Data transmission method and apparatus, terminal device, and communication base station

Abstract

The application discloses a data transmission method and device, a terminal device and a communication base station, and belongs to the technical field of communication. The method is applied to a terminal device of an Internet of Things, and comprises the following steps: receiving a maximum data retransmission number sent by a communication base station of the Internet of Things, wherein the maximum data retransmission number is determined based on network load conditions of the Internet of Things; determining a data transmission time slot corresponding to to-be-transmitted data based on the maximum data retransmission number, a priority of the to-be-transmitted data and position information of the terminal device; and transmitting the to-be-transmitted data to the communication base station based on the maximum data retransmission number and the data transmission time slot. The method can perceive network load by the communication base station, determine the maximum data retransmission number, determine the data transmission time slot for data transmission in combination with the priority of the to-be-transmitted data and the position information of the device, effectively improve data transmission reliability, reduce a data packet loss rate, and guarantee the priority transmission of emergency data.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of communication, and particularly relates to a data transmission method and device, a terminal device and a communication base station. BACKGROUND

[0002] Industrial Internet of Things (IIoT) is the combination of Internet of Things system and data with manufacturing and other industrial processes, that is, the integration of Internet of Things technology and industrial automation system, aiming to improve automation, efficiency and productivity, with the characteristics of comprehensive perception, reliable transmission, intelligent processing, self-organization and self-maintenance, and its application covers intelligent transportation, smart grid, intelligent factory, intelligent environmental detection and many other fields.

[0003] Industrial Internet of Things has strong dependence on network, and pays more attention to data interaction compared with traditional industrial automation information system. Noise in transmission process and interference between users may cause data transmission failure, and retransmission means is usually used to improve transmission reliability. Common retransmission methods include K times retransmission, retransmission based on K times retransmission improvement, and retransmission based on binary exponential backoff algorithm, but the flexibility of data transmission strategy adjustment of these methods is low, the improvement of transmission reliability is limited, and the transmission of emergency data cannot be guaranteed. SUMMARY

[0004] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides a data transmission method, device, terminal device and communication base station, which flexibly adjusts the data transmission strategy according to the network state, transmits emergency data preferentially, and effectively improves the reliability of data transmission.

[0005] In a first aspect, the present application provides a data transmission method, which is applied to a terminal device of an Internet of Things, and the method comprises:

[0006] receiving the maximum data retransmission number sent by the communication base station of the Internet of Things, the maximum data retransmission number being determined based on the network load condition of the Internet of Things;

[0007] determining the data transmission time slot corresponding to the to-be-transmitted data based on the maximum data retransmission number, the priority of the to-be-transmitted data and the position information of the terminal device;

[0008] transmitting the to-be-transmitted data to the communication base station based on the maximum data retransmission number and the data transmission time slot.

[0009] According to the data transmission method, the network load is perceived by the communication base station, the maximum data retransmission number of the terminal device for data retransmission is determined, the terminal device determines the data transmission time slot for data transmission in combination with the priority of the to-be-transmitted data and the position information of the device itself, the data transmission strategy is flexibly adjusted according to the network state, the emergency data is preferentially transmitted, the reliability of data transmission is effectively improved, and the data packet loss rate is reduced.

[0010] According to an embodiment of the present application, the data transmission time slot corresponding to the to-be-transmitted data is determined based on the maximum data retransmission number, the priority of the to-be-transmitted data and the position information of the terminal device, and includes:

[0011] The data transmission time slot is determined by a deep reinforcement learning algorithm based on the maximum data retransmission number, the priority of the to-be-transmitted data and the position information of the terminal device.

[0012] According to an embodiment of the present application, the data transmission time slot is determined by a deep reinforcement learning algorithm based on the maximum data retransmission number, the priority of the to-be-transmitted data and the position information of the terminal device, and includes:

[0013] The action of the deep reinforcement learning algorithm is to select the transmission time slot for data transmission with the to-be-transmitted data;

[0014] The reward of the deep reinforcement learning algorithm is calculated based on the transmission result and the priority of the to-be-transmitted data, and the data transmission time slot is determined.

[0015] According to an embodiment of the present application, the to-be-transmitted data is transmitted to the communication base station based on the maximum data retransmission number and the data transmission time slot, and includes:

[0016] The to-be-transmitted data is transmitted to the communication base station by a time slot ALOHA access mode or an unlicensed spectrum access mode based on the maximum data retransmission number and the data transmission time slot.

[0017] In a second aspect, the present application provides a data transmission method, which is used for a communication base station of an Internet of Things, and includes:

[0018] Obtaining the network load condition of the Internet of Things;

[0019] Determining the maximum data retransmission number corresponding to a terminal device of the Internet of Things based on the network load condition;

[0020] Sending the maximum data retransmission number to the terminal device;

[0021] receive the to-be-transmitted data sent by the terminal device, wherein a data transmission time slot corresponding to the to-be-transmitted data is determined based on the maximum data retransmission number, the priority of the to-be-transmitted data, and the position information of the terminal device.

[0022] According to the data transmission method, the network load is perceived by the communication base station, the maximum data retransmission number of the terminal device is determined, the terminal device determines a data transmission time slot for data transmission in combination with the priority of the to-be-transmitted data and the position information of the terminal device, the data transmission strategy is flexibly adjusted according to the network state, the emergency data is preferentially transmitted, the reliability of data transmission is effectively improved, and the data packet loss rate is reduced.

[0023] According to an embodiment of the present application, the maximum data retransmission number corresponding to the terminal device of the Internet of Things is determined based on the network load condition, and the maximum data retransmission number corresponding to the terminal device of the Internet of Things is determined based on the network load condition.

[0024] The maximum data retransmission number corresponding to the terminal device is determined based on the network load condition by using a deep reinforcement learning algorithm.

[0025] According to an embodiment of the present application, the maximum data retransmission number corresponding to the terminal device is determined based on the network load condition by using a deep reinforcement learning algorithm.

[0026] The network load condition is used as a state of the deep reinforcement learning algorithm, a decision of the maximum retransmission number of the terminal device is made, a reward of the deep reinforcement learning algorithm is calculated based on a data transmission result, and the maximum data retransmission number is determined.

[0027] According to an embodiment of the present application, the network load condition of the Internet of Things is obtained, and the network load condition of the Internet of Things is obtained.

[0028] The device selection condition of a competitive transmission unit of the Internet of Things is obtained.

[0029] The channel collision condition of the competitive transmission unit is determined based on the device selection condition.

[0030] The network load condition is determined based on the channel collision condition.

[0031] In a third aspect, the present application provides a data transmission device, which is applied to a terminal device of an Internet of Things, and the device comprises:

[0032] A first receiving module is configured to receive a maximum data retransmission number sent by a communication base station of the Internet of Things, wherein the maximum data retransmission number is determined based on a network load condition of the Internet of Things.

[0033] The first processing module is configured to determine a data transmission time slot corresponding to the to-be-transmitted data based on the maximum data retransmission number, a priority of the to-be-transmitted data, and location information of the terminal device.

[0034] The first sending module is configured to transmit the to-be-transmitted data to the communication base station based on the maximum data retransmission number and the data transmission time slot.

[0035] In a fourth aspect, the present application provides a data transmission device, which is configured to be used in a communication base station of an Internet of Things, and the device comprises:

[0036] The acquisition module is configured to acquire a network load condition of the Internet of Things.

[0037] The second processing module is configured to determine a maximum data retransmission number corresponding to a terminal device of the Internet of Things based on the network load condition.

[0038] The second sending module is configured to send the maximum data retransmission number to the terminal device.

[0039] The second receiving module is configured to receive to-be-transmitted data sent by the terminal device, wherein a data transmission time slot corresponding to the to-be-transmitted data is determined based on the maximum data retransmission number, a priority of the to-be-transmitted data, and location information of the terminal device.

[0040] In a fifth aspect, the present application provides a terminal device, which comprises a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the data transmission method of the first aspect when executing the program.

[0041] In a sixth aspect, the present application provides a communication base station, which comprises a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the data transmission method of the second aspect when executing the program.

[0042] In a seventh aspect, the present application provides an Internet of Things, which comprises the terminal device of the fifth aspect and the communication base station of the sixth aspect.

[0043] In an eighth aspect, the present application provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the data transmission method of the first aspect or the second aspect.

[0044] In a ninth aspect, the present application provides a chip, comprising a processor and a communication interface, the communication interface and the processor are coupled, the processor is used to run programs or instructions, and realizes the data transmission method in the first aspect or the second aspect.

[0045] In a tenth aspect, the present application provides a computer program product, comprising a computer program, the computer program is executed by a processor to realize the data transmission method in the first aspect or the second aspect.

[0046] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0047] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the appended drawings.

[0048] Figure 1 is one of the flow diagrams of the data transmission method provided by the embodiments of the present application;

[0049] Figure 2 is the second flow diagram of the data transmission method provided by the embodiments of the present application;

[0050] Figure 3 is one of the scene interaction diagrams of the Internet of Things provided by the embodiments of the present application;

[0051] Figure 4 is the second scene interaction diagram of the Internet of Things provided by the embodiments of the present application;

[0052] Figure 5 is the third flow diagram of the data transmission method provided by the embodiments of the present application;

[0053] Figure 6 is the distribution diagram of the data transmission time slot provided by the embodiments of the present application;

[0054] Figure 7 is the fourth flow diagram of the data transmission method provided by the embodiments of the present application;

[0055] Figure 8 is one of the structural diagrams of the data transmission device provided by the embodiments of the present application;

[0056] Figure 9 is the second structural diagram of the data transmission device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0057] With reference to the drawings, the technical solutions in the embodiments of the present application will be clearly described below. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of them. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art are within the scope of protection of the present application.

[0058] The terms "first", "second", and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally a class, and are not limited to the number of objects, for example, the first object can be one or more. In addition, "and / or" in the specification and claims indicates at least one of the connected objects, and the character " / ", generally indicates that the front and rear associated objects are in an "or" relationship.

[0059] The data transmission method, data transmission device, terminal device, communication base station, Internet of Things and readable storage medium provided by the embodiments of the present application will be described in detail below in combination with the drawings and specific embodiments and application scenarios.

[0060] The data transmission method can be applied to terminal devices and communication base stations in the Internet of Things, and can be executed by hardware or software in the terminal devices and communication base stations.

[0061] The data transmission method in the embodiments of the present application is applied in the Internet of Things system, which can include a communication base station and one or more terminal devices.

[0062] The communication base station of the Internet of Things determines the maximum data retransmission number of all terminal devices in the Internet of Things based on network load conditions, and broadcasts the maximum data retransmission number to the terminal devices.

[0063] It can be understood that the maximum data retransmission number is an upper limit value of the retransmission number of data transmission between the terminal device and the communication base station.

[0064] After the terminal device receives the maximum data retransmission number sent by the communication base station, the terminal device determines the data transmission time slot corresponding to the to-be-transmitted data based on the maximum data retransmission number, the priority of the to-be-transmitted data, and the location information of the terminal device.

[0065] It should be noted that the terminal device will generate to-be-transmitted data of different priorities, and the to-be-transmitted data generated by different terminal devices in the Internet of Things system also have different priorities. The priority is used to represent the degree of urgency of data transmission, and data with high priority is transmitted first.

[0066] The terminal device transmits the to-be-transmitted data to the communication base station based on the maximum data retransmission number and the data transmission time slot after determining the data transmission time slot corresponding to the to-be-transmitted data according to the maximum data retransmission number, the priority of the to-be-transmitted data and the location information of the terminal device.

[0067] In actual implementation, the communication base station adaptively changes the maximum data retransmission number according to the network load condition and broadcasts the maximum data retransmission number to the terminal devices, and each terminal device selects different data transmission time slots for data transmission according to the received maximum data retransmission number, the priority of the to-be-transmitted data and the location information of the terminal device.

[0068] In the Internet of Things, different terminal devices generate data of different priorities, and the working periods of different terminal devices are different, which causes different network loads of the Internet of Things.

[0069] Meanwhile, different terminal devices are distributed in different locations, and part of the devices have mobility, which causes different terminal devices to have different channel states.

[0070] The communication base station adaptively changes the maximum data retransmission number according to the network load condition, and the maximum data retransmission number further controls the size of the traffic from a macro perspective and improves the resource utilization rate; and the terminal device selects the data transmission time slot according to the priority of the to-be-transmitted data and the location information of the terminal device, thereby ensuring that the emergency data of high priority is transmitted preferentially.

[0071] The data transmission method of the embodiment of the application flexibly adjusts the data transmission strategy according to the network state, preferentially transmits emergency data, effectively improves the reliability of data transmission and reduces the data packet loss rate.

[0072] The data transmission method performed by the terminal device and the communication base station will be described below.

[0073] As shown in FIG. 1, the terminal device data transmission method applied to the Internet of Things includes steps 110, 120 and 130. Figure 1

[0074] Step 110: receiving the maximum data retransmission number sent by the communication base station of the Internet of Things.

[0075] In this step, the terminal device receives the maximum data retransmission number determined by the communication base station according to the network load condition of the Internet of Things.

[0076] The maximum data retransmission number is the maximum retransmission number of the data transmitted by the terminal device under the network load condition, and the maximum data retransmission number sent by the communication base station to the terminal devices under different network load conditions in the Internet of Things can be different.

[0077] ​In step 120, the data transmission time slot corresponding to the to-be-transmitted data is determined based on the maximum data retransmission number, the priority of the to-be-transmitted data, and the position information of the terminal device.

[0078] In this step, the terminal device determines the data transmission time slot corresponding to the to-be-transmitted data according to the priority of the to-be-transmitted data, the position information of the terminal device, and the maximum data retransmission number of the to-be-transmitted data.

[0079] The data transmission time slot is a transmission time slot for data transmission of the terminal device. In the Internet of Things, the data priorities of different terminal devices are different, and the position information of the terminal device is also different. The data transmission time slots corresponding to the respective to-be-transmitted data are also different.

[0080] It can be understood that the maximum data retransmission number represents the maximum number of times that the to-be-transmitted data can be retransmitted. According to the maximum data retransmission number, the priority of the to-be-transmitted data, and the position information of the terminal device, the data transmission time slot for transmitting the to-be-transmitted data each time can be determined.

[0081] In step 130, the to-be-transmitted data is transmitted to the communication base station based on the maximum data retransmission number and the data transmission time slot.

[0082] In this step, the terminal device transmits the to-be-transmitted data to the communication base station according to the data transmission time slot and the maximum data retransmission number.

[0083] For example, if the maximum data retransmission number broadcast by the base station is 2, the terminal device will make a decision twice in the subsequent two time slots, and select to transmit data in the current time slot, represented as 1, or not, represented as 0.

[0084] That is, if the terminal device decides 10, it means that the data is transmitted in the first time slot and not transmitted in the second time slot.

[0085] In actual execution, time can be divided into multiple time slots, and the terminal device accesses the network channel in the corresponding data transmission time slot and sends the to-be-transmitted data to the communication base station.

[0086] It should be noted that transmitting the to-be-transmitted data to the communication base station in the data transmission time slot can avoid the randomness of data transmission by the terminal device, reduce data conflicts in the Internet of Things, improve channel utilization, and increase data throughput. According to the maximum data retransmission number, data transmission is performed, and through data retransmission, the problem of transmission failure caused by noise and user interference during data transmission can be solved, and the reliability of data transmission is ensured.

[0087] According to the data transmission method provided in the embodiment of the present application, the network load is perceived by the communication base station, the maximum data retransmission number of the terminal device for data retransmission is determined, the terminal device determines the data transmission time slot for data transmission in combination with the priority of the data to be transmitted and the location information of the terminal device, the data transmission strategy is flexibly adjusted according to the network state, the emergency data is preferentially transmitted, the reliability of data transmission is effectively improved, and the data packet loss rate is reduced.

[0088] In some embodiments, step 120 comprises determining the data transmission time slot corresponding to the data to be transmitted based on the maximum data retransmission number, the priority of the data to be transmitted, and the location information of the terminal device.

[0089] The data transmission time slot is determined based on the maximum data retransmission number, the priority of the data to be transmitted, and the location information of the terminal device by using a deep reinforcement learning algorithm.

[0090] Deep reinforcement learning belongs to a kind of machine learning, which is different from supervised learning and unsupervised learning. Through the continuous interaction (i.e., taking actions) between an agent and an environment, the agent obtains rewards, and thus continuously optimizes its action strategy in order to maximize its long-term revenue (sum of rewards).

[0091] In this embodiment, the terminal device acts as an agent and continuously interacts with the Internet of Things environment. Through the received maximum data retransmission number, the priority of the data to be transmitted, and the location information of the terminal device, the terminal device continuously optimizes the time slot for data transmission, obtains the best data transmission time slot for the terminal device to transmit data, and ensures the transmission demand of high-priority data while minimizing the packet loss rate of the Internet of Things.

[0092] In some embodiments, the data transmission time slot is determined based on the maximum data retransmission number, the priority of the data to be transmitted, and the location information of the terminal device by using a deep reinforcement learning algorithm, which can include:

[0093] The transmission time slot selected by the data to be transmitted for data transmission is the action of the deep reinforcement learning algorithm;

[0094] The reward of the deep reinforcement learning algorithm is calculated based on the transmission result and the priority of the data to be transmitted, and the data transmission time slot is determined.

[0095] In this embodiment, the terminal device agent can include a Q network, a real value network, and a target network. The Q network selects the action of the deep reinforcement learning, i.e., selects a specific transmission time slot for data transmission using the data to be transmitted. The real value network can calculate the corresponding action value function according to the output action.

[0096] According to whether data in the selected transmission time slot collides or whether the signal-to-interference-and-noise ratio of the terminal device is lower than a certain signal-to-interference-and-noise ratio threshold, it is determined whether the transmission of the to-be-transmitted data is successful, and a transmission result of the to-be-transmitted data is obtained.

[0097] When data in the selected transmission time slot collides or the signal-to-interference-and-noise ratio of the terminal device is lower than a certain signal-to-interference-and-noise ratio threshold, it is determined that the transmission of the to-be-transmitted data fails.

[0098] When data in the selected transmission time slot does not collide and the signal-to-interference-and-noise ratio of the terminal device is not lower than a certain signal-to-interference-and-noise ratio threshold, it is determined that the transmission of the to-be-transmitted data succeeds.

[0099] In this embodiment, according to the data transmission result and the priority of the to-be-transmitted data, a corresponding reward is calculated, the target network of the terminal device can calculate the target Q value according to the calculated reward and the maximum action value function of the real value network, then calculate the loss by using the mean square error, and update the parameters of the real value network by using the gradient descent method with a step size.

[0100] In actual execution, the parameters of the real value network are assigned to the target network every certain number of steps, the update of the parameters of the target network is completed, and the next round of training is entered, and the number of data packets that are lost is calculated, so as to ensure that the data transmission time slot determined by the deep reinforcement learning can minimize the packet loss rate of the Internet of Things.

[0101] In some embodiments, step 130, transmitting the to-be-transmitted data to the communication base station based on the maximum data retransmission number and the data transmission time slot, can include:

[0102] Transmitting the to-be-transmitted data to the communication base station by using a time slot ALOHA access method or an unlicensed spectrum access method based on the maximum data retransmission number and the data transmission time slot.

[0103] The time slot ALOHA access method (s-ALOHA) divides time into multiple discrete time slots, and the terminal device synchronously accesses the network channel and transmits data at the beginning of the time slot. If there is data to be transmitted, the terminal device needs to wait until the beginning of the time slot before transmitting the data.

[0104] Transmitting the to-be-transmitted data to the communication base station by using the time slot ALOHA access method can avoid the randomness of device data transmission, reduce data collision, improve the utilization rate of the channel, and increase the throughput.

[0105] It should be noted that the terminal device in the Internet of Things scenario can use a non-orthogonal multiple access technology (NOMA) for resource division, and can use a time slot ALOHA access method or an unlicensed spectrum access method for data transmission, so as to realize multiplexing of limited spectrum resources and significantly improve the transmission rate and channel capacity.

[0106] As Figure 2 shown, the data transmission method applied to the communication base station of the Internet of Things comprises steps 210-240.

[0107] Step 210, obtaining the network load condition of the Internet of Things.

[0108] In this step, the communication base station obtains the network load condition of the Internet of Things, and according to the network load condition, it can be judged whether the channel state for data transmission between the communication base station and the terminal device is good.

[0109] In actual execution, the communication base station obtains the network load condition of the Internet of Things, and can judge the channel state for data transmission of each terminal device in the Internet of Things.

[0110] Step 220, determining the maximum data retransmission number corresponding to the terminal device of the Internet of Things based on the network load condition.

[0111] In this step, the communication base station determines the maximum data retransmission number corresponding to the terminal device in the Internet of Things according to the network load condition of the Internet of Things.

[0112] It can be understood that the distances between different terminal devices in the Internet of Things and the communication base station are different, and the channel states between the terminal devices and the communication base station are also different. According to the network load condition, the maximum data retransmission number is adaptively changed, so that the communication base station can control the size of the flow from a macro perspective and improve the resource utilization rate.

[0113] Step 230, sending the maximum data retransmission number to the terminal device.

[0114] In this step, the communication base station sends the corresponding maximum data retransmission number to the terminal device, and the maximum data retransmission number sent by the communication base station received by the terminal device under different network load conditions can be different.

[0115] Step 240, receiving the to-be-transmitted data sent by the terminal device.

[0116] Among them, the data transmission time slot corresponding to the to-be-transmitted data is determined based on the maximum data retransmission number, the priority of the to-be-transmitted data, and the position information of the terminal device.

[0117] In this step, the terminal device transmits the to-be-transmitted data to the communication base station according to the obtained data transmission time slot maximum data retransmission number, and the communication base station receives the to-be-transmitted data sent by the terminal device.

[0118] In actual execution, the communication base station can receive the to-be-transmitted data sent by different terminal devices in different transmission time slots.

[0119] It should be noted that the communication base station determines the maximum data retransmission number of the terminal device for data transmission according to different network load conditions by sensing the network state, which can prevent traffic overload caused by a large number of devices transmitting multiple times from a macro perspective, and effectively avoid network congestion caused by a large number of terminal devices of the Internet of Things transmitting.

[0120] According to the data transmission method provided in the embodiment of the application, the network load is sensed by the communication base station to determine the maximum data retransmission number of the terminal device for data retransmission, the terminal device determines the data transmission time slot for data transmission in combination with the priority of the data to be transmitted and the location information of the terminal device, the data transmission strategy is flexibly adjusted according to the network state, the emergency data is preferentially transmitted, the reliability of data transmission is effectively improved, and the data packet loss rate is reduced.

[0121] In some embodiments, the step 220 of determining the maximum data retransmission number of the terminal device of the Internet of Things based on the network load condition can include:

[0122] The maximum data retransmission number of the terminal device is determined based on the network load condition by using a deep reinforcement learning algorithm.

[0123] In this embodiment, the communication base station as an intelligent agent continuously interacts with the environment of the Internet of Things, optimizes the maximum number of data retransmission of the terminal device by sensing the network load condition, obtains the maximum data retransmission number of the terminal device in the Internet of Things, reduces the data packet loss rate, and ensures the reliability of data transmission between the terminal device and the communication base station.

[0124] In some embodiments, the maximum data retransmission number of the terminal device is determined based on the network load condition by using a deep reinforcement learning algorithm, which can include:

[0125] The maximum retransmission number of the terminal device is determined based on the network load condition as the state of the deep reinforcement learning algorithm, the reward of the deep reinforcement learning algorithm is calculated based on the data transmission result, and the maximum data retransmission number is determined.

[0126] In this embodiment, the communication base station intelligent agent can include a real value network and a target network, the communication base station takes the network load condition as the state of the deep reinforcement learning, and makes a decision according to the ε-greedy strategy, that is, the maximum retransmission number of the terminal device, the real value network calculates the action value function according to the output action, and the communication base station calculates the reward based on the information (that is, the data transmission result) received in a period of time.

[0127] The target network calculates the target Q value according to the obtained reward and the maximum action value function of the real value network, then calculates the loss by using the mean square error, and updates the parameters of the real value network by using the gradient descent method with a step size to obtain the maximum data retransmission number corresponding to each terminal device. Meanwhile, the parameters of the real value network are assigned to the target network after a certain number of steps, the parameters of the target network are updated, and the next round of training is started.

[0128] In this embodiment, the communication base station acts as an agent and continuously interacts with the Internet of Things environment. By making a decision on the maximum retransmission number of the terminal device, the maximum data retransmission number corresponding to different network load conditions is determined according to the reward corresponding to the decision, so as to ensure that each terminal device realizes reliable data transmission through retransmission and minimizes the packet loss rate of the Internet of Things.

[0129] In some embodiments, step 210 of obtaining the network load condition of the Internet of Things includes:

[0130] Obtaining the device selection condition of the contention transmission unit of the Internet of Things;

[0131] Determining the channel collision condition of the contention transmission unit based on the device selection condition;

[0132] Determining the network load condition based on the channel collision condition.

[0133] The contention transmission unit (CTU) can provide basic transmission resources for grant-free transmission.

[0134] The CTU can refer to a transmission resource combined with time, frequency, and code domain, or can refer to a transmission combined with time, frequency, and pilot, or can refer to a transmission resource combined with time, frequency, code domain, and pilot. The access region of the CTU can refer to a time-frequency region used for grant-free transmission.

[0135] In this embodiment, the communication base station determines the channel collision condition according to the device selection condition of the terminal device for the contention transmission unit, determines the network load condition of the Internet of Things according to the collision condition of each channel, and further determines the maximum data retransmission number corresponding to each terminal device.

[0136] A specific embodiment will be described below.

[0137] In this embodiment, the terminal devices of the Internet of Things can include robots and cranes and the like.

[0138] As shown in FIG. 1, the crane position is fixed and only transmits data during the day and sleeps at night. Figure 3 Figure 4 ​As shown, the robot only sends data at night and hibernates during the day, while its location constantly changes while it is working.

[0139] In actual operation, the support can periodically send monitoring data and alarm data. When the robot is triggered by different events, it can also send data of various priorities to the base station.

[0140] In this embodiment, the number and types of active terminal devices vary at different times, the network load of the Internet of Things changes over time, and different terminal devices generate data to be transmitted with different priorities.

[0141] For example, the Internet of Things (IoT) includes M terminal devices, and the set of M terminal devices is: D = {D1, D2, ..., D...} m}

[0142] In this embodiment, different terminal devices generate data packets with different priorities to be transmitted. The set of data priorities for each terminal device can be represented as: L = {l1, l2, ..., l m}

[0143] In the Internet of Things (IoT), the set of competing transmission units (CTUs) representing data transmission resources can be represented as: C = {CTU1, CTU2, ..., CTU} K}

[0144] It is understandable that the number of terminal devices and the number of competing transmission units in the Internet of Things can be different.

[0145] In this embodiment, the set of transmission time slots that can transmit data can be represented as: T = {t1, t2, ..., t} s}

[0146] There will be some noise in the channel, and the channel conditions will affect the transmission. The signal-to-interference-plus-noise ratio (SIR / NNR) of the received signal of the terminal device will affect whether the data packet can be successfully transmitted. The success of data transmission can be determined by comparing the SIR / NNR of the received signal with the SIR / NNR threshold.

[0147] The expression for calculating the signal-to-interference-plus-noise ratio (SIR) of a terminal device is as follows:

[0148]

[0149] Where, γ n p represents the signal-to-interference-plus-noise ratio (SIR) during transmission by the nth terminal device. tx Indicates transmission power, h represents channel state, and I intra σ represents the power of the interfering user. 2 Let l(r) represent the noise power, and l(r) represent the power function model of the path loss, expressed as follows:

[0150] l(r)=εr -β

[0151] Where β represents the path loss exponent and ε represents the frequency correlation coefficient, the expression is as follows:

[0152] ε=(λ c / 4π) 2

[0153] Where, λ c Indicates carrier wavelength

[0154] like Figure 5 As shown, in the Internet of Things, the dynamic selection of the maximum number of transmissions adapts to different network load environments, and the selection of transmission time slots ensures the transmission of high-priority data.

[0155] In this embodiment, after the terminal device generates data, it first selects the CTU. Then, based on network load conditions such as channel status information, the communication base station selects the maximum number of transmissions and determines the maximum number of data retransmissions for the terminal device.

[0156] The terminal device selects the data transmission time slot by combining the maximum number of data retransmissions, data priority, and its own location information. It then determines the data transmission time slot for the data to be transmitted and transmits the data through the time slot ALOHA access method or unlicensed spectrum access. The communication base station receives the data.

[0157] like Figure 6 As shown, the terminal device generates data, encapsulates it into data packets to be transmitted, selects the corresponding transmission time slots based on the maximum retransmission count determined by the base station, and performs the first transmission (K1 times) and the second transmission (K2 times). K1 and K2 are determined by the base station based on network load and broadcast to the device. In the first transmission (K1 times), the device selects several time slots from the subsequent K1 time slots for data transmission based on the priority of the data to be transmitted and its own location information.

[0158] In this context, 1 indicates that data transmission is performed in the time slot, and 0 indicates that data transmission is not performed in the time slot.

[0159] like Figure 7 As shown, the communication base station calculates the CTU collision situation, determines the maximum number of data retransmissions for the terminal device based on the network load, and broadcasts the maximum number of retransmissions to the terminal device.

[0160] After generating data, the terminal device uses a deep reinforcement learning algorithm based on the maximum number of data retransmissions received from the communication base station to select a transmission time slot for data transmission according to the priority of the data to be transmitted and its own location information.

[0161] In actual execution, if all data transmission fails after reaching the maximum number of retransmissions, it indicates that data packet loss occurs, otherwise data transmission is successful.

[0162] The first objective function for data transmission in the Internet of Things is to minimize the data packet loss rate by obtaining the optimal transmission time slot selection strategy of the device, which can be expressed as:

[0163]

[0164] where p err represents the packet loss rate of the system during transmission, a m represents the transmission time slot selection strategy of the terminal device D m , K = {k1, k2, …, k m} represents the maximum number of transmissions of each terminal device, and a m is a k m -dimensional binary vector.

[0165] The calculation formula of the packet loss rate can be expressed as:

[0166]

[0167] wherein, represents the number of data packets that have lost packets in time slot t, represents the total number of newly generated data packets in time slot t, and T represents the number of transmission time slots.

[0168] In some embodiments, when T = 1, p err represents the packet loss rate of a single transmission time slot; when T → ∞, the value of p err gradually approaches its probability.

[0169] The second objective function for data transmission in the Internet of Things is to prioritize the transmission requirements of high priority data, which can be expressed as:

[0170]

[0171] wherein, represents the packet loss rate of data packets with priority l i .

[0172] In actual execution, the retransmission number selection algorithm based on deep reinforcement learning on the side of the communication base station is shown in Table 1:

[0173] Table 1

[0174]

[0175] The communication base station calculates the corresponding reward according to the transmission result and the priority of the device and feeds it back to the terminal device Dm Then, the target network calculates the target Q value according to the calculated reward and the maximum action value function, and then calculates the loss by using the mean square error, and updates the parameters of the real value network by using the gradient descent method with a step size α. Meanwhile, the parameters of the real value network are assigned to the target network after a certain number of steps, the update of the parameters of the target network is completed, and the next round of training is entered. Finally, the number of data packets with packet loss is calculated.

[0176] In actual execution, the transmission time slot selection algorithm based on deep reinforcement learning of the communication base station is as shown in Table 2:

[0177] Table 2

[0178]

[0179] Firstly, the maximum retransmission number of the device is determined through the collision of the CTU, so that the retransmission strategy can be dynamically adjusted according to the network load condition. Secondly, the transmission time slot is selected according to the maximum retransmission number and the data priority of the terminal device itself, so that the system packet loss rate and the packet loss rate of high priority data can be reduced at the same time, so as to meet the above two objective functions.

[0180] In this embodiment, the communication base station determines the maximum data retransmission number of the terminal device through the deep reinforcement learning algorithm according to the network load condition.

[0181] The communication base station selects the CTU selection condition as prior information, then initializes and calculates the collision of each CTU, and then makes a decision a according to the ε-greedy strategy m That is, the maximum retransmission number k of each terminal device m The real value network calculates the action value function according to the output action, and the communication base station calculates the reward r according to the received information.

[0182] The target network calculates the target Q value according to the obtained reward r and the maximum action value function, and then calculates the loss by using the mean square error, and updates the parameters of the real value network by using the gradient descent method with a step size α. Meanwhile, the parameters of the real value network are assigned to the target network after a certain number of steps, the update of the parameters of the target network is completed, and the next round of training is entered.

[0183] In the embodiment of the application, the Internet of Things can reduce the packet loss rate of high priority data while reducing the average packet loss rate by using the intelligent retransmission scheme based on load sensing, and guarantee the execution of emergency services.

[0184] The communication base station can adaptively determine the maximum retransmission number according to different network load conditions by sensing the network state, which can effectively avoid network congestion caused by a large number of terminal devices in transmission.

[0185] Communication base stations and terminal equipment can use deep reinforcement learning to determine the maximum number of retransmissions and transmission time slots, adaptively change transmission strategies, and can be used in application environments of varying complexity.

[0186] The data transmission method provided in this application can be executed by a data transmission device. This application uses a data transmission device executing the data transmission method as an example to illustrate the data transmission device provided in this application.

[0187] This application provides a data transmission device for terminal devices used in the Internet of Things.

[0188] like Figure 8 As shown, the data transmission device includes:

[0189] The first receiving module 810 is used to receive the maximum number of data retransmissions sent by the communication base station of the Internet of Things (IoT). The maximum number of data retransmissions is determined based on the network load of the IoT.

[0190] The first processing module 820 is used to determine the data transmission time slot corresponding to the data to be transmitted based on the maximum number of data retransmissions, the priority of the data to be transmitted, and the location information of the terminal device.

[0191] The first transmitting module 830 is used to transmit data to be transmitted to the communication base station based on the maximum number of data retransmissions and the data transmission time slot.

[0192] According to the data transmission device provided in the embodiments of this application, the communication base station senses the network load and determines the maximum number of data retransmissions for the terminal device. The terminal device combines the priority of the data to be transmitted and its own location information to determine the data transmission time slot for data transmission. The data transmission strategy is flexibly adjusted according to the network status, and urgent data is transmitted first, which effectively improves the reliability of data transmission and reduces the data packet loss rate.

[0193] In some embodiments, the first processing module 820 is used to determine the data transmission time slot based on the maximum number of data retransmissions, the priority of the data to be transmitted, and the location information of the terminal device, using a deep reinforcement learning algorithm.

[0194] In some embodiments, the first processing module 820 is configured to select a transmission time slot for data transmission based on the data to be transmitted as an action of the deep reinforcement learning algorithm.

[0195] Based on the transmission results and priority of the data to be transmitted, the reward of the deep reinforcement learning algorithm is calculated, and the data transmission time slot is determined.

[0196] In some embodiments, the first sending module 830 is configured to transmit the data to be transmitted to the communication base station based on the maximum data retransmission number and the data transmission time slot through a time slot ALOHA access mode or an unlicensed spectrum access mode.

[0197] The embodiment of the present application provides a data transmission device of a communication base station applied to an Internet of Things.

[0198] As shown in the figure, the data transmission device comprises: Figure 9

[0199] The acquisition module 910 is configured to acquire a network load condition of the Internet of Things.

[0200] The second processing module 920 is configured to determine a maximum data retransmission number corresponding to a terminal device of the Internet of Things based on the network load condition.

[0201] The second sending module 930 is configured to send the maximum data retransmission number to the terminal device.

[0202] The second receiving module 940 is configured to receive data to be transmitted sent by the terminal device, and a data transmission time slot corresponding to the data to be transmitted is determined based on the maximum data retransmission number, a priority of the data to be transmitted and position information of the terminal device.

[0203] According to the data transmission device provided by the embodiment of the present application, the network load is perceived by the communication base station, the maximum data retransmission number of the terminal device for data retransmission is determined, the terminal device determines the data transmission time slot for data transmission in combination with the priority of the data to be transmitted and the position information of the terminal device, the data transmission strategy is flexibly adjusted according to the network state, the emergency data is preferentially transmitted, the reliability of data transmission is effectively improved, and the data packet loss rate is reduced.

[0204] In some embodiments, the second processing module 920 is configured to determine the maximum data retransmission number corresponding to the terminal device through a deep reinforcement learning algorithm based on the network load condition.

[0205] In some embodiments, the second processing module 920 is configured to make a decision on the maximum retransmission number of the terminal device by taking the network load condition as a state of the deep reinforcement learning algorithm, calculate a reward of the deep reinforcement learning algorithm based on a data transmission result, and determine the maximum data retransmission number.

[0206] In some embodiments, the acquisition module 910 is configured to acquire a device selection condition of a competitive transmission unit of the Internet of Things.

[0207] The channel collision condition of the competitive transmission unit is determined based on the device selection condition.

[0208] The network load condition is determined based on the channel collision condition. ​

[0209] The data transmission apparatus provided by the embodiments of the present application can realize Figures 1 to 7 The method embodiments realize various processes, and details are not repeated here.

[0210] In some embodiments, the embodiments of the present application further provide a terminal device, comprising a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor realizes the data transmission method of the terminal device applied to the Internet of Things when executing the program.

[0211] In this embodiment, the program is executed by the processor to realize the various processes of the data transmission method of the terminal device applied to the Internet of Things, and the same technical effects can be achieved, and details are not repeated here.

[0212] In some embodiments, the embodiments of the present application further provide a communication base station, comprising a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor realizes the data transmission method of the communication base station applied to the Internet of Things when executing the program.

[0213] In this embodiment, the program is executed by the processor to realize the various processes of the data transmission method of the communication base station applied to the Internet of Things, and the same technical effects can be achieved, and details are not repeated here.

[0214] The embodiments of the present application further provide an Internet of Things, comprising the terminal device and the communication base station.

[0215] The communication base station determines the maximum data retransmission number corresponding to the terminal device in the Internet of Things based on the network load condition, and broadcasts the maximum data retransmission number to the corresponding terminal device.

[0216] After receiving the maximum data retransmission number sent by the communication base station, the terminal device determines the data transmission time slot corresponding to the to-be-transmitted data based on the maximum data retransmission number, the priority of the to-be-transmitted data and the location information of the terminal device.

[0217] After determining the data transmission time slot corresponding to the to-be-transmitted data based on the maximum data retransmission number, the priority of the to-be-transmitted data and the location information of the terminal device, the terminal device transmits the to-be-transmitted data to the communication base station based on the maximum data retransmission number and the data transmission time slot, and the communication base station receives the to-be-transmitted data sent by the terminal device.

[0218] In the embodiments of the present application, the communication base station distributes different maximum data retransmission times for terminal devices according to network load conditions, so that the terminal devices use different maximum data retransmission times for data transmission under different loads, and the reliability of data transmission is ensured; the terminal device selects a data transmission time slot according to the priority of the data to be transmitted and its own position information, and ensures that the emergency data with high priority is transmitted preferentially.

[0219] The embodiments of the present application also provide a non-transitory computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement each process of the data transmission method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0220] The processor is the processor in the electronic device in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0221] The embodiments of the present application also provide a computer program product, which includes a computer program. The computer program is executed by a processor to implement the above data transmission method.

[0222] The processor is the processor in the electronic device in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0223] The embodiments of the present application also provide a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run a program or an instruction to implement each process of the above data transmission method and achieve the same technical effects. To avoid repetition, details are not described herein.

[0224] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system level chip, a system chip, a chip system or a system on chip, etc.

[0225] It should be noted that, in the present document, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a", "comprising", or "comprises" does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element. Additionally, it should be noted that the terms "one embodiment", "some embodiments", "certain embodiments", "certain examples", or "some examples" as used in the present document are intended to refer to one or more embodiments or examples that do not necessarily have to cover all embodiments or examples of the present application. In other words, use of the above terms does not necessarily refer to the same embodiment or example. Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0226] From the above description of the embodiments, it is apparent that the above-mentioned method can be realized by means of software and necessary universal hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solution of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disc, optical disc), and includes a plurality of instructions for making a terminal (which can be a mobile phone, computer, server, or network equipment, etc.) execute the method described in various embodiments of the present application.

[0227] The embodiments of the present application are described above in conjunction with the drawings, but the present application is not limited to the above-mentioned specific embodiments, which are only illustrative but not restrictive, and a person of ordinary skill in the art can make many forms without departing from the purpose of the present application and the scope protected by the claims.

[0228] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "certain embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Furthermore, the described specific features, structures, materials or characteristics can be combined in any suitable manner in any one or more embodiments or examples.

[0229] While the embodiments of the application have been shown and described, it is to be understood that the embodiments can be varied, modified, substituted and otherwise changed by those skilled in the art without departing from the principles and spirit of the application. It is therefore intended that this application not be limited to the particular disclosure of the embodiments but that the application be given broadest scope in accordance with the following claims and their equivalents.

Claims

1. A data transmission method, characterized by, The method is applied to a terminal device of an Internet of Things, and the method comprises: receiving a maximum data retransmission number sent by a communication base station of the Internet of Things, the maximum data retransmission number being determined based on a network load condition of the Internet of Things; determining a data transmission time slot corresponding to to-be-transmitted data based on the maximum data retransmission number, a priority of the to-be-transmitted data, and position information of the terminal device; transmitting the to-be-transmitted data to the communication base station based on the maximum data retransmission number and the data transmission time slot; The method comprises: determining the data transmission time slot based on the maximum data retransmission number, the priority of the to-be-transmitted data, and the position information of the terminal device by using a deep reinforcement learning algorithm.

2. The data transmission method of claim 1, wherein, The method comprises: taking the selection of the to-be-transmitted data transmission time slot as an action of the deep reinforcement learning algorithm; calculating a reward of the deep reinforcement learning algorithm based on a transmission result and the priority of the to-be-transmitted data, and determining the data transmission time slot.

3. The data transmission method according to claim 1 or 2, characterized in that, The method comprises: transmitting the to-be-transmitted data to the communication base station by using a time slot ALOHA access mode or an unlicensed spectrum access mode based on the maximum data retransmission number and the data transmission time slot.

4. A data transmission method, characterized by, The method is used for a communication base station of an Internet of Things, and the method comprises: obtaining a network load condition of the Internet of Things; determining a maximum data retransmission number corresponding to a terminal device of the Internet of Things based on the network load condition; sending the maximum data retransmission number to the terminal device; receiving to-be-transmitted data sent by the terminal device, a data transmission time slot corresponding to the to-be-transmitted data being determined based on the maximum data retransmission number, a priority of the to-be-transmitted data, and position information of the terminal device by using a deep reinforcement learning algorithm.

5. The data transmission method of claim 4, wherein, The method comprises: determining the maximum data retransmission number corresponding to the terminal device by using a deep reinforcement learning algorithm based on the network load condition.

6. The data transmission method of claim 5, wherein, The method comprises: taking the network load condition as a state of the deep reinforcement learning algorithm, making a decision on the maximum retransmission number of the terminal device, calculating a reward of the deep reinforcement learning algorithm based on a data transmission result, and determining the maximum data retransmission number.

7. The data transmission method according to any one of claims 4-6, characterized by, The method comprises: obtaining a device selection condition of a competitive transmission unit of the Internet of Things; determining a channel collision condition of the competitive transmission unit based on the device selection condition; determine the network load condition based on the channel collision condition.

8. A data transmission apparatus, characterized by comprising: The device is applied to a terminal device of an Internet of Things, and the device comprises: a first receiving module configured to receive a maximum data retransmission number sent by a communication base station of the Internet of Things, the maximum data retransmission number being determined based on a network load condition of the Internet of Things; a first processing module configured to determine a data transmission time slot corresponding to the to-be-transmitted data based on the maximum data retransmission number, a priority of the to-be-transmitted data, and position information of the terminal device; a first sending module configured to transmit the to-be-transmitted data to the communication base station based on the maximum data retransmission number and the data transmission time slot; the first processing module is configured to determine the data transmission time slot corresponding to the to-be-transmitted data based on the maximum data retransmission number, the priority of the to-be-transmitted data, and the position information of the terminal device, and comprises: determining the data transmission time slot based on the maximum data retransmission number, the priority of the to-be-transmitted data, and the position information of the terminal device by using a deep reinforcement learning algorithm.

9. A data transmission apparatus, characterized by comprising: The device is applied to a communication base station of an Internet of Things, and the device comprises: an acquisition module configured to acquire a network load condition of the Internet of Things; a second processing module configured to determine a maximum data retransmission number corresponding to a terminal device of the Internet of Things based on the network load condition; a second sending module configured to send the maximum data retransmission number to the terminal device; a second receiving module configured to receive to-be-transmitted data sent by the terminal device, a data transmission time slot corresponding to the to-be-transmitted data being determined based on the maximum data retransmission number, a priority of the to-be-transmitted data, and position information of the terminal device by using a deep reinforcement learning algorithm.

10. A terminal device, comprising: A computer program product comprising a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the data transmission method according to any one of claims 1-3 when executing the program.

11. A communication base station, characterized by A computer program product comprising a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the data transmission method according to any one of claims 4-7 when executing the program.

12. An Internet of Things, characterized by The computer program product is executed by the processor to implement the data transmission method according to any one of claims 1-7.

13. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program product is executed by the processor to implement the data transmission method according to any one of claims 1-7.

14. A computer program product comprising a computer program, characterized in that, ​

Images