Signal modulation method, electronic device, storage medium and program product

Abstract

The invention provides a signal modulation method, electronic equipment, a storage medium and a program product, relates to the field of energy transmission, and can solve the problem of low energy transmission efficiency in related technologies. The method comprises the following steps: determining waveform parameters on at least one subcarrier according to reference information, wherein the reference information comprises channel state information; and performing signal modulation based on the waveform parameter on the at least one subcarrier to generate a target signal. The energy transmission efficiency can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of energy transmission, and in particular to a signal modulation method, electronic equipment, storage medium, and program product. Background Art

[0002] Radio frequency wireless power transfer (RF-WPT) technology can provide wireless power to electronic devices, freeing them from the limitations of built-in batteries or external power cords. It is often used in passive IoT devices.

[0003] Due to the physical properties of RF signals, the energy of RF signals will be severely attenuated as the distance increases during the propagation process, resulting in a decrease in the energy received by the receiving end from the RF signal, that is, there is a problem of low end-to-end energy transmission efficiency. Summary of the Invention

[0004] The embodiments of the present disclosure provide a signal modulation method, an electronic device, a storage medium, and a program product, which can solve the problem of low energy transmission efficiency in related technologies.

[0005] In one aspect, a signal modulation method is provided, comprising:

[0006] determining waveform parameters on at least one subcarrier based on reference information, wherein the reference information includes channel state information;

[0007] Signal modulation is performed based on the waveform parameters of the at least one subcarrier to generate a target signal.

[0008] In yet another aspect, a signal modulation apparatus is provided, comprising: a processing unit;

[0009] The processing unit is configured to determine waveform parameters on at least one subcarrier based on reference information, wherein the reference information includes channel state information;

[0010] The processing unit is configured to perform signal modulation based on the waveform parameters on the at least one subcarrier to generate a target signal.

[0011] On the other hand, an electronic device is provided, comprising: a memory and a processor; the memory and the processor are coupled; the memory is used to store a computer program; and the processor implements the method described in any one of the above embodiments when executing the computer program.

[0012] On the other hand, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in any one of the above embodiments is implemented.

[0013] On the other hand, a computer program product is provided, which includes computer program instructions, and when the computer program instructions are executed by a processor, the method described in any one of the above embodiments is implemented.

[0014] In embodiments of the present disclosure, a signal modulation apparatus can determine waveform parameters for at least one subcarrier based on reference information and perform signal modulation based on the waveform parameters of the at least one subcarrier to generate a target signal. As such, because the reference information includes channel state information, the signal modulation apparatus of the present disclosure can determine the waveform parameters of the to-be-modulated signal based on the channel state information in the reference information, and then adjust the waveform of the target signal using these waveform parameters, thereby reducing the impact of the channel environment on the target signal and improving the energy transmission efficiency of the signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present disclosure, the following briefly introduces the drawings required for use in some embodiments of the present disclosure. Obviously, the drawings described below are only drawings of some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0016] Figure 1 An architectural diagram of a signal modulation system provided in some embodiments of the present disclosure;

[0017] Figure 2 A flowchart of a signal modulation method provided in some embodiments of the present disclosure;

[0018] Figure 3 A flowchart of another signal modulation method provided in some embodiments of the present disclosure;

[0019] Figure 4 A structural diagram of an action network provided in some embodiments of the present disclosure;

[0020] Figure 5 A structural diagram of an evaluation network provided in some embodiments of the present disclosure;

[0021] Figure 6 A structural diagram of neurons in a fully connected layer of a neural network provided in some embodiments of the present disclosure;

[0022] Figure 7 A structural diagram of a waveform of an optimized signal provided in some embodiments of the present disclosure;

[0023] Figure 8 A comparison chart of signal energy transmission efficiency provided by some embodiments of the present disclosure;

[0024] Figure 9A structural diagram of a signal modulation device provided in some embodiments of the present disclosure;

[0025] Figure 10 A structural diagram of another signal modulation device provided for some embodiments of the present disclosure. DETAILED DESCRIPTION

[0026] The following will clearly and completely describe the technical solutions of this disclosure in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this disclosure, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of this disclosure without making any creative efforts shall fall within the scope of protection of this disclosure.

[0027] It should be noted that in this disclosure, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this disclosure as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the quantity of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features.

[0029] In the description of this disclosure, unless otherwise specified, " / " means "or." For example, A / B can mean A or B. "And / or" in this document simply describes an association relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exists simultaneously, and B exists alone. Furthermore, "at least one" means one or more, and "a plurality" means two or more.

[0030] With the development of Internet of Things (IoT) technology, the demand for IoT sensor devices has increased dramatically. However, the design size and deployment space of sensor devices are often restricted by the usage environment, which limits the capacity of the built-in batteries of IoT devices and requires a lot of manual maintenance. This increases the cost of using IoT devices and makes it difficult to deploy IoT devices on a large scale.

[0031] Passive internet of things (P-IoT) devices refer to devices that do not require built-in batteries or external power cords for power. Such devices can obtain energy through other means to ensure their normal operation.

[0032] Radio frequency wireless power transfer (RF-WPT) technology enables remote communication using radio frequency electromagnetic waves. The RF transmitter acts as a wireless power source, transmitting RF signals to the receiver. The receiver converts the received RF signals into DC power through a rectifier circuit, which then drives passive IoT devices.

[0033] Compared with power supply methods such as built-in batteries or external power cords, passive IoT devices can be designed to be more portable (further reducing space occupation) and sealed (reducing power interfaces and detachable designs), thereby increasing the service life of the device and reducing manual maintenance costs.

[0034] However, due to the physical properties of RF signals, the energy of RF signals will be affected by the channel environment between the transmitter and the receiver during the propagation process, and will be severely attenuated as the distance between the devices increases. This results in a decrease in the energy received by the receiver from the RF signal, that is, there is a problem of low end-to-end energy transmission efficiency.

[0035] In view of this, in the technical solution provided by the present disclosure, a signal modulation device can determine waveform parameters on at least one subcarrier based on reference information and perform signal modulation based on the waveform parameters on at least one subcarrier to generate a target signal. In this way, because the reference information includes channel state information, the signal modulation device in the present disclosure can determine the waveform parameters of the to-be-modulated signal based on the channel state information in the reference information, and then adjust the waveform of the target signal using these waveform parameters, thereby reducing the impact of the channel environment on the target signal and improving the energy transmission efficiency of the signal.

[0036] The following describes in detail the implementation of the embodiments of the present disclosure in conjunction with the accompanying drawings.

[0037] Figure 1 This is an architecture diagram of a signal modulation system provided by an embodiment of the present disclosure. Figure 1 As shown, the signal modulation system includes: a signal modulation device 101 and a signal receiving device 102.

[0038] The signal modulation device 101 is used to determine waveform parameters on at least one subcarrier according to reference information, and perform signal modulation based on the waveform parameters on the at least one subcarrier to generate a target signal.

[0039] The reference information includes channel state information, and the waveform parameters include at least one of the following: amplitude information, phase information, and beam direction information. The amplitude information represents the maximum amplitude of the signal output on the corresponding subcarrier, the phase information represents the initial phase of the signal output on the corresponding subcarrier, and the beam direction information represents the beam direction of the electromagnetic wave output by the signal on the corresponding subcarrier.

[0040] In a possible implementation, the signal modulation device 101 includes a transmitting module 1011 , and the signal receiving device 102 includes a receiving module 1021 and a rectifier circuit 1022 .

[0041] The transmitting module 1011 is used to send a target signal to the receiving module 1021 of the signal receiving device 102. Correspondingly, the receiving module 1021 is used to receive the target signal from the transmitting module 1011. Thereafter, the signal receiving device 102 is used to convert the target signal into electrical energy through the rectifier circuit 1022.

[0042] It should be noted that the signal modulation device 101 and the transmitting module 1011 may also be separate electronic devices. The signal modulation device 101 may transmit the modulated target signal to the transmitting module 1011 via an internal circuit or an external communication link, and the transmitting module 1011 transmits the target signal via electromagnetic waves.

[0043] In addition, the present disclosure does not limit the number of the signal modulation device 101, the transmitting modules 1011, and the signal receiving device 102. For example, the signal modulation device 101 may correspond to multiple transmitting modules 1011, and the transmitting module 1011 may send a target signal to multiple signal receiving devices 102, or multiple transmitting modules 1011 may send a target signal to the same signal receiving device 102.

[0044] Exemplarily, the signal receiving device 102 is configured with a rectifier circuit. After receiving the target signal, the signal receiving device 102 can convert the target signal into direct current through the rectifier circuit to provide power for the signal receiving device.

[0045] Exemplarily, the signal receiving device 102 can be a passive IoT device, such as a wearable device (such as a smart watch, a smart bracelet, a pedometer, etc.), an in-vehicle device (such as a car, a bicycle, an electric car, an airplane, a ship, a train, a high-speed train, etc.), a virtual reality (VR) device, an augmented reality (AR) device, a passive IoT device in industrial control, a smart home device (such as a refrigerator, a television, an air conditioner, an electric meter, etc.), an intelligent robot, a workshop device, a wireless terminal in self-driving, a passive IoT device in remote medical surgery, a passive IoT device in a smart grid, a passive IoT device in transportation safety, a passive IoT device in a smart city, or a passive IoT device in a smart home, a flying device (such as an intelligent robot, a hot air balloon, a drone, an airplane), etc.

[0046] It should be pointed out that the various embodiments of the present disclosure can refer to each other, for example, the same or similar steps, method embodiments, system embodiments and device embodiments can refer to each other without limitation.

[0047] Figure 2 Flowchart of a signal modulation method provided by an embodiment of the present disclosure. Figure 2 As shown, the method includes the following steps:

[0048] Step 201: Determine waveform parameters on at least one subcarrier according to reference information.

[0049] The reference information includes channel state information, which is used to characterize the channel environment between the transmitter and the receiver.

[0050] Exemplarily, the channel state information may include phase shift and path fading of the signal on the at least one subcarrier on different paths. Phase shift refers to the phase offset of the signal during transmission, and path fading refers to the attenuation of signal strength during transmission.

[0051] For example, if there are 10 subcarriers used for signal transmission and 5 channel paths, one subcarrier corresponds to the phase shift and path fading of 5 channel paths. In this case, the channel state information includes 50 phase shifts and 50 path fadings. This channel state information can be represented in the form of a matrix or vector. The phase shift value ranges from 0 to 2π, and the path fading value ranges from 0 to 1.

[0052] Exemplarily, the signal modulation device can act as a transmitter to send a detection reference signal to a receiver, and the receiver determines channel state information based on the detection reference signal and sends the channel state information to the signal modulation device. Accordingly, the signal modulation device obtains the channel state information.

[0053] Step 202: Perform signal modulation based on waveform parameters on at least one subcarrier to generate a target signal.

[0054] In one possible implementation, the waveform parameters include at least one of the following: amplitude information, phase information, and beam direction information. Amplitude information represents the maximum amplitude of the signal output on the corresponding subcarrier, phase information represents the initial phase of the signal output on the corresponding subcarrier, and beam direction information can be the transmit beam direction of the target signal at the transmitter or the receive beam direction of the target signal at the receiver.

[0055] Exemplarily, the signal modulation of the signal modulation device satisfies the following formula 1:

[0056]

[0057] Among them, x i (t) represents the modulated signal on the i-th subcarrier, t represents the time variable, A i Represents the amplitude information of the signal modulated on the i-th subcarrier, f i Indicates the frequency corresponding to the i-th subcarrier, Represents the phase information of the signal modulated on the i-th subcarrier, where i is a positive integer.

[0058] It should be noted that the target signal is obtained by compounding the signal modulated on the at least one subcarrier, and the beam direction of the target signal can be further changed by adjusting the amplitude information and phase information of the signal modulated on the subcarrier.

[0059] Based on the above technical solution, the signal modulation device can determine the waveform parameters of at least one subcarrier based on the reference information and perform signal modulation based on the waveform parameters of the at least one subcarrier to generate a target signal. In this way, because the reference information includes channel state information, the signal modulation device in the present disclosure can determine the waveform parameters of the to-be-modulated signal based on the channel state information in the reference information, and then adjust the waveform of the target signal using these waveform parameters, thereby reducing the impact of the channel environment on the target signal and improving the energy transmission efficiency of the signal.

[0060] In some embodiments, the reference information further includes at least one of the following: transmission configuration information, power constraint information, and voltage constraint information.

[0061] The transmission configuration information includes at least one of the following: a transmit beam, a transmit beam group, a transmit beam pair, a transmit beam direction, a receive beam, a receive beam group, a receive beam pair, and a receive beam direction. The power constraint information includes at least one of the following: an average output power threshold of the transmitter and a signal power per unit frequency threshold. The voltage constraint information includes voltage thresholds for electrical components. The average output power threshold, signal power per unit frequency threshold, and voltage thresholds for electrical components can be set based on actual conditions.

[0062] Exemplarily, the transmitting beam, transmitting beam group, transmitting beam pair, receiving beam, receiving beam group, and receiving beam pair can be represented by numbering, indexing, identification, etc. The transmitting beam direction refers to the beam direction of the target signal at the transmitting end, and the receiving beam direction refers to the beam direction of the target signal at the receiving end.

[0063] It should be noted that the energy transmission efficiency of the target signal can satisfy the following formula 2:

[0064] η=α·β Formula 2

[0065] Among them, α represents the signal propagation efficiency of the target signal from the transmitter to the receiver, and β represents the energy conversion efficiency of the receiver converting the target signal into electrical energy.

[0066] Beam-related information can affect the energy transmission efficiency of the target signal by affecting the signal propagation efficiency of the target signal from the transmitter to the receiver. The beam direction of the signal received by the receiver in different channel environments will also change for the same signal. The shift in the beam direction will cause the signal strength of the signal received by the receiver to weaken (i.e., the signal propagation efficiency is reduced), thereby reducing the energy transmission efficiency. Therefore, the signal modulation device in the present disclosure can determine the waveform parameters in combination with the beam-related information represented by the transmission configuration information and the channel state information, so that the receiving beam direction of the target signal matches the receiving end, thereby improving the energy transmission efficiency of the signal.

[0067] It should be noted that the target signal sent by a high-power radio frequency unit may cause interference to surrounding electronic equipment and even cause potential harm to the human body. Therefore, the signal modulation device in the present disclosure can limit the power of the modulated target signal by configuring power constraint information in the reference information, thereby avoiding the above problems caused by excessive power.

[0068] In addition, if the voltage generated by the electric energy converted by the receiving end is too high, it may cause damage to the electrical components (such as diodes) in the receiving end, thereby affecting the service life of the receiving end. Therefore, the signal modulation device in the present disclosure can also limit the voltage after the modulated target signal is converted into electric energy by configuring voltage constraint information in the reference information, thereby avoiding damage to electrical components due to excessive voltage.

[0069] The following describes the process of determining waveform parameters by the signal modulation device.

[0070] As a possible embodiment of the present disclosure, Figure 2 ,like Figure 3 As shown, the above step 201 can also be implemented through the following step 301.

[0071] Step 301: Input reference information into a functional module to obtain waveform parameters on at least one subcarrier output by the functional module.

[0072] The name of the functional module does not limit itself. In actual implementation, the functional module can be an entity such as an agent, a model, an algorithm, or a node.

[0073] In one possible implementation, the functional module is constructed based on at least one of the following: a deep learning model; a reinforcement learning model; a distributed learning model; or an artificial intelligence model.

[0074] Among them, the deep learning model is an artificial neural network that extracts complex features from input data and performs abstract representation of the data. The deep learning model usually includes multiple layer structures, each layer structure includes multiple neurons, and the neurons are used to perform linear calculations on the data in the previous layer, and then perform nonlinear processing through activation functions.

[0075] Reinforcement learning models are used to simulate an agent in a specific environment, interacting with it to determine the optimal strategy. The agent can perform specific actions and adjust its behavior based on the feedback (reward signals) generated by the specific environment, ultimately achieving an execution result that meets the preset conditions.

[0076] A distributed learning model is an algorithmic model that coordinates the execution of machine learning by building multiple computing nodes. The distributed learning model can complete large-scale machine learning tasks by connecting multiple computing nodes. It is suitable for designing large data sets and training tasks with complex models.

[0077] Artificial intelligence models are those that analyze, process, and predict data by simulating recognition or learning processes. Examples include supervised, unsupervised, and semi-supervised learning models. Supervised learning models are trained using labeled datasets, unsupervised learning models are trained using unlabeled datasets, and semi-supervised learning models are trained using both partially labeled and unlabeled datasets.

[0078] In some embodiments, the functional module includes at least one of the following: an actor network and a critic network.

[0079] Among them, the action network is used to generate action strategies, and the evaluation network is used to simulate a specific environment based on the input reference information and evaluate the action strategies generated by the action network in a specific environment.

[0080] Exemplarily, the evaluation network includes at least an evaluation reward function, which is used to output a signal evaluation value through an efficiency factor and a constraint factor.

[0081] The efficiency factor includes at least one of signal propagation efficiency and signal power gain, and the constraint factor includes at least one of a transmitting end average output power exceeding limit, a unit frequency signal power exceeding limit, and an electrical component voltage exceeding limit.

[0082] Among them, the signal propagation efficiency can be expressed by the ratio of the output power of the receiving end to the output power of the transmitting end, the signal power gain can be expressed by the ratio of the output power of the modulated optimized signal at the receiving end to the output power of the unmodulated optimized signal (for example, a sinusoidal wave signal with the same power as the modulated optimized signal) at the receiving end, the average output power excess value of the transmitting end can be expressed by the difference between the output power of the transmitting end and the average output power threshold of the transmitting end, the unit frequency signal power excess value can be expressed by the difference between the unit frequency signal power and the unit frequency signal power threshold, and the voltage excess value of the electrical component can be expressed by the difference between the maximum voltage of the electrical component and the voltage threshold of the electrical component.

[0083] It should be noted that, in conjunction with Formula 2 above, the signal propagation efficiency in the efficiency factor represents the energy loss of the modulated signal as it propagates through the channel. A higher signal propagation efficiency indicates less energy loss during the propagation of the modulated signal through the channel, thereby improving the signal's energy conversion efficiency.

[0084] The signal power gain in the efficiency factor can represent the gain value of the output power of the modulated signal at the receiving end compared to the output power of the unmodulated signal at the receiving end. The higher the gain value, the more significant the effect of improving the signal propagation efficiency through modulation, which can effectively improve the energy conversion efficiency of the signal.

[0085] Taking the example that the functional module includes an action network and a judgment network, the signal modulation device can input the reference information into the action network and the judgment network in the functional module respectively.

[0086] The action network uses reference information to output waveform parameters for at least one subcarrier, representing the action strategy executed by the agent. The evaluation network simulates the waveform parameters of the at least one subcarrier in a specific environment and outputs a signal evaluation value. This signal evaluation value represents the energy transmission efficiency of a signal modulated by the waveform parameters of the at least one subcarrier.

[0087] The action network adjusts according to the output signal evaluation value and re-outputs the waveform parameters on at least one subcarrier. The signal modulation device repeatedly trains the functional module through the above process to improve the energy transmission efficiency.

[0088] Through the above training method, the judgment network can simulate the signal modulated by the current waveform parameters through simulation, and then obtain the energy transmission efficiency of the signal. Based on the energy transmission efficiency, the signal judgment value is output, and the action network can adjust the action strategy according to the signal judgment value. Therefore, the action network and the judgment network can be continuously trained and updated in this complementary way, thereby improving the model training effect and outputting waveform parameters that make the signal energy transmission efficiency higher.

[0089] For example, the action network and the judgment network include a fully connected layer and an activation layer. Figure 4 As shown in the figure, the data in the input action network passes through fully connected layer 1, activation layer 1, fully connected layer 2, activation layer 2, fully connected layer 3, activation layer 3, and fully connected layer 4 in sequence. After that, the data in fully connected layer 4 is input into activation layer 4 and activation layer 5 respectively. The data in activation layer 4 passes through fully connected layer 5 and the scaling layer in sequence to output the average value of the waveform parameters. The data in activation layer 5 passes through fully connected layer 6 and activation layer 6 in sequence to output the standard deviation of the waveform parameters.

[0090] like Figure 5As shown in the figure, the data input into the evaluation network passes through the fully connected layer a, activation layer a, fully connected layer b, activation layer b, fully connected layer c, activation layer c and fully connected layer d in sequence, and the output signal evaluation value is obtained.

[0091] Among them, the activation functions in activation layer 1, activation layer 2, activation layer 3, activation layer a, activation layer b, and activation layer c can be relu functions, the activation functions in activation layer 4 and activation layer 5 can be tanh functions, and the function in activation layer 6 can be softplus functions.

[0092] For example, Figure 6 A structural diagram of neurons in a fully connected layer of a neural network provided for some embodiments of the present disclosure. Each fully connected layer includes multiple neurons, each neuron has multiple input data and multiple output data, and any neuron in the current fully connected layer is connected to all neurons in the previous fully connected layer, that is, any neuron uses the data output by all neurons in the previous layer as input data for linear calculation. The activation layer (not shown in the figure) performs separate nonlinear processing on the output data of each neuron in the fully connected layer, that is, the number of data output by the activation layer is consistent with the number of data output by the corresponding fully connected layer.

[0093] In some embodiments, the ratio of the peak power to the average power of the target signal is greater than a preset ratio, or the ratio of the peak power to the average power of the target signal is greater than the ratio of the peak power to the average power of the signal before signal modulation.

[0094] The ratio of peak power to average power is also called peak to average power ratio (PAPR).

[0095] It should be noted that, in combination with the above formula 2, the energy transmission efficiency of the target signal is related to the signal propagation efficiency and the energy conversion efficiency. In the process of converting the target signal into electrical energy through the rectifier circuit at the receiving end, since the diode has a certain conduction threshold, the low-power signal will lose most of its energy due to the conduction threshold, resulting in low energy conversion efficiency. Therefore, the signal modulation device in the present disclosure can adjust the waveform of the target signal through the waveform parameters so that the ratio of the peak power to the average power of the target signal is greater than the preset ratio, or the ratio of the peak power to the average power of the target signal is greater than the ratio of the peak power to the average power of the signal before signal modulation. This type of waveform has a periodic high-power peak, so it can effectively turn on the diode and convert it into electrical energy, thereby improving the energy conversion efficiency.

[0096] The following describes the training process of the functional modules involved in the embodiments of the present disclosure in the form of examples.

[0097] Step 1: The signal modulation device determines reference information.

[0098] Taking the channel state information included in the reference information as an example, the channel state information can be obtained by simulation calculation for a simulation scenario. For example, there are five channel paths between the transmitter and the receiver, with channel path lengths of 3m, 3.2m, 3.4m, 3.6m, and 3.8m, respectively. The subcarrier frequencies required by the signal modulation device correspond to 910MHz, 911MHz, 912MHz, 913MHz, 914MHz, 915MHz, 916MHz, 917MHz, 918MHz, and 919MHz, respectively.

[0099] The signal modulation device calculates the phase shift and path fading based on the above information. For example, the signal modulation device calculates a total of 50 phase shifts by dividing the channel path length by the signal wavelength and taking the remainder. These are the phase shifts of the 10 subcarriers along the five channel paths. The signal modulation device calculates the 50 path fadings using the Friis transmission formula.

[0100] Step 2: The signal modulation device builds the specific environment required for the functional module.

[0101] Exemplarily, the signal modulation device can construct a specific environment through MATLAB, and initialize the state space parameters and action space parameters (i.e., waveform parameters) required in the specific environment and the constructor, respectively. The following is the MATLAB code in the initialization process:

[0102] classdef WPT_PPO_Env <rl.env.MATLABEnvironment

[0103] observationInfo=rlNumericSpec([103,1]);

[0104] actionInfo=rlNumericSpec([20,1]);

[0105] WPT_PPO_Env represents the specific environment, observationInfo represents the state space parameters, and actionInfo represents the action space parameters. The state space parameters are a one-dimensional vector of length 103, each containing 50 phase shifts, 50 path fadings, the average output power threshold of the transmitter, the signal power threshold per unit frequency, and the voltage threshold of the electrical component. The action space parameters are a one-dimensional vector of length 20, each containing the amplitude information corresponding to 10 subcarriers and the phase information corresponding to 10 subcarriers.

[0106] It should be noted that the above-mentioned state space parameters are defined based on the example that the reference information includes channel state information, power constraint information, and voltage constraint information, and the above-mentioned action space parameters are defined based on the example that the waveform parameters include amplitude information and phase information. When the reference information and waveform parameters also include other information, the state space parameters and action space parameters can be adapted accordingly.

[0107] The signal modulation device also needs to define the action strategy function and the judgment reward function.

[0108] Among them, the action strategy function can be defined by the following code:

[0109] function[observation,reward,isDone]=step(this,action)

[0110] The input information of the action strategy function includes the action space parameters output by the action network, and the output information of the action strategy function includes the state space parameters of the next round, the signal judgment value output by the judgment reward function, and the training stop flag parameter.

[0111] The training stop flag parameter isDone is used to indicate whether the current training meets the preset training conditions. When the preset training conditions are met, the signal modulation device can stop the current round of model training and perform the next round of model training. Exemplarily, the signal modulation device can also set this flag parameter to not stop, that is, the training will not stop until the number of training times in each round reaches the preset number of training times. For example, the code definition of the training stop flag parameter is:

[0112] isDone = false;

[0113] When the current round of training is completed, the signal modulation device can reset the specific environment and start the next round of training. The reset environment function can be defined by the following code:

[0114] function observation=reset(this)

[0115] By resetting the specific environment, the signal modulation device can train the functional module to modulate the signal in different channel environments, so that the functional module can be applied to various channel environments. For example, the signal modulation device can change the channel environment by changing the channel path.

[0116] In the process of calculating the signal evaluation value through the evaluation reward function, the signal modulation device needs to parse the action space parameters through the following code:

[0117] amp = action(1:10) + 1;

[0118] phi=action(11:20)*pi;

[0119] Here, action(1:10) refers to the amplitude information corresponding to the 10 subcarriers in the action space parameters, action(11:20) refers to the phase information corresponding to the 10 subcarriers in the action space parameters, amp is the amplitude, ranging from 0 to 2, and phi is the initial phase, ranging from -π to π.

[0120] The signal modulation device can process the above amplitude and initial phase through mathematical modeling or software simulation to obtain the signal parameters of the target signal, such as the output power of the transmitter, the output power of the receiver, the signal power per unit frequency, the maximum voltage of the electrical component, etc. After that, the signal modulation device can output the signal evaluation value through the evaluation reward function. Among them, the output power of the transmitter and the output power of the receiver can be the average output power. The evaluation reward function can be defined by the following code:

[0121] reward=u1*Pr / Pt+u2*Pmod / Punmod–u3*max(0,Pt–Pmax)–u4*max(0,Pf–Pfmax)–u5*max(Vd-Vmax)

[0122] Among them, reward is the output signal evaluation value, Pr is the output power of the receiving end, Pt is the output power of the transmitting end, Pmod is the output power of the modulated optimized signal at the receiving end, Punmod is the output power of the unmodulated optimized signal (for example, a sine wave signal with the same power as the modulated optimized signal) at the receiving end, Pmax is the average output power threshold of the transmitting end, Pf is the unit frequency signal power, Pfmax is the unit frequency signal power threshold, Vd is the maximum voltage of the electrical component, and Vmax is the voltage threshold of the electrical component. u1, u2, u3, u4, and u5 are greater than or equal to normalization coefficients, which are used to balance the impact of different factors in the reward function on the signal evaluation value and can be set according to actual conditions. For example, setting u1 to 0.5 and u2 to 0 means that the efficiency factor in the reward function only includes signal propagation efficiency.

[0123] It should be noted that the factors in the above-mentioned evaluation reward function are defined based on the example that the reference information includes channel state information, power constraint information, and voltage constraint information. When the reference information also includes other information, the evaluation reward function can be adapted accordingly.

[0124] Step 3: The signal modulation device constructs a functional module.

[0125] Among them, the functional module includes action network and evaluation network. Figure 4, the action network can be defined by the following code:

[0126]

[0127]

[0128]

[0129] Step 4: The signal modulation device performs model training on the functional module.

[0130] The signal modulation device sets the model training parameters and performs model training. The relevant process can be implemented through the following code:

[0131] trainingOptions=rlTrainingOptions(...

[0132] 'MaxEpisodes',1000,...% Maximum number of episodes

[0133] 'MaxStepsPerEpisode',80);% Maximum number of steps per round

[0134] trainStats=train(agent,env,trainingOptions);

[0135] Step 5: The signal modulation device outputs the action space parameters through the trained functional module.

[0136] The signal modulation device can input the state space parameters into the trained function module, thereby outputting the action space parameters. The relevant process can be implemented by the following code:

[0137] action=agent.getAction(observation)

[0138] Among them, action is the output action space parameter, and the waveform parameters corresponding to each subcarrier can be obtained through mapping analysis.

[0139] This paper randomly generates 3000 channel environments and calculates the reference information of different frequency subcarriers. The optimized waveform parameters are obtained through the above scheme, and the energy transmission efficiency before and after optimization is calculated under the same power. Figure 7 As shown, Figure 7 This is a structural diagram of the waveform of the optimized signal under different environments provided by some embodiments of the present disclosure.

[0140] In combination with the above example, the signal modulation device determines the waveform parameters of 10 subcarriers with frequencies of 910 MHz to 919 MHz according to the reference information as shown in Table 1 below:

[0141] Table 1 List of waveform parameters on subcarriers

[0142]

[0143] Figure 8 This is a statistical comparison chart of the energy transmission efficiency of the waveform of the signal after signal modulation optimization based on the above waveform parameters and the waveforms of other types of signals. After comparative statistical analysis, the energy transmission efficiency of the optimized signal has a significant improvement in rectification efficiency compared with other waveforms, which can significantly improve the energy transmission efficiency of the signal.

[0144] It is understandable that, in order to realize the above functions, the signal modulation device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the algorithm steps of each example described in the embodiments of the present disclosure, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present disclosure.

[0145] The embodiment of the present disclosure can divide the signal modulation device into functional modules according to the above-mentioned method embodiment. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one functional module. The above-mentioned integrated module can be implemented in the form of hardware or software. It should be noted that the division of modules in the embodiment of the present disclosure is schematic and is only a logical function division. There may be other division methods in actual implementation. The following is an example of dividing each functional module corresponding to each function.

[0146] Figure 9 : is a structural diagram of a signal modulation device provided by an embodiment of the present disclosure, and the signal modulation device can execute the signal modulation method provided by the above method embodiment. Figure 9 As shown, the signal modulation device 90 includes: a processing unit 901.

[0147] A processing unit 901 is configured to determine waveform parameters on at least one subcarrier based on reference information, where the reference information includes channel state information;

[0148] The processing unit 901 is configured to perform signal modulation based on waveform parameters on at least one subcarrier to generate a target signal.

[0149] In some embodiments, the waveform parameter includes at least one of the following: amplitude information, phase information, and beam direction information.

[0150] In some embodiments, the reference information further includes at least one of the following: transmission configuration information, power constraint information, and voltage constraint information.

[0151] In some embodiments, the transmission configuration information includes at least one of the following: a transmit beam, a transmit beam group, a transmit beam pair, a transmit beam direction, a receive beam, a receive beam group, a receive beam pair, and a receive beam direction.

[0152] In some embodiments, the power constraint information includes at least one of the following: an average output power threshold of the transmitting end, and a unit frequency signal power threshold.

[0153] In some embodiments, the voltage constraint information includes a voltage threshold value of the electrical component.

[0154] In some embodiments, the processing unit 901 is configured to input reference information into a functional module to obtain waveform parameters on at least one subcarrier output by the functional module.

[0155] In some embodiments, the functional module is constructed based on at least one of the following: a deep learning model; a reinforcement learning model; a distributed learning model; an artificial intelligence model.

[0156] In some embodiments, the functional module includes at least one of the following: an action network and a judgment network.

[0157] In some embodiments, the action network includes a judgment reward function, which is used to output a signal judgment value through an efficiency factor and a constraint factor; the efficiency factor includes at least one of the signal propagation efficiency and the signal power gain; the constraint factor includes at least one of the average output power exceeding the limit value of the transmitting end, the unit frequency signal power exceeding the limit value, and the voltage exceeding the limit value of the electrical component.

[0158] In some embodiments, the ratio of the peak power to the average power of the target signal is greater than a preset ratio, or the ratio of the peak power to the average power of the target signal is greater than the ratio of the peak power to the average power of the signal before signal modulation.

[0159] In some embodiments, the signal modulation device 90 further includes a communication unit 902 , which is configured to send a target signal.

[0160] In the case of implementing the functions of the above-mentioned integrated modules in the form of hardware, the embodiment of the present disclosure provides another possible structure of the signal modulation device involved in the above-mentioned embodiment. Figure 10As shown, the signal modulation device 100 includes: a processor 1002 and a bus 1004. Optionally, the signal modulation device 100 may further include a memory 1001; and optionally, the signal modulation device 100 may further include a communication interface 1003.

[0161] Processor 1002 may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of this disclosure. Processor 1002 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of this disclosure. Processor 1002 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, or a combination of a DSP and a microprocessor.

[0162] The communication interface 1003 is used to connect to other devices via a communication network, such as Ethernet, wireless access network, or wireless local area network (WLAN).

[0163] The memory 1001 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0164] As a possible implementation, the memory 1001 can exist independently of the processor 1002. The memory 1001 can be connected to the processor 1002 via a bus 1004 to store instructions or program codes. When the processor 1002 calls and executes the instructions or program codes stored in the memory 1001, the method described in any of the embodiments of the present disclosure can be implemented.

[0165] In another possible implementation, the memory 1001 may also be integrated with the processor 1002 .

[0166] The bus 1004 may be an extended industry standard architecture (EISA) bus, etc. The bus 1004 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0167] Some embodiments of the present disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium), which stores computer program instructions. When the computer program instructions are executed on a computer, the computer executes the method described in any of the above embodiments.

[0168] Exemplarily, the above-mentioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes, etc.), optical disks (e.g., compact disks (CDs), digital versatile disks (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memories (EPROMs), cards, sticks, or key drives, etc.). The various computer-readable storage media described in the present disclosure may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0169] An embodiment of the present disclosure provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method described in any one of the above embodiments.

[0170] The above is only a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or replacements within the technical scope disclosed in the present disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A signal modulation method, characterized in that: include: determining waveform parameters on at least one subcarrier based on reference information, wherein the reference information includes channel state information; Signal modulation is performed based on the waveform parameters of the at least one subcarrier to generate a target signal.

2. The method according to claim 1, characterized in that The waveform parameters include at least one of the following: amplitude information, phase information, and beam direction information.

3. The method according to claim 1, characterized in that The reference information also includes at least one of the following: transmission configuration information, power constraint information, and voltage constraint information.

4. The method according to claim 3, characterized in that The transmission configuration information includes at least one of the following: a transmit beam, a transmit beam group, a transmit beam pair, a transmit beam direction, a receive beam, a receive beam group, a receive beam pair, and a receive beam direction.

5. The method according to claim 3, characterized in that The power constraint information includes at least one of the following: an average output power threshold of the transmitting end and a unit frequency signal power threshold.

6. The method according to claim 3, characterized in that The voltage constraint information includes a voltage threshold of the electrical component.

7. The method according to claim 1, characterized in that The determining, according to the reference information, a waveform parameter on the at least one subcarrier includes: The reference information is input into a functional module to obtain waveform parameters on the at least one subcarrier output by the functional module.

8. The method according to claim 7, characterized in that The functional module is constructed based on at least one of the following: Deep learning models; reinforcement learning models; Distributed learning model; Artificial intelligence model.

9. The method according to claim 8, characterized in that The functional module includes at least one of the following: an action network and a judgment network.

10. The method according to claim 9, characterized in that The action network includes a judgment reward function, which is used to output a signal judgment value through an efficiency factor and a constraint factor; the efficiency factor includes at least one of the signal propagation efficiency and the signal power gain; the constraint factor includes at least one of the average output power exceeding the limit value of the transmitting end, the unit frequency signal power exceeding the limit value, and the voltage exceeding the limit value of the electrical component.

11. The method according to claim 1, wherein The ratio of the peak power to the average power of the target signal is greater than a preset ratio, or the ratio of the peak power to the average power of the target signal is greater than the ratio of the peak power to the average power of the signal before signal modulation.

12. An electronic device, characterized in that: include: memory and processor; Memory and processor coupling; The memory is used to store instructions executable by the processor; When the processor executes the instructions, the method according to any one of claims 1 to 11 is performed.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 11.

14. A computer program product, characterized in that The computer program product comprises computer program instructions, which implement the method according to any one of claims 1 to 11 when executed by a processor.

Images