Energy scheduling method, system and equipment for low earth orbit satellite and medium

Abstract

The invention discloses an energy scheduling method, system and device for a low-earth-orbit satellite and a medium. The method comprises the steps that the energy storage level is calculated according to the current generation power of the low-earth-orbit satellite, the current remaining electric quantity of an energy storage unit and the health degree of a battery; generating a future illumination time sequence according to the orbit parameters of the low-orbit satellite and the satellite attitude control data; according to the current operation state data of each device loaded on the low earth orbit satellite and a preset task list, generating corresponding task prediction energy consumption data arranged in a descending order according to the importance level through a historical energy consumption model; according to the energy storage level, the future illumination time sequence and the task prediction energy consumption data, calculating the dominant power supply amount, matching the energy consumption demand in the task prediction energy consumption data, and carrying out the preferential power supply of the equipment of the task item with the high importance level. And carrying out power supply adjustment on the other equipment by adopting at least one strategy of delaying to the illumination period, reducing the operation power and shortening the operation duration so as to realize efficient scheduling on the energy of the low-orbit satellite.

Description

Technical Field

[0001] This invention relates to the field of aerospace energy management technology, and more specifically, to an energy scheduling method, system, device, and medium for low-Earth orbit satellites. Background Technology

[0002] With the rapid development of the space industry, low-Earth orbit (LEO) satellites have been widely used in remote sensing communications, Earth observation, and scientific exploration. However, due to their low orbits and short coverage periods, LEO satellites often need to frequently change their attitude and are affected by the Earth's shadow cycles, resulting in significant fluctuations in their energy acquisition capabilities. Typically, LEO satellites rely primarily on solar panels to capture solar energy, which is then stored in batteries through a power system to power various payloads and platform equipment. Although satellites generally maintain a sun-facing orientation for maximum sunlight exposure, factors such as varying solar incidence angles, solar panel efficiency degradation, and limited battery charging rates still pose significant challenges to energy supply, especially during prolonged shadow periods or high-energy-consuming missions, where energy shortages are highly likely.

[0003] Existing energy management methods are mostly based on preset rules, such as equipment power supply strategies based on timed start-stop and fixed priority. They lack in-depth analysis and intelligent control of the satellite's current status, mission phase, and historical energy consumption data, making it difficult to achieve dynamic allocation and predictive reserve of electrical energy.

[0004] Therefore, there is an urgent need to study an energy dispatching method that can plan power supply based on the energy storage capacity, load forecasting and mission priority of low-Earth orbit satellites, so as to make more efficient planning and allocation of energy for low-Earth orbit satellites. Summary of the Invention

[0005] This specification provides a method, system, device, and medium for energy dispatching of low-Earth orbit satellites to overcome at least one technical problem existing in related technologies.

[0006] According to a first aspect of the embodiments of this specification, an energy scheduling method for low-Earth orbit satellites is provided, comprising: The current power generation capacity of the solar array on the low-Earth orbit satellite, the current remaining power of the energy storage unit, and the battery health are obtained. Based on the current power generation capacity, the current remaining power, and the battery health, the energy storage level of the low-Earth orbit satellite is obtained. The orbital parameters and attitude control data of the low-Earth orbit satellite are obtained. The light intensity variation curve is obtained based on the angle between the satellite orbital parameters and the solar vector. The effective illumination time of the solar array is calculated using the satellite attitude control data and the light intensity variation curve. The future illumination time series is generated based on the light intensity variation curve and the effective illumination time of the solar array. The system acquires the current operating status data of each device on a low-orbit satellite. Based on the operating status data and the pre-set task list on the satellite, it generates corresponding task prediction energy consumption data through a historical energy consumption model. The task prediction energy consumption data arranges the task items in descending order of their importance level. The historical energy consumption model is trained using a machine learning algorithm. Based on the input device operating status data and task list, the system calculates and outputs the predicted energy consumption required by the corresponding device to complete the corresponding task item. Based on the energy storage level, the future illumination time series, and the predicted energy consumption data of the mission, the available power supply is calculated using the energy storage level and the future illumination time series. The power supply is matched with the energy consumption demand in the predicted energy consumption data of the mission, and the power supply is allocated from high to low according to the importance level of the mission items. Priority power supply is given to the equipment corresponding to a preset number of top-ranked mission items, and power supply adjustment is carried out for the equipment corresponding to the remaining mission items by adopting at least one of the following strategies: delaying execution to the illumination period, reducing operating power, and shortening the operating time, so as to realize the energy scheduling of low-orbit satellites.

[0007] Optionally, after the step of prioritizing power supply to the devices corresponding to a preset number of top-ranked tasks, and adjusting the power supply to the devices corresponding to the remaining tasks by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, or shortening operating time, the method further includes: The system monitors the actual power consumption and real-time operating status data of each device on the low-orbit satellite in real time. If the actual power consumption of a device differs too much from the energy consumption in the mission prediction energy consumption data, the system calls the historical energy consumption model to regenerate new mission prediction energy consumption data. Then, the system re-matches the available power supply with the energy consumption demand in the new mission prediction energy consumption data to reallocate power.

[0008] Optionally, after the step of prioritizing power supply to the devices corresponding to a preset number of top-ranked tasks, and adjusting the power supply to the devices corresponding to the remaining tasks by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, or shortening operating time, the method further includes: If the future illumination time series includes a long shadow period, the energy pre-storage task item will be initiated before the low-orbit satellite enters the long shadow period. The energy pre-storage task item will be added to the task prediction energy consumption data. The energy consumption demand in the task prediction energy consumption data will be rematched according to the available power supply. The importance level of the task item corresponding to the charging of the energy storage unit will be raised to the highest level. The start-up of unnecessary load equipment will be restricted, and the tasks that can be delayed will be postponed and queued.

[0009] Optionally, after the step of prioritizing power supply to the devices corresponding to a preset number of top-ranked tasks, and adjusting the power supply to the devices corresponding to the remaining tasks by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, or shortening operating time, the method further includes: After a scheduling cycle of a low-Earth orbit satellite is completed, the energy storage level, future illumination time series, predicted energy consumption data of the mission, and the actual power consumption and real-time operating status data of each device performing the mission items are saved and added to the training set of the historical mission energy consumption model after annotation processing, so as to optimize the historical mission energy consumption model.

[0010] According to a second aspect of the embodiments of this specification, an energy dispatching system for low-Earth orbit satellites is provided. The system includes an energy storage assessment module, a light assessment module, an energy consumption prediction module, and a power supply distribution module. The energy storage assessment module is configured to acquire the current power generation on the solar array of the low-Earth orbit satellite, the current remaining power of the energy storage unit, and the battery health, and to obtain the energy storage level of the low-Earth orbit satellite based on the current power generation, the current remaining power, and the battery health. The illumination assessment module is configured to acquire the orbital parameters and attitude control data of the low-orbit satellite, obtain the illumination intensity variation curve based on the angle change between the satellite orbital parameters and the solar vector, calculate the effective illumination time of the solar array through the satellite attitude control data and the illumination intensity variation curve, and generate a future illumination time series based on the illumination intensity variation curve and the effective illumination time of the solar array. The energy consumption prediction module is configured to acquire the current operating status data of each device on the low-orbit satellite, and generate corresponding task prediction energy consumption data based on the operating status data and the pre-set task list on the satellite through a historical energy consumption model. The task prediction energy consumption data arranges the task items in descending order of task importance. The historical energy consumption model is trained using a machine learning algorithm and calculates and outputs the predicted energy consumption required by the corresponding device to complete the corresponding task based on the input device operating status data and task list. The power supply allocation module is configured to calculate the available power supply based on the energy storage level, the future illumination time series, and the task prediction energy consumption data, match the energy consumption demand in the task prediction energy consumption data, allocate the power supply according to the importance level of the task items from high to low, prioritize power supply to the equipment corresponding to a preset number of top-ranked task items, and adjust the power supply to the equipment corresponding to the remaining task items by adopting at least one of the following strategies: delaying execution to the illumination period, reducing operating power, and shortening the operating time, so as to realize the energy scheduling of low-orbit satellites.

[0011] Optionally, the system also includes a monitoring module, which is configured to monitor the actual power consumption and real-time operating status data of each device on the low-orbit satellite in real time. If the actual power consumption of a device differs too much from the energy consumption in the mission prediction energy consumption data, the system calls the historical energy consumption model to regenerate new mission prediction energy consumption data, and then re-matches the available power supply with the energy consumption demand in the new mission prediction energy consumption data to reallocate power.

[0012] Optionally, the system further includes a power pre-storage module, wherein the power pre-storage module is configured to, if the future illumination time series includes a long shadow period, initiate an energy pre-storage task item before the low-orbit satellite enters the long shadow period, add the energy pre-storage task item to the task prediction energy consumption data, rematch the energy consumption demand in the task prediction energy consumption data according to the available power supply, raise the importance level of the task item corresponding to the energy storage unit charging to the highest level, restrict the start-up of unnecessary load equipment, and postpone the queuing scheduling of tasks that can be delayed.

[0013] Optionally, the system further includes a prediction optimization module, wherein the prediction optimization module is configured to, after the end of a scheduling cycle of the low-orbit satellite, save the energy storage level, future illumination time series, mission prediction energy consumption data, and actual power consumption and real-time operating status data of each device performing the mission items during the cycle, and add them to the training set of the historical mission energy consumption model after annotation processing, so as to optimize the historical mission energy consumption model.

[0014] According to a third aspect of the embodiments of this specification, a computing device is provided, including a storage device and a processor, the storage device being used to store a computer program, and the processor running the computer program to cause the computing device to perform the steps of the energy scheduling method for low-Earth orbit satellites described above.

[0015] According to a fourth aspect of the embodiments of this specification, a storage medium is provided that stores a computer program used in the computing device, which, when executed by a processor, implements the steps of the energy scheduling method for low-Earth orbit satellites.

[0016] The beneficial effects of the embodiments in this specification are as follows: This specification provides an energy scheduling method, system, device, and medium for low-Earth orbit (LEO) satellites. This method, based on real-time comprehensive analysis of data such as the current energy storage level of each device on the LEO satellite, predictions of future shadow periods, and mission scheduling information, adjusts the power supply strategy of each device according to mission priority. This achieves mission priority awareness, load prediction, and energy storage planning, effectively improving energy utilization. Furthermore, it monitors the operation of each device in real time, and when there is a significant deviation between actual and predicted energy consumption, it can promptly adjust and optimize the power supply scheme, extending the effective operating time of the devices. In addition, before the LEO satellite enters a long shadow period, it predicts the energy demand during the shadow period and stores energy in advance to avoid mission interruptions due to insufficient energy. Moreover, in this method, the historical energy consumption model used for predicting energy consumption continuously improves the accuracy of predictions by learning from the generated data, enabling more efficient planning and allocation of energy for LEO satellites.

[0017] The innovative aspects of the embodiments in this specification include: 1. In this specification, based on the energy storage level of the low-orbit satellite, the future illumination time series, and the mission's predicted energy consumption data, the available power supply is calculated through the energy storage level and the future illumination time series. This is matched with the energy consumption demand in the mission's predicted energy consumption data, and the power supply is allocated according to the importance level of the mission items from high to low. This energy scheduling based on mission priority ensures the energy supply for critical missions, which is one of the innovative points of the embodiments in this specification.

[0018] 2. In this specification, the future energy bottleneck is predicted in advance based on the future sunlight time series, and the system enters the pre-energy storage mode. The task item corresponding to the charging of the energy storage unit is given the highest importance level, and the power supply strategy is readjusted to effectively avoid the risk of power outage. This is one of the innovative points of the embodiments in this specification.

[0019] 3. In this specification, the use of machine learning models for historical load learning and optimization improves the policy's adaptive capability, supports dynamic adjustment and anomaly response capabilities, and enhances system robustness. This is one of the innovative aspects of the embodiments in this specification. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments or related technologies of this specification, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating an energy scheduling method for low-Earth orbit satellites, provided as an embodiment of this specification. Figure 2 A schematic diagram of the structure of an energy dispatching system for low-Earth orbit satellites provided as an embodiment of this specification; Figure 3 This is a schematic diagram of the structure of a computing device provided in one embodiment of this specification; Figure 4 This is a schematic diagram of the structure of a storage medium provided in one embodiment of this specification. Detailed Implementation

[0022] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] It should be noted that the terms "comprising" and "having," and any variations thereof, in the embodiments and drawings of this specification are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0024] This specification discloses an energy scheduling method, system, device, and medium for low-Earth orbit satellites, which will be described in detail below.

[0025] Figure 1 This is a flowchart illustrating an energy scheduling method for low-Earth orbit satellites, provided as an embodiment of this specification. Figure 1 As shown, an energy scheduling method for low-Earth orbit satellites includes: S110: Obtain the current power generation on the solar array of the low-orbit satellite, the current remaining power of the energy storage unit, and the battery health. Based on the current power generation, the current remaining power, and the battery health, obtain the energy storage level of the low-orbit satellite.

[0026] The energy storage level of low-Earth orbit (LEO) satellites serves as the basis for rational planning of power supply energy. The energy capacity of LEO satellites and the decision of when to start charging are both related to the energy storage level. Accurately obtaining data to assess the energy storage level is a prerequisite for rational decision-making in subsequent power supply planning.

[0027] S120. Obtain the orbital parameters and attitude control data of the low-orbit satellite. Obtain the light intensity variation curve based on the angle change between the satellite orbital parameters and the solar vector. Calculate the effective illumination time of the solar array using the satellite attitude control data and the light intensity variation curve. Generate the future illumination time series based on the light intensity variation curve and the effective illumination time of the solar array.

[0028] The future illumination time series displays the illumination intensity within the future cycle according to time, thereby determining the illumination period and the shadow period, and thus providing a reasonable and efficient basis for subsequent task planning.

[0029] S130. Obtain the current operating status data of each device loaded on the low-orbit satellite. Based on the operating status data and the pre-set task list on the satellite, generate corresponding task prediction energy consumption data through the historical energy consumption model. The task prediction energy consumption data arranges the task items in descending order of task importance. The historical energy consumption model is trained using a machine learning algorithm. Based on the input device operating status data and task list, calculate and output the predicted energy consumption required by the corresponding device to complete the corresponding task item.

[0030] Operational status data includes the device's charging and discharging power, operating time, operating mode, and resolution of captured images.

[0031] S140. Based on the energy storage level, the future illumination time series, and the task prediction energy consumption data, the available power supply is calculated using the energy storage level and the future illumination time series. The power supply is matched with the energy consumption demand in the task prediction energy consumption data and allocated according to the importance level of the task items from high to low. Priority power supply is given to the equipment corresponding to a preset number of top-ranked task items. For the equipment corresponding to the remaining task items, at least one of the following strategies is adopted to adjust the power supply: postpone execution to the illumination period, reduce operating power, or shorten the operating time, so as to realize the energy scheduling of low-orbit satellites.

[0032] Based on energy storage levels, future sunshine duration, and task priorities, tasks are dynamically scheduled, and a power allocation plan is generated. High-priority tasks receive priority power supply, while low-priority tasks are delayed or run at reduced load.

[0033] Specifically, after the steps of prioritizing power supply to the devices corresponding to a preset number of top-ranked task items and adjusting the power supply to the devices corresponding to the remaining task items by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, and shortening operating time, the method further includes: The system monitors the actual power consumption and real-time operating status data of each device on the low-orbit satellite in real time. If the actual power consumption of a device differs too much from the energy consumption in the mission prediction energy consumption data, the system calls the historical energy consumption model to regenerate new mission prediction energy consumption data. Then, the system re-matches the available power supply with the energy consumption demand in the new mission prediction energy consumption data to reallocate power.

[0034] Specifically, after the steps of prioritizing power supply to the devices corresponding to a preset number of top-ranked task items and adjusting the power supply to the devices corresponding to the remaining task items by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, and shortening operating time, the method further includes: If the future illumination time series includes a long shadow period, the energy pre-storage task item will be initiated before the low-orbit satellite enters the long shadow period. The energy pre-storage task item will be added to the task prediction energy consumption data. The energy consumption demand in the task prediction energy consumption data will be rematched according to the available power supply. The importance level of the task item corresponding to the charging of the energy storage unit will be raised to the highest level. The start-up of unnecessary load equipment will be restricted, and the tasks that can be delayed will be postponed and queued.

[0035] Specifically, after the steps of prioritizing power supply to the devices corresponding to a preset number of top-ranked task items and adjusting the power supply to the devices corresponding to the remaining task items by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, and shortening operating time, the method further includes: After a scheduling cycle of a low-Earth orbit satellite is completed, the energy storage level, future illumination time series, predicted energy consumption data of the mission, and the actual power consumption and real-time operating status data of each device performing the mission items are saved and added to the training set of the historical mission energy consumption model after annotation processing, so as to optimize the historical mission energy consumption model.

[0036] In one specific embodiment, a low-Earth orbit satellite carrying multiple remote sensing payloads has an orbital period of 92 minutes, with an average day-night cycle of 60 minutes of sunlight and 32 minutes of shadow. The satellite carries various electrical equipment, including a high-resolution camera, infrared imager, communication transponder, attitude control unit, and thermal control system. The current battery capacity is 120 Ah, with a current remaining charge of 65 Ah; the maximum power output of the solar panels is 280 W, as measured in the current orbital segment. P sun = 240 W.

[0037] The system uses attitude and orbit information, combined with time prediction, to remain in the light for the next 12 minutes, and then enter the shadow period for 32 minutes.

[0038] Next, the task schedule for the next orbital cycle is retrieved: remote sensing imaging task (high priority) is executed from the 2nd to the 10th minute; communication relay task (medium priority) is executed from the 25th to the 35th minute; attitude control and thermal control systems continue to operate.

[0039] Further analysis of equipment energy consumption reveals that the camera consumes 90 W of power and requires full power operation during shooting; the communication module consumes 70 W; the attitude control system consumes an average of 30 W, and the thermal control system consumes 20 W.

[0040] Energy demand is predicted, and the predicted electrical energy available during the solar term is: E in = P sun * t = 240W * 12min = 48 WH; Total power requirement during the shaded period (excluding non-essential tasks) is: E need = (30W + 20W) * 32min = 26.67WH.

[0041] Based on task priorities and energy forecasts, the system determined that the next light cycle could not support the simultaneous completion of high-priority imaging and communication relay tasks. Therefore, it decided that the imaging task would proceed as planned, the communication task would be postponed to the next orbital cycle, and an additional 21.33Wh of energy would be stored to cope with the shadow period.

[0042] After the scheduling was executed, the system entered real-time monitoring mode and found that the efficiency of the solar array had decreased and the power generation had dropped to 220 W. The system promptly adjusted its strategy, reducing the shooting time to 7 minutes to maintain the energy storage target.

[0043] After the scheduling cycle ends, the system updates the task energy consumption database and optimizes the historical energy consumption model.

[0044] The methods described in this specification can be widely applied to various low-orbit satellite systems such as communication satellites, remote sensing satellites, meteorological satellites, and navigation satellites. They are particularly suitable for dynamic energy allocation during high-density mission cycles, satellite operation during long periods of shadow or polar night, mission transfer and power balancing strategies under constellation coordination, and power fault-tolerant operation when solar arrays are damaged or energy efficiency is degraded.

[0045] For scenarios involving the coordinated operation of multiple low-Earth orbit satellites in a constellation system, the ground control center can allocate tasks across multiple satellites based on their real-time battery levels, operational missions, and predicted orbital positions, maximizing the matching between missions and power supply. If a satellite's battery is insufficient, the observation mission will be transferred to another satellite with sufficient battery capacity, preventing single-satellite load imbalance.

[0046] Figure 2 This is a schematic diagram of an energy dispatching system for low-Earth orbit satellites, provided as an embodiment of this specification. Figure 2As shown, an energy dispatching system 200 for low-Earth orbit satellites includes an energy storage assessment module 210, a light intensity assessment module 220, an energy consumption prediction module 230, and a power distribution module 240. The energy storage assessment module 210 is configured to acquire the current power generation on the solar array of the low-orbit satellite, the current remaining power of the energy storage unit, and the battery health, and to obtain the energy storage level of the low-orbit satellite based on the current power generation, the current remaining power, and the battery health.

[0047] The illumination assessment module 220 is configured to acquire the orbital parameters and attitude control data of the low-orbit satellite, obtain the illumination intensity variation curve based on the angle change between the satellite orbital parameters and the solar vector, calculate the effective illumination time of the solar array using the satellite attitude control data and the illumination intensity variation curve, and generate a future illumination time series based on the illumination intensity variation curve and the effective illumination time of the solar array.

[0048] The energy consumption prediction module 230 is configured to acquire the current operating status data of each device mounted on the low-orbit satellite, and generate corresponding task prediction energy consumption data based on the operating status data and the pre-set task list on the satellite through a historical energy consumption model. The task prediction energy consumption data arranges the task items in descending order of task importance. The historical energy consumption model is trained using a machine learning algorithm, and calculates and outputs the predicted energy consumption required by the corresponding device to complete the corresponding task based on the input device operating status data and task list.

[0049] The power supply allocation module 240 is configured to calculate the available power supply based on the energy storage level, the future illumination time series, and the task prediction energy consumption data, match the energy consumption demand in the task prediction energy consumption data, allocate the power supply according to the importance level of the task items from high to low, prioritize power supply to the equipment corresponding to a preset number of top-ranked task items, and adjust the power supply for the equipment corresponding to the remaining task items by adopting at least one of the following strategies: delaying execution to the illumination period, reducing operating power, and shortening the operating time, so as to realize the energy scheduling of low-orbit satellites.

[0050] In a specific embodiment, the system further includes a monitoring module, which is configured to monitor the actual power consumption and real-time operating status data of each device on the low-orbit satellite in real time. If the actual power consumption of a certain device differs too much from the energy consumption in the mission predicted energy consumption data, the historical energy consumption model is called to regenerate new mission predicted energy consumption data, and then the available power supply is rematched with the energy consumption demand in the new mission predicted energy consumption data in order to redistribute the power supply.

[0051] In a specific embodiment, the system further includes a power pre-storage module, wherein the power pre-storage module is configured to, if the future illumination time series includes a long shadow period, initiate an energy pre-storage task item before the low-orbit satellite enters the long shadow period, add the energy pre-storage task item to the task prediction energy consumption data, rematch the energy consumption demand in the task prediction energy consumption data according to the available power supply, raise the importance level of the task item corresponding to the energy storage unit charging to the highest level, restrict the start-up of unnecessary load equipment, and postpone the queuing scheduling of tasks that can be delayed.

[0052] In a specific embodiment, the system further includes a prediction and optimization module. This module is configured to, after the completion of a scheduling cycle for the low-Earth orbit satellite, save the energy storage level, future illumination time series, predicted energy consumption data for the mission, and actual power consumption and real-time operating status data of each device performing its tasks. These data are then labeled and added to the training set of a historical mission energy consumption model to optimize the model. The historical mission energy consumption model is optimized by learning from historical operating mode data, ambient temperature records, battery degradation coefficients, and mission execution logs.

[0053] Figure 3 This is a schematic diagram of the structure of a computing device provided in one embodiment of this specification. Figure 3 As shown, a computing device 300 includes a storage device 310 and a processor 320. The storage device 310 stores a computer program, and the processor 320 runs the computer program to enable the computing device 300 to perform the steps of the energy scheduling method for low-Earth orbit satellites.

[0054] Figure 4 This is a schematic diagram of the structure of a storage medium provided in one embodiment of this specification. For example... Figure 4 As shown, a storage medium 400 stores a computer program 410 used in the computing device, which, when executed by a processor, implements the steps of the energy scheduling method for low-Earth orbit satellites.

[0055] In summary, the embodiments of this specification provide an energy scheduling method, system, device, and medium for low-Earth orbit satellites. This method manages the energy of low-Earth orbit satellites based on data-driven and model-based scheduling, solving the problem that traditional power regulation methods lack adaptability to complex tasks. Through the collaborative work of modules such as prediction, evaluation, and scheduling, it achieves intelligent control of satellite power consumption behavior and optimal energy allocation, which has high practical value and broad application prospects.

[0056] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of one embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing the present invention.

[0057] Those skilled in the art will understand that the modules in the apparatus of the embodiments can be distributed in the apparatus of the embodiments as described in the embodiments, or they can be located in one or more devices different from this embodiment with corresponding changes. The modules of the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for energy scheduling of low-Earth orbit satellites, characterized in that, include: The current power generation capacity of the solar array on the low-Earth orbit satellite, the current remaining power of the energy storage unit, and the battery health are obtained. Based on the current power generation capacity, the current remaining power, and the battery health, the energy storage level of the low-Earth orbit satellite is obtained. The orbital parameters and attitude control data of the low-Earth orbit satellite are obtained. The light intensity variation curve is obtained based on the angle between the satellite orbital parameters and the solar vector. The effective illumination time of the solar array is calculated using the satellite attitude control data and the light intensity variation curve. The future illumination time series is generated based on the light intensity variation curve and the effective illumination time of the solar array. The system acquires the current operating status data of each device on a low-orbit satellite. Based on the operating status data and the pre-set task list on the satellite, it generates corresponding task prediction energy consumption data through a historical energy consumption model. The task prediction energy consumption data arranges the task items in descending order of their importance level. The historical energy consumption model is trained using a machine learning algorithm. Based on the input device operating status data and task list, the system calculates and outputs the predicted energy consumption required by the corresponding device to complete the corresponding task item. Based on the energy storage level, the future illumination time series, and the predicted energy consumption data of the mission, the available power supply is calculated using the energy storage level and the future illumination time series. The power supply is matched with the energy consumption demand in the predicted energy consumption data of the mission, and the power supply is allocated from high to low according to the importance level of the mission items. Priority power supply is given to the equipment corresponding to a preset number of top-ranked mission items, and power supply adjustment is carried out for the equipment corresponding to the remaining mission items by adopting at least one of the following strategies: delaying execution to the illumination period, reducing operating power, and shortening the operating time, so as to realize the energy scheduling of low-orbit satellites.

2. The method according to claim 1, characterized in that, After the steps of prioritizing power supply to devices corresponding to a preset number of top-ranked tasks, and adjusting the power supply to devices corresponding to other tasks by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, or shortening operating time, the process further includes: The system monitors the actual power consumption and real-time operating status data of each device on the low-orbit satellite in real time. If the actual power consumption of a device differs too much from the energy consumption in the mission prediction energy consumption data, the system calls the historical energy consumption model to regenerate new mission prediction energy consumption data. Then, the system re-matches the available power supply with the energy consumption demand in the new mission prediction energy consumption data to reallocate power.

3. The method according to claim 1, characterized in that, After the steps of prioritizing power supply to devices corresponding to a preset number of top-ranked tasks, and adjusting the power supply to devices corresponding to other tasks by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, or shortening operating time, the process further includes: If the future illumination time series includes a long shadow period, the energy pre-storage task item will be initiated before the low-orbit satellite enters the long shadow period. The energy pre-storage task item will be added to the task prediction energy consumption data. The energy consumption demand in the task prediction energy consumption data will be rematched according to the available power supply. The importance level of the task item corresponding to the charging of the energy storage unit will be raised to the highest level. The start-up of unnecessary load equipment will be restricted, and the tasks that can be delayed will be postponed and queued.

4. The method according to claim 2, characterized in that, After the steps of prioritizing power supply to devices corresponding to a preset number of top-ranked tasks, and adjusting the power supply to devices corresponding to other tasks by adopting at least one of the following strategies: delaying execution until the daylight period, reducing operating power, or shortening operating time, the process further includes: After a scheduling cycle of a low-Earth orbit satellite is completed, the energy storage level, future illumination time series, predicted energy consumption data of the mission, and the actual power consumption and real-time operating status data of each device performing the mission items are saved and added to the training set of the historical mission energy consumption model after annotation processing, so as to optimize the historical mission energy consumption model.

5. An energy dispatching system for low-Earth orbit satellites, characterized in that, The system includes an energy storage assessment module, a light assessment module, an energy consumption prediction module, and a power supply distribution module. The energy storage assessment module is configured to obtain the current power generation on the solar array of the low-orbit satellite, the current remaining power of the energy storage unit, and the battery health, and to obtain the energy storage level of the low-orbit satellite based on the current power generation, the current remaining power, and the battery health. The illumination assessment module is configured to acquire the orbital parameters and attitude control data of the low-orbit satellite, obtain the illumination intensity variation curve based on the angle change between the satellite orbital parameters and the solar vector, calculate the effective illumination time of the solar array through the satellite attitude control data and the illumination intensity variation curve, and generate a future illumination time series based on the illumination intensity variation curve and the effective illumination time of the solar array. The energy consumption prediction module is configured to acquire the current operating status data of each device on the low-orbit satellite, and generate corresponding task prediction energy consumption data based on the operating status data and the pre-set task list on the satellite through a historical energy consumption model. The task prediction energy consumption data arranges the task items in descending order of task importance. The historical energy consumption model is trained using a machine learning algorithm and calculates and outputs the predicted energy consumption required by the corresponding device to complete the corresponding task based on the input device operating status data and task list. The power supply allocation module is configured to calculate the available power supply based on the energy storage level, the future illumination time series, and the task prediction energy consumption data, match the energy consumption demand in the task prediction energy consumption data, allocate the power supply according to the importance level of the task items from high to low, prioritize power supply to the equipment corresponding to a preset number of top-ranked task items, and adjust the power supply to the equipment corresponding to the remaining task items by adopting at least one of the following strategies: delaying execution to the illumination period, reducing operating power, and shortening the operating time, so as to realize the energy scheduling of low-orbit satellites.

6. The system according to claim 5, characterized in that, The system also includes a monitoring module, which is configured to monitor the actual power consumption and real-time operating status data of each device on the low-orbit satellite in real time. If the actual power consumption of a device differs too much from the energy consumption in the mission prediction energy consumption data, the system calls the historical energy consumption model to regenerate new mission prediction energy consumption data, and then rematches the available power supply with the energy consumption demand in the new mission prediction energy consumption data to reallocate power.

7. The system according to claim 5, characterized in that, The system also includes a power pre-storage module, wherein The power pre-storage module is configured to, if the future illumination time series includes a long shadow period, initiate an energy pre-storage task item before the low-orbit satellite enters the long shadow period, add the energy pre-storage task item to the task prediction energy consumption data, rematch the energy consumption demand in the task prediction energy consumption data according to the available power supply, raise the importance level of the task item corresponding to the energy storage unit charging to the highest level, restrict the start-up of unnecessary load equipment, and postpone the queuing scheduling of tasks that can be delayed.

8. The system according to claim 6, characterized in that, The system also includes a prediction and optimization module, which is configured to save the energy storage level, future illumination time series, mission prediction energy consumption data, and actual power consumption and real-time operating status data of each device performing the mission items during the period after a scheduling cycle of the low-orbit satellite ends, and add them to the training set of the historical mission energy consumption model after annotation processing, so as to optimize the historical mission energy consumption model.

9. A computing device, characterized in that, The device includes a storage device and a processor, the storage device being used to store a computer program, and the processor running the computer program to cause the computing device to perform the steps of the method according to any one of claims 1-4.

10. A storage medium, characterized in that, It stores a computer program used in the computing device of claim 9, which, when executed by a processor, implements the steps of the method of any one of claims 1-4.

Images