Beidou Satellite Positioning Platform Remote Monitoring and Scheduling System and Method

Abstract

The present invention discloses a remote monitoring and scheduling system and method for a Beidou satellite positioning platform, including the following steps: S1, dividing the scheduling tasks of Beidou satellite positioning data into a first layer, a second layer, and a third layer; S2, the first layer generating a preliminary scheduling plan; S3, the second layer using a graph neural network to process the dependencies and resource conflicts between tasks, and generating an optimized scheduling plan in combination with the proximal policy optimization algorithm based on policy gradients; S4, the third layer using a global graph neural network model to process the global dependencies of tasks, and generating an execution instruction for the global scheduling plan in combination with the soft actor-critic algorithm; S5, modeling the task information as a directed graph, and generating an optimal scheduling plan by propagating messages layer by layer through the graph neural network; S6, a feedback mechanism is provided between each layer; S7, graphically displaying the finally generated optimal scheduling plan through a visualization tool. The present invention realizes the precise dynamic scheduling of Beidou satellite data through hierarchical scheduling and graph neural network optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of satellite positioning and scheduling, and particularly to a Beidou satellite positioning platform remote monitoring and scheduling system and method. Background Art

[0002] With the continuous development of satellite positioning technology, the Global Navigation Satellite System has been widely applied in various industries. As a satellite navigation system independently developed in China, the Beidou satellite positioning system is rapidly becoming an important part of positioning, navigation, and timing services at home and abroad with its characteristics of high precision, high reliability, and global coverage. The Beidou satellite positioning system plays a key role in military, civilian, scientific research and other fields. Especially in scenarios such as logistics scheduling, emergency rescue, and traffic management that require precise positioning and real-time scheduling, the application prospect of the Beidou system is extremely broad.

[0003] In the prior art, scheduling methods based on satellite positioning systems usually rely on rule-driven or simple priority sorting algorithms. These methods perform well in scenarios where simple tasks or task dependencies are not complex, but in the face of large-scale tasks, complex dependencies, and multi-dimensional resource conflicts, the limitations of existing methods gradually emerge. Specifically, traditional scheduling methods are difficult to handle complex dependencies between tasks. Especially when resources are limited and multiple tasks compete for the same resource, traditional methods often cannot achieve optimal resource allocation. In addition, most traditional scheduling systems lack the ability of dynamic adjustment. When the execution of tasks deviates from the expectation, the system cannot respond and adjust in time, resulting in poor execution effects of the scheduling scheme. Existing scheduling methods are usually static and lack real-time feedback and optimization mechanisms, which makes them show low robustness and adaptability in the face of dynamic environments and emergencies.

[0004] With the rapid development of artificial intelligence and deep learning technologies, more and more research has begun to attempt to apply graph neural networks and reinforcement learning to complex task scheduling. As a deep learning model for processing graph-structured data, graph neural networks can effectively capture the dependencies between tasks and resource competition situations, while reinforcement learning learns and optimizes scheduling strategies through continuous interaction with the environment. The introduction of these technologies has brought new solutions to complex task scheduling. However, existing scheduling systems based on graph neural networks and reinforcement learning still face challenges. First, existing scheduling algorithms often apply graph neural networks only at a single level, ignoring the hierarchical processing of task complexity and urgency, which leads to a lack of pertinence and efficiency in dealing with different types of tasks. Second, existing systems usually lack an effective feedback mechanism and cannot monitor and adjust scheduling strategies in real time during task execution, which makes it difficult for the scheduling system to adapt to dynamic task requirements and environmental conditions.

[0005] Therefore, how to provide a remote monitoring and scheduling system and method for Beidou satellite positioning platform is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0006] An object of the present invention is to provide a remote monitoring and scheduling system and method for Beidou satellite positioning platform. The present invention realizes the precise dynamic scheduling of Beidou satellite positioning data in a complex task environment through a hierarchical scheduling architecture combined with a graph neural network and a reinforcement learning algorithm. Through an effective feedback mechanism and local optimization, the system can, on the basis of real-time monitoring of the task execution status, timely adjust the scheduling strategy to ensure the optimal allocation of resources and the efficient execution of tasks. This method not only improves the accuracy and response speed of scheduling, but also significantly enhances the flexibility and robustness of the system in dealing with emergencies and environmental changes, making it perform excellently in variable and complex application scenarios.

[0007] The remote monitoring and scheduling method for Beidou satellite positioning platform according to an embodiment of the present invention includes the following steps:

[0008] S1. Divide the scheduling tasks of Beidou satellite positioning data into the first layer, the second layer, and the third layer according to complexity and urgency;

[0009] S2. The first layer is processed by a lightweight rule algorithm to generate a preliminary scheduling plan, and the preliminary scheduling plan is transmitted to the second layer;

[0010] S3. The second layer uses a graph neural network to process the dependencies and resource conflicts between tasks, and combines the proximal policy optimization algorithm based on policy gradients to optimize the preliminary scheduling plan of the first layer to generate an optimized scheduling plan, and the optimized scheduling plan is transmitted to the third layer;

[0011] S4. The third layer uses a global graph neural network model to process the global dependencies of tasks, and combines the soft actor-critic algorithm to make real-time adjustments to the optimized scheduling plan of the second layer, monitor the overall scheduling execution situation, and finally generate an execution instruction for the global scheduling plan of Beidou satellite positioning data;

[0012] S5. During the scheduling process of each layer, model the scheduling task information of Beidou satellite positioning data as a directed graph, where nodes represent tasks and edges represent the dependencies and resource allocation situations between tasks, and propagate messages layer by layer through the graph neural network to generate an optimal scheduling plan;

[0013] S6. There is a feedback mechanism between each layer. If resource conflicts or poor scheduling effects are detected in the second-layer or third-layer tasks, the feedback information is transmitted to the upper layer to re-adjust the scheduling plan;

[0014] S7. Graphically display the finally generated optimal scheduling plan through a visualization tool.

[0015] Optionally, S2 specifically includes:

[0016] S21. Receive Beidou satellite positioning data, parse and filter abnormal data;

[0017] S22. Define the preliminary constraints of the scheduling task according to the preset task requirements and resource conditions, including the time window for task execution, task priority, resource availability, and the interdependencies between tasks. The defined constraints are expressed in matrix form:

[0018] C = [c ij ;

[0019] where c ij represents the dependency or conflict relationship between the i-th task and the j-th task, and the value range is 0 or 1. 0 indicates no dependency or conflict, and 1 indicates the existence of dependency or conflict;

[0020] S23. Classify and sort tasks based on task urgency, complexity, and resource occupancy. The dynamic adjustment formula for priority is expressed as:

[0021]

[0022] where P i represents the priority of the i-th task, U i represents the urgency of the i-th task, W i represents the complexity weight of the i-th task, R i represents the total amount of resources required for the i-th task, δ represents the resource occupancy scheduling factor, C ik represents the dependency relationship between the i-th task and the k-th task, D k represents the resource occupancy rate of the k-th task, and n represents the total number of tasks;

[0023] S24. Design an adaptive scheduling function, and perform preliminary scheduling on tasks in combination with the dynamic change characteristics of Beidou satellite positioning data. The optimization objective function is expressed as:

[0024]

[0025] where r ij represents the amount of the j-th type of resource allocated to the i-th task, t ij represents the estimated execution time of the i-th task after resource allocation, α i represents the urgency weight factor of the i-th task, λ represents the weight factor of task dependency relationship in the scheduling strategy, β represents the weight factor of the impact of environmental factors on scheduling, f(E j) represents the function value of the impact of the environmental dynamic data provided by the Beidou satellite on the j-th type of resource;

[0026] S25. By optimizing the objective function, an adaptive adjustment algorithm is adopted for preliminary resource allocation and scheduling to generate a preliminary scheduling plan S:

[0027] S = [s 1 , s 2 , …, s n ;

[0028] where s i represents the preliminary scheduling result of the i-th task, including the allocated resources, the estimated execution time, and the priority adjusted by environmental factors;

[0029] S26. Match and verify the preliminary scheduling plan with the task constraint conditions. If conflicts or unreasonable situations are detected, re-adjust the parameters of the adaptive scheduling function and repeat step S24;

[0030] S27. Transmit the verified preliminary scheduling plan to the second layer.

[0031] Optionally, the specific content of S3 includes:

[0032] S31. Receive the preliminary scheduling plan generated by the first layer, process the scheduling tasks using a graph neural network, and model the tasks and dependencies as a directed graph G = (N, L), where N represents the set of task nodes and L represents the set of directed edges between tasks;

[0033] S32. In the graph neural network, use a message passing mechanism to update the state of each task node layer by layer:

[0034]

[0035] where represents the state vector of node n at the (k + 1)-th layer, represents the state vector of node m at the k-th layer, Q (k) represents the weight matrix at the k-th layer, M(n) represents the set of neighbor nodes of node n, e mn represents the weight of the edge between node m and node n, p n represents the degree of node n, p m represents the degree of node m, is used for normalizing message passing, q (k) represents the bias term, and φ represents the activation function;

[0036] S33. After the state update of multiple layers of the graph neural network, obtain the final state representation of each task node to obtain the global representation Z of the entire graph task graph GG ;

[0037] S34. Based on the generated global representation Z G , combined with the Proximal Policy Optimization algorithm based on policy gradient to optimize the preliminary scheduling scheme, and the objective function for policy update is expressed as:

[0038]

[0039] where represents the optimized objective function, δ 1 represents the clipping coefficient, η represents the exploration weighting factor, represents the advantage function, E t represents the expected value symbol, T represents the total number of time steps, π ω (b t |x t ) represents the probability distribution of selecting action b t at state x t under the current policy parameter ω, represents the probability distribution of the old policy ω old , and T represents the total number of time steps;

[0040] S35. Take the optimized scheduling scheme as the output, generate the optimized scheduling scheme, and transfer the optimized scheduling scheme to the third layer.

[0041] Optionally, the S4 specifically includes:

[0042] S41. Receive the optimized scheduling scheme generated by the second layer, process the global dependency relationship of the tasks using the global graph neural network model, and model all tasks and the global dependency relationship as a directed graph G global =(N global , L global ), where N global represents the set of global task nodes, and L global represents the set of directed edges between global tasks;

[0043] S42. In the global graph neural network, use the extended message passing mechanism to obtain the global state representation of each task node through multi-layer state updates;

[0044] S43. After multi-layer state updates of the global graph neural network model, obtain the final global representation G global of the global task graph G final ;

[0045] S44. Based on the final representation G final of the global graph, combined with the Soft Actor-Critic algorithm for real-time policy adjustment, define the state space Z tFor the status of the current global task, the action space W t Represents the set of executable global scheduling actions, and the reward function U t Used to evaluate the pros and cons of each global scheduling operation;

[0046] S45. In the soft actor-critic algorithm, optimization is carried out through the soft Q function and the policy update function:

[0047]

[0048] Among them, J SAC (θ) represents the optimization objective function of the soft actor-critic algorithm, and α 2 Represents the temperature parameter, log 2 π θ (w t |z t ) represents the logarithmic probability of selecting the action w under the current policy t , Q θ (z t , w t ) represents the soft Q function, which evaluates the value of executing the action w in the state z t , β t Represents the learning rate weight factor of the policy gradient, and T represents the total number of time steps; 2 S46. Generate the execution instruction of the global scheduling scheme for Beidou satellite positioning data.

[0049] Optionally, the S5 specifically includes:

[0050] S51. Preprocess the scheduling task information in the Beidou satellite positioning data and convert it into an input format suitable for the graph structure;

[0051] S52. Assign an initial feature vector to each task node. The feature vector includes the time requirement, resource requirement, and urgency information of the task, and is represented by the vector x

[0052] =[t i , r i , u i , where t i represents the time requirement of the i-th task, r i represents the resource requirement of the i-th task, and u i represents the urgency of the i-th task; i S53. According to the dependency and conflict between tasks, assign a weight w to each edge in the graph

[0053] : ij

[0054] ​

[0055] Among them, t j represents the time requirement of the j-th task, r j represents the resource requirement of the j-th task, u j represents the urgency of the j-th task, ζ 1 represents the coefficient that controls the influence of the time difference on the weight, ζ 2 represents the coefficient that controls the influence of the resource difference on the weight, ζ 3 represents the coefficient that controls the influence of the urgency difference on the weight, |V T | represents the size of the set of task nodes;

[0056] S54. Use a graph neural network to perform layer-by-layer message passing and feature aggregation on the task graph to obtain a new feature representation of each task node;

[0057] S55. After being processed by a multi-layer graph neural network, generate an optimal scheduling scheme.

[0058] Optionally, the S6 specifically includes:

[0059] S61. Monitor the task execution status and resource usage in real time, and continuously update the system status information through sensor data, Beidou satellite positioning data, and task execution feedback information, and record the actual start time, completion time, resource consumption, and delay of all tasks;

[0060] S62. Calculate the difference between the actual scheduling effect and the expected scheduling effect based on the task execution data fed back in real time:

[0061]

[0062] Among them, Δ i represents the scheduling effect difference of task i, represents the actual completion time of task i, represents the planned completion time of task i, represents the actual resource consumption of task i, represents the planned resource consumption of task i, represents the planned priority of task i, represents the actual priority of task i, ξ 1 represents the weight coefficient of time, ξ 2 represents the weight coefficient of resources, ξ 3 represents the weight coefficient of priority;

[0063] S63. When a large difference is detected between tasks in the second or third layer, immediately trigger a feedback mechanism, transmit the difference information to the upper level, and re-evaluate the scheduling scheme;

[0064] S64. For the tasks triggered by the feedback mechanism, an enhanced local scheduling optimization algorithm is adopted for adjustment, and the optimization objective function is expressed as:

[0065]

[0066] where A represents the set of tasks to be adjusted, represents the new difference value of task i after adjustment, B represents the set of tasks affected by the adjustment, represents the completion time of task i after adjustment, C represents the set of tasks that have a direct dependency relationship with task A, represents the adjusted dependency strength between task i and task j, represents the actual dependency strength between task i and task j, V ij represents the dependency weight between task i and task j, ρ represents the weight factor for balancing time delay, and τ represents the weight factor for regulating the impact of dependency relationship adjustment on overall optimization;

[0067] S65. After local scheduling optimization, update the adjusted task plan and continue to monitor the task execution situation;

[0068] S66. If the adjusted scheme still fails to achieve the expected effect, continue to iterate the feedback and adjustment process until the task difference metric Δ i is lower than the preset threshold.

[0069] According to the Beidou satellite positioning platform remote monitoring and scheduling system of the embodiment of the present invention, it includes the following modules:

[0070] A data reception and preprocessing module, which is used to receive and parse Beidou satellite positioning data, filter abnormal data, and convert the scheduling task information into the input format of a graph structure, and define preliminary constraint conditions;

[0071] A hierarchical scheduling module, which is used to divide tasks into three layers for processing according to the complexity and urgency of the tasks; the first layer generates a preliminary scheduling scheme, the second layer optimizes the task dependency relationship, and the third layer processes the global dependency relationship and makes real-time adjustments;

[0072] A graph neural network processing module, which is used to model the scheduling tasks as directed graphs in each layer, and update the task node states layer by layer through the graph neural network to generate an optimal scheduling scheme;

[0073] A feedback mechanism and local optimization module, which is used to monitor the task execution status in real time, calculate the difference in scheduling effect, trigger the feedback mechanism, and adjust the scheduling scheme through the local optimization algorithm;

[0074] The visualization display module is used to display the finally generated scheduling scheme through a visualization tool, providing a graphical representation of task dependencies, resource allocation, and scheduling paths.

[0075] The beneficial effects of the present invention are as follows:

[0076] First, through the design of the hierarchical scheduling architecture, the system can hierarchically process scheduling tasks according to the complexity and urgency of the tasks. This design not only improves the efficiency of the system in processing tasks but also enables the system to adopt optimal scheduling strategies for different types of tasks. The lightweight rule algorithm is used to process simple tasks, the graph neural network is used to optimize the dependencies and resource conflicts of medium-complexity tasks, and the global graph neural network model is used to process global dependencies and real-time adjustment strategies. Such hierarchical processing enables the system to effectively reduce the computational burden and improve the overall scheduling efficiency when facing complex tasks.

[0077] Second, by combining the graph neural network and the reinforcement learning algorithm, especially the proximal policy optimization algorithm and the soft actor-critic algorithm, the present invention realizes the dynamic optimization of the scheduling strategy for complex tasks. The graph neural network performs excellently in handling task dependencies and resource conflicts and can capture the complex relationships between tasks; while the reinforcement learning algorithm continuously adjusts and optimizes the scheduling strategy through continuous interaction with the environment. This combination enables the system to not only generate optimized scheduling schemes when dealing with complex tasks but also adjust the strategy in real time during task execution, thus ensuring the high adaptability and robustness of the system in a dynamic environment.

[0078] In addition, the feedback mechanism and the local optimization algorithm introduced in the present invention enable the system to monitor the task execution status in real time during the scheduling process, promptly detect and adjust the deviations in the scheduling. When the system detects a significant difference between the task execution effect and the expectation, the feedback mechanism can quickly trigger the adjustment process, and the local optimization algorithm is used to adjust the resource allocation and execution order of the tasks to ensure that the scheduling scheme can always maintain the optimal state in a complex and ever-changing environment. This real-time feedback and adjustment mechanism greatly enhances the response ability and flexibility of the system in dealing with emergencies and environmental changes.

[0079] Finally, the present invention graphically displays the finally generated scheduling scheme through a visualization tool, enabling the dependencies, resource allocation, and scheduling paths of the scheduling scheme to be intuitively presented to the decision-makers. Such a visualization display not only improves the transparency of the scheduling scheme but also provides more comprehensive and clear reference information for the decision-makers, helping them make more accurate and efficient decisions in complex situations. Description of the Drawings

[0080] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the accompanying drawings:

[0081] Figure 1 is a flowchart of the remote monitoring and scheduling system and method for the Beidou satellite positioning platform proposed by the present invention;

[0082] Figure 2 is a schematic diagram of the hierarchical scheduling architecture of the remote monitoring and scheduling system and method for the Beidou satellite positioning platform proposed by the present invention;

[0083] Figure 3 is a task scheduling flowchart of the feedback mechanism and local optimization algorithm for the remote monitoring and scheduling system and method for the Beidou satellite positioning platform proposed by the present invention. Detailed implementation manners

[0084] Now, the present invention will be further described in detail with reference to the accompanying drawings. These drawings are all simplified schematic diagrams, only illustrating the basic structure of the present invention in a schematic manner, so they only show the components related to the present invention.

[0085] Refer to Figures 1-3 , the remote monitoring and scheduling method for the Beidou satellite positioning platform includes the following steps:

[0086] S1. Divide the scheduling tasks of Beidou satellite positioning data into the first layer, the second layer, and the third layer according to complexity and urgency;

[0087] S2. The first layer uses a lightweight rule algorithm for processing, generates a preliminary scheduling plan, and transmits the preliminary scheduling plan to the second layer;

[0088] S3. The second layer uses a graph neural network to process the dependencies and resource conflicts between tasks, and combines the proximal policy optimization algorithm based on policy gradients to optimize the preliminary scheduling plan of the first layer, generates an optimized scheduling plan, and transmits the optimized scheduling plan to the third layer;

[0089] S4. The third layer uses a global graph neural network model to process the global dependencies of tasks, and combines the soft actor-critic algorithm to make real-time adjustments to the optimized scheduling plan of the second layer, monitors the overall scheduling execution situation, and finally generates an execution instruction for the global scheduling plan of Beidou satellite positioning data;

[0090] S5. During the scheduling process of each layer, model the scheduling task information of Beidou satellite positioning data as a directed graph, where nodes represent tasks, and edges represent the dependencies and resource allocation situations between tasks. Propagate messages layer by layer through the graph neural network to generate an optimal scheduling plan;

[0091] S6. A feedback mechanism is provided between layers. If resource conflicts or poor scheduling effects are detected in the second or third layer tasks, the feedback information will be passed to the upper layer to readjust the scheduling plan.

[0092] S7. Graphically display the finally generated optimal scheduling plan through a visualization tool.

[0093] In this embodiment, the said S2 specifically includes:

[0094] S21. Receive Beidou satellite positioning data, parse and filter abnormal data.

[0095] S22. Define the preliminary constraint conditions of the scheduling task according to the preset task requirements and resource conditions, including the time window for task execution, task priority, resource availability, and the interdependence between tasks. The defined constraint conditions are expressed in matrix form:

[0096] C = [c ij ;

[0097] where c ij represents the dependence or conflict relationship between the i-th task and the j-th task, and the value range is 0 or 1. 0 indicates no dependence or conflict, and 1 indicates the existence of dependence or conflict.

[0098] S23. Classify and sort tasks based on task urgency, complexity, and resource occupancy. The dynamic adjustment formula for priority is expressed as:

[0099]

[0100] where P i represents the priority of the i-th task, U i represents the urgency of the i-th task, W i represents the complexity weight of the i-th task, R i represents the total amount of resources required for the i-th task, δ represents the resource occupancy scheduling factor, C ik represents the dependence relationship between the i-th task and the k-th task, D k represents the resource occupancy rate of the k-th task, and n represents the total number of tasks.

[0101] S24. Design an adaptive scheduling function, and combine the dynamic change characteristics of Beidou satellite positioning data to perform preliminary scheduling on tasks. The optimization objective function is expressed as:

[0102]

[0103] where r ij represents the amount of the j-th type of resources allocated to the i-th task, t ijrepresents the estimated execution time after resource allocation for the i-th task, α i represents the urgency weight factor of the i-th task, λ represents the weight factor for task dependencies in the scheduling strategy, β represents the weight factor for the impact of environmental factors on scheduling, f(E j ) represents the function value of the impact of environmental dynamic data provided by Beidou satellites on the j-th type of resource;

[0104] S25. Through optimizing the objective function, an adaptive adjustment algorithm is used for preliminary resource allocation and scheduling to generate a preliminary scheduling plan S:

[0105] S = [s 1 , s 2 , …, s n ;

[0106] where s i represents the preliminary scheduling result of the i-th task, including the allocated resources, the estimated execution time, and the priority adjusted by environmental factors;

[0107] S26. The preliminary scheduling plan is matched and verified with the task constraint conditions. If conflicts or unreasonable situations are detected, the parameters of the adaptive scheduling function are readjusted and step S24 is repeated;

[0108] S27. The preliminary scheduling plan that passes the verification is passed to the second layer.

[0109] In this embodiment, the specific content of S3 includes:

[0110] S31. Receive the preliminary scheduling plan generated by the first layer, use a graph neural network to process the scheduling tasks, and model the tasks and dependencies as a directed graph G=(N, L), where N represents the set of task nodes and L represents the set of directed edges between tasks;

[0111] S32. In the graph neural network, a message passing mechanism is used to update the state of each task node layer by layer:

[0112]

[0113] where represents the state vector of node n at the k+1-th layer, represents the state vector of node m at the k-th layer, Q (k) represents the weight matrix at the k-th layer, M(n) represents the set of neighbor nodes of node n, e mn represents the weight of the edge between node m and node n, p n represents the degree of node n, p m represents the degree of node m, is used for normalizing message passing, q (k)represents the bias term, and φ represents the activation function;

[0114] S33. After the state update of the multi-layer graph neural network, obtain the final state representation of each task node Obtain the global representation Z of the entire graph task graph G G ;

[0115] S34. Based on the generated global representation Z G , combine the proximal policy optimization algorithm based on policy gradient to optimize the preliminary scheduling scheme, and the objective function of policy update is expressed as:

[0116]

[0117] where represents the optimized objective function, δ 1 represents the clipping coefficient, η represents the exploration weighting factor, represents the advantage function, E t represents the expected value symbol, T represents the total number of time steps, π ω (b t |x t ) represents the probability distribution of selecting action b t at state x t under the current policy parameter ω, represents the probability distribution of the old policy ω old ; T represents the total number of time steps;

[0118] S35. Use the optimized scheduling scheme as the output, generate the optimized scheduling scheme, and pass the optimized scheduling scheme to the third layer.

[0119] In this embodiment, the S4 specifically includes:

[0120] S41. Receive the optimized scheduling scheme generated by the second layer, use the global graph neural network model to process the global dependency relationship of the tasks, and model all tasks and the global dependency relationship as a directed graph G global = (N global , L global ), where N global represents the global task node set, and L global represents the set of directed edges between global tasks;

[0121] S42. In the global graph neural network, use the extended message passing mechanism to obtain the global state representation of each task node through multi-layer state updates;

[0122] S43. After the multi-layer state updates of the global graph neural network model, obtain the final global representation G of the global task graph G global ​final ;

[0123] S44. Based on the final representation G of the global graph final , combined with the soft actor-critic algorithm for real-time policy adjustment, define the state space Z t as the state of the current global task, and the action space W t represents the set of executable global scheduling actions, and the reward function U t is used to evaluate the quality of each global scheduling operation;

[0124] S45. In the soft actor-critic algorithm, optimize through the soft Q-function and the policy update function:

[0125]

[0126] where J SAC (θ) represents the optimization objective function of the soft actor-critic algorithm, α 2 represents the temperature parameter, log 2 π θ (w t |z t ) represents the logarithmic probability of selecting the action w under the current policy t , Q θ (z t , w t ) represents the soft Q-function, evaluating the value of executing the action w in the state z t , β t represents the learning rate weight factor of the policy gradient, and T represents the total number of time steps; 2 represents the learning rate weight factor of the policy gradient, and T represents the total number of time steps;

[0127] S46. Generate the execution instructions for the global scheduling plan of the Beidou satellite positioning data.

[0128] In this embodiment, the S5 specifically includes:

[0129] S51. Preprocess the scheduling task information in the Beidou satellite positioning data and convert it into an input format suitable for the graph structure;

[0130] S52. Assign an initial feature vector to each task node. The feature vector includes the time requirement, resource requirement, and urgency information of the task, and is represented by the vector x i = [t i , r i , u i , where t i represents the time requirement of the i-th task, r i represents the resource requirement of the i-th task, and u i represents the urgency of the i-th task;

[0131] S53. Assign a weight w to each edge in the graph according to the dependencies and conflicts between tasks. ij :

[0132]

[0133] Among them, t j represents the time requirement of the j-th task, r j represents the resource requirement of the j-th task, u j represents the urgency of the j-th task, ζ 1 represents the coefficient that controls the influence of the time difference on the weight, ζ 2 represents the coefficient that controls the influence of the resource difference on the weight, ζ 3 represents the coefficient that controls the influence of the urgency difference on the weight, |V T | represents the size of the set of task nodes;

[0134] S54. Use a graph neural network to perform layer-by-layer message passing and feature aggregation on the task graph to obtain a new feature representation for each task node;

[0135] S55. After processing by a multi-layer graph neural network, generate an optimal scheduling scheme.

[0136] In this embodiment, the S6 specifically includes:

[0137] S61. Real-time monitor the task execution status and resource usage, and continuously update the system status information through sensor data, Beidou satellite positioning data, and task execution feedback information, and record the actual start time, completion time, resource consumption, and delay of all tasks;

[0138] S62. Calculate the difference between the actual scheduling effect and the expected scheduling effect according to the real-time feedback task execution data:

[0139]

[0140] Among them, Δ i represents the scheduling effect difference of task i, represents the actual completion time of task i, represents the planned completion time of task i, represents the actual resource consumption of task i, represents the planned resource consumption of task i, represents the planned priority of task i, represents the actual priority of task i, ξ 1 represents the weight coefficient of time, ξ 2 represents the weight coefficient of resources, ξ 3 represents the weight coefficient of priority;

[0141] S63. When a large difference is detected among tasks in the second or third layer, immediately trigger the feedback mechanism, transmit the difference information to the upper level, and re-evaluate the scheduling plan;

[0142] S64. For the tasks triggered by the feedback mechanism, use the enhanced local scheduling optimization algorithm for adjustment. The optimization objective function is expressed as:

[0143]

[0144] where A represents the set of tasks to be adjusted, represents the new difference value of task i after adjustment, B represents the set of tasks affected by the adjustment, represents the completion time of task i after adjustment, C represents the set of tasks that have a direct dependency relationship with task A, represents the adjusted dependency relationship strength between task i and task j, represents the actual dependency relationship strength between task i and task j, V ij represents the dependency weight between task i and task j, ρ represents the weight factor for balancing time delay, and τ represents the weight factor for regulating the impact of dependency relationship adjustment on the overall optimization;

[0145] S65. After local scheduling optimization, update the adjusted task plan and continue to monitor the task execution situation;

[0146] S66. If the adjusted plan still does not achieve the expected effect, continue to iterate the feedback and adjustment process until the task difference metric Δ i is lower than the preset threshold.

[0147] The Beidou satellite positioning platform remote monitoring and scheduling system includes the following modules:

[0148] The data reception and preprocessing module is used to receive and parse Beidou satellite positioning data, filter abnormal data, and convert the scheduling task information into the input format of a graph structure, and define preliminary constraint conditions;

[0149] The hierarchical scheduling module is used to divide tasks into three layers for processing according to the complexity and urgency of the tasks; the first layer generates a preliminary scheduling plan, the second layer optimizes the task dependency relationship, and the third layer processes the global dependency relationship and makes real-time adjustments;

[0150] The graph neural network processing module is used to model the scheduling tasks as directed graphs in each layer, and update the task node states layer by layer through the graph neural network to generate the optimal scheduling plan;

[0151] Feedback mechanism and local optimization module, used to monitor the task execution status in real time, calculate the difference in scheduling effects, trigger the feedback mechanism, and adjust the scheduling scheme through local optimization algorithms;

[0152] Visualization display module, used to display the finally generated scheduling scheme through visualization tools, providing graphical representations of task dependencies, resource allocation situations, and scheduling paths.

[0153] Example 1:

[0154] To verify the feasibility of the present invention in implementation, the present invention is applied in a large logistics enterprise. The Beidou satellite positioning system is widely used in logistics scheduling and vehicle management across the country. This enterprise processes tens of thousands of transportation tasks every day, involving the real-time scheduling of thousands of logistics vehicles. These tasks are not only distributed over a vast geographical area, but there are also complex dependencies between each task, such as priority, timeliness requirements, and resource conflicts. Although the existing scheduling system can complete basic task allocation, with the increase in the task volume and the complexity of the scheduling environment, the system gradually exposes problems such as low scheduling efficiency, unreasonable resource allocation, and untimely response, resulting in a decline in logistics efficiency and an increase in operating costs.

[0155] To address these challenges, the enterprise introduces the remote monitoring and scheduling system and method based on the Beidou satellite positioning platform proposed by the present invention. This system effectively improves the efficiency and accuracy of logistics scheduling through the combination of a hierarchical scheduling architecture, graph neural network, reinforcement learning algorithm, feedback mechanism, and visualization tools.

[0156] In practical applications, the enterprise starts the scheduling system at 6 am every morning according to the logistics demands across the country. First, the system preprocesses all the received transportation task data. Using the accurate positioning information provided by the Beidou satellite and real-time traffic data, the tasks are divided into three layers for processing according to complexity and urgency. For simple and independent tasks, the system uses lightweight rule algorithms in the first layer to quickly generate a preliminary scheduling scheme; for tasks involving multi-task dependencies and resource competition, the system uses a graph neural network in the second layer to optimize the dependencies between tasks and combines the proximal policy optimization algorithm to adjust resource allocation and scheduling strategies; for the most complex tasks, such as urgent tasks requiring global coordination, the system uses a global graph neural network model combined with the soft actor-critic algorithm in the third layer for global optimization and real-time adjustment to ensure the rationality and efficiency of the overall scheduling.

[0157] On July 15, 2024, the enterprise faced an urgent scheduling task: in the case of multiple highway closures due to heavy rain, a batch of urgently needed medical supplies needed to be delivered from City A to City B within 12 hours, and this batch of supplies also needed to be coordinated with the logistics tasks of 12 other cities. The complexity of this task was extremely high, not only because of the strict timeliness requirements, but also because it was necessary to coordinate multiple transportation routes within the disaster area to avoid resource conflicts and minimize interference with other ongoing tasks.

[0158] The system first made a preliminary resource allocation and time arrangement for all tasks at the first layer, but found that due to the road closures caused by heavy rain, many tasks could not be carried out as originally planned, and resource conflicts and task dependencies became more complex. At this time, the system passed these complex tasks to the second layer, used a graph neural network to re-model all affected tasks, and analyzed the dependencies between tasks and possible resource conflicts. Through the proximal policy optimization algorithm, the system recalculated the optimal resource allocation plan and generated an optimized scheduling plan.

[0159] However, due to the continuous heavy rain and the changing traffic conditions, the system monitored at the third layer that the main highway in the direction of City B was closed again. The system immediately triggered a feedback mechanism, transmitted the task status update information back to the second layer, and made real-time adjustments to this route through a local scheduling optimization algorithm. After multiple iterations of optimization, the system finally generated a globally optimized scheduling plan and displayed it to the operators in the scheduling center through a visualization tool. The plan showed that the system recommended using other secondary roads and splitting the transportation task from City A to City B into multiple phased tasks, which were transferred through different routes and cities respectively, thus avoiding the main traffic congestion areas. Finally, this batch of medical supplies was successfully delivered to City B at 6 pm, with the whole journey taking only 11.5 hours, saving nearly 2 hours compared with the traditional scheduling method.

[0160] The application of this system not only ensured the smooth execution of logistics tasks, but also demonstrated significant beneficial effects at multiple levels. According to the statistical data, since the system was put into use on July 1, 2024, the overall logistics efficiency of the enterprise has increased by about 23%, the average response time of a single scheduling task has been reduced by 15%, especially in complex task scheduling, the resource utilization rate has increased by about 18%. At the same time, through the application of the feedback mechanism and the local optimization algorithm, the flexibility and emergency response ability of the system have been greatly improved, and the scheduling success rate in emergencies has increased from the original 78% to 92%. In addition, the visualization display function of the system makes scheduling decisions more transparent and easy to understand, and the workload of schedulers has been reduced by about 30%.

[0161] Table 1 Comparison table of enterprise logistics scheduling performance indicators before and after the introduction of the present invention

[0162]

[0163]

[0164] The above Table 1 clearly shows that after the Beidou satellite positioning platform remote monitoring and dispatching system of the present invention is introduced, the enterprise has made significant improvements in multiple key indicators such as logistics dispatching efficiency, task response time, resource utilization rate, and emergency handling ability. The overall logistics efficiency has increased by 23%, the average response time for a single dispatching task has decreased by 15%, and the resource utilization rate for complex tasks has increased to 82.6%. In addition, the dispatching success rate for emergencies has increased from 78% to 92%, the total time of transportation tasks and the average delay time of logistics tasks have both been shortened, the work burden of dispatchers has been significantly reduced, and the transparency and understandability of dispatching decisions have also been significantly improved. These data indicate that the implementation of the present invention effectively solves the problems of low efficiency and untimely response in the existing dispatching system, and greatly improves the operation efficiency of the enterprise and the ability to handle complex dispatching scenarios.

[0165] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A Beidou satellite positioning platform remote monitoring and scheduling method, characterized in that: The steps include: S1. The scheduling tasks of Beidou satellite positioning data are divided into the first layer, the second layer and the third layer according to the complexity and urgency; S2, the first layer uses a lightweight rule algorithm to process, generate a preliminary scheduling plan, and pass the preliminary scheduling plan to the second layer; S3: The second layer uses graph neural network to process dependencies and resource conflicts between tasks, and optimizes the preliminary scheduling plan of the first layer in combination with the proximal policy optimization algorithm based on policy gradient, generates an optimized scheduling plan, and passes the optimized scheduling plan to the third layer; S4, the third layer uses a global graph neural network model to process the global dependencies of the tasks, and combines the soft actor critic algorithm to adjust the optimization scheduling plan of the second layer in real time, monitor the overall scheduling execution, and finally generate execution instructions for the global scheduling plan of Beidou satellite positioning data; S5. In the scheduling process of each layer, the scheduling task information of Beidou satellite positioning data is modeled as a directed graph, where nodes represent tasks and edges represent dependencies and resource allocation between tasks. The message is propagated layer by layer through the graph neural network to generate the optimal scheduling plan. S6. There is a feedback mechanism between each layer. If resource conflicts or poor scheduling effects are detected in the second or third layer tasks, the feedback information will be passed to the upper layer to readjust the scheduling plan. S7. The optimal scheduling plan finally generated is graphically displayed through a visualization tool.

2. The Beidou satellite positioning platform remote monitoring and scheduling method according to claim 1, characterized in that: The S2 specifically includes: S21, receiving Beidou satellite positioning data, parsing and filtering abnormal data; S22. Based on the preset task requirements and resource conditions, the preliminary constraints for scheduling tasks are defined, including the time window for task execution, task priority, resource availability, and interdependencies between tasks. The defined constraints are expressed in matrix form: C=[c ij ]; Among them, c ij Indicates the dependency or conflict relationship between the i-th task and the j-th task. The value range is 0 or 1, 0 means no dependency or conflict, and 1 means there is dependency or conflict; S23. Based on the urgency, complexity and resource occupancy of tasks, tasks are classified and sorted. The dynamic priority adjustment formula is expressed as: Among them, P i represents the priority of the i-th task, U i represents the urgency of the i-th task, W i represents the complexity weight of the i-th task, R i represents the total amount of resources required for the i-th task, δ represents the resource occupancy scheduling factor, and C ik represents the dependency relationship between the i-th task and the k-th task, D k represents the resource occupancy rate of the kth task, and n represents the total number of tasks; S24. Design an adaptive scheduling function, combine the dynamic change characteristics of Beidou satellite positioning data, and perform preliminary scheduling of tasks. The optimization objective function is expressed as: Among them, r ij represents the amount of resources of the jth type allocated to the i-th task, t ij represents the estimated execution time of the i-th task after resources are allocated, α i represents the urgency weight factor of the i-th task, λ represents the weight factor of the task dependency in the scheduling strategy, β represents the weight factor of the environmental factor on the scheduling, f(E j ) represents the function value of the impact of the environmental dynamic data provided by the BeiDou satellite on the j-th type of resources; S25. By optimizing the objective function, an adaptive adjustment algorithm is used to perform preliminary resource allocation and scheduling, and a preliminary scheduling plan S is generated: S=[s1,s2,…,s n ]; Among them, s i represents the preliminary scheduling result of the ith task, including the allocated resources, the estimated execution time, and the priority adjusted for environmental factors; S26, matching and verifying the preliminary scheduling plan with the task constraints, if a conflict or unreasonable situation is detected, readjusting the parameters of the adaptive scheduling function and repeating step S24; S27. Pass the verified preliminary scheduling plan to the second layer.

3. The Beidou satellite positioning platform remote monitoring and scheduling method according to claim 1, characterized in that: The S3 specifically includes: S31, receiving the preliminary scheduling plan generated by the first layer, processing the scheduling tasks using a graph neural network, and modeling the tasks and dependencies as a directed graph G = (N, L), where N represents a set of task nodes and L represents a set of directed edges between tasks; S32. In the graph neural network, the message passing mechanism is used to update the status of each task node layer by layer: in, represents the state vector of node n at the k+1th layer, represents the state vector of node m at layer k, Q (k) represents the weight matrix of the kth layer, M(n) represents the set of neighbor nodes of node n, and e mn represents the weight of the edge between node m and node n, p n represents the degree of node n, p m represents the degree of node m, For normalized message passing, q (k) represents the bias term, φ represents the activation function; S33. After the state of the multi-layer graph neural network is updated, the final state representation of each task node is obtained Get the global representation Z of the entire task graph G G ; S34. Based on the generated global representation Z G , combined with the proximal policy optimization algorithm based on policy gradient to optimize the preliminary scheduling plan, the objective function of the policy update is expressed as: in, represents the optimized objective function, δ1 represents the cropping coefficient, η represents the exploration weighting factor, represents the advantage function, E t represents the expected value symbol, T represents the total number of time steps, and π ω (b t |x t ) represents the state x under the current policy parameter ω t Select action b t The probability distribution of Represents the old strategy ω old The probability distribution of S35. Use the optimized scheduling plan as output, generate an optimized scheduling plan, and pass the optimized scheduling plan to the third layer.

4. The Beidou satellite positioning platform remote monitoring and scheduling method according to claim 1, characterized in that: The S4 specifically includes: S41, receiving the optimized scheduling plan generated by the second layer, using the global graph neural network model to process the global dependencies of the tasks, and modeling all tasks and global dependencies as a directed graph G global =(N global ,L global ), where N global represents the global task node set, L global Represents the set of directed edges between global tasks; S42. In the global graph neural network, an extended message passing mechanism is used to obtain the global state representation of each task node through multi-layer state updates; S43. After the multi-layer state of the global graph neural network model is updated, the global task graph G is obtained. global The final global representation G final ; S44. Final representation G based on the global graph final , combined with the soft actor critic algorithm to adjust the strategy in real time, define the state space Z t is the state of the current global task, action space W t represents the set of executable global scheduling actions, and the reward function U t Used to evaluate the pros and cons of each step of global scheduling operation; S45. In the soft actor-critic algorithm, optimization is performed through the soft Q function and the policy update function: Among them, J SAC (θ) represents the optimization objective function of the soft actor-critic algorithm, α2 represents the temperature parameter, log2π θ (w t |z t ) indicates the action w is selected under the current strategy t The logarithmic probability, Q θ (z t ,w t ) represents the soft Q function, evaluating t Next, execute action w t The value of , β2 represents the learning rate weight factor of the policy gradient, and T represents the total number of time steps; S46: Generate execution instructions for a global scheduling solution for Beidou satellite positioning data.

5. The Beidou satellite positioning platform remote monitoring and scheduling method according to claim 1, characterized in that: The S5 specifically includes: S51, preprocessing the scheduling task information in the Beidou satellite positioning data and converting it into an input format suitable for the graph structure; S52, assign an initial feature vector to each task node, the feature vector includes the time requirement, resource requirement and urgency information of the task, and uses vector x i =[t i ,r i ,u i ] indicates that t i represents the time requirement of the i-th task, r i represents the resource requirement of the ith task, u i Indicates the urgency of the i-th task; S53. According to the dependencies and conflicts between tasks, each edge in the graph is assigned a weight w. ij : Among them, t j represents the time requirement of the jth task, r j represents the resource requirement of the jth task, u j represents the urgency of the jth task, ζ1 represents the coefficient of the influence of the control time difference on the weight, ζ2 represents the coefficient of the control resource difference on the weight, ζ3 represents the coefficient of the control urgency difference on the weight, |V T | represents the size of the task node set; S54. Use the graph neural network to perform layer-by-layer message transmission and feature aggregation on the task graph to obtain a new feature representation for each task node. S55. After being processed by a multi-layer graph neural network, an optimal scheduling solution is generated.

6. The Beidou satellite positioning platform remote monitoring and scheduling method according to claim 1, characterized in that: The S6 specifically includes: S61, real-time monitoring of task execution status and resource usage, continuously updating system status information through sensor data, Beidou satellite positioning data and task execution feedback information, and recording the actual start time, completion time, resource consumption and delay of all tasks; S62. Calculate the difference between the actual scheduling effect and the expected scheduling effect based on the real-time feedback of the task execution data: Among them, Δ i represents the difference in scheduling effect of task i, represents the actual completion time of task i, represents the planned completion time of task i, represents the actual resource consumption of task i, represents the planned resource consumption of task i, represents the planning priority of task i, represents the actual priority of task i, ξ1 represents the weight coefficient of time, ξ2 represents the weight coefficient of resources, and ξ3 represents the weight coefficient of priority; S63, when a large difference between tasks is detected in the second or third layer, the feedback mechanism is immediately triggered to pass the difference information to the upper layer to re-evaluate the scheduling plan; S64. For the tasks triggered by the feedback mechanism, an enhanced local scheduling optimization algorithm is used for adjustment. The optimization objective function is expressed as: Among them, A represents the set of tasks that need to be adjusted. represents the new difference value of task i after adjustment, B represents the set of tasks affected by the adjustment, represents the adjusted completion time of task i, C represents the set of tasks that have a direct dependency on task A, represents the adjusted dependency strength between task i and task j, represents the actual dependency strength between task i and task j, V ij represents the dependency weight between task i and task j, ρ represents the weight factor for balancing time delay, and τ represents the weight factor for adjusting the impact of dependency adjustment on the overall optimization; S65. After the local scheduling optimization, update the adjusted task plan and continue to monitor the task execution; S66. If the adjusted solution still does not achieve the expected effect, continue the iterative feedback and adjustment process until the task difference metric Δ i until it falls below a preset threshold.

7. Beidou satellite positioning platform remote monitoring and dispatching system, characterized in that: Includes the following modules: The data receiving and preprocessing module is used to receive and parse Beidou satellite positioning data, filter abnormal data, convert scheduling task information into a graph structure input format, and define preliminary constraints; Hierarchical scheduling module, which is used to divide tasks into three levels according to their complexity and urgency; The first layer generates preliminary scheduling plans, the second layer optimizes task dependencies, and the third layer processes global dependencies and makes real-time adjustments; The graph neural network processing module is used to model the scheduling tasks as directed graphs at each level, update the task node status layer by layer through the graph neural network, and generate the optimal scheduling solution; Feedback mechanism and local optimization module, used to monitor the task execution status in real time, calculate the scheduling effect difference, trigger the feedback mechanism, and adjust the scheduling plan through the local optimization algorithm; The visualization display module is used to display the final generated scheduling plan through visualization tools, providing a graphical representation of task dependencies, resource allocation and scheduling paths.

Images