CN116129648A - Road network congestion key node identification method, equipment and medium - Google Patents
Road network congestion key node identification method, equipment and medium Download PDFInfo
- Publication number
- CN116129648A CN116129648A CN202310184104.1A CN202310184104A CN116129648A CN 116129648 A CN116129648 A CN 116129648A CN 202310184104 A CN202310184104 A CN 202310184104A CN 116129648 A CN116129648 A CN 116129648A
- Authority
- CN
- China
- Prior art keywords
- node
- nodes
- road network
- network
- neighbor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a method, equipment and medium for identifying road network congestion key nodes, which comprises the following steps: 1) Collecting real road network data and carrying out road network modeling: 2) Based on a neighbor node set searching method, an SIR propagation model method and the like are applied to a complex network model to incorporate a network model function; 3) Performing k-shell decomposition on the original complex road network, storing the ks layer of each node and determining neighbor node sets in three layers of the ks layer; 4) Calculating three layers of influence functions and total influence functions of each node according to traffic jam characteristics; 5) And determining the importance degree of each node under the traffic jam situation according to the ks layer and the total influence function value of each node. Compared with the prior art, the improved k-shell key node identification method combines the topological characteristic of the traffic road network and the characteristic of traffic flow, and can accurately identify the road gateway key node under the condition of traffic jam.
Description
Technical Field
The invention relates to the technical field of urban traffic planning, in particular to a method, equipment and medium for identifying road network congestion key nodes.
Background
The traffic road network comprises a plurality of traffic nodes and complicated traffic lines connected with the nodes, is the most important infrastructure of a city, has long-term existing characteristics once constructed, and the structure and the layout of the traffic road network intensively reflect the topological structure and the spatial distribution of the city. However, with the increase of travel modes and the popularization of vehicles, the occurrence of traffic jams not only directly increases the travel time and cost of residents, but also brings great economic loss to society. The method has important significance in analyzing and researching key areas and key nodes of the traffic network and researching complex characteristics of the traffic network, and is very significant in solving the problems related to traffic jam evacuation, traffic trip decision adjustment and the like.
According to the difference of the types and the directions of the statistical complex network information, the network node importance evaluation method can be divided into the following three types: the neighbor nodes and local information are considered, the feature vectors and the random jump mechanism are considered, and the node positions and the related attributes are considered. The first type of method only counts the neighborhood information of the nodes, has low computational complexity, but ignores the measurement of the nodes in the global network, so that the method is not suitable for a large-scale network. The method for considering the feature vector and the random jump mechanism originates from node identification of the web page connection network, classical algorithms comprise PageRank, leaderRank and the like, the method is used for counting node importance from the global angle, and the calculation complexity is high, but the random challenge mechanism is mainly applied to the directed structure and is not in line with other networks in reality. The method for considering the node position and the related attribute is a coarse-grained decomposition method based on a global structure. Based on the importance of nodes located in the center of the network compared to nodes located at the edges of the network, the method assigns ks values to the nodes to quickly evaluate the importance of the nodes, but does not order the importance of the nodes at the same layer.
However, to date, all methods for complex network key node improvement have the following two research blanks: firstly, the methods are not researched towards the actual road network, and meanwhile traffic jam characteristics and road network topological structures are ignored.
Under the above circumstances, development and practical application of complex network information mining in the traffic field are hindered to a certain extent, and an improved method for solving the above-mentioned problems is currently lacking.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a road network congestion key node identification method, equipment and medium, wherein a traffic network with a plurality of nodes and connected edges is constructed based on traffic network original data, neighbor nodes in a multi-layer neighborhood are determined through k-shell decomposition, influence degree evaluation indexes of the nodes are calculated, and the road network congestion key node identification is realized based on the influence degree evaluation indexes.
The aim of the invention can be achieved by the following technical scheme:
the invention provides a road network congestion key node identification method, which comprises the following steps:
acquiring traffic network original data, and acquiring a traffic network comprising a plurality of nodes and connected edges through network modeling;
performing k-shell decomposition on the traffic network to obtain neighbor nodes in the multi-layer neighborhood of each node;
and calculating an influence degree evaluation index based on the neighboring nodes in the multi-layer neighborhood aiming at each node, and acquiring the congestion key node based on the influence degree evaluation index to realize the identification of the road network congestion key node.
As a preferred technical solution, each of the nodes includes the following information: the method comprises the steps of current node degree, neighbor node information, unique identification information, a ks layer corresponding to the node and SIR simulation state value information.
As a preferred technical solution, the process of obtaining a traffic network including a plurality of nodes and edges by network modeling includes the following steps:
modeling an intersection in an actual environment as a node in the traffic network, and modeling a road in the actual environment as a connecting edge in the traffic network.
As a preferred technical solution, the determining process of the neighboring node includes the following steps:
and recursively stripping each node in the traffic network by carrying out k-shell decomposition on the traffic network, distributing each node to different ks layers, and determining neighbor nodes in the current node multi-layer neighborhood based on a preset search strategy.
As a preferable technical scheme, the preset search strategy is a breadth-first search strategy.
As a preferable technical scheme, the influence degree evaluation index of the neighbor node is calculated by adopting the following formula:
S＝∑S i
S1＝∑β
wherein S is the influence degree evaluation index of the current node, S1 is the influence degree evaluation index of the first layer neighbor node, S n Is an influence degree evaluation index of the n-layer neighbor node, wherein n is as follows>1, β is the propagation probability in SIR model, neighbor_n-1 is the n-layer neighbor node of the current node, εi is all paths from the current node to each node in neighbor_n-1, and d is the path length between nodes.
As a preferred solution, the traffic network is an undirected and unauthorized network.
As a preferred technical solution, the obtaining of the congestion key node includes the following steps:
and sequencing all the nodes according to the influence degree evaluation index of each node and the affiliated ks layer to obtain the congestion key node.
In another aspect of the present invention, there is provided an electronic apparatus including: one or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs comprise instructions for executing the road network congestion key node identification method.
In another aspect of the invention, a computer-readable storage medium is provided that includes one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing the above-described road network congestion key node identification method.
Compared with the prior art, the invention has the following advantages:
(1) The identification precision is high: the method comprises the steps of constructing a traffic network with a plurality of nodes and connected edges based on traffic network original data, determining neighbor nodes in a multi-layer neighborhood through k-shell decomposition, calculating influence degree evaluation indexes of all the nodes, and identifying road network congestion key nodes based on the influence degree evaluation indexes.
(2) The operation complexity is low: the node importance identification is determined by calculating the influence function of the node, and when the network modeling is performed, the information such as the neighbor node set of the node, the breadth-first neighbor node search algorithm and the like is packaged into the information of the node, so that the influence function of the node is calculated only by simple operation, and the operation complexity is greatly reduced.
Drawings
Fig. 1 is a flowchart of a method for identifying a road network congestion key node in embodiment 1;
FIG. 2 is a graph of probability of a degree distribution of a Manhattan road network in a double logarithmic coordinate system;
figure 3 is a graph of the average number of infected nodes per step for ten top-ranked nodes with a SIR simulation model run repeatedly 1000 times.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
As shown in fig. 1, in order to solve the problem that the road network congestion propagation factor cannot be considered in the complex road network in the existing scheme, the embodiment provides a road network congestion key node identification method, improves a k-shell algorithm in combination with traffic congestion characteristics, and designs a new important node ordering mode aiming at road network characteristics so as to accurately identify key nodes under the congested road network. The method can comprehensively analyze important traffic congestion nodes of the traffic complex road network with lower operation complexity and higher calculation accuracy, and deeply dig key nodes in the network, and has strong practicability.
The method comprises the following steps:
step S1, collecting real complex road network data, wherein the real complex road network data comprises nodes and connecting side information of a road network, in the invention, an intersection is modeled as nodes in a network model, and a road connecting the intersection is modeled as sides among the nodes.
Wherein the node set is defined as:
V(G)＝{v1,v2,v3,……vn}
the edge set is defined as:
E(G)＝{e1,e2,e3,……,en}
and S2, encapsulating the node class in the complex road network, generating the road network, and incorporating the number, degree and neighbor node set of the node, the ks layer to which the node belongs, and the SIR simulation state value into the attribute of the node.
And S3, packaging the complex network model, incorporating a k-shell decomposition method into a network model function by applying an SIR propagation model method and the like to the complex network model based on a breadth-first neighbor node set searching method. And (3) carrying out k-shell decomposition on a network formed by node classes, wherein nodes are distributed to different ks layers, determining a ks value of each node, and determining all nodes neighbor_0, neighbor_1 and neighbor_2 in three-layer neighbors of each node based on a breadth-first search strategy.
Step S4, for each node i, calculating an influence function S1= sigma of a layer of neighbor nodes Neighbor_0 Beta, wherein neighbor_0 is a layer one Neighbor node of node i, beta is a propagation probability in the SIR model, and an influence function on a layer two Neighbor node
Wherein neighbor_1 is a two-layer Neighbor node of node i, beta is a propagation probability in the SIR model, and εi is all of each of nodes i to neighbor_1The path d is the path length between the nodes, and the invention sets the connecting edge between the nodes as the dimension without length, so the path length d of the two-layer neighbor node is set as 2. Influence function on three-layer neighbor node>
Wherein neighbor_2 is a three-layer Neighbor node of node i, β is a propagation probability in the SIR model, εi is all paths from node i to each node in neighbor_2, d is a path length between nodes, and the distance between the three-layer nodes is set to 3. The total influence function of one node i is the sum of the influences on three layers of neighbor nodes, and the total influence function is expressed as s=s1+s2+s3, wherein S1, S2 and S3 are the three layers of influence functions. The total influence function S is calculated for each node in the network based on the above steps.
Step S5, the importance ordering mode of the complex network nodes is as follows: and outputting the node serial numbers with large ks values, and outputting the node serial numbers with large total influence function S for the nodes with the same ks values, wherein the nodes which are output firstly are important nodes of the road network under the traffic jam background.
The implementation scheme of the road network congestion key node identification method is as follows:
step1: subject selection and dataset collection. The invention selects a commonly selected object in road network complexity research, namely New York Manhattan, in order to grasp the universality and representativeness of the test object. The Manhattan road network is regular in shape, the streets are staggered, horizontal and vertical, and the data set of the road network is conveniently obtained through a driving data open source website in New York City, wherein the road network data comprises node data and edge data, the node CSV data comprises 3 columns which are respectively node numbers (numbers), latitudes (latitudes) and longitudes (longitudes). The edge CSV data comprises two columns, namely a Source node (Source ID), a Target node (Target ID), and 4091 nodes and 9452 edges in the Manhattan road network data.
Step2: modeling road network data. On the basis of original data, the invention firstly establishes a complex undirected road network model, then establishes node classes, numbers, degrees of nodes, neighbor node sets and ks to which the nodes belongAnd the SIR simulation state value is packaged, so that the subsequent steps can be conveniently called. Then, the invention analyzes the complex network characteristics of the road network according to the topology index, and fig. 2 shows the degree distribution of the road network under a double-logarithmic coordinate system, and can find that the degree distribution of the Manhattan road network better follows the power rate, P (k is larger than or equal to x) oc x -μ Fitting with MATLAB power-of-power ratio to obtain a μ of 4.934 with 95% confidence interval [6.952,2.917 ]]This indicates that the manhattan road network is a scaleless network. The scaleless property is an important property of complex networks, and the manhattan road network has obvious scaleless property, which indicates the representative meaning of the example selected as an experimental object.
Step3: manhattan road network k-shell decomposition. The method comprises the steps of completing road network structure decomposition based on a k-shell method, and continuously recursively stripping nodes with the degree less than or equal to ks in a network, specifically, analyzing from the angle of a degree index, wherein the node with the degree of 1 is the least important node in the network, so that the node with the degree of 1 and the connecting edge thereof are deleted from the network. New nodes with the degree of 1 appear in the network after the deletion operation is performed, and then the newly appearing nodes with the degree of 1 and the connecting edges thereof are deleted. The above operation is repeated until the node with the degree of 1 is no longer newly appeared in the network. All deleted nodes at this time constitute the first layer, i.e. the ks value of the 1-shell node is equal to 1. In the remaining network, each node has a degree of at least 2. And continuing to repeat the deleting operation to obtain a second layer with the ks value equal to 2, namely the 2-shell. And so on until all nodes in the network are assigned ks values.
Step4: and calculating an influence function based on the traffic congestion characteristics. The method comprises the steps of calculating a node influence function under the traffic jam background, and counting influence functions of nodes on all nodes in a three-layer neighborhood according to definition in a technical route. Node three-layer Neighbor node sets are defined as neighbor_0, neighbor_1, neighbor_2, respectively. And adopting different processing strategies for nodes in different neighborhoods and neighbor nodes. The scoring function S1 for the neighbor node is Σ Neighbor_0 Beta is the influence function to the two-layer neighbor node
The neighbor_1 is a two-layer Neighbor node of the node i, beta is the propagation probability in the SIR model, epsilon i is all paths from the node i to each node in the neighbor_1, d is the path length between the nodes, and the connecting edge between the nodes is set to be a dimension without length, so that the path length d of the two-layer Neighbor node is set to be 2. Influence function on three-layer neighbor node>
Wherein neighbor_2 is a three-layer Neighbor node of node i, β is a propagation probability in the SIR model, εi is all paths from node i to each node in neighbor_2, d is a path length between nodes, and the distance between the three-layer nodes is set to 3. The total impact function of one node i is the sum of the impact on three layers of neighboring nodes, denoted s=s1+s2+s3.
Step5: in this example, the SIR simulation model is run repeatedly 1000 times, the average number of infected nodes in each step of each node is recorded, and the nodes 10 before the nodes are ordered are shown in fig. 3, and it can be known from the graph that the higher the ordinate value in the same step, the stronger the infectivity of the nodes, i.e. the more important the nodes. Figure 3 shows that the two most infectious nodes in SIR model are 3556 and 3226, respectively.
The invention provides a road network congestion key node identification method aiming at the problem that the road network congestion propagation factor cannot be considered in the current complex road network, combines the topological characteristic of the traffic road network and the characteristic of traffic flow, and can accurately identify the road gateway key node under the condition of traffic congestion.
Example 2
The present embodiment provides an electronic device, including: one or more processors and memory, the memory having stored therein one or more programs including instructions for performing the road network congestion key node identification method of embodiment 1.
Example 3
The present embodiment provides a computer-readable storage medium including one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing the road network congestion key node identification method described in embodiment 1.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The method for identifying the road network congestion key nodes is characterized by comprising the following steps:
acquiring traffic network original data, and acquiring a traffic network comprising a plurality of nodes and connected edges through network modeling;
performing k-shell decomposition on the traffic network to obtain neighbor nodes in the multi-layer neighborhood of each node;
and calculating an influence degree evaluation index based on the neighboring nodes in the multi-layer neighborhood aiming at each node, and acquiring the congestion key node based on the influence degree evaluation index to realize the identification of the road network congestion key node.
2. The method of claim 1, wherein each of the nodes includes the following information: the method comprises the steps of current node degree, neighbor node information, unique identification information, a ks layer corresponding to the node and SIR simulation state value information.
3. The method for identifying a congestion key node of a road network according to claim 2, wherein the step of obtaining the congestion key node comprises the steps of:
and sequencing all the nodes according to the influence degree evaluation index of each node and the affiliated ks layer to obtain the congestion key node.
4. The method for identifying a critical node of road network congestion according to claim 1, wherein the process of obtaining a traffic network comprising a plurality of nodes and edges by network modeling comprises the steps of:
modeling an intersection in an actual environment as a node in the traffic network, and modeling a road in the actual environment as a connecting edge in the traffic network.
5. The method for identifying a road network congestion key node according to claim 1, wherein the determining process of the neighbor node comprises the following steps:
and recursively stripping each node in the traffic network by carrying out k-shell decomposition on the traffic network, distributing each node to different ks layers, and determining neighbor nodes in the current node multi-layer neighborhood based on a preset search strategy.
6. The method for identifying a road network congestion key node according to claim 5, wherein the preset search strategy is a breadth-first search strategy.
7. The method for identifying road network congestion key nodes according to claim 1, wherein the influence degree evaluation index of the neighboring nodes is calculated by the following formula:
S＝∑s i
wherein S is the influence degree evaluation index of the current node, S1 is the influence degree evaluation index of the first layer neighbor node, S n Is an influence degree evaluation index of the n-layer neighbor node, wherein n is as follows>1, beta is in SIR modelNeighbor_n-1 is the n-layer neighbor node of the current node, εi is all paths from the current node to each node in neighbor_n-1, and d is the path length between nodes.
8. The method of claim 1, wherein the traffic network is an undirected and unauthorized network.
9. An electronic device, comprising: one or more processors and memory, the memory having stored therein one or more programs, the one or more programs comprising instructions for performing the road network congestion key node identification method of any of claims 1-8.
10. A computer readable storage medium comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs comprising instructions for performing the road network congestion key node identification method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310184104.1A CN116129648A (en) | 2023-02-28 | 2023-02-28 | Road network congestion key node identification method, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310184104.1A CN116129648A (en) | 2023-02-28 | 2023-02-28 | Road network congestion key node identification method, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116129648A true CN116129648A (en) | 2023-05-16 |
Family
ID=86310056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310184104.1A Pending CN116129648A (en) | 2023-02-28 | 2023-02-28 | Road network congestion key node identification method, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116129648A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116797055A (en) * | 2023-08-28 | 2023-09-22 | 日照朝力信息科技有限公司 | Urban road planning method and system based on Internet of things |
-
2023
- 2023-02-28 CN CN202310184104.1A patent/CN116129648A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116797055A (en) * | 2023-08-28 | 2023-09-22 | 日照朝力信息科技有限公司 | Urban road planning method and system based on Internet of things |
| CN116797055B (en) * | 2023-08-28 | 2023-11-07 | 日照朝力信息科技有限公司 | Urban road planning method and system based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109584553B (en) | Road section relevance missing completion method based on space-time information | |
| Liu et al. | PSO-based power-driven X-routing algorithm in semiconductor design for predictive intelligence of IoT applications | |
| CN107092984B (en) | Network function end node propagation prediction method based on cascade failure | |
| CN110543728B (en) | Urban traffic network key intersection discovery method | |
| CN112215427B (en) | Vehicle driving track reconstruction method and system under condition of bayonet data loss | |
| CN107145991B (en) | Time-varying random network dynamic path searching method considering road section correlation | |
| Sohouenou et al. | Using a random road graph model to understand road networks robustness to link failures | |
| CN105303839A (en) | Latent congested road intersection prediction method and device | |
| CN116129648A (en) | Road network congestion key node identification method, equipment and medium | |
| Wang et al. | LHNN: Lattice hypergraph neural network for VLSI congestion prediction | |
| CN116151324A (en) | RC interconnection delay prediction method based on graph neural network | |
| Grzybek et al. | Evaluation of dynamic communities in large-scale vehicular networks | |
| Fakhrmoosavi et al. | An iterative learning approach for network contraction: Path finding problem in stochastic time‐varying networks | |
| CN111008730B (en) | Crowd concentration prediction model construction method and device based on urban space structure | |
| Zhang et al. | Off-deployment traffic estimation—a traffic generative adversarial networks approach | |
| CN111953651B (en) | Urban road network cascade failure node identification method | |
| CN113284030B (en) | Urban traffic network community division method | |
| CN106408155A (en) | Reliability evaluating and preconceived fault set searching method based on related circuit set | |
| CN115086224B (en) | Shortest route implementation method and system based on Farey model | |
| Satyananda et al. | Deep learning to handle congestion in vehicle routing problem: A review | |
| Zhao et al. | Vehicle route assignment optimization for emergency evacuation in a complex network | |
| CN111914039A (en) | Road network updating method and device | |
| Yang et al. | Transmission Line Planning Based on Artificial Intelligence in Smart Cities | |
| Rampalli et al. | Redesigning infrastructure for autonomous vehicles and evaluating its impact on traffic | |
| CN112084609B (en) | Power supply partition dividing method for power industry |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |