Digital twin edge collaborative quasi-static deployment method and system based on vehicle movement locality characteristics

Abstract

The invention discloses a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics. The method comprises the following steps: acquiring a rasterized map of an area to be deployed, and performing first clustering on grids in the rasterized map to obtain K final first clusters; constructing a target model to obtain an optimization target; selecting a final first cluster as a final second cluster; performing second clustering on the grids in the final second cluster to obtain a plurality of final third clusters; according to the optimization target, generating a server distribution scheme corresponding to each final third cluster by using a simulated annealing and particle swarm optimization algorithm; selecting another final first cluster as a final second cluster; repeating until all final first clusters are selected; and integrating all the server distribution schemes to obtain a final server distribution scheme. The method can effectively deploy the digital twin, and is low in resource overhead and configuration cost.

Description

Technical Field

[0001] The present invention relates to the field of digital twins of Internet of Vehicles, and more specifically, to a quasi-static deployment method of digital twins based on the local characteristics of vehicle movement. Background Art

[0002] The Internet of Vehicles forms a highly intelligent and automated transportation network by interconnecting and sharing information among multiple systems such as vehicles, transportation infrastructure, smart devices, and cloud platforms. Digital twins are the core enabling technology that promotes the digitalization and intelligent development of smart transportation in the Internet of Vehicles. A large number of digital twins of the Internet of Vehicles will be configured on network edge servers to form digital twins at the edge of the Internet of Vehicles. Digital twins use modeling tools to build high-fidelity digital models of physical entities such as vehicles, pedestrians, transportation infrastructure, and communication networks in the Internet of Vehicles - digital twins. The model maintains real-time interactive connection with physical entities in the real environment, and uses virtual models to simulate the behavior of physical entities in reality. With the assistance of the central cloud server, the digital twins at the edge of the Internet of Vehicles collaborate to calculate the vehicle's autonomous driving tasks, provide digital twin services such as early warning, navigation, traffic flow monitoring, and network optimization for vehicle autonomous driving, and promote the process of intelligent networking and digitalization of vehicles.

[0003] Because vehicles are always in a dynamic movement process, and the road environment they face is constantly changing, the digital twin also needs to be constantly adjusted to adapt to the changes in the road environment. However, due to the large size of the digital twin, frequent switching back and forth causes task migration and network scheduling problems, which in turn increases configuration costs. Therefore, digital twins are often deployed to multiple edge servers to reduce switching costs. However, traditional deployment methods cannot efficiently deploy digital twins, which brings about problems such as high resource overhead and high configuration costs.

[0004] The prior art discloses a method for deploying edge digital twins based on transfer learning, including the following steps: using the KM algorithm to formulate the matching of the edge server of a new factory and the edge server of an existing factory, and using the simulated annealing algorithm to formulate the matching of the edge server in the newly built factory and the IIoT device m; each edge server in the newly built factory is matched with an existing factory edge server; the source domain model in the existing factory edge server is transferred to the corresponding new factory edge server; the edge server in the newly built factory migrates the received source domain model to the matching IIoT device m, and builds the source domain model for the IIoT device m; in the newly built factory, the edge server uses the source domain model and combines the data uploaded by the IIoT device m to build a digital twin for the matching IIoT device m. This method cannot effectively deploy the Internet of Vehicles digital twin according to the characteristics of vehicle operation. Summary of the invention

[0005] In view of the defects of low efficiency, large resource overhead and high configuration cost of digital twins in the prior art, the present invention provides a digital twin edge collaborative quasi-static deployment method based on the local characteristics of vehicle movement. This method can effectively deploy digital twins with low resource overhead and low configuration cost.

[0006] The primary purpose of the present invention is to solve the above technical problems. The technical solution of the present invention is as follows:

[0007] A digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics, comprising:

[0008] S1: Obtain a rasterized map of the area to be deployed, perform a first clustering on the grids in the rasterized map, and obtain K final first clustering clusters;

[0009] S2: Construct the optimization target model of the Internet of Vehicles digital twin and obtain the optimization target of digital twin deployment;

[0010] S3: Select a final first cluster as the final second cluster;

[0011] S4: performing a second clustering on the grids in the final second clustering cluster to obtain a plurality of final third clustering clusters;

[0012] S5: Generate a server allocation plan corresponding to each final third cluster using simulated annealing and particle swarm optimization algorithms according to the digital twin deployment optimization goal;

[0013] S6: Select another final first cluster as the final second cluster; repeat steps S4 to S5 until all final first clusters are selected;

[0014] S7: Integrate all server allocation plans to obtain a final server allocation plan.

[0015] Furthermore, the first clustering includes:

[0016] S101: Obtain a rasterized map and use it as a cluster to form a cluster set;

[0017] S102: Selecting a cluster with the largest diameter in the cluster set as the second cluster;

[0018] S103: Calculate the average dissimilarity between each grid in the second cluster and other grids in the second cluster as the first average dissimilarity; and sort the first average dissimilarity to obtain the grid with the largest first average dissimilarity as the new first grid;

[0019] S104: Calculate the dissimilarity between each grid in the second cluster and the first grid as a second dissimilarity;

[0020] S105: comparing the first average dissimilarity and the second dissimilarity of each grid in the second cluster; if the first average dissimilarity is greater than or equal to the second dissimilarity, adding the grid to the fourth cluster; if the first average dissimilarity is less than the second dissimilarity, adding the grid to the third cluster;

[0021] S106: replacing the second cluster in the cluster set with the third cluster, and adding the fourth cluster as a new first cluster to the cluster set;

[0022] S107: Establish two empty clusters as a new third cluster and a new fourth cluster respectively; repeat steps S102 to S106 until the number of clusters in the cluster set is K, and take all clusters in the cluster set as the final first cluster.

[0023] Furthermore, the calculation formula of the diameter of the cluster is as follows:

[0024]

[0025] DIS(i,j)=ε1D nom (i,j)+ε2TR mom (i,j)

[0026] ε1 and ε2 represent weight factors, ε1+ε2=1, D nom (i,j) represents the geographical distance from grid i to grid j, TR mom (i, j) represents the number of switching digital twins required for the vehicle to move between grid i and grid j, and i and j represent serial numbers.

[0027] Furthermore, the dissimilarity is the Euclidean distance between two grids.

[0028] Furthermore, the second clustering includes:

[0029] S301: Select grids in the final first cluster to construct a grid sparse graph to form a grid sparse graph matrix; wherein the nodes of the sparse graph represent grids; and the edges of the sparse graph represent the traffic intensity distance between grids;

[0030] S302: Inputting the grid sparse graph matrix and the corresponding grid attributes into a deep feature model to obtain grid deep features;

[0031] S303: soft clustering the grid deep features to obtain a plurality of final third clusters.

[0032] Furthermore, the deep feature model includes: a self-loop layer, a linear layer, a first GCN unit, and a second GCN unit;

[0033] The grid sparse graph matrix is ​​input into the input end of the self-loop layer, the grid attribute is input into the input end of the first GCN unit; the output end of the second GCN unit outputs the classification result;

[0034] The output end of the self-loop layer is connected to the input end of the linear layer, the output end of the linear layer is connected to the input end of the first GCN unit and the input end of the second GCN unit, and the output end of the first GCN unit is connected to the input end of the second GCN unit.

[0035] Further, the first GCN unit includes a first hidden layer, a first fully connected layer, and a first activation layer connected in sequence;

[0036] The grid attributes and the output end of the linear layer are input to the input end of the first hidden layer, and the output end of the first activation layer is connected to the input end of the second GCN unit.

[0037] Further, the second GCN unit includes a second hidden layer, a second fully connected layer, and a second activation layer connected in sequence;

[0038] The output end of the first activation layer and the output end of the linear layer are connected to the input end of the second hidden layer, and the second activation layer outputs the classification result.

[0039] Furthermore, the digital twin deployment optimization objectives are as follows:

[0040]

[0041] M is the unit deployment benefit, is the coefficient for balancing the load balancing LO(A, L) and the virtual-real interaction delay DE(A, L), ρ represents the cost of a single switch, and μ is the cost of a single deployment; a i,k =1 means that the i-th grid is assigned to the k-th final third cluster, i, k, q represent the sequence number, l k,q Indicates that the kth final third cluster is assigned to the qth server, Q is the total number of servers, K is the total number of final third clusters, N is the total number of grids, and w i (t) represents the load of the i-th grid from t-1 to t, b k,q represents the bandwidth resource allocated by the qth server to the kth final third cluster, B q represents the total bandwidth resource of the qth server, F q represents the total computing power resources of the qth server, f i represents the computing power resources required for the i-th grid, and A and L represent the obtained deployment utility optimization solution.

[0042] A digital twin edge collaborative quasi-static deployment system based on vehicle movement locality characteristics, comprising:

[0043] The first clustering module: obtains a rasterized map of the area to be deployed, performs a first clustering on the grids in the rasterized map, and obtains K final first clustering clusters;

[0044] Model building module: builds the optimization target model of the digital twin of the Internet of Vehicles and obtains the optimization target of the digital twin deployment;

[0045] Cluster selection module: select a final first cluster as the final second cluster;

[0046] A second clustering module: performing a second clustering on the grids in the final second clustering cluster to obtain a plurality of final third clustering clusters;

[0047] Allocation plan generation module: according to the digital twin deployment optimization goal, using simulated annealing and particle swarm optimization algorithm, generate a server allocation plan corresponding to each final third cluster;

[0048] The third clustering module: select another final first clustering cluster as the final second clustering cluster; return to the second clustering module until all final first clustering clusters are selected;

[0049] Allocation plan integration module: integrates all server allocation plans to obtain the final server allocation plan.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The present invention decomposes the global map data into multiple local areas through the first clustering, further simplifying and optimizing the data processing process; through the second clustering, the complex spatial relationship between geographical locations can be effectively mined; the simulated annealing and particle swarm optimization algorithms can be used to comprehensively consider the optimization problems composed of virtual-real interaction delay, load balancing, number of switching times and deployment costs. At the same time, the global search capability of simulated annealing and the fast local search advantage of particle swarms are combined to obtain the optimal solution. This hybrid optimization algorithm effectively avoids the problem of falling into the local optimal solution and realizes the optimal configuration of resources. In summary, the deployment method of the present invention can effectively deploy digital twins with low resource overhead and low configuration cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A flowchart of a digital twin edge collaborative quasi-static deployment method based on the local characteristics of vehicle movement provided in Example 1.

[0053] Figure 2 This is a flow chart of the first clustering provided in Example 1.

[0054] Figure 3 This is a flow chart of the second clustering provided in Example 1.

[0055] Figure 4 This is a structural diagram of the deep feature model provided in Example 1.

[0056] Figure 5 This is a structural diagram of the first GCN unit provided in Example 1.

[0057] Figure 6 This is a structural diagram of the second GCN unit provided in Example 1.

[0058] Figure 7 A schematic diagram of the principle of the deep feature model provided in Example 1.

[0059] Figure 8 A schematic diagram of the principle of the second clustering provided in Example 1.

[0060] Fig. 9 This is a schematic diagram of the application of the server allocation solution provided in Example 1. DETAILED DESCRIPTION

[0061] The drawings are for illustrative purposes only and should not be construed as limiting the present patent;

[0062] In order to better illustrate the present embodiment, some parts in the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0063] It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0064] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0065] Example 1

[0066] like Figure 1 As shown, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics includes:

[0067] S1: Obtain a rasterized map of the area to be deployed, perform a first clustering on the grids in the rasterized map, and obtain K final first clustering clusters;

[0068] S2: Construct the optimization target model of the Internet of Vehicles digital twin and obtain the optimization target of digital twin deployment;

[0069] S3: Select a final first cluster as the final second cluster;

[0070] S4: performing a second clustering on the grids in the final second clustering cluster to obtain a plurality of final third clustering clusters;

[0071] S5: Generate a server allocation plan corresponding to each final third cluster using simulated annealing and particle swarm optimization algorithms according to the digital twin deployment optimization goal;

[0072] S6: Select another final first cluster as the final second cluster; repeat steps S4 to S5 until all final first clusters are selected;

[0073] S7: Integrate all server allocation plans to obtain a final server allocation plan.

[0074] Furthermore, if Figure 2 As shown, the first clustering includes:

[0075] S101: Obtain a rasterized map and use it as a cluster to form a cluster set;

[0076] S102: Selecting a cluster with the largest diameter in the cluster set as the second cluster;

[0077] S103: Calculate the average dissimilarity between each grid in the second cluster and other grids in the second cluster as the first average dissimilarity; and sort the first average dissimilarity to obtain the grid with the largest first average dissimilarity as the new first grid;

[0078] S104: Calculate the dissimilarity between each grid in the second cluster and the first grid as a second dissimilarity;

[0079] S105: comparing the first average dissimilarity and the second dissimilarity of each grid in the second cluster; if the first average dissimilarity is greater than or equal to the second dissimilarity, adding the grid to the fourth cluster; if the first average dissimilarity is less than the second dissimilarity, adding the grid to the third cluster;

[0080] S106: replacing the second cluster in the cluster set with the third cluster, and adding the fourth cluster as a new first cluster to the cluster set;

[0081] S107: Establish two empty clusters as a new third cluster and a new fourth cluster respectively; repeat steps S102 to S106 until the number of clusters in the cluster set is K, and take all clusters in the cluster set as the final first cluster.

[0082] It should be noted that the grid represents the map grid, that is, the grid-based map representation method. The cluster cluster in the first clustering represents a collection of grids. The first clustering decomposes the global map into multiple local areas, that is, the global problem is transformed into multiple local problems.

[0083] It should be noted that the data complexity of the global map is high, and a single data processing mode is difficult to adapt to diverse analysis needs, such as traffic flow control, accident prevention, etc., which limits the response speed and accuracy of the system. Using hierarchical recursive clustering to decompose the global map can effectively solve this problem. Dividing the global map into multiple relatively independent local areas not only reduces the complexity of a single processing task, but also improves the efficiency of data processing. Each local area can be specially analyzed and managed according to its unique geographical and traffic characteristics, so as to respond more accurately to the actual local situation.

[0084] Furthermore, the calculation formula of the diameter of the cluster is as follows:

[0085]

[0086] DIS(i,j)=ε1D nom (i,j)+ε2TR mom (i,j)

[0087] ε1 and ε2 represent weight factors, ε1+ε2=1, D nom (i,j) represents the geographical distance from grid i to grid j, TR mom (i, j) represents the number of switching digital twins required for the vehicle to move between grid i and grid j, and i and j represent serial numbers.

[0088] Furthermore, the dissimilarity is the Euclidean distance between two grids.

[0089] Furthermore, if Figure 3 As shown, the second clustering includes:

[0090] S301: Select grids in the final first cluster to construct a grid sparse graph to form a grid sparse graph matrix; wherein the nodes of the sparse graph represent grids; and the edges of the sparse graph represent the traffic intensity distance between grids;

[0091] S302: Inputting the grid sparse graph matrix and the corresponding grid attributes into a deep feature model to obtain grid deep features;

[0092] S303: soft clustering the grid deep features to obtain a plurality of final third clusters.

[0093] In a specific embodiment, the soft clustering adopts the soft-kmeans algorithm.

[0094] Furthermore, if Figure 4 As shown, the deep feature model includes: a self-loop layer, a linear layer, a first GCN unit, and a second GCN unit;

[0095] The grid sparse graph matrix is ​​input into the input end of the self-loop layer, the grid attribute is input into the input end of the first GCN unit; the output end of the second GCN unit outputs the classification result;

[0096] The output end of the self-loop layer is connected to the input end of the linear layer, the output end of the linear layer is connected to the input end of the first GCN unit and the input end of the second GCN unit, and the output end of the first GCN unit is connected to the input end of the second GCN unit.

[0097] Furthermore, if Figure 5 As shown, the first GCN unit includes a first hidden layer, a first fully connected layer, and a first activation layer connected in sequence;

[0098] The grid attributes and the output end of the linear layer are input to the input end of the first hidden layer, and the output end of the first activation layer is connected to the input end of the second GCN unit.

[0099] Furthermore, if Figure 6 As shown, the second GCN unit includes a second hidden layer, a second fully connected layer, and a second activation layer connected in sequence;

[0100] The output end of the first activation layer and the output end of the linear layer are connected to the input end of the second hidden layer, and the second activation layer outputs the classification result.

[0101] It should be noted that the application of GCN units not only improves the accuracy of data analysis, but also makes the characteristics of local areas more obvious, which is convenient for accurate clustering analysis. A topological graph is constructed with grids as vertices and traffic flow intensity distances as edges. The topological graph is passed into the GCN neural network for feature extraction, and the deeper relationship between grids is mined to obtain node embedding representation. Traditional clustering often fails to fully utilize the complex spatial relationship and topological structure between geographical locations, resulting in limited accuracy in traffic flow analysis. These methods usually focus on the independent attributes of points rather than their interactions, making the analysis results unable to reflect the actual traffic conditions and dynamic changes in the geographical environment. For this purpose, a graph convolutional network (GCN) is used to process local area data. By utilizing the topological relationship between grids, GCN can effectively capture and learn the traffic flow and spatial dependence between grids, thereby improving the accuracy and efficiency of data analysis and obtaining a reasonably distributed clustering result.

[0102] like Figure 7 As shown, the GCN unit can be expressed by the following formula:

[0103]

[0104]

[0105] is a matrix with self-connection, I N is the identity matrix, for The degree matrix of W (0) , W (1) Respectively represent the weight matrices of the first and second layers in the normalization layer, σ(·) and ReLU(·) are activation functions. Each GCN unit obtains the summary of the neighbor features of each vertex by multiplying the adjacency matrix M and the feature matrix H, and then multiplies it by a parameter matrix W(l), adds the activation function σ, and performs a nonlinear transformation to obtain the matrix H(l+1) of the aggregated adjacent vertex features. This matrix is ​​the required clustering matrix A.

[0106] The training uses modularity as the loss function. The specific formula is as follows:

[0107]

[0108] M∈R N×N is the adjacency matrix of the graph, which represents the actual connections between nodes in the graph. ij represents the actual connection weight between nodes i and j. represents the connection probability between nodes in a random graph, Indicates the difference between actual connections and random connections. m is the total number of edges in the graph, i.e. m = ∑M ij . k is the node degree vector, k i =∑ j M ij , represents the degree of node i, that is, the sum of the number of connected edges. Z∈R N×k is the community distribution matrix of the node, i.e., the output feature of GCN, Z i represents the distribution of node i in k clusters. Tr(·) is a trace operation, which is used to extract the overall characteristics of the matrix.

[0109] Construct the difference matrix between actual connections and random connections This difference matrix is ​​weightedly projected through the node community distribution matrix Z, that is, calculated Thus, the connection quality contribution of the node in each community is obtained. Through the trace operation Tr(·), the sum of the connection differences within all communities is extracted to reflect the overall difference between the current community division and random connection. Finally, through the normalization term The results are standardized to ensure that the value of modularity Q is within a reasonable range. The training goal is to maximize the modularity Q so that the actual connection density inside the graph is as high as possible, while the connection between communities is as sparse as possible, thereby obtaining a reasonable partitioning structure.

[0110] The present invention performs training with the goal of maximizing the modularity function, which is a standard for measuring whether the community division is reasonable.

[0111] Furthermore, the digital twin deployment optimization objectives are as follows:

[0112]

[0113]

[0114] M is the unit deployment benefit, is the coefficient for balancing the load balancing LO(A, L) and the virtual-real interaction delay DE(A, L), ρ represents the cost of a single switch, and μ is the cost of a single deployment; a i,k =1 means that the i-th grid is assigned to the k-th final third cluster, i, k, q represent the sequence number, l k,q Indicates that the kth final third cluster is assigned to the qth server, Q is the total number of servers, K is the total number of final third clusters, N is the total number of grids, and w i (t) represents the load of the i-th grid from t-1 to t, b k,q represents the bandwidth resource allocated by the qth server to the kth final third cluster, B q represents the total bandwidth resource of the qth server, F q represents the total computing power resources of the qth server, f i represents the computing power resources required for the i-th grid, and A and L represent the obtained deployment utility optimization solution.

[0115] It should be noted that constraint C1 indicates that the grid is uniquely assigned, that is, any grid can only be divided into one cluster. Constraint C2 indicates that the final third clustering cluster is uniquely matched, that is, any final third clustering cluster can only match one edge server. Constraint C3 indicates that the edge server can match multiple final third clustering clusters if bandwidth resources and computing power allow. Constraints C4 and C5 represent the bandwidth resource and computing power resource constraints of edge server g, respectively. Constraint C6 represents the optimization solution type constraint, that is, the optimization solutions are all integers of 0 or 1.

[0116] It should be noted that the optimization objectives of digital twin deployment are divided into virtual-real interaction delay, load balancing, number of switching times, and deployment cost;

[0117] It should be noted that the virtual-real interaction delay can be deduced from this, assuming that the computing capacity of the edge server meets the maximum workload, thus ignoring the processing delay and focusing on the transmission delay and computing delay. i The distance to edge server q is d i,q , then the grid within the cluster g i The channel gain with edge server q is:

[0118]

[0119] Where β is the fixed transmission loss.

[0120] B q It represents the bandwidth resource set provided by BS or RSU for virtual-real interaction within the map range. Assuming that the entire map can be covered, b is used to represent the bandwidth required for communication with the edge server q. The grid g within the cluster i The communication rate of data uploaded to edge server q is:

[0121]

[0122] where p q represents the transmission power of edge server q, and σ represents the noise power.

[0123] In-cluster grid g i The amount of data is D i , then the grid within the cluster g i The transmission delay of data uploaded to edge server q is:

[0124]

[0125] where w i (t) is the grid g i The load of the grid g i Number of virtual-real interactions between vehicle users

[0126] The total transmission delay is the sum of the transmission delays of the grid data in each cluster in the map being uploaded to the edge server:

[0127]

[0128] Among them l k,q represents the placement of the digital twin of the grid vehicle within the cluster, a i,k Represents the raster clustering result.

[0129] The computing power required per unit load is f i , the computing power of edge server q is F q , the computing delay measured by the computing power resources of the edge server is:

[0130]

[0131] The total computing latency is the sum of the computing latency measured by the computing resources of each edge server in the map:

[0132]

[0133] In summary, the virtual-real interaction delay of the system can be expressed as:

[0134] DE(A,L)=T up +T per

[0135] It should be noted that load balancing is derived from this.

[0136] The load balancing index of the system based on Jain fairness is as follows. The goal is to evaluate the load balancing in the system by considering the placement and connection of the digital twins of grid vehicles in different clusters:

[0137]

[0138] in

[0139]

[0140] |Q| represents the cardinality of set Q, that is, the number of edge servers Q; U Q Represents the total load on the edge server Q, which is a weighted sum of the connections of the vehicle digital twins of each grid in the cluster on the server. By optimizing this index, the system configuration can be adjusted to make resource allocation more fair, thereby improving the performance and efficiency of the entire system.

[0141] It should be noted that the number of switching times is derived from this.

[0142] In the trace, the total workload of all clusters is constant for a given duration, so the maintenance cost can be simply expressed as the migration cost, i.e., the number of switches. The goal is stated as:

[0143]

[0144] in

[0145]

[0146] tr k,k′ (t) represents cluster C k To cluster C k′ The number of switching times from time t to time t-1, tr i,j (t) represents the grid g in this time period i To grid g jThe number of switching times.

[0147] It should be noted that the deployment cost is derived from this.

[0148] Considering the peak total load of each cluster in the time dimension, the maximum workload of each cluster in a given time period is:

[0149]

[0150] Bandwidth and computing power are considered as part of the cost because they are applied to cluster C at the edge server k In the process of communication, it involves the use of communication and computing resources.

[0151] Use edge server q in cluster C k The bandwidth and computing power generated in are expressed as:

[0152]

[0153] The total deployment cost is the total cost of bandwidth and computing power required for the peak total load of each cluster in the time dimension:

[0154]

[0155] In a specific embodiment, the generation process of the simulated annealing and particle swarm optimization algorithm includes:

[0156] S501: Define the objective function f(x), set the particle swarm size N, determine the maximum number of iterations max_iter, and initialize the particle position x i and speed v i Set the inertia weight w, learning factors c1 and c2, initial temperature T0, cooling rate α, and minimum temperature T min .

[0157] S502: For each particle i, calculate the fitness f(x i ).

[0158] If this fitness f(x i ) is better than the individual optimal fitness f(p besti ), then update the individual optimal position to the current position p besti For x i ;

[0159] If the individual's optimal fitness f(p besti ) is better than the global optimal fitness f(g best ), then update the global optimal position g best For p vesti ;

[0160] S503: Update the particle's velocity v i and position x i .

[0161] S504: Generate new solution x new By perturbing x i , calculate the fitness of the new solution f(x new ). If f(x new ) is better than f(x i ), directly accept the new solution, otherwise calculate the energy difference ΔE=f(x new )-f(x i ) and accepts the new solution with probability P = exp(-ΔE / T).

[0162] S505: If the temperature T is lower than the minimum temperature T min , the iteration is terminated and the global optimal solution g is returned best And its objective function value f(g best ).

[0163] It should be noted that the traditional matching algorithm cannot handle the matching problem between the final third cluster and the edge server very well. Using simulated annealing and particle swarm optimization algorithm to solve the optimal cluster and edge server matching problem can optimize resource allocation and improve service response speed and efficiency. This optimization algorithm combines the advantages of global search and local search, can effectively avoid falling into the local optimal solution, and find a more reasonable matching solution.

[0164] In a specific embodiment, simulated annealing and particle swarm optimization algorithms are used to generate a server allocation scheme corresponding to each final third cluster. The final third cluster can only be matched with one server, and the server can be matched with multiple clusters if bandwidth resources and computing power allow. The cluster matrix and simulated annealing and particle swarm optimization algorithms continuously search for the optimal solution so that the cluster and the server achieve a stable and ideal match. The digital twin is placed on the corresponding server, and the vehicle user can interact and update the digital twin in the server through the adjacent road test unit.

[0165] A digital twin edge collaborative quasi-static deployment system based on vehicle movement locality characteristics, comprising:

[0166] The first clustering module: obtains a rasterized map of the area to be deployed, performs a first clustering on the grids in the rasterized map, and obtains K final first clustering clusters;

[0167] Model building module: builds the optimization target model of the digital twin of the Internet of Vehicles and obtains the optimization target of the digital twin deployment;

[0168] Cluster selection module: select a final first cluster as the final second cluster;

[0169] A second clustering module: performing a second clustering on the grids in the final second clustering cluster to obtain a plurality of final third clustering clusters;

[0170] Allocation plan generation module: according to the digital twin deployment optimization goal, using simulated annealing and particle swarm optimization algorithm, generate a server allocation plan corresponding to each final third cluster;

[0171] The third clustering module: select another final first clustering cluster as the final second clustering cluster; return to the second clustering module until all final first clustering clusters are selected;

[0172] Allocation plan integration module: integrates all server allocation plans to obtain the final server allocation plan.

[0173] like Figure 8 , Fig. 9 As shown in the figure, the global map is decomposed into multiple local areas after the first clustering. For each local area, a topological map is constructed with grids as vertices and traffic flow intensity distances between grids as edges, and is passed to the GCN neural network model for training, with the aim of mining deeper relationships between grids. After training the neural network model, the feature matrix of aggregated adjacent nodes can be obtained. The learned node embedding representation is clustered using the Soft-Kmeans algorithm to obtain clustering results and clustering matrices. Through simulated annealing and particle swarm optimization algorithms, an optimal solution for the deployment of a cluster and an edge server is obtained, that is, the best matching result, under which the deployment utility is maximized. Each cluster is associated with its corresponding edge server, that is, the cluster places the grid vehicle digital twin on the corresponding edge server, and the grid vehicle users in the cluster interact with the digital twin in the edge server through the adjacent road test unit and perform virtual-real interaction and synchronous update.

[0174] The same or similar reference numerals correspond to the same or similar components;

[0175] The terms used in the drawings to describe positional relationships are only used for illustrative purposes and should not be construed as limiting this patent;

[0176] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A digital twin edge collaborative quasi-static deployment method based on the local characteristics of vehicle movement, characterized in that: include: S1: Obtain a rasterized map of the area to be deployed, perform a first clustering on the grids in the rasterized map, and obtain K final first clustering clusters; S2: Construct the optimization target model of the Internet of Vehicles digital twin and obtain the optimization target of digital twin deployment; S3: Select a final first cluster as the final second cluster; S4: performing a second clustering on the grids in the final second clustering cluster to obtain a plurality of final third clustering clusters; S5: Generate a server allocation plan corresponding to each final third cluster using simulated annealing and particle swarm optimization algorithms according to the digital twin deployment optimization goal; S6: Select another final first cluster as the final second cluster; repeat steps S4 to S5 until all final first clusters are selected; S7: Integrate all server allocation plans to obtain a final server allocation plan.

2. According to claim 1, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics is characterized by: The first clustering includes: S101: Obtain a rasterized map and use it as a cluster to form a cluster set; S102: Selecting a cluster with the largest diameter in the cluster set as the second cluster; S103: Calculate the average dissimilarity between each grid in the second cluster and other grids in the second cluster as the first average dissimilarity; and sort the first average dissimilarity to obtain the grid with the largest first average dissimilarity as the new first grid; S104: Calculate the dissimilarity between each grid in the second cluster and the first grid as a second dissimilarity; S105: comparing the first average dissimilarity and the second dissimilarity of each grid in the second cluster; if the first average dissimilarity is greater than or equal to the second dissimilarity, adding the grid to the fourth cluster; if the first average dissimilarity is less than the second dissimilarity, adding the grid to the third cluster; S106: replacing the second cluster in the cluster set with the third cluster, and adding the fourth cluster as a new first cluster to the cluster set; S107: Establish two empty clusters as a new third cluster and a new fourth cluster respectively; repeat steps S102 to S106 until the number of clusters in the cluster set is K, and take all clusters in the cluster set as the final first cluster.

3. According to claim 2, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics is characterized by: The calculation formula of the diameter of the cluster is as follows: DIS(i,j)=ε1D nom (i,j)+ε2TR mom (i,j) ε1 and ε2 represent weight factors, ε1+ε2=1, D nom (i,j) represents the geographical distance from grid i to grid j, TR mom (i, j) represents the number of switching digital twins required for the vehicle to move between grid i and grid j, and i and j represent serial numbers.

4. According to claim 2, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics is characterized in that: The dissimilarity is the Euclidean distance between two grids.

5. According to claim 1, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics is characterized by: The second clustering includes: S301: Select grids in the final first cluster to construct a grid sparse graph to form a grid sparse graph matrix; wherein the nodes of the sparse graph represent grids; and the edges of the sparse graph represent the traffic intensity distance between grids; S302: Inputting the grid sparse graph matrix and the corresponding grid attributes into a deep feature model to obtain grid deep features; S303: soft clustering the grid deep features to obtain a plurality of final third clusters.

6. According to claim 5, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics is characterized in that: The deep feature model includes: a self-loop layer, a linear layer, a first GCN unit, and a second GCN unit; The grid sparse graph matrix is ​​input into the input end of the self-loop layer, the grid attribute is input into the input end of the first GCN unit; the output end of the second GCN unit outputs the classification result; The output end of the self-loop layer is connected to the input end of the linear layer, the output end of the linear layer is connected to the input end of the first GCN unit and the input end of the second GCN unit, and the output end of the first GCN unit is connected to the input end of the second GCN unit.

7. According to claim 6, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics is characterized by: The first GCN unit includes a first hidden layer, a first fully connected layer, and a first activation layer connected in sequence; The grid attributes and the output end of the linear layer are input to the input end of the first hidden layer, and the output end of the first activation layer is connected to the input end of the second GCN unit.

8. According to claim 7, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics is characterized in that: The second GCN unit includes a second hidden layer, a second fully connected layer, and a second activation layer connected in sequence; The output end of the first activation layer and the output end of the linear layer are connected to the input end of the second hidden layer, and the second activation layer outputs the classification result.

9. According to claim 1, a digital twin edge collaborative quasi-static deployment method based on vehicle movement locality characteristics is characterized by: The digital twin deployment optimization objectives are as follows: M is the unit deployment benefit, is the coefficient that balances the load balancing LO(A, L) and the virtual-real interaction delay DE(A, L), ρ represents the cost of a single switch, and μ is the cost of a single deployment; a i,k =1 means that the i-th grid is assigned to the k-th final third cluster, i, k, q represent the sequence number, l k,q Indicates that the kth final third cluster is assigned to the qth server, Q is the total number of servers, K is the total number of final third clusters, N is the total number of grids, and w i (t) represents the load of the i-th grid from t-1 to t, b k,q represents the bandwidth resource allocated by the qth server to the kth final third cluster, B q represents the total bandwidth resource of the qth server, F q represents the total computing power resources of the qth server, f i represents the computing power resources required for the i-th grid, and A and L represent the obtained deployment utility optimization solution.

10. A digital twin edge collaborative quasi-static deployment system based on vehicle movement locality characteristics, applied to the deployment method according to any one of claims 1 to 9, characterized in that: include: The first clustering module: obtains a rasterized map of the area to be deployed, performs a first clustering on the grids in the rasterized map, and obtains K final first clustering clusters; Model building module: builds the optimization target model of the digital twin of the Internet of Vehicles and obtains the optimization target of the digital twin deployment; Cluster selection module: select a final first cluster as the final second cluster; A second clustering module: performing a second clustering on the grids in the final second clustering cluster to obtain a plurality of final third clustering clusters; Allocation plan generation module: according to the digital twin deployment optimization goal, using simulated annealing and particle swarm optimization algorithm, generate a server allocation plan corresponding to each final third cluster; The third clustering module: select another final first cluster as the final second cluster; Return to the second clustering module until all final first clustering clusters are selected; Allocation plan integration module: integrates all server allocation plans to obtain the final server allocation plan.

Images