Dynamic security resource scheduling system and method for low-altitude economy AI communication server

Abstract

The invention discloses a low-altitude economy AI communication server dynamic security resource scheduling system and method, and the method comprises the steps: obtaining the route and link state data of flight equipment in a region, and determining one or more resource scheduling coordinates and scheduling time; acquiring and analyzing historical acquisition data, determining a final sample point group of the resource scheduling coordinates in a plurality of continuous prediction time intervals, and calculating a time adjustment coefficient and a distance adjustment coefficient of each final sample point; calculating predicted interference influence scores of the resource scheduling coordinates in each predicted time interval according to the time adjustment coefficient and the distance adjustment coefficient, and drawing a curve; and analyzing the predicted interference influence score curve, determining the final interference influence score of the resource scheduling coordinate at the scheduling time, and calculating the allocation bandwidth and allocation power of each flight device for resource scheduling. According to the method, the flight link state is analyzed in real time, and the bandwidth and power resources are scheduled and allocated, so that the safety of low-altitude economic communication is ensured.

Description

Technical Field

[0001] This application relates to the field of communication server resource scheduling technology, and more specifically, to a dynamic and secure resource scheduling system and method for low-altitude economic AI communication servers. Background Technology

[0002] With the rapid rise of the low-altitude economy, the number of low-altitude flight equipment is increasing daily, placing higher demands on the stability, safety, and efficiency of low-altitude communication. Communication resource scheduling, as a core component of the low-altitude economy's AI communication system, directly impacts the data transmission quality and flight operation efficiency of flight equipment. However, in scenarios such as dense flight of multiple devices and sudden regional interference, traditional scheduling methods often fail to accurately quantify the impact of interference, easily leading to unbalanced bandwidth allocation, low resource utilization, and even safety hazards such as data transmission interruptions, severely restricting the large-scale development of the low-altitude economy.

[0003] Therefore, the existing technology has defects and urgently needs improvement. Summary of the Invention

[0004] In view of the above problems, the purpose of this invention is to provide a dynamic security resource scheduling system and method for low-altitude economic AI communication servers. By sensing the route trajectory and link status of flight equipment in real time, the system can accurately quantify the impact of interference, dynamically optimize bandwidth and power allocation strategies, achieve efficient adaptation and secure scheduling of communication resources, and ensure the stability, security and efficiency of communication transmission in low-altitude environments with dense flight of multiple devices and complex and ever-changing interference, thereby contributing to the large-scale development of the low-altitude economy.

[0005] The first aspect of this invention provides a method for dynamic and secure resource scheduling of low-altitude economic AI communication servers, comprising: Acquire route and link status data for each flight device within the area, and determine one or more resource scheduling coordinates and scheduling times based on preset scheduling time intervals; acquire historical data. Based on the analysis of the historical data collected, the final sample point group of resource scheduling coordinates in multiple consecutive prediction time intervals is determined, and the time adjustment coefficient and distance adjustment coefficient of each final sample point are calculated. Based on the time adjustment coefficient and distance adjustment coefficient of each final sample point, calculate the prediction interference impact score of the resource scheduling coordinates in each prediction time interval, and plot the prediction interference impact score curve. Based on the predicted interference impact score curve, the final interference impact score of the resource scheduling coordinates at the scheduling time is determined. Resource scheduling is performed by calculating the allocated bandwidth and allocated power of each flight device based on the final interference impact score of each resource scheduling coordinate at the scheduling time.

[0006] In this solution, the step of analyzing the historically collected data to determine the final sample point set of resource scheduling coordinates across multiple consecutive prediction time intervals includes: The preset historical time interval is divided into y prediction time intervals according to the preset time interval; Based on the historical data acquisition time, the historical data is allocated to each prediction time interval, and the historical data acquisition coordinates of the historical data within the preset range of the resource scheduling coordinates are determined as the first sample points to obtain y first sample point groups. Analyze each first sample point group, and randomly arrange and combine the first sample points in ascending order of quantity to obtain one or more undetermined second sample point groups containing multiple undetermined second sample points. Each group of undetermined second sample points is analyzed sequentially. The time difference between adjacent undetermined second sample points in the group is calculated in chronological order, and the time differences are summed to obtain the total time difference. The group of undetermined second sample points whose total time difference is less than the product of the preset time difference threshold and the number of undetermined second sample points in the corresponding undetermined second sample point group is determined as the second sample point group. Based on the number of undetermined second sample points in each second sample point group, the levels of each second sample point group are determined in descending order of the number of undetermined second sample points, corresponding to the levels of each second sample point group in descending order of the number of undetermined second sample points. If no second sample point group exists, then the candidate prediction time interval determination strategy is executed; The location analysis of each second sample point group is performed in descending order of level, and the first second sample point group that meets the requirements is determined as the final sample point group. If the final sample point group cannot be determined after analyzing all levels of the second sample point group, then the candidate prediction time interval determination strategy is executed.

[0007] In this scheme, the location analysis of each second sample point group is performed sequentially according to the order of high to low level, and the first second sample point group that meets the requirements is determined as the final sample point group, including: A two-dimensional coordinate system is constructed using the resource scheduling coordinates, with the resource scheduling coordinates as the origin and 0 degrees directly above. The angle corresponding to each undetermined second sample point in the second sample point group is θ. j ; Calculate the relative angle θ of all undetermined second sample points within the second sample point group. a : ; Where j is the number of undetermined second sample points in the corresponding second sample point group; If the relative angle θ aIf the angle is less than or equal to the preset angle threshold, the undetermined second sample point in the corresponding second sample point group will be determined as the final sample point and added to the final sample point group. If the relative angle θ a If the angle exceeds the preset threshold, the corresponding second sample point group will be removed and the next second sample point group will be analyzed until the final sample point group is determined.

[0008] In this scheme, the strategy for determining the candidate prediction time interval includes: The prediction time intervals for which there is no second sample point group or for which the final sample point group cannot be determined are identified as candidate prediction time intervals. If the prediction time intervals on both sides of the candidate prediction time interval meet the sample point selection conditions, or if there are three consecutive prediction time intervals on one side that meet the sample point selection conditions, then the prediction interference impact score corresponding to the candidate prediction time interval is directly determined by the preset fitting method. Conversely, if the candidate prediction time interval is not selected, the adjacent prediction time interval is selected and merged with the candidate prediction time interval. The merged time interval is then used as the prediction time interval for further analysis to determine the corresponding final sample point group.

[0009] In this scheme, the calculation of the time adjustment coefficient and distance adjustment coefficient for each final sample point includes: Each final sample point group is analyzed sequentially, and the Euclidean distance between each final sample point and the resource scheduling coordinates is calculated. Calculate the average of the historical elapsed times for all final sample points to determine the predicted elapsed time; Calculate the interval between the historical elapsed time and the predicted elapsed time for each final sample point; Based on the Euclidean distance and interval time corresponding to each final sample point, the time adjustment coefficient and distance adjustment coefficient of each final sample point are determined according to the preset determination method.

[0010] In this scheme, the step of calculating the prediction interference impact score of resource scheduling coordinates in each prediction time interval based on the time adjustment coefficient and distance adjustment coefficient of each final sample point, and plotting the prediction interference impact score curve, includes: Obtain the interference impact score for each final sample point in the link status data; If there are historical flight devices that have passed through the resource scheduling coordinates within the predicted time interval, then the historical interference impact score and historical data acquisition time when the flight devices passed through the resource scheduling coordinates are obtained, and the predicted interference impact score of the resource scheduling coordinates within the predicted time interval is no longer calculated. If there are no historical flight devices passing through the resource scheduling coordinates within the prediction time interval, the prediction interference impact score of the resource scheduling coordinates within the prediction time interval is calculated based on the time adjustment coefficient, distance adjustment coefficient, and interference impact score of each final sample point. Based on historical elapsed time and predicted elapsed time, a predicted interference impact score curve is plotted according to the historical interference impact score and predicted interference impact score corresponding to each predicted time interval.

[0011] In this scheme, the step of analyzing the predicted interference impact score curve to determine the final interference impact score of the resource scheduling coordinates at the scheduling time includes: Based on the predicted interference impact score curve, linear regression is used to fit the relationship between the interference impact score and time, and the curve trend features are extracted. By analyzing the trend characteristics of the curve, a preliminary interference impact score is obtained when the flight equipment passes through the resource scheduling coordinates; The initial interference impact score is corrected to obtain the final interference impact score.

[0012] In this scheme, the step of calculating the allocated bandwidth and allocated power of each flight device based on the final interference impact score of each resource scheduling coordinate at the scheduling time for resource scheduling includes: The overall score M is calculated based on the final interference impact score of all flight equipment and the currently allocated bandwidth. ; Where M is the overall score, E is the maximum interference impact score, P(i) is the final interference impact score of the i-th prediction device, kP(i) is the risk impact coefficient of the i-th flight device, kQ(i) is the resource allocation coefficient of the i-th flight device, Q(i) is the allocated bandwidth of the i-th flight device, and Q(i) is the bandwidth allocated to the i-th flight device. max Let n be the maximum allocatable bandwidth for the i-th flight device, and n be the total number of flight devices in the area. The allocated bandwidth Q(i) of each flight device is dynamically adjusted under the following conditions: ; ; Where n is the total number of flight equipment, Q max Q represents the total available bandwidth. a For the minimum emergency scheduling bandwidth, Q(i) min The minimum bandwidth required to meet the minimum communication requirements of the i-th flight device; The Q(i) value of each flight device when the overall score M is at its maximum value is determined as the final allocated bandwidth.

[0013] In this scheme, the specific method for calculating the allocated power of each flight device is as follows: Calculate the power difference between the total available power and the minimum emergency dispatch power to determine the remaining power; Based on the interference impact score ratio of each flight device, the remaining power of each flight device is allocated to determine the allocated power of each flight device.

[0014] A second aspect of the present invention provides a dynamic and secure resource scheduling system for low-altitude economic AI communication servers, comprising: The data acquisition module is used to acquire route and link status data of each flight device in the area, and determine one or more resource scheduling coordinates and scheduling times in combination with preset scheduling time intervals; and acquire historical data. The sample point determination module is used to analyze the historical data to determine the final sample point group of each resource scheduling coordinate in multiple consecutive prediction time intervals, and to calculate the time adjustment coefficient and distance adjustment coefficient of each final sample point. The first data analysis module is used to calculate the prediction interference impact score of resource scheduling coordinates in each prediction time interval based on the time adjustment coefficient and distance adjustment coefficient of each final sample point, and to draw the prediction interference impact score curve. The second data analysis module is used to analyze the predicted interference impact score curve to determine the final interference impact score of the resource scheduling coordinates at the scheduling time. The resource scheduling module is used to calculate the allocated bandwidth and allocated power of each flight device based on the final interference impact score of each resource scheduling coordinate at the scheduling time, and then perform resource scheduling.

[0015] This invention discloses a dynamic security resource scheduling system and method for low-altitude economic AI communication servers. The method includes: acquiring route and link status data of flight equipment within a region, determining one or more resource scheduling coordinates and scheduling times; acquiring and analyzing historical data to determine the final sample point group of resource scheduling coordinates in multiple consecutive prediction time intervals, and calculating the time adjustment coefficient and distance adjustment coefficient for each final sample point; calculating the predicted interference impact score of resource scheduling coordinates in each prediction time interval based on the time adjustment coefficient and distance adjustment coefficient, and plotting the curve; analyzing the predicted interference impact score curve, determining the final interference impact score of resource scheduling coordinates at the scheduling time, and calculating the allocated bandwidth and allocated power for each flight equipment for resource scheduling. This invention ensures the security of low-altitude economic communication by analyzing flight link status in real time and allocating bandwidth and power resources accordingly. Attached Figure Description

[0016] Figure 1 A flowchart of the dynamic security resource scheduling method for low-altitude economic AI communication servers provided by the present invention is shown. Figure 2 A block diagram of the dynamic security resource scheduling system for low-altitude economic AI communication servers provided by the present invention is shown. Detailed Implementation

[0017] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0019] Figure 1 A flowchart of the dynamic security resource scheduling method for low-altitude economic AI communication servers provided by the present invention is shown.

[0020] like Figure 1 As shown, this invention discloses a dynamic security resource scheduling method for low-altitude economic AI communication servers, comprising: S101: Obtain route and link status data of each flight device in the area, and determine one or more resource scheduling coordinates and scheduling times in combination with preset scheduling time intervals; obtain historical data. S102, Based on the analysis of historical data, determine the final sample point group of resource scheduling coordinates in multiple consecutive prediction time intervals, and calculate the time adjustment coefficient and distance adjustment coefficient of each final sample point; S103. Based on the time adjustment coefficient and distance adjustment coefficient of each final sample point, calculate the predicted interference impact score of the resource scheduling coordinates in each predicted time interval, and plot the predicted interference impact score curve. S104. Based on the analysis of the predicted interference impact score curve, determine the final interference impact score of the resource scheduling coordinates at the scheduling time. S105. Based on the final interference impact score of each resource scheduling coordinate at the scheduling time, calculate the allocated bandwidth and allocated power of each flight equipment for resource scheduling.

[0021] According to an embodiment of the present invention, route and link status data and historical data of each flight device in the area are acquired, and one or more resource scheduling coordinates and scheduling times are determined in combination with a preset scheduling time interval; the historical acquisition coordinates of the historical data are determined as first sample points according to the historical data acquisition time, resulting in y first sample point groups; the first sample point groups are randomly arranged and combined in ascending order of quantity to obtain multiple undetermined second sample point groups; the time difference between adjacent undetermined second sample points in the undetermined second sample point groups is calculated in chronological order and summed to obtain the total time difference; a preset time difference threshold for the total time difference is set, and the undetermined second sample point groups that meet the requirements are determined as second sample point groups; if there are no undetermined second sample point groups, a candidate prediction time interval determination strategy is executed to determine the prediction time interval and analyze it again; the level of the second sample point groups is set sequentially based on the number of undetermined second sample points in each second sample point group, and the position analysis of each second sample point group is performed in descending order of level; a two-dimensional coordinate system is constructed with resource scheduling coordinates, and the resource scheduling coordinates are defined as the origin of the coordinate system; all undetermined second sample points in the second sample point group are calculated. The relative angle is analyzed to determine the undetermined second sample points that meet the requirements, and the first group of second sample points that meet the requirements is determined as the final sample point group. The Euclidean distance between each final sample point in each final sample point group and the resource scheduling coordinates, as well as the interval between the historical elapsed time and the predicted elapsed time for each final sample point, are calculated sequentially. Based on the calculated interval distance and interval time, the time adjustment coefficient and distance adjustment coefficient corresponding to each sample point are determined, and the predicted interference impact score of the resource scheduling coordinates in each predicted time interval is calculated based on the calculation results, and the predicted interference impact score curve is plotted. According to the predicted interference impact score curve, the relationship between the interference impact score and time is fitted using linear regression to obtain the preliminary interference impact score when the flight equipment passes the resource scheduling coordinates, and then corrected to obtain the final interference impact score. The comprehensive score M is calculated based on the final interference score and the current allocated bandwidth. Under the condition that relevant conditions are met, the allocated bandwidth of each flight equipment is dynamically adjusted, and the allocated bandwidth corresponding to each flight equipment is determined when the comprehensive score M reaches its maximum value. The allocated power of each flight equipment is calculated and resource scheduling is performed in conjunction with the corresponding allocated bandwidth.

[0022] According to an embodiment of the present invention, based on the analysis of historically collected data, the final sample point set of resource scheduling coordinates in multiple consecutive prediction time intervals is determined, including: Divide a preset historical time interval (e.g., the past 24 hours) into y predicted time intervals according to a preset time interval (e.g., 5 minutes); Based on the historical data acquisition time, the historical data is allocated to each prediction time interval. The historical data acquisition coordinates of the historical data within the preset range of resource scheduling coordinates (e.g., within a radius of one kilometer) are determined as the first sample points to obtain y first sample point groups. Analyze each first sample point group, and randomly arrange and combine the first sample points in ascending order of quantity to obtain one or more undetermined second sample point groups containing multiple undetermined second sample points. Each group of undetermined second sample points is analyzed sequentially. The time difference between adjacent undetermined second sample points in the group is calculated in chronological order, and the time differences are summed to obtain the total time difference. The group of undetermined second sample points whose total time difference is less than the product of the preset time difference threshold and the number of undetermined second sample points in the corresponding undetermined second sample point group is determined as the second sample point group. Based on the number of undetermined second sample points in each second sample point group, the levels of each second sample point group are determined in descending order of the number of undetermined second sample points, corresponding to the levels of each second sample point group in descending order of the number of undetermined second sample points. If no second sample point group exists, then the candidate prediction time interval determination strategy is executed; The location analysis of each second sample point group is performed in descending order of level, and the first second sample point group that meets the requirements is determined as the final sample point group. If the final sample point group cannot be determined after analyzing all levels of the second sample point group, then the candidate prediction time interval determination strategy is executed.

[0023] It should be noted that dividing the preset historical time interval into multiple prediction time intervals transforms the analysis of continuous long time intervals into the analysis and integration of discrete short time intervals, improving the accuracy of subsequent data prediction and providing the necessary data foundation for drawing the prediction interference impact score curve; the preset range is selected, for example, within a radius of one kilometer, in order to select sample points that have an effective impact on resource scheduling coordinates.

[0024] By setting corresponding levels from fewest to most and from highest to lowest, and analyzing them sequentially from highest to lowest level, the efficiency of sample point determination is improved and the execution cost is reduced. Setting a time difference threshold for time difference retains undetermined second sample points with strong time correlation as second sample points, ensuring that sample points are evenly distributed in the time dimension and improving the accuracy of subsequent data prediction. Limiting the location distribution of sample points under the premise of setting time filtering balances the comprehensiveness and effectiveness of sample points, providing data support for the prediction or optimization of resource scheduling.

[0025] The prediction time interval, historical time interval, preset range, and preset time difference threshold can be specifically set by professionals in this field according to the actual situation.

[0026] According to an embodiment of the present invention, positional analysis is performed on each second sample point group in descending order of level, and the first second sample point group that meets the requirements is determined as the final sample point group, including: A two-dimensional coordinate system is constructed using resource scheduling coordinates. The origin is defined as the resource scheduling coordinates, with 0 degrees directly above it. The angle corresponding to each undetermined second sample point within the second sample point group is θ. j ; Calculate the relative angle θ of all undetermined second sample points within the second sample point group. a : ; Where j is the number of undetermined second sample points in the corresponding second sample point group; If the relative angle θ a If the angle is less than or equal to the preset angle threshold, the undetermined second sample point in the corresponding second sample point group will be determined as the final sample point and added to the final sample point group. If the relative angle θ a If the angle exceeds the preset threshold, the corresponding second sample point group will be removed and the next second sample point group will be analyzed until the final sample point group is determined.

[0027] It should be noted that by analyzing the angles corresponding to each undetermined second sample point in the second sample point group, sample combinations with excessive spatial orientation (such as all sample points being concentrated on the same side of the scheduling core area) are filtered out, ensuring that the final selected sample point group achieves uniform spatial orientation coverage within the preset coordinate range of resource scheduling, and accurately determining the interference impact of resource scheduling coordinates.

[0028] The preset angle threshold can be set by professionals in the field according to the actual situation.

[0029] According to an embodiment of the present invention, the candidate prediction time interval determination strategy is executed, including: The prediction time intervals for which there is no second sample point group or for which the final sample point group cannot be determined are identified as candidate prediction time intervals. If the prediction time intervals on both sides of the candidate prediction time interval meet the sample point selection conditions, or if there are three consecutive prediction time intervals on one side that meet the sample point selection conditions, then the prediction interference impact score corresponding to the candidate prediction time interval is directly determined by the preset fitting method. Conversely, if the candidate prediction time interval is not selected, the adjacent prediction time interval is selected and merged with the candidate prediction time interval. The merged time interval is then used as the prediction time interval for further analysis to determine the corresponding final sample point group.

[0030] It should be noted that the preset fitting method can be, for example, linear fitting. Linear fitting is used to obtain the corresponding prediction interference impact score curve for the prediction time intervals that meet the sample point selection criteria, thus obtaining the prediction interference impact score for the candidate prediction time intervals. The steps for calculating the prediction interference impact score for the prediction time intervals that meet the sample point selection criteria are the same as those in subsequent embodiments. When there is no qualified prediction time interval, the specific method for merging the candidate prediction time interval with the adjacent prediction time interval is to select the prediction time interval that is to the left and right of the candidate prediction time interval. Adjacent prediction time intervals are merged with candidate prediction time intervals, and the merged prediction time intervals are analyzed separately to determine the qualified merged prediction time intervals as the corresponding prediction time intervals. If none of the merged prediction time intervals meet the sample point selection criteria, the above steps are repeated for the merged prediction time intervals, continuing to merge with adjacent candidate prediction time intervals until the corresponding prediction time interval is determined. The purpose of this step is to avoid interruption of prediction data due to the failure of data in a single interval, and to ensure that the entire sample screening and interference score prediction process can always output effective and consistent results when facing complex situations such as uneven distribution of historical data and insufficient sample size.

[0031] The preset fitting method can be specifically set by professionals in this field according to the actual situation.

[0032] According to an embodiment of the present invention, calculating the time adjustment factor and distance adjustment factor for each final sample point includes: Each final sample point group is analyzed sequentially, and the Euclidean distance between each final sample point and the resource scheduling coordinates is calculated. Calculate the average of the historical elapsed times for all final sample points to determine the predicted elapsed time; Calculate the time interval between the historical elapsed time and the predicted elapsed time for each final sample point; Based on the Euclidean distance and interval time corresponding to each final sample point, the time adjustment coefficient and distance adjustment coefficient of each final sample point are determined according to the preset determination method.

[0033] It should be noted that, based on the Euclidean distance and interval time corresponding to each final sample point, the relative time adjustment coefficient and distance adjustment coefficient are determined. The preset determination method is, for example, for the time adjustment coefficient, the corresponding time adjustment coefficient (with a value of 0-1) is set based on the distance and time between the resource scheduling coordinates and the corresponding final sample point. The closer the distance and time, the larger the corresponding time adjustment coefficient. The method for determining the distance adjustment coefficient is as follows: For each final sample point, the angle formed by the resource scheduling coordinates and the final sample point and other final sample points at that final sample point is calculated. Combined with the detection time difference between the final sample point and other final sample points, a weighted sum is performed (the weight coefficients of the angle and the detection time difference are set by the system. Under normal circumstances, the weight coefficient of the detection time difference is greater than the weight coefficient of the angle) to obtain the corresponding comparison score. The other final sample point with the smallest comparison score is taken as the corresponding comparison sample point. The difference in interference impact score between the final sample point and the comparison sample point is calculated. When the difference in interference impact score is positive, the distance adjustment coefficient is S (with a value of 0-1). When the difference is negative, the distance adjustment coefficient is 1 / S.

[0034] The specific values ​​of the time adjustment coefficient and the distance adjustment coefficient can be set according to the actual situation.

[0035] The preset determination method can be specifically set by professionals in this field according to the actual situation.

[0036] According to an embodiment of the present invention, based on the time adjustment coefficient and distance adjustment coefficient of the final sample point, the predicted interference impact score of the resource scheduling coordinates in each predicted time interval is calculated, and the predicted interference impact score curve is plotted, including: Obtain the interference impact score for each final sample point in the link status data; If there are historical flight devices that have passed through the resource scheduling coordinates within the prediction time interval, then the historical interference impact score and historical data acquisition time when the flight devices passed through the resource scheduling coordinates are obtained, and the prediction interference impact score of the resource scheduling coordinates within the prediction time interval is no longer calculated. If there are no historical flight devices that have passed through the resource scheduling coordinates within the prediction time interval, the prediction interference impact score of the resource scheduling coordinates within the prediction time interval is calculated based on the time adjustment coefficient, distance adjustment coefficient, and interference impact score of each final sample point. Based on historical elapsed time and predicted elapsed time, a predicted interference impact score curve is plotted according to the historical interference impact score and predicted interference impact score corresponding to each predicted time interval.

[0037] It should be noted that the interference impact score is obtained by weighting the data transmission efficiency, transmission delay and packet loss rate in the link status data. The specific weights can be set according to the actual situation.

[0038] The method for calculating the predicted interference impact score of resource scheduling coordinates within the predicted time interval is as follows: ; Where K is the predicted interference impact score, KT a KS is the time adjustment factor for the a-th final sample point. a P is the distance adjustment factor for the a-th final sample point, N is the number of final sample points, and P is the distance adjustment factor for the a-th final sample point. a The interference impact score for the a-th final sample point.

[0039] By prioritizing the use of historical interference impact scores from flight equipment that passed through resource scheduling coordinates within the predicted time interval, the accuracy and objectivity of the scores are ensured. Meanwhile, for cases where there is no corresponding historical flight data, the predicted interference impact scores are calculated by combining the time adjustment coefficient, distance adjustment coefficient, and interference impact scores of the final sample points, ensuring the completeness of the scores. This visually presents the changing trend of the interference impact scores of flight equipment that passed through resource scheduling coordinates within the predicted time interval over time, providing accurate and continuous data support for the subsequent prediction of the final interference impact scores.

[0040] According to an embodiment of the present invention, the final interference impact score of the resource scheduling coordinates at the scheduling time is determined by analyzing the predicted interference impact score curve, including: Based on the predicted interference impact score curve, linear regression is used to fit the relationship between the interference impact score and time, and the curve trend features are extracted. By analyzing the trend characteristics of the curve, a preliminary interference impact score is obtained when the flight equipment passes through the resource scheduling coordinates; The initial interference impact score is corrected to obtain the final interference impact score.

[0041] It should be noted that the linear regression fitting method is used to extract curve trend features, including slope, intercept, and goodness of fit. These features are then used to analyze the trend of the predicted interference impact score curve, yielding a preliminary interference impact score. The correction process involves analyzing the trend of the difference between the preliminary interference impact score at a given point and the interference impact score at the previous resource scheduling coordinate point over a historical period, plotting the difference change curve, and analyzing the curve. Based on the linear transformation of this curve, the curve-predicted interference impact score for the next resource scheduling coordinate point is predicted. This is combined with a system-preset threshold for the fluctuation range of the impact score difference (e.g., ±50% of the curve-predicted interference impact score; this threshold is a relatively large value, set primarily to avoid extreme values ​​that do not conform to reality due to calculation errors). The corresponding fluctuation range of the impact score difference is then determined. Preliminary interference impact scores that do not meet this fluctuation range are adjusted to fall within it, ensuring that the corrected final interference impact score conforms to the actual interference impact score trend and more closely matches the true value. This compensates for potential biases or omissions in linear fitting, improving the accuracy of the final interference impact score calculation.

[0042] According to an embodiment of the present invention, resource scheduling is performed by calculating the allocated bandwidth and allocated power of each flight device based on the final interference impact score of each resource scheduling coordinate at the scheduling time, including: The overall score M is calculated based on the final interference impact score of all flight equipment and the currently allocated bandwidth. ; Where M is the overall score, E is the maximum interference impact score, P(i) is the final interference impact score of the i-th prediction device, kP(i) is the risk impact coefficient of the i-th flight device, kQ(i) is the resource allocation coefficient of the i-th flight device, Q(i) is the allocated bandwidth of the i-th flight device, and Q(i) is the bandwidth allocated to the i-th flight device. max Let n be the maximum allocatable bandwidth for the i-th flight device, and n be the total number of flight devices in the area. The allocated bandwidth Q(i) of each flight device is dynamically adjusted under the following conditions: ; ; Where n is the total number of flight equipment, Q max Q represents the total available bandwidth. a For the minimum emergency scheduling bandwidth, Q(i) min The minimum bandwidth required to meet the minimum communication requirements of the i-th flight device; The Q(i) value of each flight device when the overall score M is at its maximum value is determined as the final allocated bandwidth.

[0043] It should be noted that the purpose of setting a minimum emergency dispatch bandwidth is to reserve the dispatch bandwidth required when a certain flight equipment needs to urgently increase its bandwidth due to a sudden situation (such as a sudden increase in interference), so as to ensure the priority of emergency dispatch and the normal operation of the flight equipment; the purpose of setting a minimum bandwidth to meet the minimum communication requirements of the flight equipment is to ensure the flight safety of the flight equipment and to ensure that command interaction is not interrupted in complex airspace environments.

[0044] Under the premise that the difference between the total available bandwidth and the total allocated bandwidth of the flight equipment is greater than or equal to the minimum emergency dispatch bandwidth and the minimum bandwidth requirement for minimum communication needs, the comprehensive score M is adjusted to obtain the final allocated bandwidth corresponding to each flight equipment when the comprehensive score M is at its maximum value. This ensures that the flight equipment meets both the actual communication needs of the equipment and the requirements for the overall safe operation of the system, thereby improving the scientificity, balance and reliability of resource scheduling and allocation.

[0045] A warning will be issued when there are flight devices that do not meet the minimum bandwidth requirements for basic communication.

[0046] According to an embodiment of the present invention, the method for calculating the allocated power of each flight device is as follows: Calculate the power difference between the total available power and the minimum emergency dispatch power to determine the remaining power; Based on the interference impact score ratio of each flight device, the remaining power of each flight device is allocated to determine the allocated power of each flight device.

[0047] It should be noted that the minimum emergency dispatch power is the minimum power value to ensure the basic operation of flight equipment and is the core power threshold to ensure the stable and safe operation of flight equipment. The remaining power is calculated by using the total available power and the minimum emergency dispatch power to define the safety boundary of power allocation, ensuring that emergency dispatch needs can be met and avoiding the impact of conventional power allocation on emergency response capabilities. Based on the interference impact score ratio of each flight equipment, more remaining power is allocated to flight equipment with higher interference impact scores, so that flight equipment with higher interference impact levels can obtain more suitable power support, effectively improving the utilization efficiency of power resources and the scientific nature of resource scheduling and allocation.

[0048] In this invention, all data calculations are performed using dimensionless calculations.

[0049] Figure 2 A block diagram of the dynamic security resource scheduling system for low-altitude economic AI communication servers provided by the present invention is shown.

[0050] like Figure 2As shown, the second aspect of the present invention provides a dynamic security resource scheduling system for low-altitude economic AI communication servers, comprising: The data acquisition module is used to acquire route and link status data of each flight device in the area, and determine one or more resource scheduling coordinates and scheduling times in combination with preset scheduling time intervals; and acquire historical data. The sample point determination module is used to analyze historical data to determine the final sample point group of each resource scheduling coordinate in multiple consecutive prediction time intervals, and to calculate the time adjustment coefficient and distance adjustment coefficient of each final sample point. The first data analysis module is used to calculate the predicted interference impact score of resource scheduling coordinates in each predicted time interval based on the time adjustment coefficient and distance adjustment coefficient of each final sample point, and to plot the predicted interference impact score curve. The second data analysis module is used to analyze the predicted interference impact score curve and determine the final interference impact score of the resource scheduling coordinates at the scheduling time. The resource scheduling module is used to calculate the allocated bandwidth and allocated power of each flight device based on the final interference impact score of each resource scheduling coordinate at the scheduling time, and then perform resource scheduling.

[0051] All information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals (including but not limited to signals transmitted between user terminals and other devices) involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the "bandwidth allocation" mentioned in this disclosure was obtained under full authorization.

[0052] This invention discloses a dynamic security resource scheduling system and method for low-altitude economic AI communication servers. The method includes: acquiring route and link status data of flight equipment within a region, determining one or more resource scheduling coordinates and scheduling times; acquiring and analyzing historical data to determine the final sample point group of resource scheduling coordinates in multiple consecutive prediction time intervals, and calculating the time adjustment coefficient and distance adjustment coefficient for each final sample point; calculating the predicted interference impact score of resource scheduling coordinates in each prediction time interval based on the time adjustment coefficient and distance adjustment coefficient, and plotting the curve; analyzing the predicted interference impact score curve, determining the final interference impact score of resource scheduling coordinates at the scheduling time, and calculating the allocated bandwidth and allocated power for each flight equipment for resource scheduling. This invention ensures the security of low-altitude economic communication by analyzing flight link status in real time and allocating bandwidth and power resources accordingly.

[0053] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods 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, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0054] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0055] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0056] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0057] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, 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 methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for dynamic and secure resource scheduling of low-altitude economic AI communication servers, characterized in that, include: Acquire route and link status data of each flight device in the area, and determine one or more resource scheduling coordinates and scheduling times in combination with preset scheduling time intervals; Acquire historical data; Based on the analysis of the historical data collected, the final sample point group of resource scheduling coordinates in multiple consecutive prediction time intervals is determined, and the time adjustment coefficient and distance adjustment coefficient of each final sample point are calculated. Based on the time adjustment coefficient and distance adjustment coefficient of each final sample point, calculate the prediction interference impact score of the resource scheduling coordinates in each prediction time interval, and plot the prediction interference impact score curve. Based on the predicted interference impact score curve, the final interference impact score of the resource scheduling coordinates at the scheduling time is determined. Resource scheduling is performed by calculating the allocated bandwidth and allocated power of each flight device based on the final interference impact score of each resource scheduling coordinate at the scheduling time.

2. The dynamic security resource scheduling method for low-altitude economic AI communication servers according to claim 1, characterized in that, The step of analyzing the historically collected data to determine the final sample point set of resource scheduling coordinates across multiple consecutive prediction time intervals includes: The preset historical time interval is divided into y prediction time intervals according to the preset time interval; Based on the historical data acquisition time, the historical data is allocated to each prediction time interval, and the historical data acquisition coordinates of the historical data within the preset range of the resource scheduling coordinates are determined as the first sample points to obtain y first sample point groups. Analyze each first sample point group, and randomly arrange and combine the first sample points in ascending order of quantity to obtain one or more undetermined second sample point groups containing multiple undetermined second sample points. Each group of undetermined second sample points is analyzed sequentially. The time difference between adjacent undetermined second sample points in the group is calculated in chronological order, and the time differences are summed to obtain the total time difference. The group of undetermined second sample points whose total time difference is less than the product of the preset time difference threshold and the number of undetermined second sample points in the corresponding undetermined second sample point group is determined as the second sample point group. Based on the number of undetermined second sample points in each second sample point group, the levels of each second sample point group are determined in descending order of the number of undetermined second sample points, corresponding to the levels of each second sample point group in descending order of the number of undetermined second sample points. If no second sample point group exists, then the candidate prediction time interval determination strategy is executed; The location analysis of each second sample point group is performed in descending order of level, and the first second sample point group that meets the requirements is determined as the final sample point group. If the final sample point group cannot be determined after analyzing all levels of the second sample point group, then the candidate prediction time interval determination strategy is executed.

3. The dynamic security resource scheduling method for low-altitude economic AI communication servers according to claim 2, characterized in that, The step of performing positional analysis on each second sample point group in descending order of level, and determining the first second sample point group that meets the requirements as the final sample point group, includes: A two-dimensional coordinate system is constructed using the resource scheduling coordinates, with the resource scheduling coordinates as the origin and 0 degrees directly above. The angle corresponding to each undetermined second sample point in the second sample point group is θ. j ; Calculate the relative angle θ of all undetermined second sample points within the second sample point group. a : ； Where j is the number of undetermined second sample points in the corresponding second sample point group; If the relative angle θ a If the angle is less than or equal to the preset angle threshold, the undetermined second sample point in the corresponding second sample point group will be determined as the final sample point and added to the final sample point group. If the relative angle θ a If the angle exceeds the preset threshold, the corresponding second sample point group will be removed and the next second sample point group will be analyzed until the final sample point group is determined.

4. The dynamic security resource scheduling method for low-altitude economic AI communication servers according to claim 2, characterized in that, The strategy for determining the candidate prediction time interval includes: The prediction time intervals for which there is no second sample point group or for which the final sample point group cannot be determined are identified as candidate prediction time intervals. If the prediction time intervals on both sides of the candidate prediction time interval meet the sample point selection conditions, or if there are three consecutive prediction time intervals on one side that meet the sample point selection conditions, then the prediction interference impact score corresponding to the candidate prediction time interval is directly determined by the preset fitting method. Conversely, if the candidate prediction time interval is not selected, the adjacent prediction time interval is selected and merged with the candidate prediction time interval. The merged time interval is then used as the prediction time interval for further analysis to determine the corresponding final sample point group.

5. The dynamic security resource scheduling method for low-altitude economic AI communication servers according to claim 2, characterized in that, The calculation of the time adjustment factor and distance adjustment factor for each final sample point includes: Each final sample point group is analyzed sequentially, and the Euclidean distance between each final sample point and the resource scheduling coordinates is calculated. Calculate the average of the historical elapsed times for all final sample points to determine the predicted elapsed time; Calculate the interval between the historical elapsed time and the predicted elapsed time for each final sample point; Based on the Euclidean distance and interval time corresponding to each final sample point, the time adjustment coefficient and distance adjustment coefficient of each final sample point are determined according to the preset determination method.

6. The dynamic security resource scheduling method for low-altitude economic AI communication servers according to claim 5, characterized in that, The step of calculating the prediction interference impact score of resource scheduling coordinates in each prediction time interval based on the time adjustment coefficient and distance adjustment coefficient of each final sample point, and plotting the prediction interference impact score curve, includes: Obtain the interference impact score for each final sample point in the link status data; If there are historical flight devices that have passed through the resource scheduling coordinates within the predicted time interval, then the historical interference impact score and historical data acquisition time when the flight devices passed through the resource scheduling coordinates are obtained, and the predicted interference impact score of the resource scheduling coordinates within the predicted time interval is no longer calculated. If there are no historical flight devices passing through the resource scheduling coordinates within the prediction time interval, the prediction interference impact score of the resource scheduling coordinates within the prediction time interval is calculated based on the time adjustment coefficient, distance adjustment coefficient, and interference impact score of each final sample point. Based on historical elapsed time and predicted elapsed time, a predicted interference impact score curve is plotted according to the historical interference impact score and predicted interference impact score corresponding to each predicted time interval.

7. The dynamic security resource scheduling method for low-altitude economic AI communication servers according to claim 1, characterized in that, The step of analyzing the predicted interference impact score curve to determine the final interference impact score of the resource scheduling coordinates at the scheduling time includes: Based on the predicted interference impact score curve, linear regression is used to fit the relationship between the interference impact score and time, and the curve trend features are extracted. By analyzing the trend characteristics of the curve, a preliminary interference impact score is obtained when the flight equipment passes through the resource scheduling coordinates; The initial interference impact score is corrected to obtain the final interference impact score.

8. The dynamic security resource scheduling method for low-altitude economic AI communication servers according to claim 1, characterized in that, The process of calculating the allocated bandwidth and allocated power of each flight device based on the final interference impact score of each resource scheduling coordinate at the scheduling time, and then performing resource scheduling, includes: The overall score M is calculated based on the final interference impact score of all flight equipment and the currently allocated bandwidth. ； Where M is the overall score, E is the maximum interference impact score, P(i) is the final interference impact score of the i-th prediction device, kP(i) is the risk impact coefficient of the i-th flight device, kQ(i) is the resource allocation coefficient of the i-th flight device, Q(i) is the allocated bandwidth of the i-th flight device, and Q(i) is the bandwidth allocated to the i-th flight device. max Let n be the maximum allocatable bandwidth for the i-th flight device, and n be the total number of flight devices in the area. The allocated bandwidth Q(i) of each flight device is dynamically adjusted under the following conditions: ； ； Where n is the total number of flight equipment, Q max Q represents the total available bandwidth. a For the minimum emergency scheduling bandwidth, Q(i) min The minimum bandwidth required to meet the minimum communication requirements of the i-th flight device; The Q(i) value of each flight device when the overall score M is at its maximum value is determined as the final allocated bandwidth.

9. The dynamic security resource scheduling method for low-altitude economic AI communication servers according to claim 8, characterized in that, The specific method for calculating the allocated power of each flight device is as follows: Calculate the power difference between the total available power and the minimum emergency dispatch power to determine the remaining power; Based on the interference impact score ratio of each flight device, the remaining power of each flight device is allocated to determine the allocated power of each flight device.

10. A dynamic security resource scheduling system for low-altitude economic AI communication servers, used to implement the dynamic security resource scheduling method for low-altitude economic AI communication servers as described in any one of claims 1-9, characterized in that, include: The data acquisition module is used to acquire route and link status data of each flight device in the area, and determine one or more resource scheduling coordinates and scheduling time in combination with preset scheduling time intervals; Acquire historical data; The sample point determination module is used to analyze the historical data to determine the final sample point group of each resource scheduling coordinate in multiple consecutive prediction time intervals, and to calculate the time adjustment coefficient and distance adjustment coefficient of each final sample point. The first data analysis module is used to calculate the prediction interference impact score of resource scheduling coordinates in each prediction time interval based on the time adjustment coefficient and distance adjustment coefficient of each final sample point, and to draw the prediction interference impact score curve. The second data analysis module is used to analyze the predicted interference impact score curve to determine the final interference impact score of the resource scheduling coordinates at the scheduling time. The resource scheduling module is used to calculate the allocated bandwidth and allocated power of each flight device based on the final interference impact score of each resource scheduling coordinate at the scheduling time, and then perform resource scheduling.

Images