Method and device for controlling laser emission power in satellite communication and storage medium

Abstract

The invention discloses a method and device for controlling laser transmitting power in satellite communication and a storage medium, and the method comprises the steps: receiving the receiving power transmitted by a second satellite in communication connection at the current moment, and determining a receiving power deviation value according to the receiving power and preset reference receiving power; determining a proportional term, an integral term and a differential term for PID control based on the received power deviation value; determining a plurality of statistical periods before the current moment, and determining a mean value and a variance of the received power deviation values corresponding to each statistical period; determining a mean value and a variance of the received power deviation values corresponding to each statistical period as input features, inputting the input features into a pre-trained convolutional neural network, and outputting a first weight value corresponding to a proportional item, a second weight value corresponding to an integral item and a third weight value corresponding to a differential item; and determining a power control signal for controlling the transmitting power of the laser transmitter based on the determined value.

Description

Technical Field

[0001] This application relates to the field of satellite communication technology, and in particular to a method, apparatus and storage medium for controlling laser emission power in satellite communication. Background Technology

[0002] With the rapid development of space information networks, inter-satellite laser communication technology has become a core means of building a high-speed integrated space-ground communication network due to its advantages such as high bandwidth, high security, and strong anti-interference capabilities. However, in the dynamic link environment of ultra-long distances and high-speed relative motion between transmitting and receiving satellites, this technology faces severe challenges: the satellite communication link distance is extremely far, and the two communicating parties (i.e., the two satellites connected by the communication) are always in high-speed orbital motion. In this scenario, the stability of the satellite link is easily affected. For example, the inherent micro-vibration environment of the satellite can cause directional jitter in the transmitted beam; atmospheric turbulence and scintillation effects can cause beam wavefront distortion, beam drift, and intensity fluctuations; atmospheric refraction can cause angular shifts in the beam, and so on. These factors cause fluctuations in the stability of the laser link. Therefore, if the satellite always transmits lasers at a fixed power, it is difficult to adapt to the complex laser communication environment, resulting in power jitter and bit setting errors.

[0003] The existing technologies mentioned above are prone to stability fluctuations in ultra-long-distance dynamic links. Therefore, if the satellite always emits lasers at a fixed power, it is difficult to adapt to the complex laser communication environment, which can easily lead to technical problems such as receiving power jitter or even bit errors. At present, no effective solution has been proposed. Summary of the Invention

[0004] The embodiments of this disclosure provide a method, apparatus, and storage medium for controlling laser transmission power in satellite communication, in order to at least solve the technical problem that exists in the prior art: in ultra-long-distance dynamic links, the stability of laser links is prone to fluctuations. Therefore, if the satellite always transmits lasers at a fixed power, it is difficult to adapt to the complex laser communication environment, which can easily lead to received power jitter or even bit errors.

[0005] According to one aspect of the present disclosure, a method for controlling laser emission power in satellite communication is provided, comprising: a first satellite receiving received power transmitted by a second satellite connected in communication at a current time, and determining a received power deviation value based on the received power and a pre-set reference received power; the first satellite determining a proportional term, an integral term, and a derivative term for PID control based on the received power deviation value; the first satellite determining multiple statistical periods prior to the current time, and determining the mean and variance of the received power deviation values ​​corresponding to each statistical period, wherein the statistical period includes multiple statistical times; the first satellite determining the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputting the input features into a pre-trained convolutional neural network, outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the derivative term; and the first satellite determining a power control signal for controlling the emission power of a laser transmitter based on the proportional term, the first weight value, the integral term, the second weight value, the derivative term, and the third weight value, and sending the power control signal to the laser transmitter.

[0006] According to another aspect of the present disclosure, a storage medium is also provided, the storage medium including a stored program, wherein, when the program is executed, a processor performs any of the methods described above.

[0007] According to another aspect of the present disclosure, an apparatus for controlling laser emission power in satellite communication is also provided, comprising: a received power deviation value determination module, configured to: a first satellite receive received power transmitted by a second satellite connected in communication at a current time, and determine a received power deviation value based on the received power and a preset reference received power; a PID control term determination module, configured to: the first satellite determine a proportional term, an integral term, and a derivative term for PID control based on the received power deviation value; and a mean and variance determination module, configured to: the first satellite determine multiple statistical periods prior to the current time, and determine the mean and variance of the received power deviation values ​​corresponding to each statistical period. The system comprises: a statistical period including multiple statistical moments; a weight value determination module, used by the first satellite to determine the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputting the input features into a pre-trained convolutional neural network, outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term; and a power control signal determination module, used by the first satellite to determine a power control signal for controlling the transmission power of the laser transmitter based on the proportional term, the first weight value, the integral term, the second weight value, the differential term, and the third weight value, and sending the power control signal to the laser transmitter.

[0008] According to another aspect of the present disclosure, an apparatus for controlling laser emission power in satellite communication is also provided, comprising: a processor; and a memory connected to the processor, configured to provide the processor with instructions for processing the following steps: a first satellite receives received power transmitted by a second satellite connected in communication at a current time, and determines a received power deviation value based on the received power and a preset reference received power; the first satellite determines a proportional term, an integral term, and a derivative term for PID control based on the received power deviation value; the first satellite determines multiple statistical periods prior to the current time, and determines the mean and variance of the received power deviation values ​​corresponding to each statistical period, wherein the statistical period includes multiple statistical times; the first satellite determines the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputs the input features into a pre-trained convolutional neural network, outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the derivative term; and the first satellite determines a power control signal for controlling the emission power of a laser transmitter based on the proportional term, the first weight value, the integral term, the second weight value, the derivative term, and the third weight value, and sends the power control signal to the laser transmitter.

[0009] This application provides a method for controlling laser emission power in satellite communication. First, a first satellite receives the received power transmitted by a second satellite connected via a communication link at the current moment, and determines a received power deviation value based on the received power and a pre-set reference received power. Then, based on the received power deviation value, the first satellite determines the proportional, integral, and derivative terms for PID control. Further, the first satellite determines multiple statistical periods prior to the current moment and determines the mean and variance of the received power deviation values ​​corresponding to each statistical period. The first satellite then uses the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputs these features into a pre-trained convolutional neural network, which outputs a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the derivative term. Finally, based on the proportional term, the first weight value, the integral term, the second weight value, the derivative term, and the third weight value, the first satellite determines a power control signal for controlling the emission power of the laser transmitter and sends the power control signal to the laser transmitter.

[0010] As described above, this application determines the received power deviation value based on the received power transmitted by the second satellite and a pre-set reference received power. The received power deviation value indicates the fluctuation of the received power of the first satellite. Then, based on the received power deviation value, the first satellite determines the proportional, integral, and derivative terms for PID control. After determining the first, second, and third weight values, it determines a power control signal for controlling the laser transmitter's transmission power based on the proportional, first, integral, second, derivative, and third weight values, and sends the power control signal to the laser transmitter. Thus, the laser transmitter can transmit power to the second satellite based on the fluctuation of the received power from the first satellite.

[0011] This achieves the technical effect of adjusting laser transmission power according to the fluctuations in the laser link, thereby adapting to complex laser communication environments and avoiding power jitter or even bit errors. It also solves the technical problem in existing technologies where the stability of the laser link is prone to fluctuations in ultra-long-distance dynamic links. Therefore, if the satellite always transmits lasers at a fixed power, it is difficult to adapt to complex laser communication environments, which can easily lead to received power jitter or even bit errors. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this application, illustrate exemplary embodiments of this disclosure and are used to explain this disclosure, but do not constitute an undue limitation of this disclosure. In the drawings:

[0013] Figure 1 This is a schematic diagram of the communication connection between the first satellite and the second satellite according to Embodiment 1 of this application;

[0014] Figure 2 These are the communication module diagrams of the first satellite and the second satellite as described in Embodiment 1 of this application;

[0015] Figure 3 This is a schematic diagram of the hardware architecture of the first and second satellites according to Embodiment 1 of this application;

[0016] Figure 4 This is a flowchart of a method for controlling laser emission power in satellite communication according to Embodiment 1 of this application;

[0017] Figure 5 This is a modular schematic diagram of the laser power controller according to Embodiment 1 of this application;

[0018] Figure 6 This is a schematic diagram of the convolutional neural network according to Embodiment 1 of this application;

[0019] Figure 7 This is a schematic diagram of a device for controlling laser emission power in satellite communication according to Embodiment 2 of this application;

[0020] Figure 8 This is a schematic diagram of a device for controlling laser emission power in satellite communication according to Embodiment 3 of this application. Detailed Implementation

[0021] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this disclosure.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] Example 1

[0024] According to this embodiment, a method embodiment for controlling laser emission power in satellite communication is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] Figure 1 This is a schematic diagram illustrating the communication connection between a first satellite and a second satellite according to an embodiment of this application. (Reference) Figure 1 As shown, the first satellite S1 establishes a communication connection with the second satellite S2 through a laser link, so that the first satellite S1 and the second satellite S2 can transmit data information to each other.

[0026] Figure 2 yes Figure 1The diagrams shown depict the communication modules of the first and second satellites. (Reference) Figure 2 As shown, the communication module of the first satellite S1 is taken as an example. The communication module of the first satellite S1 includes a laser transmitter, a laser receiver communication circuit, and a laser power controller.

[0027] In this system, the laser transmitter of the first satellite S1 modulates the data to be transmitted received from the communication circuit and transmits the modulated laser signal to the second satellite S2. The laser receiver of the first satellite S1 receives the laser signal emitted by the laser transmitter of the second satellite S2, demodulates the laser signal into data, and transmits it to the communication circuit, which then transmits it to the corresponding module of the first satellite S1. The laser power controller of the first satellite S1 receives the received power transmitted from the second satellite S2 from the communication circuit and sends a power control signal s to the laser transmitter based on the received power.

[0028] Figure 3 Further shown Figure 1 A schematic diagram of the hardware architecture of the first and second satellites. (Reference) Figure 3 As shown, the first and second satellites include an integrated electronic system, which includes a processor, a memory, a bus management module, and a communication interface. The memory is connected to the processor, allowing the processor to access the memory, read program instructions stored in the memory, read data from the memory, or write data to the memory. The bus management module is connected to the processor and also to a bus such as a CAN bus. Thus, the processor can communicate with onboard peripherals connected to the bus through the bus managed by the bus management module. Furthermore, the processor also communicates with devices such as cameras, star sensors, telemetry and control transponders, and data transmission equipment via the communication interface. Those skilled in the art will understand that… Figure 3 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, a satellite system may also include... Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown.

[0029] It should be noted that, Figure 3 One or more processors and / or other data processing circuits shown herein may generally be referred to as "data processing circuitry". This data processing circuitry may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be integrated, in whole or in part, into any other element in a computing device. As involved in embodiments of this disclosure, the data processing circuitry serves as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0030] Figure 3 The memory shown can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the method for controlling laser emission power in satellite communication in this embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the method for controlling laser emission power in satellite communication described above. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0031] It should be noted here that, in some optional embodiments, the above... Figure 3 The device shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 3 This is only one instance of a specific particular instance, and is intended to illustrate the types of components that may exist in the aforementioned devices.

[0032] Under the aforementioned operating environment, according to the first aspect of this embodiment, a method for controlling laser emission power in satellite communication is provided, the method comprising: Figure 2 The laser power controller shown is implemented. Figure 4 A flowchart illustrating the method is shown below. (Refer to...) Figure 4 As shown, the method includes:

[0033] S402: The first satellite receives the received power transmitted by the second satellite connected by the communication link at the current time, and determines the received power deviation value based on the received power and the preset reference received power;

[0034] S404: The first satellite determines the proportional, integral, and derivative terms for PID control based on the received power deviation value;

[0035] S406: The first satellite determines multiple statistical periods prior to the current time and determines the mean and variance of the received power deviation values ​​corresponding to each statistical period, wherein the statistical period includes multiple statistical times;

[0036] S408: The first satellite determines the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputs these features into a pre-trained convolutional neural network, outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term; and

[0037] S410: The first satellite determines the power control signal for controlling the transmission power of the laser transmitter based on the proportional term, the first weight value, the integral term, the second weight value, the differential term, and the third weight value, and sends the power control signal to the laser transmitter.

[0038] Specifically, Figure 5 A modular schematic diagram of the laser power controller is shown. (Reference) Figure 5 As shown, the laser controller includes a deviation determination module, a PID control module, and a PID weight adjustment module. The deviation determination module is communicatively connected to the PID control module and is used to determine the received power deviation value based on the received power corresponding to the second satellite and a pre-set reference received power. The PID weight adjustment module is also communicatively connected to the PID control module and is used to dynamically adjust the first weight value corresponding to the proportional term, the second weight value corresponding to the integral term, and the third weight value corresponding to the derivative term based on the received power deviation values ​​over multiple statistical periods. Finally, the deviation determination module, also communicatively connected to the PID control module, is used to determine the power control signal s based on the received power deviation value sent by the deviation determination module, as well as the first, second, and third weight values.

[0039] Therefore, firstly, the laser receiver in the first satellite S1 receives the current time t. m The received power p is transmitted by the second satellite S2 connected by communication. Then, the deviation determination module in the laser power controller determines the received power based on the received power corresponding to the second satellite S2 and the preset reference received power p. r The received power deviation value e is determined (S402). The reference received power can be, for example, the standard received power determined by the first satellite S1 based on historical data, or the power determined by the user based on practical experience and uploaded to the first satellite S1 via the gateway station; there is no limitation here. Furthermore, the deviation determination module determines the received power deviation value e based on the following formula. m :

[0040] e m =pp r

[0041] Among them, e m This represents the received power deviation value, where p represents the received power transmitted by the second satellite. r This indicates the reference received power.

[0042] Then, the PID weighting module in the laser emission controller determines the proportional, integral, and derivative terms for PID control based on the received power deviation value (S404). Specifically, firstly, the first satellite determines the received power deviation values ​​corresponding to multiple historical moments prior to the current moment and generates a received power deviation sequence. Then, based on the received power deviation sequence, the first satellite determines the proportional, integral, and derivative terms for PID control. The above will be described in detail later, so it will not be repeated here.

[0043] The PID weight adjustment module in the first satellite then determines multiple statistical periods prior to the current moment and the mean and variance of the received power deviation corresponding to each statistical period, where the statistical period includes multiple statistical moments (S406). Since the environment of inter-satellite laser communication is relatively complex, using fixed weight values ​​could easily lead to the PID control module being unable to adapt well to the complex changes in the space environment. Therefore, a weight adjustment module is deployed in the laser power controller to adjust the first weight value k corresponding to the proportional term. p The second weight value k corresponding to the integral term i And the third weight value k corresponding to the differential term d .

[0044] Therefore, the PID weight adjustment module determines the current time t. m The previous statistical time points are used, and each n statistical time points is defined as a statistical period. The PID weight adjustment module then determines l statistical periods. Taking the first statistical period as an example (e.g., including statistical time point t...),... m-n ~t m Specifically, firstly, the PID weight adjustment module determines the statistical time t. m The corresponding received power deviation value e m , and statistical time t m-1 The corresponding received power deviation value e m-1 ..., and statistical time t m-n The corresponding received power deviation value e m-n .

[0045] Then, the PID weight adjustment module is based on the statistical time t. m-n ~t m The corresponding received power deviation value e m-n ~e m The mean value of the received power deviation corresponding to the first statistical period is determined. The specific formula is as follows:

[0046]

[0047] Where α1 represents the mean value of the received power deviation corresponding to the first statistical period, e j This represents the received power deviation value corresponding to the j-th statistical time.

[0048] The PID weighting module then determines the variance corresponding to the received power deviation value based on the mean of the received power deviation value corresponding to the first statistical period. The specific formula is as follows:

[0049]

[0050] in, This represents the variance of the received power deviation value corresponding to the first statistical period.

[0051] Therefore, the PID weight adjustment module can determine the mean value α2 to α3 of the received power deviation corresponding to the second statistical period to the first statistical period in the same way as described above. l and variance This will not be elaborated upon further here.

[0052] Furthermore, the PID weight adjustment module in the first satellite determines the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputs the input features into a pre-trained convolutional neural network, thereby outputting the first weight value corresponding to the proportional term, the second weight value corresponding to the integral term, and the third weight value corresponding to the differential term (S408). Figure 6 This is a schematic diagram of a convolutional neural network according to an embodiment of this application. (Reference) Figure 6 As shown, the convolutional neural network includes convolutional layers, fully connected layers, and a softmax classifier. Specifically, the PID weight adjustment module in the first satellite determines the mean values ​​α1 to α2 of the received power deviations corresponding to the first statistical period to the 1st statistical period. l and variance In this case, further determine the input features I1~I l .in,

[0053] Then, in the PID weight adjustment module, the input features I1~I l When input is fed into a convolutional neural network, the convolutional neural network can output the first weight value k corresponding to the scaling term. p The second weight value k corresponding to the integral term i And the third weight value k corresponding to the differential term d .

[0054] Finally, the PID weight adjustment module will adjust the first weight value k corresponding to the proportional term. p The second weight value k corresponding to the integral term iAnd the third weight value k corresponding to the differential term d The power deviation value is sent to the PID control module. The deviation determination module receives the power deviation value and sends it to the PID control module, which then determines the power control signal s used to control the laser emitter power and sends the power control signal s to the laser emitter (S410). The above will be described in detail later, so it will not be repeated here.

[0055] As described in the background section, the inherent micro-vibration environment of a satellite can cause directional jitter in the transmitted laser beam; atmospheric turbulence and scintillation can lead to beam wavefront distortion, beam drift, and intensity fluctuations; atmospheric refraction can cause angular shifts in the beam, and so on. These factors cause fluctuations in the stability of the laser link. Therefore, if a satellite always transmits lasers at a fixed power, it will be difficult to adapt to the complex laser communication environment, resulting in power jitter and bit setting errors.

[0056] In view of this, this application determines a received power deviation value based on the received power transmitted by the second satellite and a pre-set reference received power. The received power deviation value represents the fluctuation of the received power of the first satellite. Then, based on the received power deviation value, the first satellite determines the proportional, integral, and derivative terms for PID control. After determining the first, second, and third weight values, it determines a power control signal for controlling the laser transmitter's transmission power based on the proportional, first, integral, second, derivative, and third weight values, and sends the power control signal to the laser transmitter. Thus, the laser transmitter can transmit power to the second satellite based on the fluctuation of the received power from the first satellite.

[0057] This achieves the technical effect of adjusting laser transmission power according to the fluctuations in the laser link, thereby adapting to complex laser communication environments and avoiding power jitter or even bit errors. It also solves the technical problem in existing technologies where the stability of the laser link is prone to fluctuations in ultra-long-distance dynamic links. Therefore, if the satellite always transmits lasers at a fixed power, it is difficult to adapt to complex laser communication environments, which can easily lead to received power jitter or even bit errors.

[0058] Optionally, the first satellite determines the proportional, integral, and derivative terms for PID control based on the received power deviation value, including: the first satellite determines the received power deviation values ​​corresponding to multiple historical moments prior to the current moment and generates a received power deviation sequence, wherein the received power deviation sequence includes the received power deviation value corresponding to the current moment; the first satellite determines the proportional, integral, and derivative terms for PID control based on the received power deviation sequence, using the following calculation formula: P m =e mAmong them, P m e represents the proportion term. m The received power deviation value at the current moment; Among them, I m e represents the integral term. i Let e ​​represent the received power deviation value corresponding to the i-th time point, where i = 0 to m, and when i = m, e m This represents the received power deviation value corresponding to the current time. When i = 0 to m-1, e0 to e m-1 D represents the received power deviation value corresponding to a historical time. m =e m -e m-1 Among them, D m Denotes the differential term, e m-1 This represents the received power deviation value corresponding to the (m-1)th historical moment.

[0059] Specifically, first, the PID control module determines the received power deviation values ​​e0 to e10 corresponding to multiple historical moments prior to the current moment. m-1 For example, e m-1 e represents the received power deviation value corresponding to the first historical moment before the current moment. m-2 e represents the received power deviation value corresponding to the second historical time before the current time, ..., e0 represents the received power deviation value corresponding to the m-th historical time before the current time.

[0060] The PID control module then generates a received power deviation sequence e based on the received power deviation value corresponding to the current time and the received power deviation values ​​corresponding to multiple historical times prior to the current time. 0～ e m .

[0061] Furthermore, the PID control module determines the proportional term used for PID control based on the received power deviation sequence. The specific calculation formula is as follows:

[0062] P m =e m

[0063] Among them, P m e represents the proportion term. m This represents the received power deviation value at the current moment.

[0064] The PID control module determines the integral term used for PID control based on the received power deviation sequence. The specific calculation formula is as follows:

[0065]

[0066] Among them, I me represents the integral term. i Let e ​​represent the received power deviation value corresponding to the i-th historical time, where i = 0 to m, and when i = m, e m This represents the received power deviation value corresponding to the current time. When i = 0 to m-1, e0 to e m-1 This represents the received power deviation value corresponding to a historical time.

[0067] The PID control module determines the derivative term used for PID control based on the received power deviation sequence. The specific calculation formula is as follows:

[0068] D m =e m -e m-1

[0069] Among them, D m Denotes the differential term, e m-1 This represents the received power deviation value corresponding to the (m-1)th historical moment.

[0070] Optionally, the convolutional neural network includes convolutional layers, fully connected layers, and a softmax classifier. The operation of the first satellite inputting input features into the pre-trained convolutional neural network and outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term includes: the first satellite inputting input features into the convolutional layer and the fully connected layer, and outputting vectors corresponding to the first weight value, the second weight value, and the third weight value; and the first satellite inputting the vectors corresponding to the first weight value, the second weight value, and the third weight value into the softmax classifier, and outputting the first weight value, the second weight value, and the third weight value.

[0071] Specifically, Figure 6 This is a schematic diagram of a convolutional neural network according to an embodiment of this application. (Reference) Figure 6 As shown, the convolutional neural network includes convolutional layers, fully connected layers, and a softmax classifier. Specifically, the PID weight adjustment module in the first satellite determines the mean values ​​α1 to α2 of the received power deviations corresponding to the first statistical period to the 1st statistical period. l and variance In this case, further determine the input features I1~I l .in,

[0072] Then, in the PID weight adjustment module, the input features I1~I l When input is fed into a convolutional neural network, the convolutional neural network can output the first weight value k corresponding to the scaling term. p The second weight value k corresponding to the integral termi And the third weight value k corresponding to the differential term d .

[0073] Optionally, the first satellite determines the operation of the power control signal for controlling the emission power of the laser emitter based on a proportional term, a first weight value, an integral term, a second weight value, a differential term, and a third weight value, including: the first satellite determines the power control signal based on the following formula: s m =k p ×P m +k i ×I m +k d ×D m Among them, s m Indicates the power control signal, k p P represents the first weight value. m k represents the proportion term. i Indicates the second weight value, I m Let k represent the integral term. d D represents the third weight value. m This represents the differential term.

[0074] Specifically, given the proportional term, first weight value, integral term, second weight value, derivative term, and third weight value, the PID control module can determine the power control signal based on the following formula:

[0075] s m =k p ×P m +k i ×I m +k d ×D m

[0076] Among them, s m Indicates the power control signal, k p P represents the first weight value. m k represents the proportion term. i Indicates the second weight value, I m Let k represent the integral term. d D represents the third weight value. m This represents the differential term.

[0077] Thus, when the PID control module determines the power control signal, it sends the power control signal to the laser emitter and uses it to adjust the power of the laser emitter.

[0078] In other words, through the above method, during laser communication by the first satellite, the transmission power of the laser transmitter can be controlled in real time based on the receiving power transmitted by the second satellite. It is worth noting for those skilled in the art that the above description uses the first satellite as an example; the second satellite can also perform the same operation, which will not be elaborated upon here.

[0079] Thus, according to the first aspect of this embodiment, the technical effect of being able to change the laser emission power according to the fluctuation of the laser link is achieved, thereby adapting to complex laser communication environments and avoiding power jitter or even bit errors.

[0080] In addition, refer to Figure 1 As shown, according to a second aspect of this embodiment, a storage medium is provided. The storage medium includes a stored program, wherein, when the program is executed, a processor performs any of the methods described above.

[0081] Thus, according to this embodiment, the laser emission power can be varied according to the fluctuation of the laser link, thereby adapting to complex laser communication environments and avoiding power jitter or even bit errors.

[0082] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0083] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0084] Example 2

[0085] Figure 7 An apparatus 700 for controlling laser emission power in satellite communication according to this embodiment is shown, which corresponds to the method described according to Embodiment 1. Reference Figure 7As shown, the device 700 includes: a received power deviation value determination module 710, used for a first satellite to receive the received power transmitted by a second satellite connected by a communication link at the current time, and to determine a received power deviation value based on the received power and a preset reference received power; a PID control term determination module 720, used for the first satellite to determine the proportional term, integral term, and derivative term for PID control based on the received power deviation value; and a mean and variance determination module 730, used for the first satellite to determine multiple statistical periods prior to the current time, and to determine the mean and variance of the received power deviation values ​​corresponding to each statistical period, wherein the statistical period includes multiple statistical periods. The system includes a timing module; a weight value determination module 740, which is used by the first satellite to determine the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and input the input features into a pre-trained convolutional neural network, outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term; and a power control signal determination module 750, which is used by the first satellite to determine a power control signal for controlling the transmission power of the laser transmitter based on the proportional term, the first weight value, the integral term, the second weight value, the differential term, and the third weight value, and send the power control signal to the laser transmitter.

[0086] Optionally, the PID control term determination module 720 includes: a received power deviation sequence generation module, used by the first satellite to determine the received power deviation values ​​corresponding to multiple historical moments before the current moment and generate a received power deviation sequence, wherein the received power deviation sequence includes the received power deviation value corresponding to the current moment; and a first calculation module, used by the first satellite to determine the proportional term, integral term, and derivative term for PID control based on the received power deviation sequence, the calculation formula being as follows: P m =e m Among them, P m e represents the proportion term. m The received power deviation value at the current moment; Among them, I m e represents the integral term. i Let e ​​represent the received power deviation value corresponding to the i-th time point, where i = 0 to m, and when i = m, e m This represents the received power deviation value corresponding to the current time. When i = 0 to m-1, e0 to e m-1 D represents the received power deviation value corresponding to a historical time. m =e m -e m-1 Among them, D m Denotes the differential term, e m-1 This represents the received power deviation value corresponding to the (m-1)th historical moment.

[0087] Optionally, the convolutional neural network includes convolutional layers, fully connected layers, and a softmax classifier. The weight determination module 740 includes: a vector output module, used by the first satellite to input input features into the convolutional layer and the fully connected layer, and output a vector corresponding to a first weight value, a vector corresponding to a second weight value, and a vector corresponding to a third weight value; and a weight determination submodule, used by the first satellite to input the vector corresponding to the first weight value, the vector corresponding to the second weight value, and the vector corresponding to the third weight value into the softmax classifier, and output the first weight value, the second weight value, and the third weight value.

[0088] Optionally, the power control signal determination module 750 includes: a second calculation module for determining the power control signal of the first satellite based on the following formula: s m =k p ×P m +k i ×I m +k d ×d m Among them, s m Indicates the power control signal, k p P represents the first weight value. m k represents the proportion term. i Indicates the second weight value, I m Let k represent the integral term. d D represents the third weight value. m This represents the differential term.

[0089] Thus, according to this embodiment, the laser emission power can be varied according to the fluctuation of the laser link, thereby adapting to complex laser communication environments and avoiding power jitter or even bit errors.

[0090] Example 3

[0091] Figure 8 An apparatus 800 for controlling laser emission power in satellite communication according to this embodiment is shown, which corresponds to the method described according to Embodiment 1. (See reference...) Figure 8As shown, the device 800 includes: a processor 810; and a memory 820 connected to the processor 810, used to provide the processor 810 with instructions to process the following steps: a first satellite receives the received power transmitted by a second satellite connected in communication at the current time, and determines a received power deviation value based on the received power and a preset reference received power; the first satellite determines the proportional term, integral term, and derivative term for PID control based on the received power deviation value; the first satellite determines multiple statistical periods prior to the current time, and determines the mean and variance of the received power deviation values ​​corresponding to each statistical period, wherein the statistical period includes multiple statistical times; the first satellite determines the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputs the input features into a pre-trained convolutional neural network, outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the derivative term; and the first satellite determines a power control signal for controlling the emission power of the laser emitter based on the proportional term, the first weight value, the integral term, the second weight value, the derivative term, and the third weight value, and sends the power control signal to the laser emitter.

[0092] Optionally, the first satellite determines the proportional, integral, and derivative terms for PID control based on the received power deviation value, including: the first satellite determines the received power deviation values ​​corresponding to multiple historical moments prior to the current moment and generates a received power deviation sequence, wherein the received power deviation sequence includes the received power deviation value corresponding to the current moment; the first satellite determines the proportional, integral, and derivative terms for PID control based on the received power deviation sequence, using the following calculation formula: P m =e m Among them, P m e represents the proportion term. m The received power deviation value at the current moment; Among them, I m e represents the integral term. i Let e ​​represent the received power deviation value corresponding to the i-th time point, where i = 0 to m, and when i = m, e m This represents the received power deviation value corresponding to the current time. When i = 0 to m-1, e0 to e m-1 D represents the received power deviation value corresponding to a historical time. m =e m -e m-1 Among them, D m Denotes the differential term, e m-1 This represents the received power deviation value corresponding to the (m-1)th historical moment.

[0093] Optionally, the convolutional neural network includes convolutional layers, fully connected layers, and a softmax classifier. The operation of the first satellite inputting input features into the pre-trained convolutional neural network and outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term includes: the first satellite inputting input features into the convolutional layer and the fully connected layer, and outputting vectors corresponding to the first weight value, the second weight value, and the third weight value; and the first satellite inputting the vectors corresponding to the first weight value, the second weight value, and the third weight value into the softmax classifier, and outputting the first weight value, the second weight value, and the third weight value.

[0094] Optionally, the first satellite determines the operation of the power control signal for controlling the emission power of the laser emitter based on a proportional term, a first weight value, an integral term, a second weight value, a differential term, and a third weight value, including: the first satellite determines the power control signal based on the following formula: s m =k p ×P m +k i ×I m +k d ×D m Among them, s m Indicates the power control signal, k p P represents the first weight value. m k represents the proportion term. i Indicates the second weight value, I m Let k represent the integral term. d D represents the third weight value. m This represents the differential term.

[0095] Thus, according to this embodiment, the laser emission power can be varied according to the fluctuation of the laser link, thereby adapting to complex laser communication environments and avoiding power jitter or even bit errors.

[0096] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0097] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0099] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0102] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for controlling laser emission power in satellite communication, characterized in that, include: The first satellite receives the received power transmitted by the second satellite connected by communication at the current moment, and determines the received power deviation value based on the received power and the preset reference received power. Based on the received power deviation value, the first satellite determines the proportional term, integral term, and derivative term for PID control; The first satellite determines multiple statistical periods prior to the current time and determines the mean and variance of the received power deviation values ​​corresponding to each statistical period, wherein the statistical period includes multiple statistical times. The first satellite determines the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputs the input features into a pre-trained convolutional neural network, outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term, respectively. as well as The first satellite determines a power control signal for controlling the emission power of the laser transmitter based on the proportional term, the first weight value, the integral term, the second weight value, the differential term, and the third weight value, and sends the power control signal to the laser transmitter.

2. The method according to claim 1, characterized in that, Based on the received power deviation value, the first satellite determines the operation of the proportional, integral, and derivative terms for PID control, including: The first satellite determines the received power deviation values ​​corresponding to multiple historical moments prior to the current moment and generates a received power deviation sequence, wherein the received power deviation sequence includes the received power deviation value corresponding to the current moment; Based on the received power deviation sequence, the first satellite determines the proportional, integral, and derivative terms for PID control, using the following calculation formulas: P m =and m Among them, P m e represents the proportional term. m The received power deviation value at the current moment; Among them, I m Denotes the integral term, e i Let e ​​represent the received power deviation value corresponding to the i-th time point, where i = 0 to m, and when i = m, e m This represents the received power deviation value corresponding to the current time. When i = 0 to m-1, e0 to e m-1 This represents the received power deviation value corresponding to the historical time. D m =and m -And m-1 Among them, D m Denotes the differential term, e m-1 This represents the received power deviation value corresponding to the (m-1)th historical moment.

3. The method according to claim 2, characterized in that, The convolutional neural network includes convolutional layers, fully connected layers, and a softmax classifier. The first satellite inputs the input features into the pre-trained convolutional neural network and outputs a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term. This operation includes: The first satellite inputs the input features into the convolutional layer and the fully connected layer, and outputs a vector corresponding to the first weight value, a vector corresponding to the second weight value, and a vector corresponding to the third weight value; and The first satellite inputs the vector corresponding to the first weight value, the vector corresponding to the second weight value, and the vector corresponding to the third weight value into the softmax classifier, and outputs the first weight value, the second weight value, and the third weight value.

4. The method according to claim 3, characterized in that, The first satellite determines the operation of the power control signal for controlling the emission power of the laser emitter based on the proportional term, the first weight value, the integral term, the second weight value, the differential term, and the third weight value, including: The first satellite determines the power control signal based on the following formula: s m =k p ×P m +k i ×I m +k d ×D m Among them, s m This represents the power control signal, k p P represents the first weight value. m k represents the proportional term. i I represents the second weight value. m Let k represent the integral term. d D represents the third weight value. m This represents the differential term.

5. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, the method described in any one of claims 1 to 4 is performed by a processor.

6. A device for controlling laser emission power in satellite communication, characterized in that, include: The receiving power deviation value determination module is used to determine the receiving power value based on the receiving power transmitted by the second satellite connected by the communication at the current time, and the receiving power and the preset reference receiving power. The PID control term determination module is used by the first satellite to determine the proportional term, integral term, and derivative term for PID control based on the received power deviation value. The mean and variance determination module is used by the first satellite to determine multiple statistical periods prior to the current time and to determine the mean and variance of the received power deviation value corresponding to each statistical period, wherein the statistical period includes multiple statistical times. The weight value determination module is used by the first satellite to determine the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and input the input features into a pre-trained convolutional neural network to output a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term. as well as A power control signal determination module is used for the first satellite to determine a power control signal for controlling the emission power of the laser transmitter based on the proportional term, the first weight value, the integral term, the second weight value, the differential term, and the third weight value, and to send the power control signal to the laser transmitter.

7. The apparatus according to claim 6, characterized in that, The PID control term determination module includes: A received power deviation sequence generation module is used for the first satellite to determine the received power deviation values ​​corresponding to multiple historical moments before the current moment and generate a received power deviation sequence, wherein the received power deviation sequence includes the received power deviation value corresponding to the current moment; The first calculation module is used by the first satellite to determine the proportional, integral, and derivative terms for PID control based on the received power deviation sequence. The calculation formula is as follows: P m =and m Among them, P m e represents the proportional term. m The received power deviation value at the current moment; Among them, I m Denotes the integral term, e i Let e ​​represent the received power deviation value corresponding to the i-th time point, where i = 0 to m, and when i = m, e m This represents the received power deviation value corresponding to the current time. When i = 0 to m-1, e0 to e m-1 This represents the received power deviation value corresponding to the historical time. D m =and m -And m-1 Among them, D m Denotes the differential term, e m-1 This represents the received power deviation value corresponding to the (m-1)th historical moment.

8. The apparatus according to claim 7, characterized in that, The convolutional neural network includes convolutional layers, fully connected layers, and a softmax classifier. The weight determination module includes: A vector output module is used for the first satellite to input the input features into the convolutional layer and the fully connected layer, and to output a vector corresponding to the first weight value, a vector corresponding to the second weight value, and a vector corresponding to the third weight value; and The weight value determination submodule is used to input the vector corresponding to the first weight value, the vector corresponding to the second weight value, and the vector corresponding to the third weight value into the softmax classifier, and output the first weight value, the second weight value, and the third weight value.

9. The apparatus according to claim 8, characterized in that, The power control signal determination module includes: The second calculation module is used by the first satellite to determine the power control signal based on the following formula: s m =k p ×P m +k i ×I m +k d ×D m Among them, s m This represents the power control signal, k p P represents the first weight value. m k represents the proportional term. i I represents the second weight value. m Let k represent the integral term. d D represents the third weight value. m This represents the differential term.

10. A device for controlling laser emission power in satellite communication, characterized in that, include: processor; as well as A memory, connected to the processor, for providing the processor with instructions to perform the following processing steps: The first satellite receives the received power transmitted by the second satellite connected by communication at the current moment, and determines the received power deviation value based on the received power and the preset reference received power. Based on the received power deviation value, the first satellite determines the proportional term, integral term, and derivative term for PID control; The first satellite determines multiple statistical periods prior to the current time and determines the mean and variance of the received power deviation values ​​corresponding to each statistical period, wherein the statistical period includes multiple statistical times. The first satellite determines the mean and variance of the received power deviation values ​​corresponding to each statistical period as input features, and inputs the input features into a pre-trained convolutional neural network, outputting a first weight value corresponding to the proportional term, a second weight value corresponding to the integral term, and a third weight value corresponding to the differential term, respectively. as well as The first satellite determines a power control signal for controlling the emission power of the laser transmitter based on the proportional term, the first weight value, the integral term, the second weight value, the differential term, and the third weight value, and sends the power control signal to the laser transmitter.

Images