A LoRa wireless resource allocation method, device and storage medium

Abstract

This application discloses a LoRa wireless resource allocation method, apparatus, and storage medium. The method includes: acquiring node information and channel information forwarded by a gateway; obtaining a corresponding adjustment strategy through a neural network based on the node information and the channel information; setting node parameter values ​​according to the adjustment strategy and sending them to the gateway; generating a corresponding reward value and a next state based on a preset reward function; placing the reward value and the next state into an experience pool; and training and updating the neural network based on the data in the experience pool. This reduces the collision rate of data in the LoRa channel, reduces transmission latency, and increases the number of IoT devices that can be connected to a single gateway.

Description

Technical Field

[0001] This application relates to the Internet of Things (IoT) field, and in particular to a LoRa wireless resource allocation method, apparatus, and storage medium. Background Technology

[0002] LoRa is a spread spectrum modulation technology, also known as Chirp modulation. LoRa features long transmission distance, strong anti-interference capability, low power consumption, and on-demand networking. Currently, it has been widely used in the market, for example in agricultural and livestock plant tracking and monitoring, and forest and building environmental information monitoring. LoRaWAN is a communication protocol and system architecture launched by the LoRa Alliance. Its network components mainly include terminal nodes, gateways, network servers, and application servers.

[0003] In related technologies, LoRa's uplink communication between terminal nodes and gateways uses the ALOHA mechanism. Users are allowed to send data whenever they have it, which can lead to collisions and frame corruption. Because broadcast channels have feedback capabilities, the sender can perform collision detection during data transmission, comparing the received data with the data in the buffer to determine if the data frame is corrupted. Similarly, other users operate in the same manner. If the sender knows that a data frame has been corrupted (i.e., a collision has been detected), it can wait a randomly long period before retransmitting the frame. As the number of uplink messages transmitted by users increases, the number of data packets with detected collisions in the channel will increase exponentially, which is detrimental to some services with time-sensitive requirements.

[0004] Therefore, the aforementioned technical problems in the relevant technologies urgently need to be solved. Summary of the Invention

[0005] This application aims to solve the technical problems in related technologies. To this end, embodiments of this application provide a LoRa wireless resource allocation method, apparatus, and storage medium, which can reduce data collision rate, reduce communication latency, and thereby increase the number of gateway nodes that can access the network.

[0006] According to one aspect of an embodiment of this application, a LoRa wireless resource allocation method is provided, the method comprising:

[0007] Obtain the node information and channel information forwarded by the gateway;

[0008] Based on the node information and the channel information, a corresponding adjustment strategy is obtained through a neural network;

[0009] The node parameter values ​​are set according to the adjustment strategy and sent to the gateway, and the corresponding reward value and the next state are generated according to the preset reward function;

[0010] Add the reward value and the next state to the experience pool;

[0011] The neural network is trained and updated based on the data in the experience pool.

[0012] In one embodiment, before obtaining the node information and channel information forwarded by the gateway, the method further includes:

[0013] Detect whether data collisions occur in the channel;

[0014] If no collision occurs in the channel, the receiving node sends the data and forwards it to the server.

[0015] In one embodiment, after the server receives the data, the method further includes:

[0016] The data is parsed to obtain node information and channel information.

[0017] In one embodiment, after the gateway receives the node parameter value, the method further includes:

[0018] MAC commands are sent to the node based on the node parameter values ​​to adjust the node's parameter settings.

[0019] In one embodiment, obtaining the corresponding adjustment strategy through a neural network based on the node information and the channel information includes:

[0020] Based on the node information and the channel information, an adjustment action is obtained through a neural network. The adjustment action is the action of the node dynamically adjusting the spreading factor and bandwidth and deciding whether to perform channel switching.

[0021] In one embodiment, the step of generating a corresponding reward value and a next state based on a preset reward function includes: environmental state information, the corresponding action, the new environmental state, and the reward value generated by the adjusted reward function.

[0022] In one embodiment, the method further includes:

[0023] The process of adding the reward value and the next state to the experience pool is considered an interaction.

[0024] If the number of interactions reaches a preset number, data is retrieved from the experience pool to train and update the neural network.

[0025] According to one aspect of an embodiment of this application, a LoRa wireless resource allocation device is provided, the device comprising:

[0026] The first module is used to obtain node information and channel information forwarded by the gateway;

[0027] The second module is used to obtain a corresponding adjustment strategy through a neural network based on the node information and the channel information;

[0028] The third module is used to set node parameter values ​​according to the adjustment strategy and send them to the gateway, and generate corresponding reward values ​​and the next state according to the preset reward function;

[0029] The fourth module is used to put the reward value and the next state into the experience pool;

[0030] The fifth module is used to train and update the neural network based on the data in the experience pool.

[0031] According to one aspect of an embodiment of this application, a LoRa wireless resource allocation device is provided, the device comprising:

[0032] At least one processor;

[0033] At least one memory for storing at least one program;

[0034] When at least one of the programs is executed by at least one of the processors, a LoRa wireless resource allocation method as described in any one of claims 1-7 is implemented.

[0035] According to one aspect of the embodiments of this application, a storage medium is provided, the storage medium storing a processor-executable program, which, when executed by a processor, implements a LoRa wireless resource allocation method as described in any one of claims 1-7.

[0036] The beneficial effects of the LoRa wireless resource allocation method, apparatus, and storage medium provided in this application are as follows: This application provides methods for obtaining node information and channel information forwarded by the gateway; obtaining a corresponding adjustment strategy through a neural network based on the node information and the channel information; setting node parameter values ​​according to the adjustment strategy and sending them to the gateway; generating a corresponding reward value and next state according to a preset reward function; placing the reward value and next state into an experience pool; training and updating the neural network based on the data in the experience pool, thereby reducing the collision rate of data in the LoRa channel, reducing transmission latency, and increasing the number of IoT devices that can be accessed by a single gateway.

[0037] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A flowchart illustrating a LoRa wireless resource allocation method provided in this application embodiment;

[0040] Figure 2 A flowchart illustrating a specific implementation of a LoRa wireless resource allocation method provided in this application embodiment;

[0041] Figure 3 A communication optimization flowchart of a LoRa wireless resource allocation method provided in this application embodiment;

[0042] Figure 4 A schematic diagram of a LoRa wireless resource allocation device provided in an embodiment of this application;

[0043] Figure 5 This is a schematic diagram of another LoRa wireless resource allocation device provided in an embodiment of this application. Detailed Implementation

[0044] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0045] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0046] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0047] LoRa is a spread spectrum modulation technology, also known as Chirp modulation. LoRa features long transmission distance, strong anti-interference capability, low power consumption, and on-demand networking. Currently, it has been widely used in the market, for example in agricultural and livestock plant tracking and monitoring, and forest and building environmental information monitoring. LoRaWAN is a communication protocol and system architecture launched by the LoRa Alliance. Its network components mainly include terminal nodes, gateways, network servers, and application servers.

[0048] In related technologies, LoRa's uplink communication between terminal nodes and gateways uses the ALOHA mechanism. Users are allowed to send data whenever they have it, which can lead to collisions and frame corruption. Because broadcast channels have feedback capabilities, the sender can perform collision detection during data transmission, comparing the received data with the data in the buffer to determine if the data frame is corrupted. Similarly, other users operate in the same manner. If the sender knows that a data frame has been corrupted (i.e., a collision has been detected), it can wait a randomly long period before retransmitting the frame. As the number of uplink messages transmitted by users increases, the number of data packets with detected collisions in the channel will increase exponentially, which is detrimental to some services with time-sensitive requirements.

[0049] In LoRaWAN, there are four main parameters affecting data collisions: bandwidth, spreading factor, time, and power. The choice of bandwidth and spreading factor affects the node's speed and transmission distance. A larger spreading factor results in a lower speed but a longer transmission distance. Therefore, in LoRaWAN, the primary consideration is to maximize the node's transmission speed while ensuring reachability. Thus, LoRaWAN tends to choose the optimal parameters to guarantee optimal transmission for a single node. This strategy keeps the collision rate within acceptable limits when the number of nodes is small. However, as the number of nodes increases, this strategy, while considering the optimal performance for a single node, fails to consider the global optimality, easily leading to a situation where one channel resource is overwhelmed while other channels remain idle. Currently, the industry has proposed some improvements to address this issue. For example, if a collision occurs, a random channel switch is performed during the next retransmission. However, this random channel switching method cannot guarantee that the switched channel will not experience collisions in large-scale connection scenarios.

[0050] To address the aforementioned issues, this application proposes a LoRa wireless resource allocation method, apparatus, and storage medium.

[0051] First, the technical terms that may appear in this instruction manual will be explained as follows:

[0052] LoRa: A physical layer modulation technology for linear frequency modulation spread spectrum, characterized by low power consumption, long transmission distance, and strong anti-interference capability.

[0053] LoRaWAN: LoRaWAN is a standard developed by the LoRa Alliance based on LoRa technology. This standard currently dominates the LoRa standard.

[0054] MAC layer: Media Access Control, responsible for handling the physical transmission or reception of media.

[0055] Deep reinforcement learning: Deep learning has strong perception capabilities but lacks decision-making ability; while reinforcement learning has decision-making ability but is helpless in perception problems. Therefore, combining the two, with their complementary advantages, provides a solution to the perception and decision-making problems of complex systems.

[0056] Experience pool: Its main function is to overcome the problems of correlated data and non-stationary distribution in empirical data. It works by randomly sampling from past state transitions (experience) for training. Advantages include the ability to reuse a single sample multiple times, resulting in high data utilization.

[0057] Figure 1 A flowchart of a LoRa wireless resource allocation method provided in this application embodiment is shown below. Figure 1 As shown, this application proposes a LoRa wireless resource allocation method, the method comprising:

[0058] S101. Obtain the node information and channel information forwarded by the gateway.

[0059] Optionally, before obtaining the node information and channel information forwarded by the gateway in step S101, the method further includes: detecting whether data collision occurs in the channel; if data collision does not occur in the channel, then receiving the data sent by the node and forwarding it to the server.

[0060] It should be noted that the AI ​​algorithm is designed to be embedded in the network server, and the LoRa gateway performs the forwarding function of the nodes. The LoRa nodes send uplink data based on the ALOHA mechanism. Only when the data does not collide in the channel can the LoRa gateway successfully receive the data sent by the node and forward it to the network server. After receiving the data, the server parses the data to obtain node information and channel information.

[0061] S102. Based on the node information and the channel information, a corresponding adjustment strategy is obtained through a neural network.

[0062] Step S102, which involves obtaining a corresponding adjustment strategy through a neural network based on the node information and the channel information, may specifically include: obtaining an adjustment action through a neural network based on the node information and the channel information, wherein the adjustment action is the action of the node dynamically adjusting the spreading factor and bandwidth and deciding whether to perform channel switching.

[0063] S103. Set the node parameter values ​​according to the adjustment strategy and send them to the gateway, and generate the corresponding reward value and the next state according to the preset reward function.

[0064] Optionally, when node parameter values ​​are sent to the gateway, the gateway, upon receiving these values, will send a MAC command to the node to adjust its parameter settings. Specifically, the gateway sends a MAC command when the node's receive window is open, thereby adjusting the channel parameter settings of each node to maximize the utilization of each channel resource and reduce the data collision rate.

[0065] In step S103, the corresponding reward value and the next state are generated according to the preset reward function. The reward value and the next state include: environmental state information, the corresponding action, the new environmental state, and the reward value generated by the adjusted reward function.

[0066] S104. Put the reward value and the next state into the experience pool.

[0067] S105. Train and update the neural network based on the data in the experience pool.

[0068] Optionally, the process of adding the reward value and the next state to the experience pool is considered as one interaction; if the number of interactions reaches a preset number, data is retrieved from the experience pool to train and update the neural network.

[0069] Figure 2 A flowchart illustrating a specific implementation of a LoRa wireless resource allocation method provided in this application is shown below. Figure 2 As shown, when applied to a specific process, the wireless resource allocation method proposed in this application operates as follows:

[0070] (1) The network server with embedded AI intelligent agent obtains node information and business information from the gateway as the state S of the environment.

[0071] (2) Based on these environmental state information S, the agent generates an action a according to the strategy it has learned, which dynamically adjusts the spreading factor and bandwidth of the node, i.e. whether to switch the channel.

[0072] (3) The adjustment in step (2) will dynamically change the communication status of the channel in the communication environment. The new communication environment status information is called S'. The adjusted communication status will be evaluated by a reward function set manually to obtain a reward value R, which is used to judge the quality of the adjustment.

[0073] (4) The above steps are called an interaction process between the agent and the environment. The generated data includes environmental state information S, the corresponding action a, the new environmental state S', and the R generated by the adjusted reward function. The four parameters will be stored in the experience pool as an interaction process. When the number of interactions reaches the set number, the data is taken out from the experience pool to update and optimize the strategy.

[0074] It should be noted that the parameter design for the specific states in step (1) is shown in Table 1 below:

[0075] Table 1 Parameter Design Table for Specific States

[0076]

[0077] It should be added that the specific data format design for the experience pool in step (4) above is shown in Table 2 below:

[0078] Table 2. Specific Data Format Design for the Experience Pool

[0079]

[0080] Furthermore, the method of extracting data from the experience pool in step (4) above is random extraction. The purpose of random extraction is to break the correlation between data and prevent data from getting trapped in a certain local interest maximization. Since the size of the experience pool is set to be limited, when the data is full, the oldest historical data is overwritten according to the FIFO (First-In-First-Out) strategy, and the latest data is retained.

[0081] The algorithms used in mainstream LoRaWAN employ optimal transmission strategies based on individual nodes, considering local optima but not global optima. This application utilizes deep reinforcement learning algorithms to embed intelligent agents into the network server on top of the existing LoRaWAN communication protocol. While maintaining the ALOHA mechanism, it dynamically adjusts nodes within the receiving window, significantly reducing the collision rate between nodes and improving resource utilization. Simultaneously, the number of devices that can be connected to a single gateway within the allowable collision rate is also greatly increased. This application primarily uses a deep reinforcement learning-based LoRaWAN network server to initialize and dynamically adjust the four parameters affecting the collision rate for nodes. The reinforcement learning algorithm is set up and embedded in the network server, solving the static allocation problem of traditional scheduling algorithms through dynamic adjustment of the allocation strategy.

[0082] Figure 3 A communication optimization flowchart for a LoRa wireless resource allocation method provided in this application embodiment is shown below. Figure 3 As shown, the AI ​​algorithm is embedded in the network server, and the LoRa gateway acts as a forwarding function for the nodes. LoRa nodes send uplink data based on the ALOHA mechanism. The LoRa gateway can only successfully receive and forward data to the network server if no collision occurs in the channel. Upon receiving the data, the network server parses it, including some channel parameter information. The AI ​​algorithm then provides corresponding adjustment strategies based on the node and channel information. These strategies are forwarded through the gateway, which sends MAC commands when the node's receive window is open, thereby adjusting the channel parameter settings of each node to maximize the utilization of channel resources and reduce the data collision rate.

[0083] Figure 4 A schematic diagram of a LoRa wireless resource allocation device provided in an embodiment of this application is shown below. Figure 4 As shown, the LoRa wireless resource allocation device provided in this application includes:

[0084] The first module 401 is used to obtain node information and channel information forwarded by the gateway;

[0085] The second module 402 is used to obtain a corresponding adjustment strategy through a neural network based on the node information and the channel information;

[0086] The third module 403 is used to set node parameter values ​​according to the adjustment strategy and send them to the gateway, and generate corresponding reward values ​​and the next state according to the preset reward function;

[0087] The fourth module 404 is used to put the reward value and the next state into the experience pool;

[0088] The fifth module 405 is used to train and update the neural network based on the data in the experience pool.

[0089] Figure 5 A schematic diagram of another LoRa wireless resource allocation device provided in the embodiments of this application is shown below. Figure 5 As shown, the LoRa wireless resource allocation device provided in this application includes:

[0090] At least one processor 501;

[0091] At least one memory 502, the memory 502 being used to store at least one program;

[0092] When at least one of the programs is executed by at least one of the processors 501, a LoRa wireless resource allocation method as described in the preceding embodiments is implemented.

[0093] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0094] In addition, this application also provides a storage medium storing a processor-executable program that, when executed by a processor, implements a LoRa wireless resource allocation method as described in the preceding embodiments.

[0095] Similarly, the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0096] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0097] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0098] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0099] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0100] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0101] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0102] In the foregoing description of this specification, the references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0103] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0104] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A LoRa wireless resource allocation method, characterized in that, The method comprises: The gateway detects whether the data collides in the channel; If the data does not collide in the channel, the gateway receives the data sent by the node and forwards to the server; The server receives the data and parses the data to obtain node information and channel information; The AI agent obtains the node information and the channel information forwarded by the gateway, and the AI agent is embedded in the server; The AI agent obtains the corresponding adjustment strategy through a neural network according to the node information and the channel information; The AI agent obtains the corresponding adjustment strategy through a neural network according to the node information and the channel information, comprising: the AI agent obtains an adjustment action through a neural network according to the node information and the channel information, wherein the adjustment action is an action of dynamically adjusting a spreading factor and a bandwidth of a node and deciding whether to perform channel switching; The AI agent sets node parameter values according to the adjustment strategy and sends them to the gateway, and generates a corresponding reward value and a next state according to a preset reward function; When the receiving window of the node is opened, the gateway sends a MAC command to the node according to the node parameter values, adjusts the parameter settings of the node, and the parameter settings are channel parameter settings of each node; The AI agent puts the reward value and the next state into an experience pool; The AI agent trains and updates the neural network according to the data in the experience pool; The AI agent puts the reward value and the next state into the experience pool as an interaction; If the number of interactions reaches a preset number, the AI agent extracts data from the experience pool to train and update the neural network, and the way of extracting data from the experience pool is random extraction.

2. The LoRa wireless resource allocation method of claim 1, wherein, The reward value and the next state generated according to the preset reward function include: environmental state information, corresponding generated actions, new environmental state, and reward value generated by the adjusted reward function.

3. A LoRa wireless resource allocation apparatus, characterized by, The device comprises: At least one processor; At least one memory for storing at least one program; When at least one program is executed by at least one processor, a LoRa wireless resource allocation method as claimed in any one of claims 1-2 is implemented.

4. Storage medium, characterized in that The storage medium stores a program executable by the processor, and the program executable by the processor is executed by the processor to implement a LoRa wireless resource allocation method as claimed in any one of claims 1-2.

Images