Time distribution method of power transmission line detection scene based on unmanned aerial vehicle wireless energy supply and related device thereof

Abstract

The invention relates to an unmanned aerial vehicle wireless energy supply-based power transmission line detection scene time allocation method and a related device thereof, and the device comprises a wireless edge computing network which comprises an unmanned aerial vehicle and wireless equipment. Comprising the steps that a full-connection neural network model with channel gains of wireless devices as input and data transmission duration proportions as output is constructed, the channel gains of at least one wireless device are input into the full-connection neural network model, and the data transmission duration proportions of the at least one wireless device in a single time slot are obtained; obtaining an energy capture duration proportion of the wireless device according to the data transmission duration proportion and the channel gain of the wireless device; and determining the maximum transmission rate between the wireless equipment and the unmanned aerial vehicle according to the data transmission duration proportion, the energy capture duration proportion and the channel gain. According to the scheme provided by the invention, the calculation rate of the whole edge calculation network can be maximized by adjusting the energy capture duration and the data transmission duration of the wireless equipment, and the transmission delay is reduced.

Description

Technical Field

[0001] The present application relates to the field of edge computing technology, and in particular to a time allocation method for a power transmission line detection scenario based on wireless power supply from drones and related devices. Background Art

[0002] In recent years, with the development of wireless communication and hardware computing technologies, more and more wireless Internet of Things (IoT) devices have been deployed in daily life and industrial scenarios, bringing convenience to people and improving production efficiency. However, limited computing power and energy may lead to short lifespan and unacceptable delays in IoT devices. In order to cope with the processing of large amounts of data in IoT devices and meet the low latency requirements of devices with limited energy, the combination of RF energy harvesting and mobile edge computing (MEC) has emerged. Despite the computing advantages of MEC, limited power supply remains a thorny challenge for battery-based smart terminals. Therefore, wireless power transmission (WPT) has recently emerged as an effective way to provide harvested energy for smart mobile communications.

[0003] At present, most of the time allocation methods of wirelessly powered mobile edge computing networks mostly use traditional optimization methods, but they are usually complex and difficult to solve, and require multiple iterations to obtain the optimal solution, which will consume a lot of time. This is unacceptable for delay-sensitive edge computing applications, especially in the power transmission line detection scenario. The high latency of edge computing leads to low transmission rate. Therefore, there is an urgent need for a time allocation method and related devices for the power transmission line detection scenario based on wireless power supply from drones that can enable the entire edge computing network to achieve a higher rate. Summary of the invention

[0004] In order to solve or partially solve the problems existing in the related technology, the present application provides a time allocation method and related devices for a power transmission line detection scenario based on wireless power supply of drones, which is suitable for communication using time division multiplexing (TDMA) and can maximize the computing rate of the entire edge computing network and reduce transmission delay by adjusting the energy capture time and data transmission time of the wireless device.

[0005] The first aspect of the present application provides a time allocation method for a power transmission line detection scenario based on wireless power supply of unmanned aerial vehicles, including constructing a fully connected neural network model with the channel gain of the wireless device as input and the data transmission time ratio as output, inputting the channel gain of at least one of the wireless devices into the fully connected neural network model, and obtaining the data transmission time ratio of at least one of the wireless devices in a single time slot; obtaining the energy capture time ratio of the wireless device according to the data transmission time ratio and the channel gain of the wireless device, and the energy capture time ratio is the time ratio occupied by the wireless device to obtain the energy emitted by the unmanned aerial vehicle in a single time slot; determining the maximum transmission rate between the wireless device and the unmanned aerial vehicle according to the data transmission time ratio, the energy capture time ratio and the channel gain.

[0006] In combination with the first aspect, in a possible implementation of the first aspect, the fully connected neural network model includes 1 input layer, 2 hidden layers and 1 output layer, the first hidden layer has 200 neurons, the second hidden layer has 120 neurons, the output layer has 1 neuron, and the activation function is a Sigmoid function.

[0007] In combination with the first aspect, in a possible implementation manner of the first aspect, obtaining the energy capture duration ratio of the wireless device according to the data transmission duration ratio of the wireless device and the channel gain includes:

[0008] The formula for calculating the energy capture duration ratio of the wireless device is as follows:

[0009]

[0010] in, 0≤a≤1, p is the transmission power of the radio frequency energy transmitter in the UAV, h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, and v is the coefficient of the additional data overhead generated during the transmission process; the dichotomy method is used to solve the f(a), and when the a meets the preset threshold range, the value of a at this time is determined as the energy capture time ratio of the wireless device.

[0011] In combination with the first aspect, in a possible implementation manner of the first aspect, determining the total transmission rate between the wireless device and the drone according to the data transmission duration ratio, the energy capture duration ratio, and the channel gain includes:

[0012] The formula for calculating the total transmission rate is as follows:

[0013]

[0014] Where r is the total transmission rate between the wireless device and the drone, p is the transmission power of the RF energy transmitter in the drone, and h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, v is the coefficient of the additional data overhead generated during the transmission process, and a is the energy capture time ratio of the wireless device.

[0015] In combination with the first aspect, in a possible implementation manner of the first aspect, the loss function of the fully connected neural network model includes:

[0016]

[0017] Among them, S is the loss function.

[0018] In combination with the first aspect, in a possible implementation method of the first aspect, the data transmission duration of each of the wireless devices is obtained according to the data transmission duration ratio; according to the data transmission duration of each of the wireless devices, each wireless device is configured to transmit data to the drone in each time slot according to the data transmission duration of each wireless device.

[0019] The second aspect of the present application provides a time allocation device for a power transmission line detection scenario based on wireless power supply of unmanned aerial vehicles, including an acquisition module for constructing a fully connected neural network model with the channel gain of a wireless device as input and the data transmission time ratio as output, and inputting the channel gain of at least one of the wireless devices into the fully connected neural network model to obtain the data transmission time ratio of at least one of the wireless devices in a single time slot; a processing module for obtaining the energy capture time ratio of the wireless device according to the data transmission time ratio of the wireless device and the channel gain, wherein the energy capture time ratio is the time ratio occupied by the wireless device in obtaining the energy emitted by the unmanned aerial vehicle in a single time slot; a determination module for determining the total transmission rate between the wireless device and the unmanned aerial vehicle according to the data transmission time ratio, the energy capture time ratio and the channel gain.

[0020] In combination with the second aspect, in a possible implementation of the second aspect, the acquisition module is also used for a fully connected neural network model including 1 input layer, 2 hidden layers and 1 output layer, the first hidden layer has 200 neurons, the second hidden layer has 120 neurons, the output layer has 1 neuron, and the activation function is a Sigmoid function.

[0021] In combination with the second aspect, in a possible implementation manner of the second aspect, the processing module is further used to obtain the energy capture duration ratio of the wireless device according to the data transmission duration ratio of the wireless device and the channel gain, including:

[0022] The formula for calculating the energy capture duration ratio of the wireless device is as follows:

[0023]

[0024] in, 0≤a≤1, p is the transmission power of the radio frequency energy transmitter in the UAV, h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, and v is the coefficient of the additional data overhead generated during the transmission process; the dichotomy method is used to solve the f(a), and when the a meets the preset threshold range, the value of a at this time is determined as the energy capture time ratio of the wireless device.

[0025] In combination with the second aspect, in a possible implementation manner of the second aspect, the determination module is further used to determine the maximum transmission rate between the wireless device and the drone according to the data transmission duration ratio, the energy capture duration ratio, and the channel gain, including:

[0026] The formula for calculating the total transmission rate is as follows:

[0027]

[0028] Where r is the maximum transmission rate between the wireless device and the drone, p is the transmission power of the RF energy transmitter in the drone, and h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, v is the coefficient of the additional data overhead generated during the transmission process, a is the energy capture time ratio of the wireless device, and N is the number of wireless devices.

[0029] In combination with the second aspect, in a possible implementation of the second aspect, the loss function of the acquisition module for the fully connected neural network model includes:

[0030]

[0031] Among them, S is the loss function.

[0032] In combination with the second aspect, in a possible implementation method of the second aspect, the determination module is also used to obtain the data transmission duration of each of the wireless devices based on the data transmission duration ratio; according to the data transmission duration of each of the wireless devices, configure each wireless device to transmit data to the drone in each time slot using the data transmission duration of each wireless device.

[0033] A third aspect of the present application provides an electronic device, including:

[0034] Processor; and

[0035] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0036] A fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0037] A fifth aspect of the present application provides a computer program product, comprising a computer program / instruction, which implements the method described above when executed by a processor.

[0038] The technical solution provided by this application may have the following beneficial effects:

[0039] The time allocation method for a power transmission line detection scenario based on wireless power supply from a drone of the present application includes a wireless edge computing network, which includes a drone and a wireless device, and includes constructing a fully connected neural network model with the channel gain of the wireless device as input and the data transmission time ratio as output, inputting the channel gain of at least one wireless device into the fully connected neural network model, and obtaining the data transmission time ratio of at least one wireless device in a single time slot; obtaining the energy capture time ratio of the wireless device according to the data transmission time ratio and the channel gain of the wireless device, and the energy capture time ratio is the time ratio occupied by the wireless device in obtaining the energy emitted by the drone in a single time slot; determining the maximum transmission rate between the wireless device and the drone according to the data transmission time ratio, the energy capture time ratio, and the channel gain, and maximizing the computing rate of the entire edge computing network and reducing the transmission delay by adjusting the energy capture time and the data transmission time of the wireless device.

[0040] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0042] Figure 1 It is a flow chart of a time allocation method for a power transmission line detection scenario based on wireless power supply of a drone shown in an embodiment of the present application;

[0043] Figure 2 It is a structural schematic diagram of a time allocation device for a power transmission line detection scenario based on wireless power supply from a drone, as shown in an embodiment of the present application;

[0044] Figure 3 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0046] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0047] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0048] First, some of the terms and related technologies involved in this application are explained to facilitate understanding by those skilled in the art.

[0049] Channel gain indicates the transmission capacity of the signal in the channel, usually expressed by the quality of the channel or the signal strength. The increase in channel gain means that the transmission capacity of the signal in the channel is enhanced, which can improve the communication quality. The increase in channel gain may be due to factors such as more available paths in the channel, better wireless environment, and stronger signal sources. The channel gain between the drone and the sensor can be affected by the distance between the drone and the sensor.

[0050] The fully connected neural network model (Fully Connected Neural Network, FCNN) is a basic neural network structure. In a fully connected neural network, each neuron is connected to all neurons in the previous layer, and each connection has a weight that describes the relationship between input and output. When receiving an input signal, the network calculates the activation value of each neuron by weighted summation, and then obtains the final output through a nonlinear activation function (such as ReLU or sigmoid).

[0051] Gaussian White Noise is an ideal noise model, whose characteristics are that the probability density function follows the Gaussian distribution, while the power spectrum density is uniformly distributed. Gaussian white noise includes thermal noise and shot noise, etc., and is an ideal model for analyzing channel additive noise. In practical applications, Gaussian white noise is often used as a background noise model to evaluate system performance. Its definition emphasizes the statistical characteristics of noise and the uniformity of power spectrum density, which makes it occupy an important position in both theory and practical applications, and helps to analyze and predict the impact of noise on system performance.

[0052] Mobile Edge Computing (MEC) is an application of edge computing in mobile networks. It provides low-latency, high-bandwidth computing and data processing capabilities for mobile devices by deploying computing resources at the edge of mobile networks. MEC is particularly suitable for latency-sensitive applications such as Internet of Vehicles, video analysis, and augmented reality.

[0053] In machine learning and statistics, a loss function is a function that measures the difference between the model's predicted value and the actual observed value. The loss function is usually used to guide the model's training process and optimize the model parameters by minimizing the loss function.

[0054] In the relevant technologies, my country currently has complex terrain, low efficiency of manual inspection and prone to safety accidents. The use of drones to inspect transmission lines is a key part of the national interconnected power grid. Due to the instability of communication links in some remote areas and low data transmission reliability, edge computing is sunk into drone systems. Drones can provide computing services and energy supply for wireless devices deployed on transmission lines at a relatively close distance.

[0055] In recent years, with the development of wireless communication and hardware computing technologies, more and more wireless Internet of Things (IoT) devices have been deployed in daily life and industrial scenarios, bringing convenience to people and improving production efficiency. However, limited computing power and energy may lead to short lifespan and unacceptable delays in IoT devices. In order to cope with the processing of large amounts of data in IoT devices and meet the low latency requirements of devices with limited energy, the combination of RF energy harvesting and mobile edge computing (MEC) came into being.

[0056] Currently, most time allocation methods for wirelessly powered mobile edge computing networks use traditional optimization methods, but they are usually complex and difficult to solve, and require multiple iterations to obtain the optimal solution, which consumes a lot of time. This is unacceptable for delay-sensitive edge computing applications.

[0057] In response to the above problems, the embodiments of the present application provide a time allocation method and related devices for a power transmission line detection scenario based on wireless power supply for drones, which is suitable for communication using time division multiplexing (TDMA). It can maximize the computing rate of the entire edge computing network and reduce transmission delay by adjusting the energy capture time and data transmission time of the wireless device. It can transmit the acquired power transmission line data to the drone through the wireless device for edge computing.

[0058] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0059] Figure 1 It is a flow chart of a time allocation method for a power transmission line detection scenario based on wireless power supply of a drone shown in an embodiment of the present application.

[0060] See also Figure 1 , a time allocation method for a transmission line detection scenario based on wireless power supply of unmanned aerial vehicles, comprising:

[0061] S110: Construct a fully connected neural network model with the channel gain of the wireless device as input and the data transmission time ratio as output, input the channel gain of at least one wireless device into the fully connected neural network model, and obtain the data transmission time ratio of at least one wireless device in a single time slot.

[0062] Specifically, on a transmission line, a wireless edge computing network can be formed by a drone and multiple wireless devices. Each wireless device has an antenna, an energy collection circuit and a battery to provide energy for the wireless device. The wireless device can collect data for transmission line detection and transmit the data to the drone for edge computing. The drone hovers at a fixed position. The drone is integrated with a radio frequency energy transmitter and an edge server. The radio frequency energy transmitter can radiate energy outward. The wireless device can simultaneously capture the energy radiated outward by the drone through the energy collection circuit and store the energy in the battery. When obtaining the channel gain h = [h1,h2,…,h i ,…,h N ],h i After the channel gain between the ith wireless device and the drone is input into the fully connected neural network model, the data transmission time ratio of each wireless device can be obtained. i …,τ N ],τ i is the data transmission duration ratio of the i-th wireless device, which is the ratio of the time it takes for the wireless device to transmit data to the drone to the entire time excluding energy capture, and 0≤τ i ≤1, N represents the number of wireless devices.

[0063] Specifically, the coordinates of the drone and the coordinates of the wireless device may be obtained, and the channel gain between each wireless device and the drone may be obtained based on the distance between the coordinates of the drone and the coordinates of the wireless device.

[0064] In a possible implementation, the fully connected neural network model includes 1 input layer, 2 hidden layers and 1 output layer, the first hidden layer has 200 neurons, the second hidden layer has 120 neurons, and the output layer has 1 neuron, wherein the activation function is a Sigmoid function.

[0065] S120: Obtain the energy capture time ratio of the wireless device according to the data transmission time ratio and channel gain of the wireless device. The energy capture time ratio is the time ratio occupied by the wireless device in obtaining the energy transmitted by the drone in a single time slot.

[0066] Specifically, the energy capture duration ratio of the wireless device can be obtained according to the data transmission duration ratio and channel gain of the wireless device. The energy captured by the wireless device can be expressed as E i =μPh i a,i=1,2,…,N,h i is the channel gain between the i-th wireless device and the drone, μ is the energy capture efficiency of the wireless device, p is the transmission power of the RF energy transmitter in the drone, and a is the energy capture time ratio of the wireless device. The energy captured by the wireless device can be calculated based on the energy capture time ratio of the wireless device.

[0067] In a possible implementation, the formula for calculating the energy capture duration ratio of the wireless device is as follows:

[0068]

[0069] in, 0≤a≤1, p is the transmission power of the RF energy transmitter in the drone, h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, and v is the coefficient of the additional data overhead generated during the transmission process. The binary method is used to solve f(a). When a meets the preset threshold range, the value of a at this time is determined as the energy capture time ratio of the wireless device.

[0070] Specifically, a=0.5 can be preset, a min =0,a max =1, a min is the lower limit of the value of a, amax is the upper limit of the value of a. In the calculation process, a=0.5 can be substituted into f(a) for calculation. If f(a)>0, then let a min =a, that is, a at this time min =0.5, and let a=(a min +a max ) / 2, that is, a=0.75 at this time; if f(a)<0, then let a at this time max =a, that is, a at this time max =0.5, and let a=(a min +a max ) / 2, that is, a=0.25 at this time. By performing multiple iterative calculations, the value of a is obtained. When the threshold range is preset, for example, the threshold range is -0.00001 <a-a min <0.00001, determine the value of a at this time, and use a at this time as the energy capture time ratio of the wireless device. The a obtained in this way can obtain the optimal energy capture time ratio of the wireless device, which is conducive to maximizing the computing rate of the entire edge computing network.

[0071] S130: Determine the maximum transmission rate between the wireless device and the drone according to the data transmission time ratio, the energy capture time ratio, and the channel gain.

[0072] Specifically, after obtaining the data transmission time ratio, energy capture time ratio, and channel gain, the transmission rate between the wireless device and the drone can be calculated. Since a at this time is the optimal energy capture time ratio of the wireless device, the transmission rate calculated at this time is the maximum transmission rate of the wireless edge computing network. By using drones to perform wireless power supply and data calculation for wireless devices deployed on transmission lines, the functional time of the drone can be set, and the computing rate can be maximized by setting the energy capture time ratio and data transmission time ratio of the wireless device. The wireless device transmits data to the drone for edge computing according to the data transmission time.

[0073] In a possible implementation, determining the maximum transmission rate between the wireless device and the drone according to the data transmission duration ratio, the energy capture duration ratio, and the channel gain includes:

[0074] The formula for calculating the total transmission rate of N wireless devices is as follows:

[0075]

[0076] Among them, r is the maximum transmission rate between the wireless device and the drone, p is the transmission power of the RF energy transmitter in the drone, and h iis the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, v is the coefficient of the additional data overhead generated during the transmission process, a is the energy capture time ratio of the wireless device, and N is the number of wireless devices.

[0077] Specifically, N0 can be Gaussian white noise or channel white noise, p is the transmission power of the RF energy transmitter in the drone and μ is the energy capture efficiency of the wireless device. The values ​​of p, μ, v, and B can all be obtained in advance. By calculating the transmission rate of each wireless device and performing a summary calculation, the maximum transmission rate of the entire wireless edge computing network can be obtained.

[0078] In a possible implementation, a function of the maximum transmission rate and the negative of can be used as a loss function to train a neural network model, and the loss function includes:

[0079]

[0080] Among them, S is the loss function.

[0081] In a possible implementation, the data transmission duration of each wireless device is obtained according to the data transmission duration ratio.

[0082] According to the data transmission duration of each wireless device, each wireless device is configured to transmit data to the drone within each time slot according to the data transmission duration of each wireless device. After calculating the maximum transmission rate, the data transmission duration of the wireless device can be obtained, and the captured energy can be used to transmit data to the drone. The data of the power transmission line detection obtained by the wireless device is transmitted to the drone for edge computing.

[0083] The time allocation method for a power transmission line detection scenario based on wireless power supply from a drone of the present application includes a wireless edge computing network, which includes a drone and a wireless device, and includes constructing a fully connected neural network model with the channel gain of the wireless device as input and the data transmission time ratio as output, inputting the channel gain of at least one wireless device into the fully connected neural network model, and obtaining the data transmission time ratio of at least one wireless device in a single time slot; obtaining the energy capture time ratio of the wireless device according to the data transmission time ratio and the channel gain of the wireless device, and the energy capture time ratio is the time ratio occupied by the wireless device in obtaining the energy emitted by the drone in a single time slot; determining the maximum transmission rate between the wireless device and the drone according to the data transmission time ratio, the energy capture time ratio, and the channel gain, and maximizing the computing rate of the entire edge computing network and reducing the transmission delay by adjusting the energy capture time and the data transmission time of the wireless device.

[0084] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a time allocation device, electronic device and corresponding embodiments for a power transmission line detection scenario based on wireless power supply of drones.

[0085] Figure 3 It is a structural schematic diagram of a time allocation device for a power transmission line detection scenario based on wireless power supply from a drone shown in an embodiment of the present application.

[0086] See also Figure 2 , a time allocation device 200 for a power transmission line detection scenario based on wireless power supply of drones, comprising an acquisition module 210, a processing module 220 and a determination module 230. Among them:

[0087] An acquisition module 210 is used to construct a fully connected neural network model with a channel gain of a wireless device as an input and a data transmission duration ratio as an output, input the channel gain of at least one wireless device into the fully connected neural network model, and obtain the data transmission duration ratio of at least one wireless device in a single time slot;

[0088] Specifically, on a transmission line, a wireless edge computing network can be formed by a drone and multiple wireless devices. Each wireless device has an antenna, an energy collection circuit and a battery to provide energy for the wireless device. The wireless device can collect data for transmission line detection and transmit the data to the drone for edge computing. The drone hovers at a fixed position. The drone is integrated with a radio frequency energy transmitter and an edge server. The radio frequency energy transmitter can radiate energy outward. The wireless device can simultaneously capture the energy radiated outward by the drone through the energy collection circuit and store the energy in the battery. When obtaining the channel gain h = [h1,h2,…,h i ,…,hN ],h i After the channel gain between the ith wireless device and the drone is input into the fully connected neural network model, the data transmission time ratio of each wireless device can be obtained. i …,τ N ],τ i is the data transmission duration ratio of the i-th wireless device, which is the ratio of the time it takes for the wireless device to transmit data to the drone to the entire time excluding energy capture, and 0≤τ i ≤1, N represents the number of wireless devices.

[0089] In one possible implementation, the acquisition module 210 is also used for a fully connected neural network model including 1 input layer, 2 hidden layers and 1 output layer, the first hidden layer has 200 neurons, the second hidden layer has 120 neurons, and the output layer has 1 neuron, wherein the activation function is a Sigmoid function.

[0090] In a possible implementation, the loss function of the acquisition module 210 for the fully connected neural network model includes:

[0091]

[0092] Among them, S is the loss function.

[0093] The processing module 220 is used to obtain the energy capture time ratio of the wireless device according to the data transmission time ratio and channel gain of the wireless device. The energy capture time ratio is the time ratio occupied by the wireless device to obtain the energy transmitted by the drone in a single time slot.

[0094] Specifically, the energy capture duration ratio of the wireless device can be obtained according to the data transmission duration ratio and channel gain of the wireless device. The energy captured by the wireless device can be expressed as E i =μPh i a,i=1,2,…,N,h i is the channel gain between the i-th wireless device and the drone, μ is the energy capture efficiency of the wireless device, p is the transmission power of the RF energy transmitter in the drone, and a is the energy capture time ratio of the wireless device. The energy captured by the wireless device can be calculated based on the energy capture time ratio of the wireless device.

[0095] In one implementation, the processing module 220 is further configured to obtain the energy capture duration ratio of the wireless device according to the data transmission duration ratio and the channel gain of the wireless device, including:

[0096] The formula for calculating the energy capture duration ratio of a wireless device is as follows:

[0097]

[0098] in, 0≤a≤1, p is the transmission power of the RF energy transmitter in the drone, h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, and v is the coefficient of the additional data overhead generated during the transmission process. The binary method is used to solve f(a). When a meets the preset threshold range, the value of a at this time is determined as the energy capture time ratio of the wireless device.

[0099] The determination module 230 is used to determine the maximum transmission rate between the wireless device and the drone according to the data transmission time ratio, the energy capture time ratio, and the channel gain.

[0100] Specifically, after obtaining the data transmission time ratio, energy capture time ratio, and channel gain, the transmission rate between the wireless device and the drone can be calculated. Since a at this time is the optimal energy capture time ratio of the wireless device, the transmission rate calculated at this time is the maximum transmission rate of the wireless edge computing network.

[0101] In a possible implementation, the determination module 230 is further used to determine the maximum transmission rate between the wireless device and the drone according to the data transmission duration ratio, the energy capture duration ratio, and the channel gain, including:

[0102] The formula for calculating the total transmission rate of N wireless devices is as follows:

[0103]

[0104] Among them, r is the maximum transmission rate between the wireless device and the drone, p is the transmission power of the RF energy transmitter in the drone, and h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, v is the coefficient of the additional data overhead generated during the transmission process, a is the energy capture time ratio of the wireless device, and N is the number of wireless devices.

[0105] In one possible implementation, the determination module 230 is also used to obtain the data transmission duration of each wireless device based on the data transmission duration ratio; according to the data transmission duration of each wireless device, each wireless device is configured to transmit data to the drone within each time slot according to the data transmission duration of each wireless device.

[0106] The time allocation device for the power transmission line detection scenario based on wireless power supply of unmanned aerial vehicles of the present application includes an acquisition module, a processing module and a determination module. The acquisition module is used to construct a fully connected neural network model with the channel gain of the wireless device as input and the data transmission time ratio as output, and the channel gain of at least one wireless device is input into the fully connected neural network model to obtain the data transmission time ratio of at least one wireless device in a single time slot; the processing module is used to obtain the energy capture time ratio of the wireless device according to the data transmission time ratio and channel gain of the wireless device, and the energy capture time ratio is the time ratio occupied by the wireless device to obtain the energy emitted by the unmanned aerial vehicle in a single time slot; the determination module is used to determine the maximum transmission rate between the wireless device and the unmanned aerial vehicle according to the data transmission time ratio, the energy capture time ratio and the channel gain, and can maximize the computing rate of the entire edge computing network and reduce the transmission delay by adjusting the energy capture time and data transmission time of the wireless device.

[0107] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0108] Figure 3 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.

[0109] See also Figure 3 , the electronic device 300 includes a memory 310 and a processor 320.

[0110] The processor 320 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0111] The memory 310 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 320 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 310 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 310 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0112] The memory 310 stores executable codes, and when the executable codes are processed by the processor 320 , the processor 320 can execute part or all of the methods described above.

[0113] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0114] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0115] Alternatively, the present application also provides a computer program product that can implement part or all of the steps of the method in the above embodiments, and the computer program product includes a computer program / instructions, which implement part or all of the steps of the method in the above embodiments when the computer program / instructions are executed by a processor.

[0116] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A time allocation method for a power transmission line detection scenario based on wireless power supply from drones, characterized in that: A wireless edge computing network is included, wherein the wireless edge computing network includes a drone and a wireless device, and the method includes: Constructing a fully connected neural network model with the channel gain of the wireless device as input and the data transmission duration ratio as output, inputting the channel gain of at least one of the wireless devices into the fully connected neural network model, and obtaining the data transmission duration ratio of at least one of the wireless devices in a single time slot; According to the data transmission time ratio of the wireless device and the channel gain, the energy capture time ratio of the wireless device is obtained, and the energy capture time ratio is the time ratio occupied by the wireless device in obtaining the energy transmitted by the drone in a single time slot; The maximum transmission rate between the wireless device and the UAV is determined according to the data transmission time ratio, the energy capture time ratio, and the channel gain.

2. The method according to claim 1, characterized in that The fully connected neural network model includes 1 input layer, 2 hidden layers and 1 output layer, the first hidden layer has 200 neurons, the second hidden layer has 120 neurons, the output layer has 1 neuron, and the activation function is a Sigmoid function.

3. The method according to claim 1, characterized in that The step of obtaining the energy capture duration ratio of the wireless device according to the data transmission duration ratio of the wireless device and the channel gain includes: The formula for calculating the energy capture duration ratio of the wireless device is as follows: in, 0≤a≤1, p is the transmission power of the radio frequency energy transmitter in the UAV, h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission duration ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, and v is the coefficient of the additional data overhead generated during the transmission process; The f(a) is solved by using a binary search method. When a satisfies a preset threshold range, the value of a at this time is determined as the energy capture duration ratio of the wireless device.

4. The method according to claim 1, characterized in that: The determining the maximum transmission rate between the wireless device and the drone according to the data transmission duration ratio, the energy capture duration ratio, and the channel gain includes: The formula for calculating the total transmission rate is as follows: Where r is the maximum transmission rate between the wireless device and the drone, p is the transmission power of the RF energy transmitter in the drone, and h i is the channel gain between the ith wireless device and the drone, μ is the energy capture efficiency of the wireless device, τ i is the data transmission time ratio of the i-th wireless device, B is the total bandwidth in the wireless edge computing network, N0 is the noise power, v is the coefficient of the additional data overhead generated during the transmission process, a is the energy capture time ratio of the wireless device, and N is the number of wireless devices.

5. The method according to claim 4, characterized in that The loss function of the fully connected neural network model includes: Among them, S is the loss function.

6. The method according to claim 1, characterized in that Also includes: According to the data transmission duration ratio, obtaining the data transmission duration of each of the wireless devices; According to the data transmission duration of each of the wireless devices, each wireless device is configured to transmit data to the drone within each time slot for the data transmission duration of each wireless device.

7. A time allocation device for a power transmission line detection scenario based on wireless power supply from drones, characterized in that: include: An acquisition module is used to construct a fully connected neural network model with a channel gain of a wireless device as input and a data transmission duration ratio as output, input the channel gain of at least one of the wireless devices into the fully connected neural network model, and obtain the data transmission duration ratio of at least one of the wireless devices in a single time slot; A processing module, configured to obtain an energy capture duration ratio of the wireless device according to the data transmission duration ratio of the wireless device and the channel gain, wherein the energy capture duration ratio is a duration ratio occupied by the wireless device in obtaining energy transmitted by the drone in a single time slot; A determination module is used to determine the maximum transmission rate between the wireless device and the drone according to the data transmission time ratio, the energy capture time ratio, and the channel gain.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: An executable code is stored thereon, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as claimed in any one of claims 1 to 6.

Images