, and tasks of the faulty network node are allocated to non-faulty network nodes in the network topology map.
[0017] In combination with the first aspect, in one implementation, a method for detecting a faulty network node includes a heartbeat mechanism and a response timeout.
[0018] In combination with the first aspect, in one implementation, when the Internet of Things system reaches a preset performance level, it further includes:
[0019] The IoT system continuously collects various quality indicators of the channel, including bit error rate, packet loss rate and latency.
[0020] When any quality indicator does not meet the preset standard, the IoT system reselects the frequency band, adjusts the transmission rate, or switches to an alternative transmission path.
[0021] In combination with the first aspect, in one implementation, before the sending end of the Internet of Things system sends data, it also includes:
[0022] Perform RS (Reed-Solomon) encoding or LDPC (Low Density Parity Check Codes) encoding on the original data to be sent to generate redundant data;
[0023] Combining the original data and the redundant data into a first data packet;
[0024] The sending end of the Internet of Things system sends a first data packet.
[0025] In combination with the first aspect, in one implementation, after the receiving end of the Internet of Things system receives the data, it also includes:
[0026] Decoding the first data packet into original data and redundant data;
[0027] Perform CRC (Cyclic Redundancy Check) check on the original data. If there is erroneous data in the original data, correct the erroneous data in the original data according to the redundant data.
[0028] In combination with the first aspect, in one implementation, when the proportion of erroneous data in the original data exceeds a preset proportion threshold, the method further includes:
[0029] The receiving end of the IoT system sends a retransmission request to the sending end of the IoT system.
[0030] In a second aspect, an embodiment of the present application provides an adaptive device for a communication mode in an Internet of Things system, the device comprising:
[0031] A preprocessing module is used to preprocess the environmental parameter data and channel status data monitored by the IoT system, remove abnormal values and noise in the environmental parameter data and channel status data, and extract characteristic values from the processed environmental parameter data and channel status data;
[0032] A prediction module, used to input the characteristic value into a preset machine learning model, predict the data transmission situation of the Internet of Things system through the preset machine learning model, and obtain a prediction result;
[0033] The adjustment module is used to adjust the communication mode and communication parameters of the Internet of Things system according to the prediction result so that the Internet of Things system reaches a preset performance level.
[0034] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:
[0035] This application preprocesses environmental parameter data and channel state data to remove outliers and noise, ensure the data quality of the input machine learning model, and thus improve the accuracy of the machine learning model prediction. By adjusting the communication mode and communication parameters according to the prediction results of the machine learning model, the IoT system can always maintain the best working state under different environmental conditions, thereby ensuring the stability and reliability of data transmission. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 A schematic diagram of a flow chart of a method for self-adapting a communication mode in an Internet of Things system according to an embodiment of the present application;
[0037] Figure 2 This is a schematic diagram of the structure of an adaptive device for communication mode in an Internet of Things system according to an embodiment of the present application;
[0038] Figure 3 This is a schematic diagram of the structure of a self-healing network module of a communication mode adaptive device in an Internet of Things system according to an embodiment of the present application;
[0039] Figure 4 This is a structural schematic diagram of a robustness enhancement module of an adaptive device for communication mode in an Internet of Things system in an embodiment of the present application. DETAILED DESCRIPTION
[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0042] First, please refer to Figure 1 , Figure 1 The flowchart of the adaptive method of the communication mode in the Internet of Things system of the present application embodiment is as follows. The adaptive method of the communication mode in the Internet of Things system provided by the present embodiment includes the following steps:
[0043] Step S1: pre-process the environmental parameter data and channel status data monitored by the Internet of Things system, remove outliers and noise in the environmental parameter data and channel status data, and extract feature values from the processed environmental parameter data and channel status data.
[0044] The above environmental parameter data include temperature and humidity, and the above channel status data include signal strength and channel noise.
[0045] Step S2: Input the characteristic value into a preset machine learning model, and predict the data transmission situation of the Internet of Things system through the preset machine learning model to obtain a prediction result.
[0046] Step S3: adjusting the communication mode and communication parameters of the IoT system according to the prediction results, so that the IoT system reaches a preset performance level.
[0047] This method removes outliers and noise by preprocessing environmental parameter data and channel state data, ensuring the data quality of the input machine learning model, thereby improving the accuracy of the machine learning model prediction. By adjusting the communication mode and communication parameters according to the prediction results of the machine learning model, the Internet of Things system can always maintain the best working state under different environmental conditions, thereby ensuring the stability and reliability of data transmission.
[0048] In some embodiments, in the above step S1, after extracting the characteristic value from the processed environmental parameter data and channel state data, the following steps are further included:
[0049] According to the location and connection relationship of network nodes in the Internet of Things system, a network topology map is constructed. When a faulty network node is detected in the network topology map, the network path that cannot transmit data due to the faulty network node is replanned, and the tasks of the faulty network node are assigned to the healthy network nodes in the network topology map.
[0050] In some embodiments, the method of detecting a failed network node includes a heartbeat mechanism and a response timeout.
[0051] In some embodiments, in the above step S2, the preset machine learning model is one of linear regression, decision tree, random forest and neural network.
[0052] In some embodiments, in the above step S3, adjusting the communication mode and communication parameters of the Internet of Things system according to the prediction result so that the Internet of Things system reaches a preset performance level includes the following steps:
[0053] S31: Adjusting the communication mode of the Internet of Things system according to the prediction result.
[0054] S32: Selecting preset communication parameters corresponding to the adjusted communication mode from a preset communication parameter library.
[0055] S33: Adjust preset communication parameters according to the channel status data monitored by the IoT system, so that the IoT system reaches a preset performance level.
[0056] The above preset communication parameters include signal power, signal frequency and signal modulation mode.
[0057] In some embodiments, in the above step S31, the communication method includes LoRa, NB-IoT and satellite communication.
[0058] In some embodiments, in the above step S33, when the IoT system reaches a preset performance level, the following steps are further included:
[0059] The IoT system continuously collects various quality indicators of the channel, including bit error rate, packet loss rate and latency. When any quality indicator does not meet the preset standard, the IoT system reselects the frequency band, adjusts the transmission rate or switches to an alternative transmission path.
[0060] In some embodiments, before the sending end of the Internet of Things system sends data, the following steps are also included:
[0061] The original data to be sent is RS-encoded or LDPC-encoded to generate redundant data, and the original data and the redundant data are combined into a first data packet. The transmitting end of the Internet of Things system then sends the first data packet.
[0062] In some embodiments, after the receiving end of the Internet of Things system receives the data, the following steps are also included:
[0063] The first data packet is decoded into original data and redundant data, and then a CRC check is performed on the original data. If erroneous data exists in the original data, the erroneous data in the original data is corrected according to the redundant data.
[0064] In some embodiments, when the proportion of erroneous data in the original data exceeds a preset proportion threshold, the following steps are further included:
[0065] The receiving end of the IoT system sends a retransmission request to the sending end of the IoT system.
[0066] Second, please refer to Figure 2 , Figure 2 This is a schematic diagram of the structure of the adaptive device of the communication mode in the Internet of Things system of the present application embodiment. The adaptive device of the communication mode in the Internet of Things system provided by this embodiment includes a preprocessing module, a prediction module and an adjustment module, wherein:
[0067] The preprocessing module is used to preprocess the environmental parameter data and channel status data monitored by the Internet of Things system, remove abnormal values and noise in the environmental parameter data and channel status data, and extract feature values from the processed environmental parameter data and channel status data.
[0068] The prediction module is used to input the feature value into the preset machine learning model, predict the data transmission situation of the Internet of Things system through the preset machine learning model, and obtain the prediction result.
[0069] The adjustment module is used to adjust the communication mode and communication parameters of the Internet of Things system according to the prediction results, so that the Internet of Things system reaches a preset performance level.
[0070] The device preprocesses environmental parameter data and channel status data through a preprocessing module to remove outliers and noise, ensure the data quality of the input machine learning model, and thus improve the accuracy of the prediction of the machine learning model. The feature value is input into the preset machine learning model through the prediction module, and the data transmission of the Internet of Things system is predicted through the preset machine learning model to obtain the prediction result. The adjustment module adjusts the communication mode and communication parameters according to the prediction result of the machine learning model, which can ensure that the Internet of Things system always maintains the best working state under different environmental conditions, thereby ensuring the stability and reliability of data transmission.
[0071] In some embodiments, the preprocessing module includes a data acquisition unit, a feature extraction unit and a model training unit, wherein:
[0072] The data acquisition unit is used to collect environmental parameter data and channel status data in real time through sensors in the Internet of Things system.
[0073] The feature extraction unit is used to remove abnormal values and noise in the environmental parameter data and the channel state data, and to extract feature values from the processed environmental parameter data and the channel state data.
[0074] The model training unit is used to train a machine learning model using the historical data collected by the data collection unit. The machine learning model is one of a decision tree, a random forest and a neural network.
[0075] In some embodiments, the adjustment module includes a parameter library, a parameter selection unit and a dynamic adjustment unit, wherein:
[0076] The parameter library contains preset communication parameters for various communication modes, and each communication mode corresponds to a set of preset communication parameters.
[0077] The parameter selection unit is used to select preset communication parameters corresponding to the selected communication mode from a parameter library according to the selected communication mode.
[0078] The dynamic adjustment unit is used to dynamically adjust communication parameters according to the real-time monitored channel status data to adapt to the changing environmental conditions.
[0079] In some embodiments, the adaptive communication device in the IoT system further includes a self-healing network module. For specific structure, please refer to Figure 3, Figure 3 This is a schematic diagram of the structure of a self-healing network module of an adaptive device for communication mode in an Internet of Things system according to an embodiment of the present application.
[0080] exist Figure 3 In the self-healing network module, the network topology management submodule, the fault detection and recovery submodule and the network status monitoring submodule are included, among which:
[0081] The network topology management submodule includes a node discovery unit, a topology construction unit, a topology update unit and a status monitoring unit.
[0082] The fault detection and recovery submodule includes a fault detection and isolation unit, a path recalculation unit, a task reallocation unit and a recovery mechanism unit.
[0083] The network status monitoring submodule includes a real-time monitoring unit, an alarm unit, a log recording unit and a visual display unit.
[0084] The node discovery unit is used to automatically discover new nodes in the network and add the new nodes to the network topology map.
[0085] The topology construction unit is used to construct a network topology diagram according to the location and connection relationship of the nodes.
[0086] The topology update unit is used to update the network topology map in real time to reflect the addition, deletion and status changes of nodes.
[0087] The status monitoring unit is used to continuously monitor the status of each node and record the node's online, offline, and fault information.
[0088] The fault detection and isolation unit is used to detect node failures through heartbeat mechanisms, response timeouts, etc., isolate the faulty nodes from the network, and prevent the fault from spreading.
[0089] The path recalculation unit is used to recalculate the network path when a node failure is detected to ensure the connectivity of data transmission.
[0090] The task reallocation unit is used to reallocate the tasks of the faulty nodes to other healthy nodes in the network topology to ensure the continuous execution of the tasks.
[0091] The recovery mechanism unit is used to automatically rejoin the failed node to the network and restore its tasks and paths after the failed node is recovered.
[0092] The real-time monitoring unit is used to continuously monitor the overall status of the network, including information such as node status, link status, and data transmission rate.
[0093] The alarm unit is used to trigger the alarm mechanism when the network status is abnormal, notify the administrator or take automatic measures.
[0094] The logging unit is used to record network status changes and event logs, and is also used for troubleshooting and performance analysis.
[0095] The visualization unit is used to display the network status through a graphical interface, providing an intuitive network topology view and key indicators.
[0096] In some embodiments, the adaptive device for the communication mode in the above-mentioned Internet of Things system further includes a robustness enhancement module. For specific structure, please refer to Figure 4 , Figure 4 This is a structural schematic diagram of a robustness enhancement module of an adaptive device for communication mode in an Internet of Things system in an embodiment of the present application.
[0097] exist Figure 4 In the embodiment, the robustness enhancement module includes a forward error correction submodule and an automatic retransmission request submodule, wherein:
[0098] The forward error correction submodule includes a redundant information generation unit, an encoding unit, a transmission unit and a decoding unit.
[0099] The automatic retransmission request submodule includes an error detection unit, a confirmation unit, a retransmission request unit, a retransmission unit and a retransmission counting unit.
[0100] The redundant information generating unit is used to generate redundant information at the transmitting end of the Internet of Things system by using a coding method such as RS coding or LDPC coding.
[0101] The encoding unit is used to combine the original data and the redundant information into an encoded data packet.
[0102] The transmission unit is used to send the encoded data packets to the receiving end of the IoT system.
[0103] The decoding unit is used to decode the received data packets at the receiving end of the IoT system and use the decoded redundant information to correct errors that may occur during the transmission process.
[0104] The error detection unit is used to detect the integrity of the data packet using CRC check or other check methods at the receiving end.
[0105] The confirmation unit is used to send a confirmation message to the sending end after confirming that the received data packet has no errors.
[0106] The retransmission request module is used to send a retransmission request to the sender after confirming that the received data packet has an error.
[0107] The retransmission unit is used to resend the data packet after receiving the retransmission request at the sending end.
[0108] The retransmission counting unit is used to record the number of retransmissions to prevent infinite retransmissions from wasting system resources.
[0109] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.
[0110] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.
[0111] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.
[0112] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.
[0113] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.
[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.
[0115] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. An adaptive method for communication mode in an Internet of Things system, characterized in that: The method comprises: Preprocessing the environmental parameter data and channel status data monitored by the IoT system, removing abnormal values and noise in the environmental parameter data and channel status data, and extracting characteristic values from the processed environmental parameter data and channel status data; the environmental parameter data includes temperature and humidity; the channel status data includes signal strength and channel noise; Inputting the characteristic value into a preset machine learning model, predicting the data transmission situation of the Internet of Things system through the preset machine learning model, and obtaining a prediction result; The communication mode and communication parameters of the Internet of Things system are adjusted according to the prediction results so that the Internet of Things system reaches a preset performance level.
2. The adaptive method for communication mode in the Internet of Things system according to claim 1, characterized in that: The communication mode and communication parameters of the Internet of Things system are adjusted according to the prediction result so that the Internet of Things system reaches a preset performance level, including: adjusting the communication mode of the IoT system according to the prediction result; Selecting preset communication parameters corresponding to the adjusted communication mode from a preset communication parameter library; The preset communication parameters are adjusted according to the channel status data monitored by the Internet of Things system so that the Internet of Things system reaches a preset performance level; the preset communication parameters include signal power, signal frequency and signal modulation method.
3. The adaptive method for communication mode in the Internet of Things system according to claim 1, characterized in that: The preset machine learning model is one of linear regression, decision tree, random forest and neural network.
4. The adaptive method for communication mode in the Internet of Things system according to claim 1, characterized in that: After extracting the feature values from the processed environmental parameter data and channel status data, it also includes: Construct a network topology diagram based on the location and connection relationship of network nodes in the IoT system; When a faulty network node is detected in the network topology map, a network path that cannot transmit data due to the faulty network node is replanned, and tasks of the faulty network node are allocated to non-faulty network nodes in the network topology map.
5. The adaptive method for communication mode in the Internet of Things system according to claim 4, characterized in that: Ways to detect failed network nodes include heartbeat mechanisms and response timeouts.
6. The adaptive method for communication mode in the Internet of Things system according to claim 1, characterized in that: When the IoT system reaches a preset performance level, it also includes: The IoT system continuously collects various quality indicators of the channel, including bit error rate, packet loss rate and latency. When any quality indicator does not meet the preset standard, the IoT system reselects the frequency band, adjusts the transmission rate, or switches to an alternative transmission path.
7. The adaptive method for communication mode in the Internet of Things system according to claim 1, characterized in that: Before the sending end of the IoT system sends data, it also includes: Perform RS encoding or LDPC encoding on the original data to be sent to generate redundant data; Combining the original data and the redundant data into a first data packet; The sending end of the Internet of Things system sends a first data packet.
8. The adaptive method for communication mode in the Internet of Things system according to claim 7, characterized in that: When the receiving end of the IoT system receives data, it also includes: Decoding the first data packet into original data and redundant data; Perform CRC check on the original data. If there is erroneous data in the original data, correct the erroneous data in the original data according to the redundant data.
9. The adaptive method for communication mode in the Internet of Things system according to claim 8, characterized in that: When the proportion of erroneous data in the original data exceeds the preset proportion threshold, it also includes: The receiving end of the IoT system sends a retransmission request to the sending end of the IoT system.
10. An adaptive device for communication mode in an Internet of Things system based on the method according to any one of claims 1 to 9, characterized in that: The device comprises: A preprocessing module is used to preprocess the environmental parameter data and channel status data monitored by the IoT system, remove abnormal values and noise in the environmental parameter data and channel status data, and extract characteristic values from the processed environmental parameter data and channel status data; A prediction module, used to input the characteristic value into a preset machine learning model, predict the data transmission situation of the Internet of Things system through the preset machine learning model, and obtain a prediction result; The adjustment module is used to adjust the communication mode and communication parameters of the Internet of Things system according to the prediction result so that the Internet of Things system reaches a preset performance level.