A method and device for generating a low-altitude monitoring network node deployment

Abstract

The application relates to a low-altitude monitoring network node deployment generation method and device. The application comprises the following steps: acquiring the attributes of candidate nodes and deployment areas, and constructing an initial data set based on a double-layer network architecture; constructing a double-layer network node deployment model according to the initial data set; iteratively optimizing the double-layer network node deployment model to obtain a double-layer network node deployment optimal solution that satisfies the deployment constraints and optimizes the deployment target; and generating low-altitude monitoring network node deployment according to the double-layer network node deployment optimal solution. The embodiment of the application acquires an initial data set and constructs a network deployment model based on a double-layer network architecture, differentiates the deployment of core nodes and edge nodes, fully considers multiple factors such as signal coverage, interference shielding and inter-base station communication constraints, realizes the consideration of communication coverage and efficient inter-node cooperation during low-altitude monitoring network node deployment, and can avoid the variable explosion risk and solution efficiency bottleneck in large-scale node-level deployment.

Description

Technical Field

[0001] This invention relates to the field of low-altitude airspace control technology, and in particular to a method and apparatus for generating low-altitude monitoring network nodes. Background Technology

[0002] With the rapid development of consumer drones, the phenomenon of drones flying haphazardly is becoming increasingly serious. To prevent issues such as data leaks, collisions, and safety problems caused by unauthorized drone flights, it is necessary to deploy low-altitude monitoring nodes.

[0003] Low-altitude monitoring can be deployed in three ways: single-point, local, and networked. Existing single-point and localized deployments can detect drones in a specific area; however, their monitoring range is limited and cannot provide reliable large-scale monitoring. Existing networked deployments involve the site selection of a large number of drone detection nodes, and their performance is affected by technical conditions such as signal coverage, strength, and interference, as well as communication constraints related to the transmission and aggregation of detection results. This makes it difficult to simultaneously meet communication coverage requirements and efficient inter-node coordination. Summary of the Invention

[0004] Based on the above analysis, the embodiments of the present invention aim to provide a method for deploying nodes of a low-altitude monitoring network, in order to solve the problem that the existing low-altitude monitoring network cannot simultaneously meet the requirements for deployment communication coverage and efficient collaboration between nodes.

[0005] A first aspect of the present invention provides a method for deploying nodes of a low-altitude monitoring network, comprising:

[0006] Obtain the attributes of candidate nodes and deployment regions, and construct an initial dataset based on a two-layer network architecture;

[0007] Based on the initial dataset, a two-layer network node deployment model is constructed, which includes deployment objectives and deployment constraints.

[0008] The two-layer network node deployment model is iteratively optimized to obtain the optimal solution for the two-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective.

[0009] Based on the optimal solution for the two-layer network node deployment, the low-altitude monitoring network node deployment is generated.

[0010] Furthermore, the attributes of candidate nodes and deployment areas are obtained to construct an initial dataset based on a two-layer network architecture;

[0011] Based on the initial dataset, a two-layer network node deployment model is constructed, which includes deployment objectives and deployment constraints.

[0012] The two-layer network node deployment model is iteratively optimized to obtain the optimal solution for the two-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective.

[0013] Based on the optimal solution for the two-layer network node deployment, the low-altitude monitoring network node deployment is generated.

[0014] Furthermore, the two-layer network architecture includes core nodes and edge nodes;

[0015] Based on the attributes of candidate nodes and deployment regions, an initial dataset based on a two-layer network architecture is constructed, including:

[0016] The attributes of the candidate nodes are matched with the attributes of the nodes in the two-layer network architecture. If a match is made with the core node, the candidate node is added to the first set as a core node. If a match is made with the edge node, the candidate node is added to the second set as an edge node.

[0017] Add the deployment area to the third set;

[0018] The attributes of the candidate nodes and the deployment area are extracted and transformed to obtain the datasets corresponding to the first set, the second set and the third set respectively. The initial dataset includes the three datasets.

[0019] Furthermore, the dataset corresponding to the first set includes the node identifier, node location, and communication radius of each core node; the dataset corresponding to the second set includes the node identifier, node location, communication radius, and sensing radius of each edge node; and the dataset corresponding to the third set includes the region identifier and region location of each deployment area.

[0020] Furthermore, the deployment objective is the objective function of minimizing deployment costs;

[0021] The deployment constraints include deployment area coverage constraints, edge node deployment constraints, core node capacity constraints, two-layer network connection constraints, edge node connection constraints, and connection distance constraints.

[0022] Furthermore, the deployment constraints are divided into first deployment constraints and second deployment constraints. The first deployment constraints include two-layer network connection constraints, edge node connection constraints, and connection distance constraints. The second deployment constraints include deployment area coverage constraints, edge node deployment constraints, and core node capacity constraints.

[0023] Each iteration in the iterative optimization based on the two-layer network node deployment model includes:

[0024] Calculate candidate solutions that satisfy the first deployment constraint and optimize the deployment objective;

[0025] The candidate solution is verified using the second deployment constraint.

[0026] Furthermore, the objective function for minimizing deployment costs is calculated as follows:

[0027]

[0028] Where, N c Let N represent the first set. e This represents the second set. This represents the deployment cost of core node i. Let λ represent the deployment cost of edge node j, λ represent the distance cost coefficient, and d represent the distance cost coefficient. ij This represents the distance from core node i to edge node j. For the deployment variables of the core node i, u is the deployment variable for the edge node. ij This represents the deployment variable for the connection from core node i to edge node j.

[0029] Furthermore, the deployment area coverage constraint is expressed as follows:

[0030]

[0031] The edge node deployment constraints are expressed as follows:

[0032]

[0033] The core node capacity constraint is expressed as follows:

[0034]

[0035] The two-layer network connection constraint is expressed as follows:

[0036]

[0037] The edge node connection constraint is expressed as follows:

[0038]

[0039] The connection distance constraint is expressed as follows:

[0040]

[0041] Where, N c Let N represent the first set. e Let L represent the second set, and let the third set be L. This represents the probability of edge node j being monitored in region l. For the deployment variables of the core node i, is the deployment variable for the edge node, u ij represents the connection deployment variable from the core node i to the edge node j represents the coverage deployment variable between the edge node j and the area l represents the load capacity of the core node i, β i represents the number of edge nodes supported by the core node i, d ij represents the distance from the core node i to the edge node j, D max represents the maximum distance threshold for the connection

[0042] Furthermore, the monitoring probability of the edge node j at the point l is as follows:

[0043] [[ID=...]]

[0044] where R represents the sensing radius of the edge node j; Re represents the monitoring reliability parameter of the edge node j, 0 < Re < R; d(j, l) represents the distance between the edge node j and the point l; δ and β respectively represent the sensing attenuation degree and the monitoring environment factor of the edge node j

[0045] Furthermore, before performing iterative optimization based on the double-layer network node deployment model, it further includes: screening the connection deployment variables from the core node to the edge node according to the attributes of the core node and the edge node

[0046] In the second aspect of the embodiments of the present invention, a low-altitude monitoring network node deployment device is provided, including:

[0047] A data acquisition module, configured to acquire the attributes of candidate nodes and deployment areas, and construct an initial data set based on a double-layer network architecture

[0048] A model construction module, configured to construct a double-layer network node deployment model according to the initial data set, and the double-layer network deployment model includes a deployment objective and deployment constraints

[0049] An iterative optimization module, configured to perform iterative optimization on the double-layer network node deployment model to obtain an optimal solution of the double-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective

[0050] A deployment generation module, configured to generate a low-altitude monitoring network node deployment according to the optimal solution of the double-layer network node deployment

[0051] The present invention can at least achieve the following beneficial effects:

[0052] This invention, based on a two-layer network architecture, acquires the initial dataset and constructs a network deployment model. It deploys nodes in a differentiated manner, fully considering multiple factors such as signal coverage, interference masking, and communication constraints between base stations. This achieves a balance between communication coverage and efficient inter-node collaboration during the deployment of low-altitude monitoring network nodes. Furthermore, this invention's two-layer network architecture-based network deployment model, through iterative optimization, facilitates a reduction in the decision space size and avoids the variable explosion risk and solution efficiency bottlenecks inherent in large-scale node-level deployments.

[0053] In this invention, the above-described technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of this invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of this invention can be realized and obtained from what is particularly pointed out in the description and drawings. Attached Figure Description

[0054] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0055] Figure 1 This is a flowchart of the main process for generating low-altitude monitoring network nodes in one embodiment of the present invention.

[0056] Figure 2 This is a flowchart of the main process for generating low-altitude monitoring network nodes in another embodiment of the present invention.

[0057] Figure 3 This is a schematic diagram of the network topology of a two-layer network architecture in an embodiment of the present invention.

[0058] Figure 4 This is a schematic diagram of the monitoring probability model for edge nodes in an embodiment of the present invention.

[0059] Figure 5 This is a schematic diagram of the process for obtaining the optimal solution for deploying two-layer network nodes in an embodiment of the present invention.

[0060] Figure 6 This is a block diagram of the low-altitude monitoring network node deployment and generation device in an embodiment of the present invention. Detailed Implementation

[0061] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0062] The deployment of low-altitude monitoring network nodes differs from the site selection of common low-altitude logistics networks. Low-altitude monitoring networks must consider technical factors such as the coverage, strength, and interference of base station signals, while also ensuring communication constraints between base stations to facilitate the transmission and aggregation of detection results. Furthermore, the deployment of low-altitude monitoring network nodes typically involves thousands of base station nodes. Therefore, the deployment of low-altitude monitoring network nodes is a large-scale site selection problem that must satisfy both regional monitoring coverage and ensure efficient collaboration between nodes. Existing methods often suffer from variable explosion and a sharp drop in solution efficiency when faced with a large number of decision variables and complex constraints.

[0063] Therefore, in order to solve the above-mentioned technical problems, embodiments of the present invention provide a method and apparatus for generating low-altitude monitoring network nodes.

[0064] A first aspect of this invention provides a method for generating low-altitude monitoring network nodes, such as... Figure 1 As shown, it includes steps S101 to S104.

[0065] Step S101: Obtain the attributes of candidate nodes and deployment areas, and construct an initial dataset based on a two-layer network architecture.

[0066] Understandably, for the deployment of low-altitude monitoring network nodes, candidate nodes are the monitoring subjects, and the deployment area is the monitoring object; these are the two basic elements for deployment generation. The attributes of candidate nodes and deployment areas constitute the initial data for generating the low-altitude monitoring network node deployment. To balance regional monitoring coverage and efficient inter-node collaboration, the low-altitude monitoring network node deployment in this embodiment of the invention adopts a two-layer network architecture. This two-layer architecture divides the network into two layers, each performing different functions and objectives. One layer enables efficient inter-node collaboration, while the other layer achieves regional monitoring coverage. Therefore, the initial dataset in this embodiment of the invention is constructed based on this two-layer network architecture. Specifically, the initial dataset based on the two-layer network architecture is obtained by extracting (filtering), transforming (format unification, etc.), and integrating the attributes of the acquired candidate nodes and deployment areas.

[0067] Step S102: Based on the initial dataset, construct a two-layer network node deployment model, which includes deployment objectives and deployment constraints.

[0068] Understandably, in this embodiment of the invention, the two-layer network deployment model is based on a two-layer network architecture and uses mathematical methods to model the objectives and constraints of low-altitude monitoring network node deployment. This allows for the search for the globally optimal network performance by adjusting the deployment locations and connectivity of the nodes. Deployment objectives are metrics that need to be maximized or minimized, reflecting the expected performance and benefits of the network deployment. Examples include maximizing coverage, minimizing cost, and maximizing network connectivity. Deployment constraints are conditions that must be met to ensure the feasibility and practicality of the deployment, such as communication distance between nodes, node deployment density, and environmental adaptability.

[0069] Step S103: Iteratively optimize the two-layer network node deployment model to obtain the optimal solution for two-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective.

[0070] Specifically, iterative optimization based on the aforementioned two-layer network node deployment model fully considers multiple deployment constraints such as signal coverage, interference masking, and inter-base station communication constraints, gradually adjusting the network node deployment scheme to find a solution that satisfies all deployment constraints and optimizes the deployment objective. For example, gradient information can be used to gradually adjust node positions and connections; heuristic algorithms such as genetic algorithms and simulated annealing can be used to explore the solution space; or a combination of optimization methods can be employed, such as first using heuristic algorithms to find an approximate solution, and then using gradient-based optimization for fine-tuning.

[0071] Step S104: Generate the low-altitude monitoring network node deployment based on the optimal solution for the two-layer network node deployment.

[0072] Understandably, the optimal solution for deploying a two-layer network of nodes needs to be transformed into a specific low-altitude monitoring network node deployment before it can be actually deployed and verified. For example, it is necessary to generate the specific location, connection relationship, and task allocation of each node in each layer.

[0073] Based on the above description, it can be concluded that Figure 1 The illustrated embodiment is for the deployment of low-altitude monitoring network nodes. It selects a two-layer network node deployment for differentiated deployment and optimization, compared with the flat architecture of single-layer network nodes. It takes into account the functional differences between nodes, fully considers multiple factors such as signal coverage, interference masking, and communication constraints between base stations, balances communication coverage and efficient collaboration between nodes, and can reduce the dimensionality of decision variables and the complexity of deployment constraints, making it easier to quickly and effectively generate low-altitude monitoring network node deployments.

[0074] Figure 2 This is a main flowchart of a low-altitude monitoring network node deployment and generation method in another embodiment of the present invention. See also Figure 2 The method for generating low-altitude monitoring network nodes in this embodiment includes steps S201 to S207.

[0075] Step S201: Obtain the attributes of candidate nodes and deployment regions.

[0076] Specifically, in this embodiment and some embodiments of the present invention, the attributes of the candidate nodes include the node identifier, node location (latitude and longitude coordinates), detection method (radar / radio / infrared, etc.), communication radius, sensing radius, etc.; the attributes of the deployment area include the area identifier, area location (latitude and longitude coordinates), area land use type, area importance level, etc.

[0077] Step S202: Match the attributes of the candidate node with the attributes of the nodes in the two-layer network architecture. If the candidate node matches the core node, add it to the first set as a core node. If the candidate node matches the edge node, add it to the second set as an edge node.

[0078] Specifically, in this embodiment and some embodiments of the present invention, the two-layer network architecture includes core nodes and edge nodes. The core nodes are responsible for the transmission and aggregation of detection results in the low-altitude monitoring network, while the edge nodes are responsible for regional coverage and real-time perception of low-altitude targets. The core nodes form the core node layer, and the edge nodes form the edge node layer.

[0079] Understandably, since core nodes and edge nodes have different functions, they use different attributes when deploying nodes in the low-altitude monitoring network. Therefore, candidate nodes are first distinguished. Specifically, in this embodiment and some embodiments of the present invention, feature matching is used for distinction, matching the attributes of candidate nodes with the characteristics of core nodes and edge nodes in the two-layer network architecture. If a candidate node matches a core node, for example, if its communication radius is greater than or equal to the minimum communication radius requirement of the core node, the candidate node is added to the first set (i.e., the core node set) as a core node. If a candidate node matches an edge node, for example, if the candidate node is a radar detector and meets the detection method required by the edge node, the candidate node is added to the second set (i.e., the edge node set) as an edge node. To reduce the dimensionality of decision variables and the complexity of deployment constraints, in this embodiment and some embodiments of the present invention, there is no overlap between the first set and the second set.

[0080] Step S203: Add the deployment area to the third set.

[0081] Step S204: Extract and transform the attributes of the candidate nodes and the deployment area to obtain the datasets corresponding to the first set, the second set and the third set respectively. The initial dataset includes the three datasets.

[0082] Understandably, by differentiating candidate nodes and deployment areas based on a two-layer network architecture, data can be extracted and transformed according to the specific functions and attributes of each set. For example, only the data needed for subsequent processing can be extracted, or the latitude and longitude of the nodes can be converted into standard geographic grid numbers and used as node numbers. This facilitates data standardization and storage, and also improves the efficiency of data retrieval when calculating deployment targets and deployment constraints in the future.

[0083] Specifically, in this embodiment and some embodiments of the present invention, the dataset corresponding to the first set includes at least the node identifier, node location, and communication radius of each core node, and may also include load capacity, number of supported edge nodes, and deployment cost as needed; the dataset corresponding to the second set includes at least the node identifier, node location, communication radius, and sensing radius of each edge node, and may also include monitoring reliability parameters, sensing attenuation degree, monitoring environmental factors, and deployment cost as needed; the dataset corresponding to the third set includes at least the area identifier and area location of each deployment area.

[0084] Step S205: Based on the initial dataset, construct a two-layer network node deployment model, which includes a deployment objective, a first deployment constraint, and a second deployment constraint.

[0085] Step S206: Iteratively optimize the two-layer network node deployment model to obtain the optimal solution for the two-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective. Each iteration includes: calculating candidate solutions that satisfy the first deployment constraints and optimize the deployment objective; and verifying the candidate solutions using the second deployment constraints.

[0086] For steps S205 and S206, it is understood that in this embodiment and some embodiments of the present invention, the deployment constraints are decomposed into two parts for optimization. First, candidate solutions that satisfy the first deployment constraints and optimize the deployment objective are found. Then, it is verified whether the candidate solutions satisfy the second deployment constraints. If they do, the candidate solutions are feasible; otherwise, the candidate solutions are not feasible. The deployment objective is adjusted according to the verification results. In this way, the optimal solution is approximated through multiple iterations.

[0087] Step S207: Generate the low-altitude monitoring network node deployment based on the optimal solution for the two-layer network node deployment.

[0088] Based on the above description, it can be concluded that Figure 2 The illustrated embodiment is for the deployment of low-altitude monitoring network nodes, and in addition to having Figure 1The advantages of the illustrated embodiment are further as follows: First, the candidate nodes and deployment areas are distinguished based on a two-layer network architecture, which facilitates the construction of a two-layer network node deployment model that fully considers multiple factors such as signal coverage, interference masking, and inter-base station communication constraints, and determines the deployment target and deployment constraints. Second, each iteration performs decomposition and optimization, gradually approaching and finally obtaining the optimal solution through iteration. When faced with a large number of decision variables and complex constraints, it can avoid the risks of variable explosion and a sharp drop in solution efficiency. By reducing the dimensionality of decision variables and the complexity of deployment constraints, the robustness and speed of generating low-altitude monitoring network node deployments are improved.

[0089] Furthermore, Figure 1 and Figure 2 The illustrated embodiments and other embodiments of the present invention include a two-layer network deployment model that includes deployment objectives and deployment constraints. The deployment objective is the objective function of minimizing deployment costs. The deployment constraints include deployment area coverage constraints, edge node deployment constraints, core node capacity constraints, two-layer network connection constraints, edge node connection constraints, and connection distance constraints.

[0090] Figure 3 This is a schematic diagram of the network topology of a two-layer network architecture in an embodiment of the present invention. See also... Figure 3 The objective function for minimizing deployment costs is calculated as follows:

[0091]

[0092] Deployment area coverage constraints are expressed as follows:

[0093]

[0094] Edge node deployment constraints are represented as follows:

[0095]

[0096] The core node capacity constraint is expressed as:

[0097]

[0098] The connection constraints of a two-layer network are represented as follows:

[0099]

[0100] Edge node connection constraints are represented as follows:

[0101]

[0102] The connection distance constraint is expressed as:

[0103]

[0104] Where, Nc denotes the first set (core node set), N e denotes the second set (peripheral node set), and L denotes the third set (deployment area set). denotes the deployment cost of core node i denotes the deployment cost of peripheral node j, and λ denotes the distance cost coefficient, d ij denotes the distance from core node i to peripheral node j is the deployment variable of the core node i is the deployment variable of the peripheral node, u ij denotes the connection deployment variable from core node i to peripheral node j denotes the coverage deployment variable between peripheral node j and area l denotes the monitoring probability of peripheral node j in area l denotes the load capacity of core node i, β i denotes the number of peripheral nodes supported by core node i, D max denotes the maximum distance threshold for connection; the definitions of each deployment variable are as follows: <{

[0105]

[0106]

[0107] Figure 4 is a schematic diagram of the monitoring probability model of the peripheral node in the embodiment of the present invention. Refer to Figure 4 , further, to accurately describe the function of the peripheral node in the deployment of the low-altitude monitoring network nodes, improve the accuracy of the deployment of the peripheral nodes in the deployment of the low-altitude monitoring network nodes, and fully consider multiple factors such as signal coverage and interference shielding, in some embodiments of the present invention, the monitoring probability of peripheral node j at point l

[0108]

[0109] is:

[0110] where R denotes the sensing radius of peripheral node j; Re denotes the monitoring reliability parameter of peripheral node j, 0 < Re < R; d(j, l) denotes the distance between peripheral node j and point l; δ and β respectively denote the sensing attenuation degree and monitoring environment factor of peripheral node j

[0111] Figure 5This is a schematic diagram illustrating the process of obtaining the optimal solution for deploying two-layer network nodes in an embodiment of the present invention. See also... Figure 5 To further avoid variable explosion and solution efficiency bottlenecks encountered in large-scale node-level deployments, in some embodiments of the present invention, the process for obtaining the optimal solution for two-layer network node deployment includes steps S501 to S504.

[0112] Step S501: Initialize the initial feasible solution of the deployment variables, and set the upper bound UB, lower bound LB and iteration threshold ε of the deployment objective function value. In one embodiment of the present invention, UB = +∞, LB = -∞ and ε = 200.

[0113] Step S502: In some embodiments of the present invention, the number of nodes is enormous. To improve the solution speed and avoid a sharp drop in solution efficiency caused by variable explosion, it is necessary to filter the connection deployment variables. Specifically, the connection deployment variable u from core node i to edge node j is filtered according to the attributes of core nodes and edge nodes. ij Specifically, this includes:

[0114] Step S502a, in all candidate node sets N (i.e., the first set N) c The second set N e Choose one point as the center point n from the given information. c Set a communication radius threshold, for example, 10km.

[0115] Step S502b, find the center point n c All points whose distance is less than the communication radius threshold are added to set N′, and the points in set N′ belong to cluster clu.

[0116] Step S502c, calculate from the center point n c The distance vectors to each element in set N′ are calculated, and the average of these vectors is obtained by summing the vectors to obtain the offset vector sft(n). c The calculation formula is as follows: |N′| represents the number of nodes in the current cluster, n i The vector representing the node position of node i within the cluster can be obtained from the node coordinates.

[0117] Step S502d, center point n c Along the offset vector sft(n c Move in the direction of ) and move a distance of ||sft(n) c )||.

[0118] Step S502e, if the offset value ||sft(n) c If the offset distance is less than the preset threshold, record the center point at this time; otherwise, return to step S502b.

[0119] In step S502f, if there are still nodes that have not been classified, return to step S502a; otherwise, calculate the distance from each cluster center point to all core nodes, and select the core node with the smallest distance as the node to which the cluster belongs.

[0120] In step S502g, if edge node j belongs to cluster clu, and cluster clu belongs to core node i, then add the definition constraint for the connection deployment variable. Deployment constraints for the two-layer network node deployment model.

[0121] Step S503: Iteratively optimize the two-layer network node deployment model to obtain the optimal solution for the two-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective. Each iteration includes: step S503a: calculate the candidate solution that satisfies the first deployment constraints and optimizes the deployment objective; step S503b: verify the candidate solution using the second deployment constraints.

[0122] Specifically, in these embodiments of the present invention, the first deployment constraint includes a two-layer network connection constraint, an edge node connection constraint, and a connection distance constraint, and the second deployment constraint includes a deployment area coverage constraint, an edge node deployment constraint, and a core node capacity constraint.

[0123] Specifically, step S503a involves calculating candidate solutions that satisfy the first deployment constraint and optimize the deployment objective, as follows:

[0124] The master solution model is constructed based on the two-layer network deployment model. The master solution model is described as follows:

[0125]

[0126] Where η is the cost of validating the model feedback ( (representing the positive real number field), the decision variables of the master solution model include the deployment variables of the core node i. Deployment variables of edge nodes Deployment variable u for the connection from core node i to edge node j ij Therefore, candidate solutions include u ij Coverage deployment variables of edge node j and region l Added by validating the model.

[0127] Understandably, in some embodiments of the present invention, when the number of nodes is small, it is not necessary to filter connection deployment variables, that is, not to add clustering information constraints. Constraints of the master solution model Should be

[0128] Step S503b: Fix the candidate solutions of the master solution model and verify the feasibility of the model.

[0129] The validation model verifies the feasibility of the second deployment constraints, specifically whether the deployment area coverage constraint, edge node deployment constraint, and core node capacity constraint can be satisfied, while keeping the decision variables of the master solution model fixed. This involves fixing step S503a to obtain candidate solutions for the master solution model. Verify whether the verification model can find the coverage deployment variables of edge node j and region l that satisfy the second deployment constraint.

[0130] The validation model is as follows:

[0131]

[0132] When the verification model is deemed infeasible, i.e., the verification model has no solution, the first cost η1 is returned to the main solution model. The constraint expression for the first cost η1 is as follows:

[0133]

[0134] Where, σ l η1 is the first dual variable, representing the penalty for insufficient coverage of region l. In some embodiments of the present invention, in order to improve the calculation speed, η1 = 0 is given to the main solution model, and η = η1 = 0 is set.

[0135] When the model is verified to be feasible, i.e., the model has a solution, the second cost η2 is fed back to the master solution model. The constraint expression for the second cost η2 is as follows:

[0136]

[0137] Where, π l Let be the second dual variable, representing the impact of coverage achievement on total cost. In some embodiments of this invention, Given the master solution model, let

[0138] Furthermore, in some embodiments of the present invention, the first and second dual variables σ l π l It is obtained directly from solving the master solution model using modeling software such as CPLEX.

[0139] Step S504: Update the upper and lower bounds of the function value of the deployment target: the upper bound is UB = min(UB,η), and the lower bound is LB = max(LB,η). When UB - LB ≤ ε, output the current solution as the optimal solution; otherwise, return to step S503a to continue iteratively solving the problem.

[0140] A second aspect of the present invention provides a low-altitude monitoring network node deployment device, such as... Figure 6 As shown, it includes:

[0141] The data acquisition module is used to acquire the attributes of candidate nodes and deployment areas, and to build an initial dataset based on a two-layer network architecture.

[0142] The model building module is used to build a two-layer network node deployment model based on the initial dataset. The two-layer network deployment model includes deployment objectives and deployment constraints.

[0143] The iterative optimization module is used to iteratively optimize the two-layer network node deployment model to obtain the optimal solution for the two-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective.

[0144] The deployment generation module is used to generate the low-altitude monitoring network node deployment based on the optimal solution for the two-layer network node deployment.

[0145] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0146] This invention, based on a two-layer network architecture, acquires the initial dataset and constructs a network deployment model. It deploys nodes in a differentiated manner, fully considering multiple factors such as signal coverage, interference masking, and communication constraints between base stations. This achieves a balance between communication coverage and efficient inter-node collaboration during the deployment of low-altitude monitoring network nodes. Furthermore, this invention's two-layer network architecture-based network deployment model, through iterative optimization, facilitates a reduction in the decision space size and avoids the variable explosion risk and solution efficiency bottlenecks inherent in large-scale node-level deployments.

[0147] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating low-altitude monitoring network nodes, characterized in that, include: Based on the attributes of candidate nodes and deployment regions, an initial dataset is constructed based on a two-layer network architecture; the two-layer network architecture includes core nodes and edge nodes; the initial dataset includes a set of core nodes, a set of edge nodes, and a set of deployment regions. Based on the initial dataset, a two-layer network node deployment model is constructed. The two-layer network node deployment model includes deployment objectives and deployment constraints. The deployment constraints are divided into a first deployment constraint and a second deployment constraint. The first deployment constraint includes a two-layer network connection constraint, an edge node connection constraint, and a connection distance constraint. The second deployment constraint includes a deployment area coverage constraint, an edge node deployment constraint, and a core node capacity constraint. The deployment area coverage constraint is expressed as follows: ； The edge node deployment constraints are expressed as follows: ； The core node capacity constraint is expressed as follows: ； The two-layer network connection constraint is expressed as follows: ； The edge node connection constraint is expressed as follows: ； The connection distance constraint is expressed as follows: ； in, Represents the set of core nodes. Represents the set of edge nodes. Indicates a set of deployment areas. Represents edge nodes In the region The monitoring probability, For the core node Deployment variables, For the deployment variables of the edge nodes, Represents the core node To edge nodes Connection deployment variables, Represents edge nodes With the region Override deployment variables, Represents the core node Load capacity, Represents the core node Number of supported edge nodes Represents the core node To edge nodes distance, This represents the maximum distance threshold for the connection; The two-layer network node deployment model is iteratively optimized to obtain an optimal solution for the two-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective; wherein each iteration includes: calculating a candidate solution that satisfies the first deployment constraints and optimizes the deployment objective; and verifying the candidate solution using the second deployment constraints; Based on the optimal solution for the two-layer network node deployment, the low-altitude monitoring network node deployment is generated.

2. The method according to claim 1, characterized in that, Based on the attributes of candidate nodes and deployment regions, an initial dataset based on a two-layer network architecture is constructed, including: The attributes of the candidate nodes are matched with the attributes of the nodes in the two-layer network architecture. If a match is made with the core node, the candidate node is added to the core node set as a core node. If a match is made with the edge node, the candidate node is added to the edge node set as an edge node. Add the deployment region to the deployment region set; The attributes of the candidate nodes and the deployment areas are extracted and transformed to obtain the datasets corresponding to the core node set, the edge node set, and the deployment area set, respectively. The initial dataset includes the three datasets.

3. The method of claim 2, wherein, The dataset corresponding to the core node set includes the node identifier, node location, and communication radius of each core node; the dataset corresponding to the edge node set includes the node identifier, node location, communication radius, and sensing radius of each edge node; and the dataset corresponding to the deployment area set includes the area identifier and area location of each deployment area.

4. The method according to claim 3, characterized in that, The deployment objective is the objective function of minimizing deployment costs.

5. The method of claim 4, wherein, The objective function for minimizing deployment costs is calculated as follows: ； in, Represents the core node Deployment costs Represents edge nodes Deployment costs This represents the distance cost coefficient.

6. The method according to claim 1, characterized in that, Edge node In the region The monitoring probability Is: ； in, Represents edge nodes The radius of perception; Represents edge nodes Monitoring reliability parameters ; Represents edge nodes With the region The distance between them; Representing edge nodes respectively The degree of perceived attenuation and monitoring of environmental factors.

7. The method according to claim 1, characterized in that, Before iteratively optimizing the two-layer network node deployment model, the method further includes: filtering the connection deployment variables from the core node to the edge node based on the attributes of the core node and the edge node.

8. A low-altitude monitoring network node deployment device, characterized in that, include: The data acquisition module is used to construct an initial dataset based on a two-layer network architecture, according to the attributes of candidate nodes and deployment areas. The two-layer network architecture includes core nodes and edge nodes; the initial dataset includes a set of core nodes, a set of edge nodes, and a set of deployment regions. The model building module is used to construct a two-layer network node deployment model based on the initial dataset. The two-layer network node deployment model includes deployment objectives and deployment constraints. The deployment constraints are divided into a first deployment constraint and a second deployment constraint. The first deployment constraint includes a two-layer network connection constraint, an edge node connection constraint, and a connection distance constraint. The second deployment constraint includes a deployment area coverage constraint, an edge node deployment constraint, and a core node capacity constraint. The deployment area coverage constraint is expressed as follows: ； The edge node deployment constraints are expressed as follows: ； The core node capacity constraint is expressed as follows: ； The two-layer network connection constraint is expressed as follows: ； The edge node connection constraint is expressed as follows: ； The connection distance constraint is expressed as follows: ； in, Represents the set of core nodes. Represents the set of edge nodes. Indicates a set of deployment areas. Represents edge nodes In the region The monitoring probability, For the core node Deployment variables, For the deployment variables of the edge nodes, Represents the core node To edge nodes Connection deployment variables, Represents edge nodes With the region Override deployment variables, Represents the core node Load capacity, Represents the core node Number of supported edge nodes Represents the core node To edge nodes distance, This represents the maximum distance threshold for the connection; An iterative optimization module is used to iteratively optimize the two-layer network node deployment model to obtain an optimal solution for the two-layer network node deployment that satisfies the deployment constraints and optimizes the deployment objective; wherein, each iteration includes: calculating a candidate solution that satisfies the first deployment constraints and optimizes the deployment objective; and verifying the candidate solution using the second deployment constraints; The deployment generation module is used to generate the low-altitude monitoring network node deployment based on the optimal solution for the two-layer network node deployment.

Images