CN113824641B - Internet of vehicles routing method, system, equipment and storage medium - Google Patents

Internet of vehicles routing method, system, equipment and storage medium Download PDF

Info

Publication number
CN113824641B
CN113824641B CN202111192874.8A CN202111192874A CN113824641B CN 113824641 B CN113824641 B CN 113824641B CN 202111192874 A CN202111192874 A CN 202111192874A CN 113824641 B CN113824641 B CN 113824641B
Authority
CN
China
Prior art keywords
grid
vehicle
weight
routing
grids
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.)
Active
Application number
CN202111192874.8A
Other languages
Chinese (zh)
Other versions
CN113824641A (en
Inventor
刘冰艺
张浩杰
盛扬
熊盛武
陈新海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Research Institute Of Wuhan University Of Technology
Wuhan University of Technology WUT
China Merchants Testing Vehicle Technology Research Institute Co Ltd
Original Assignee
Chongqing Research Institute Of Wuhan University Of Technology
Wuhan University of Technology WUT
China Merchants Testing Vehicle Technology Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Research Institute Of Wuhan University Of Technology, Wuhan University of Technology WUT, China Merchants Testing Vehicle Technology Research Institute Co Ltd filed Critical Chongqing Research Institute Of Wuhan University Of Technology
Priority to CN202111192874.8A priority Critical patent/CN113824641B/en
Publication of CN113824641A publication Critical patent/CN113824641A/en
Application granted granted Critical
Publication of CN113824641B publication Critical patent/CN113824641B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H04W40/20—Communication route or path selection, e.g. power-based or shortest path routing based on geographic position or location
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/142—Network analysis or design using statistical or mathematical methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H04L45/126—Shortest path evaluation minimising geographical or physical path length
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • H04W4/46—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H04W40/22—Communication route or path selection, e.g. power-based or shortest path routing using selective relaying for reaching a BTS [Base Transceiver Station] or an access point

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Mathematical Optimization (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Algebra (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to a method, a system, equipment and a storage medium for routing Internet of vehicles, wherein the method comprises the steps of dividing a target area into a plurality of grids; predicting the vehicle density in the grid by using a pre-established vehicle density prediction model to obtain grid vehicle density parameters; calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by utilizing the grid vehicle density parameters, and forming a grid weight map by the grid weight and the grid edge weight of each grid; when a request of sending a data packet to a target vehicle by a current vehicle in the target area is received, determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the grid weight graph; and carrying out routing forwarding on the data packet based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to a target vehicle. The application can realize simple and efficient internet of vehicles data packet transmission.

Description

Internet of vehicles routing method, system, equipment and storage medium
Technical Field
The application relates to the technical field of internet of vehicles, in particular to an internet of vehicles routing method, an internet of vehicles routing system, internet of vehicles routing equipment and a storage medium.
Background
Among existing internet of vehicles routing technologies, VANET is receiving increasing attention for ITS potential role in Intelligent Transportation Systems (ITS). In VANET, each vehicle on a road may share a considerable amount of information such as traffic conditions, advertising news, road safety, etc. The broad nature of traffic information and efficient routing protocols are important for VANET because the information must reliably reach the destination node in a very short time. Because of the characteristics of large wireless channel loss, high mobility, complex road conditions and the like of the VANET, the design of the routing protocol faces considerable challenges.
The existing routing protocol scheme also uses the position information to guide the routing, but because the road condition is complex in the urban scene, the communication link is frequently lost and established, the position information can not reflect the communication state between vehicles, and the position prediction of each vehicle on the road is a time-consuming work, a large amount of time is required to carry out complex calculation to cover a large-area global routing by using the position information, and the efficiency is low.
Disclosure of Invention
In view of the above, the present application provides a method, a system, a device and a storage medium for internet of vehicles, which are used for solving the technical problem of low internet of vehicles routing efficiency.
To solve the above problem, in a first aspect, the present application provides a method for routing internet of vehicles, the method comprising:
dividing a target area into a plurality of grids;
predicting the vehicle density in the grid by using a pre-established vehicle density prediction model to obtain grid vehicle density parameters;
calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by utilizing the grid vehicle density parameters, and forming a grid weight map by the grid weight and the grid edge weight of each grid;
when a request of sending a data packet to a target vehicle by a current vehicle in the target area is received, determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the grid weight graph;
and carrying out routing forwarding on the data packet based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to a target vehicle.
Optionally, the vehicle density prediction model includes a pre-trained two-dimensional convolutional neural network model and a long-term memory artificial neural network model, and the predicting the vehicle density in the grid by using the pre-established vehicle density prediction model to obtain a grid vehicle density parameter includes:
taking the gray value in the image corresponding to the target area as a vehicle density characteristic, taking the gray value and the RGB channel value in the image corresponding to the target area as the input of the two-dimensional convolutional neural network, and obtaining a vehicle density space characteristic parameter of the grid through the convolutional processing of the two-dimensional convolutional neural network;
and extracting the vehicle density time sequence characteristic parameters of the grid by using the long-short-term memory artificial neural network model.
Optionally, calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by using the grid vehicle density parameter, and forming a grid weight map by the grid weight and the grid edge weight of each grid, including:
the grid weight map is stored in a vehicle of the target area, and the grid weight map comprises the weight omega of grids and the adjacent edge weight tau among grids;
computing connectivity between gridsMetrics for representing packet transfer connectivity between mesh i and mesh j:
wherein ,ui Representing vehicles located within grid i; r is R 2 Representing the communication transmission range of the vehicle, and measuring the communication transmission range by radius; s (u) i I j) expressed in terms of vehicle u i Is taken as a center, and has a radius R 2 The coverage area of the communication circle and the neighbor grid j; delta is a preset first control factor;
calculating the weight omega (i) of the grid i:
wherein N represents the number of meshes adjacent to the mesh i; and />Grid vehicle density parameters predicted for the vehicle density prediction model; gamma is a preset second control factor; q represents a set of grids, E represents a set of edges between adjacent grids;
calculating adjacent edge weights tau (< i, j >) of the grid:
wherein S (i, j) represents a historical communication success rate between grid i and grid j;
defining the communication route eta of all grids:
η＝〈i,j,k,...,y,z〉
calculating a communication routing weight W (eta) of the grid:
where |η| represents the length of the communication route η; grid n is the next hop route for grid m; α and β are preset weight coefficients satisfying α+β=1.
Optionally, the determining, according to the grid weight map, a minimum grid weight routing path between the current vehicle and the target vehicle includes:
and calculating to obtain the minimum grid weight routing path between the current vehicle and the target vehicle by using a Di Jie Style algorithm.
Optionally, the routing forwarding of the data packet based on the minimum grid weight routing path includes:
when the routing forwarding of the data packet is started based on the minimum grid weight routing path, adding the one-hop routing neighbor vehicle set and the two-hop routing neighbor vehicle set of the current vehicle into a preset candidate vehicle set, selecting a relay vehicle from the preset candidate vehicle set by using a greedy algorithm, and performing the routing forwarding of the inter-grid data packet by using the relay vehicle.
Optionally, the method further comprises:
and screening out core vehicles of which the number of neighbor vehicles in the preset candidate vehicle set is larger than a preset threshold value, and selecting a relay vehicle from the core vehicles.
Optionally, the method further comprises:
and taking the vehicle closest to the target vehicle in the core vehicles as an optimal relay vehicle.
In a second aspect, the present application provides an internet of vehicles routing system, the system comprising:
the dividing module is used for dividing the target area into a plurality of grids;
the prediction module is used for predicting the vehicle density in the grid by utilizing a pre-established vehicle density prediction model to obtain grid vehicle density parameters;
the calculation module is used for calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by utilizing the grid vehicle density parameters, and a grid weight map is formed by the grid weight and the grid edge weight of each grid;
the determining module is used for determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the grid weight graph when receiving a request of the current vehicle in the target area for sending a data packet to the target vehicle;
and the routing module is used for carrying out routing forwarding on the data packet based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to the target vehicle.
In a third aspect, the present application provides a computer device, which adopts the following technical scheme:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the internet of vehicles routing method when the computer program is executed.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer readable storage medium storing a computer program which when executed by a processor implements the steps of the internet of vehicles routing method.
The beneficial effects of adopting the embodiment are as follows: predicting the vehicle density in grids divided by the target area by using a pre-established vehicle density prediction model to obtain grid vehicle density parameters, and calculating the communication routing weight of each grid; determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the communication routing weight of each grid; and carrying out routing forwarding on the data packet based on the minimum grid weight routing path. Because the data packet transmission grids can be divided by combining the vehicle density prediction module, data packet routing is carried out among the grids, and the position information of each vehicle in the target area is not required to be calculated, so that simple and efficient internet-of-vehicles data packet transmission is realized.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for Internet of vehicles routing according to the present application;
FIG. 2 is a schematic block diagram of one embodiment of a vehicle networking routing system provided by the present application;
FIG. 3 is a functional block diagram of an embodiment of a computer device according to the present application.
Detailed Description
The following detailed description of preferred embodiments of the application is made in connection with the accompanying drawings, which form a part hereof, and together with the description of the embodiments of the application, are used to explain the principles of the application and are not intended to limit the scope of the application.
In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The application provides a method, a system, equipment and a storage medium for routing internet of vehicles, which are respectively described in detail below.
Referring to fig. 1, a method flowchart of an embodiment of a method for routing internet of vehicles provided by the present application, the method for routing internet of vehicles includes the following steps:
s101, dividing a target area into a plurality of grids; for example, a target area of 100 x 100 may be divided into several grids of 10 x 10;
s102, predicting the vehicle density in the grid by using a pre-established vehicle density prediction model to obtain grid vehicle density parameters;
s103, calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by utilizing the grid vehicle density parameters, and forming a grid weight map by the grid weight and the grid edge weight of each grid;
s104, when a request of sending a data packet to a target vehicle by a current vehicle in the target area is received, determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the grid weight graph;
and S105, carrying out routing forwarding on the data packet based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to a target vehicle.
In the embodiment, a pre-established vehicle density prediction model is utilized to predict the vehicle density in grids divided by a target area, so as to obtain grid vehicle density parameters, and the communication routing weight of each grid is calculated; determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the communication routing weight of each grid; and carrying out routing forwarding on the data packet based on the minimum grid weight routing path. Because the data packet transmission grids can be divided by combining the vehicle density prediction module, data packet routing is carried out among the grids, and the position information of each vehicle in the target area is not required to be calculated, so that simple and efficient internet-of-vehicles data packet transmission is realized.
Specifically, in one embodiment, the vehicle density prediction model includes a pre-trained two-dimensional convolutional neural network model and a long-term memory artificial neural network model, and step S102 includes:
taking the gray value in the image corresponding to the target area as a vehicle density characteristic, taking the gray value and the RGB channel value in the image corresponding to the target area as the input of the two-dimensional convolutional neural network, and obtaining a vehicle density space characteristic parameter of the grid through the convolutional processing of the two-dimensional convolutional neural network;
and extracting the vehicle density time sequence characteristic parameters of the grid by using the long-short-term memory artificial neural network model.
The vehicle density prediction module is constructed according to the change trend of the vehicle density and comprises a spatial feature extraction module based on a two-dimensional convolutional neural network (2D-CNN) and a time-varying feature extraction module based on a long-short-term memory artificial neural network (LSTM). The 2D-CNN may extract two-dimensional data features similar to pixels of an image, define a target area as an image by mapping, treat the vehicle density of the target area as a gray value, and treat the gray value of the pixels and the RGB channel value as input data of a convolutional neural network. According to the first law of the tobutler geography, the density of vehicles in a particular region is related to the density of vehicles in the vicinity of that region. Thus, for region a, at time t, the vehicle density characteristics of region aConsisting of the vehicle density characteristics of region a and its neighbors. Vehicle Density feature->Is input into an s-layer convolutional neural network, the output of which is +.>Data defining the layers of the convolutional network are converted into:
where x represents the convolution operation, f () represents the activation function, ω s and bs Is a set of parameters for the convolutional layer. Obtaining the characteristic vector at the time t through convolution operationFinally, the feature vector dimension reduction is achieved through the full connection layer:
wherein ,Wfc and bfc Is the learning parameter of the full-connection layer,the vehicle density data of the region a is a space feature vector parameter obtained by convolution processing, namely a vehicle density space feature parameter.
Further, the vehicle density prediction can be regarded as a time series problem, wherein the time-varying feature extraction module is very suitable for solving by using LSTM. LSTM has four important concepts, input gate, forget gate, output gate and memory cell. Memory cell C t The historical sequence before the current time t is analyzed and the sequence correlation is learned. According to the output h of the last time as the hidden state t-1 Input x at the current time t Forgetting door f t Discard the data from the previous cell C t-1 Is a part of the information of the (b). Output gate i t It will determine how much information to retain as the next time memory cell C t Is input to the computer. Output door o t Control memory cell C t Is provided.
i t ＝σ(W i x i +U i h i-1 +b i ) (1)
f t ＝σ(W f x i +U f h i-1 +b f ) (2)
o t ＝σ(W o x i +U o h i-1 +b o ) (3)
θ t ＝tanh(W g x i +U g h i-1 +b g ) (4)
C t ＝f t oC t-1 +i t oθ t (5)
h t ＝o t otanh(C t ) (6)
Formulas (1) to (3) define an input gate, a forget gate and an output gate, respectively. Equation (4) calculates a new candidate vector that cooperates with the input gate to equation (5) to update the state of the memory cell. The old memory cell state in equation (5) is multiplied by the forgetting gate and the new candidate vector is added to obtain the memory cell state at the current time. Equation (6) defines the hidden state h obtained by multiplying the output gate by the memory cell state t . After the time sequence data is input into the LSTM, the hidden state h is output under each time sequence t The final output result h is obtained by the final time sequence data end The output results include time-dependent characteristics of the time series data, that is, as a vehicle density time series characteristic parameter.
Further, in an alternative embodiment, a grid weight map G of the target area is constructed by using the vehicle density prediction result obtained in the above step, where the grid weight map G is stored in a vehicle in the target area, and the weight terms are represented in the form of four tuples (Q, E, τ, ω), where:
q= { i, j, k, m, } represents a set of meshes in the target region.
E= { (i, j), (j, k), (k, m) } represents a set of edges between adjacent meshes.
Omega Q- (0, M) represents the weight function of the vertex in the weight graph, the larger the weight of the vertex is, the more favorable the grid represented by the vertex is for transmitting the data packet, and M is the maximum value interval of the weight.
And τ.E.fwdarw.0, M represents the weight of the adjacent edges between the grids.
Defining connectivity between gridsA metric representing packet transfer connectivity between mesh i and mesh j:
in the formula ,ui Representing vehicles located within grid i; r is R 2 Representing the communication transmission range of the vehicle, and measuring the communication transmission range by radius; s (u) i I j) expressed in terms of vehicle u i Is taken as a center, and has a radius R 2 The coverage area of the communication circle and the neighbor grid j, and the size of the coverage area is used for measuring the connectivity of the neighbor grid; delta is a control factor that gives a high probability of communication between adjacent cells occurring in the connected region.
Define the weights ω (i) of grid i in grid weight map G:
wherein N represents the number of grids adjacent to grid i; and />Representing the prediction results obtained by the vehicle density prediction module, namely vehicle density space characteristic parameters and vehicle density time sequence characteristic parameters; gamma is a control factor. The vertex weights of grid i are related by the vehicle density of grid i and the vehicle density predictions of neighboring grids adjacent to grid i. When data packets are transmitted within the mesh, the dense mesh of vehicles has better network connectivity. Furthermore, in the same grid, the communication taking place in the connection area is significantly more than in the other areas. Thus, the grid weights take into account the vehicle density in the grid and connection area.
Defining adjacent edge weights τ (< i, j >):
wherein S (i, j) represents the stability of the communication link between grid i and grid j, characterized by the historical communication success rate of both grids; γ is a control factor that relates the adjacent edge weight τ (< i, j >) e (0, m >) between grid i and grid j to the vehicle density predictions for both grids relative to each other and to their communication link stability.
Defining a communication route eta:
η＝<i,j,k,...,y,z>
where < i, j >, < j, k >, < y, z >. E.
Defining a weight W (η) of a communication route:
where |η| represents the length of the route η; grid n is the next hop route for grid m; α and β are weight coefficients satisfying α+β=1.
After a grid weight map of the whole network topology is obtained, before a current vehicle sends a data packet, a minimum grid weight routing path of a grid where a target vehicle is located is obtained by inquiring the grid weight map and utilizing a Dijiestra algorithm, and routing forwarding of the data packet is carried out based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to the target vehicle.
When the routing forwarding of the data packet is started based on the minimum grid weight routing path, adding the one-hop routing neighbor vehicle set and the two-hop routing neighbor vehicle set of the current vehicle into a preset candidate vehicle set, selecting a relay vehicle from the preset candidate vehicle set by using a greedy algorithm, and performing the routing forwarding of the inter-grid data packet by using the relay vehicle. Optionally, screening out core vehicles with the number of neighbor vehicles in the preset candidate vehicle set being greater than a preset threshold, and selecting a relay vehicle from the core vehicles. Further, a vehicle closest to the target vehicle among the core vehicles may also be regarded as an optimal relay vehicle.
In this embodiment, each vehicle may obtain information of its neighboring vehicles to maintain the one-hop and two-hop routing neighbor vehicle sets of the current vehicle by periodically exchanging beacons with the neighboring vehicles. To prevent dead loops, each packet has a TTL field. After each unit time, the TTL is reduced by 1. If TTL >0, send the message according to the design tactics. If TTL times out, the message is discarded. In order to improve the packet transmission success rate and the packet transmission efficiency per hop, an optimal relay vehicle is selected. In this embodiment, the vehicle is allowed to save the data packet when it cannot find the appropriate neighbor to transmit the message. Although a vehicle carrying a data packet may improve the transmission success rate, in the case of a low vehicle density, the transmission delay may be too long due to difficulty in finding a relay node. Therefore, in the selection of the optimal relay vehicle, a vehicle having a large number of neighbors is selected as the core vehicle, and a vehicle closest to the target vehicle is preferentially selected from among the core vehicles as the relay vehicle.
The present embodiment uses CNN and LSTM to build a vehicle density prediction model, where CNN and LSTM are used to extract spatial and time-dependent features, respectively. In particular, by analysis of urban rail data, we add the time period law of the rail data to the model in the form of embedded vectors. In combination with the prediction result, the embodiment provides a path weight evaluation scheme taking the vehicle density, the link quality and the path length into consideration, and weight evaluation is performed on each path. The optimal routing path is stored in the data packet to guide routing, so that communication overhead required by data packet transmission is effectively reduced.
Further, in order to better describe the present application, the prediction performance of the vehicle density prediction module of the present embodiment is evaluated using a real city vehicle dataset, and the trajectory dataset used in the present embodiment is derived from the GAIA open dataset. The acquisition interval of the track points is 2-4s. The track points are bound with the road, so that the data is ensured to correspond to the actual road information. The information in the report includes ID, latitude/longitude, time stamp, speed of movement and status. And carrying out statistical analysis on the data in the range of 5km multiplied by 5km of the target area. The size of each grid is 1km×1km, which is related to the accuracy of the predictions and the communication range of the vehicle. The two parameters of average absolute percentage error and average root mean square error are used as the measurement standard of model prediction performance, and the evaluation result of the spatial feature extraction module is as follows:
the vehicle density was predicted using the usual MLP and compared to LSTM. Through experimental comparison, the LSTM has a better processing effect on time series data than that of the MLP.
By embedding additional information on the LSTM, the experimental results are superior to LSTM alone. The result shows that the periodic law of mining vehicle density data can be effectively applied to vehicle density prediction.
And (3) evaluating a time-varying feature extraction module of the vehicle density prediction by using the data set in the steps, wherein the evaluation result is as follows:
the combination of the spatio-temporal features of the CNN and LSTM mined data resulted in better experimental results than LSTM mining alone. The results show that the spatial characteristics of the data are of great significance to the prediction of vehicle density.
The best experimental result is obtained by combining the CNN, the LSTM and the embedded vector, which shows that the vehicle density prediction model provided by the embodiment has better prediction results than other combination models.
In this embodiment, an open-source vehicle network simulator veins is selected as a simulation platform, which combines OMNET++ network simulation based on discrete events with a vehicle movement simulator SUMO. The simulation area is set to 5000m×5000m, the simulation time is set to 400s, the beacon is periodically transmitted for 1s, the data packet generation speed is 10 packets/s, the communication range of the vehicle is 500m, and the starting vehicle and the destination of the data packet are random. The starting position of the vehicle on the map is based on the actual vehicle distribution at a particular moment in time. The mesh size is set to 1000m by 1000m. The vehicle operation data set in the steps is imported into the SUMO in combination with the map information to simulate the continuous movement of the vehicle on the road of the real map. Before the simulation starts, a grid weight graph G in an initial state is constructed by using the prediction result of the vehicle density prediction module in the steps, and the grid weight graph G is stored and cloud for vehicle calling. Weights ω (i) of grid i:
adjacent edge weights τ (< i, j >) for grid i and grid j:
weight W (η) of communication route:
and (3) performing simulation operation, namely randomly selecting a vehicle as a transmitting vehicle and a target vehicle, inquiring a grid weight graph by the transmitting vehicle, and obtaining the minimum grid weight route eta of the grid where the target vehicle is positioned by using a Dijiestra algorithm.
And in the inter-grid data packet sending stage, each vehicle can obtain the information of the adjacent vehicles by periodically exchanging beacons with the adjacent vehicles so as to maintain the one-hop neighbor vehicle set and the two-hop neighbor vehicle set of the current vehicle. The current vehicle screens out candidate relay vehicles in the grid according to the candidate relay vehicle selection process, and then selects a core relay node according to the optimal relay vehicle selection process. After each unit time, the TTL is reduced by 1. If TTL >0, send the message according to the design tactics. If TTL times out, the message is discarded. In this embodiment, 3 indexes are used to measure the transmission performance of the data packet of the proposed routing protocol, where the data packet is: (1) Packet transmission success rate, which is the ratio of successfully received packets to the total packets generated. (2) The average transmission delay, which is the average time interval from the generation of a packet to the successful arrival at the destination. (3) Throughput, which is the number of messages successfully sent per unit time.
According to the method, the data packet transmission grids are divided by combining the vehicle networking density prediction module at the macroscopic routing level, core vehicles are selected from the grids to serve as relay nodes at the inter-grid routing level, and efficient and reliable vehicle networking data packet transmission is achieved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
The embodiment also provides a vehicle networking routing system, which corresponds to the vehicle networking routing method in the embodiment one by one. As shown in fig. 2, the internet of vehicles routing system includes a dividing module 201, a predicting module 202, a calculating module 203, a determining module 204, and a routing module 205. The functional modules are described in detail as follows:
a dividing module 201, configured to divide a target area into a plurality of grids;
the prediction module 202 is configured to predict a vehicle density in the grid by using a pre-established vehicle density prediction model, so as to obtain a grid vehicle density parameter;
the calculating module 203 is configured to calculate a grid weight and a grid edge weight of each grid according to a preset weight calculation rule by using the grid vehicle density parameter, and form a grid weight map from the grid weight and the grid edge weight of each grid;
a determining module 204, configured to determine, when a request that a current vehicle sends a data packet to a target vehicle in the target area is received, a minimum mesh weight routing path between the current vehicle and the target vehicle according to the mesh weight map;
a routing module 205, configured to route forwarding of the data packet based on the minimum mesh weight routing path, so as to forward the data packet from the current vehicle to the target vehicle.
The specific limitation of each module of the internet of vehicles routing system can be referred to the limitation of the internet of vehicles routing method hereinabove, and will not be described herein. The modules in the internet of vehicles routing system can be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Referring to fig. 3, the present embodiment further provides a computer device, which may be a mobile terminal, a desktop computer, a notebook computer, a palm computer, a server, or other computing devices. The computer device includes a processor 10, a memory 20, and a display 30. Fig. 3 shows only some of the components of the computer device, but it should be understood that not all of the illustrated components are required to be implemented, and more or fewer components may be implemented instead.
The memory 20 may in some embodiments be an internal storage unit of a computer device, such as a hard disk or memory of a computer device. The memory 20 may also be an external storage device of the computer device in other embodiments, such as a plug-in hard disk provided on the computer device, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. Further, the memory 20 may also include both internal storage units and external storage devices of the computer device. The memory 20 is used for storing application software installed on the computer device and various types of data, such as program codes for installing the computer device. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 20 has stored thereon a vehicle networking routing computer program 40.
The processor 10 may in some embodiments be a central processing unit (Central Processing Unit, CPU), microprocessor or other data processing chip for executing program code or processing data stored in the memory 20, for example, for performing internet of vehicles routing methods and the like.
The display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like in some embodiments. The display 30 is for displaying information at the computer device and for displaying a visual user interface. The components 10-30 of the computer device communicate with each other via a system bus.
In one embodiment, the following steps are implemented when the processor 10 executes the internet of vehicles routing computer program 40 in the memory 20:
dividing a target area into a plurality of grids;
predicting the vehicle density in the grid by using a pre-established vehicle density prediction model to obtain grid vehicle density parameters;
calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by utilizing the grid vehicle density parameters, and forming a grid weight map by the grid weight and the grid edge weight of each grid;
when a request of sending a data packet to a target vehicle by a current vehicle in the target area is received, determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the grid weight graph;
and carrying out routing forwarding on the data packet based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to a target vehicle.
The present embodiment also provides a computer-readable storage medium having stored thereon a vehicle networking routing computer program which, when executed by a processor, performs the steps of:
dividing a target area into a plurality of grids;
predicting the vehicle density in the grid by using a pre-established vehicle density prediction model to obtain grid vehicle density parameters;
calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by utilizing the grid vehicle density parameters, and forming a grid weight map by the grid weight and the grid edge weight of each grid;
when a request of sending a data packet to a target vehicle by a current vehicle in the target area is received, determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the grid weight graph;
and carrying out routing forwarding on the data packet based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to a target vehicle.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above.
Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The present application is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present application are intended to be included in the scope of the present application.

Claims (9)

1. A method for internet of vehicles routing, the method comprising:
dividing a target area into a plurality of grids;
predicting the vehicle density in the grid by using a pre-established vehicle density prediction model to obtain grid vehicle density parameters;
calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by utilizing the grid vehicle density parameters, and forming a grid weight map by the grid weight and the grid edge weight of each grid;
when a request of sending a data packet to a target vehicle by a current vehicle in the target area is received, determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the grid weight graph;
routing forwarding of the data packet is performed based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to a target vehicle;
the method for calculating the grid weight and the grid edge weight of each grid by using the grid vehicle density parameters according to a preset weight calculation rule comprises the steps of:
the grid weight map is stored in a vehicle of the target area, and the grid weight map comprises the weight omega of grids and the adjacent edge weight tau among grids;
computing connectivity between gridsA metric representing packet transfer connectivity between mesh i and mesh j:
wherein ,representing vehicles located within grid i;R 2 representing the communication transmission range of the vehicle, and measuring the communication transmission range by radius; />Expressed in terms of vehicle->Is centered and has a radius ofR 2 The coverage area of the communication circle and the neighbor grid j; />Is a preset first control factor;
calculating the weights of grid i：
Wherein N represents the number of meshes adjacent to the mesh i; and />Grid vehicle density parameters predicted for the vehicle density prediction model; />Is a preset second control factor; q represents a set of grids, E represents a set of edges between adjacent grids;
computing adjacent edge weights of grids ：
wherein ,representing a historical communication success rate between grid i and grid j;
defining communication routes for all grids：
Computing communication routing weights for grids：
wherein ,representing communication route->Is a length of (2); grid->Is grid->Is the next hop route of (a); /> and />Is a preset weight coefficient, satisfies +.> 。
2. The internet of vehicles routing method according to claim 1, wherein the vehicle density prediction model includes a pre-trained two-dimensional convolutional neural network model and a long-term memory artificial neural network model, the predicting the vehicle density in the grid by using the pre-established vehicle density prediction model to obtain a grid vehicle density parameter, and the method includes:
taking the gray value in the image corresponding to the target area as a vehicle density characteristic, taking the gray value and the RGB channel value in the image corresponding to the target area as the input of the two-dimensional convolutional neural network, and obtaining a vehicle density space characteristic parameter of the grid through the convolutional processing of the two-dimensional convolutional neural network;
and extracting the vehicle density time sequence characteristic parameters of the grid by using the long-short-term memory artificial neural network model.
3. The internet of vehicles routing method according to claim 1 or 2, wherein the determining a minimum mesh weight routing path between the current vehicle and a target vehicle according to the mesh weight map comprises:
and calculating to obtain the minimum grid weight routing path between the current vehicle and the target vehicle by using a Di Jie Style algorithm.
4. The internet of vehicles routing method according to claim 1 or 2, wherein said routing forwarding of the data packet based on the minimum mesh weight routing path comprises:
when the routing forwarding of the data packet is started based on the minimum grid weight routing path, adding the one-hop routing neighbor vehicle set and the two-hop routing neighbor vehicle set of the current vehicle into a preset candidate vehicle set, selecting a relay vehicle from the preset candidate vehicle set by using a greedy algorithm, and performing the routing forwarding of the inter-grid data packet by using the relay vehicle.
5. The internet of vehicles routing method of claim 4, wherein the method further comprises:
and screening out core vehicles of which the number of neighbor vehicles in the preset candidate vehicle set is larger than a preset threshold value, and selecting a relay vehicle from the core vehicles.
6. The internet of vehicles routing method of claim 5, further comprising:
and taking the vehicle closest to the target vehicle in the core vehicles as an optimal relay vehicle.
7. An internet of vehicles routing system, the system comprising:
the dividing module is used for dividing the target area into a plurality of grids;
the prediction module is used for predicting the vehicle density in the grid by utilizing a pre-established vehicle density prediction model to obtain grid vehicle density parameters;
the calculation module is used for calculating the grid weight and the grid edge weight of each grid according to a preset weight calculation rule by utilizing the grid vehicle density parameters, and a grid weight map is formed by the grid weight and the grid edge weight of each grid;
the determining module is used for determining a minimum grid weight routing path between the current vehicle and the target vehicle according to the grid weight graph when receiving a request of the current vehicle in the target area for sending a data packet to the target vehicle;
the routing module is used for carrying out routing forwarding on the data packet based on the minimum grid weight routing path so as to forward the data packet from the current vehicle to a target vehicle;
the method for calculating the grid weight and the grid edge weight of each grid by using the grid vehicle density parameters according to a preset weight calculation rule comprises the steps of:
the grid weight map is stored in a vehicle of the target area, and the grid weight map comprises the weight omega of grids and the adjacent edge weight tau among grids;
computing connectivity between gridsA metric representing packet transfer connectivity between mesh i and mesh j:
wherein ,representing vehicles located within grid i;R 2 representing the communication transmission range of the vehicle, and measuring the communication transmission range by radius; />Expressed in terms of vehicle->Is centered and has a radius ofR 2 The coverage area of the communication circle and the neighbor grid j; />Is a preset first control factor;
calculating the weights of grid i：
Wherein N represents the number of meshes adjacent to the mesh i; and />Grid vehicle density parameters predicted for the vehicle density prediction model; />Is a preset second control factor; q represents a set of grids, E represents a set of edges between adjacent grids;
computing adjacent edge weights of grids ：
wherein ,representation ofHistorical communication success rate between grid i and grid j;
defining communication routes for all grids：
Computing communication routing weights for grids：
wherein ,representing communication route->Is a length of (2); grid->Is grid->Is the next hop route of (a); /> and />Is a preset weight coefficient, satisfies +.> 。
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the internet of vehicles routing method according to any one of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the steps of the internet of vehicles routing method according to any one of claims 1 to 6.
CN202111192874.8A 2021-10-13 2021-10-13 Internet of vehicles routing method, system, equipment and storage medium Active CN113824641B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111192874.8A CN113824641B (en) 2021-10-13 2021-10-13 Internet of vehicles routing method, system, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111192874.8A CN113824641B (en) 2021-10-13 2021-10-13 Internet of vehicles routing method, system, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113824641A CN113824641A (en) 2021-12-21
CN113824641B true CN113824641B (en) 2023-09-22

Family

ID=78920286

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111192874.8A Active CN113824641B (en) 2021-10-13 2021-10-13 Internet of vehicles routing method, system, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113824641B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114338497B (en) * 2021-12-24 2022-10-11 中南大学 Train fleet data routing system and method based on online reinforcement learning
CN114422422B (en) * 2022-04-01 2022-07-08 广东省通信产业服务有限公司 Data transmission method, device and system based on node information

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108093458A (en) * 2017-12-22 2018-05-29 北京航空航天大学 Suitable for car networking based on cluster structured fast and stable method for routing and device
CN109640370A (en) * 2019-02-02 2019-04-16 北京邮电大学 A kind of car networking transmission method and device based on information fresh degree
CN109886509A (en) * 2019-03-29 2019-06-14 长春理工大学 A kind of mobile poly concourse nodes paths planning method, system and electronic equipment

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8504034B2 (en) * 2010-11-09 2013-08-06 Ntt Docomo, Inc. System and method for population tracking, counting, and movement estimation using mobile operational data and/or geographic information in mobile network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108093458A (en) * 2017-12-22 2018-05-29 北京航空航天大学 Suitable for car networking based on cluster structured fast and stable method for routing and device
CN109640370A (en) * 2019-02-02 2019-04-16 北京邮电大学 A kind of car networking transmission method and device based on information fresh degree
CN109886509A (en) * 2019-03-29 2019-06-14 长春理工大学 A kind of mobile poly concourse nodes paths planning method, system and electronic equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
高扬水.软件定义车联网负载均衡关键技术的研究.《中国博士学位论文全文数据库 工程科技Ⅱ辑》.2021,(第2021年第01期),第三章. *

Also Published As

Publication number Publication date
CN113824641A (en) 2021-12-21

Similar Documents

Publication Publication Date Title
Chen et al. Delay-aware grid-based geographic routing in urban VANETs: A backbone approach
CN113824641B (en) Internet of vehicles routing method, system, equipment and storage medium
Zhang et al. On geocasting over urban bus-based networks by mining trajectories
Li et al. An intersection-based QoS routing in vehicular ad hoc networks
CN101977226B (en) Novel opportunity network data transmission method
Zhang et al. CBS: Community-based bus system as routing backbone for vehicular ad hoc networks
Zhao et al. A novel prediction-based temporal graph routing algorithm for software-defined vehicular networks
CN102664805B (en) Predictive routing method for bus delay tolerant network
He et al. Cost-efficient traffic-aware data collection protocol in VANET
Lo et al. Traffic‐aware routing protocol with cooperative coverage‐oriented information collection method for VANET
Yeferny et al. MPC: A RSUs deployment strategy for VANET
CN102843301B (en) Routing method for mobile delay tolerant network based on contact predication
CN108966148A (en) Prediction technique, server and the storage medium of trip information
Abdrabou et al. Delay analysis for sparse vehicular sensor networks with reliability considerations
Medjiah et al. Sailing over data mules in delay-tolerant networks
Chancay-García et al. Optimising message broadcasting in opportunistic networks
Milojevic et al. Short paper: Distributed vehicular traffic congestion detection algorithm for urban environments
Mokhtari et al. The deployment of roadside units in vehicular networks based on the V2I connection duration
Sun et al. A novel cloudlet-dwell-time estimation method for assisting vehicular edge computing applications
de Sousa et al. DisTraC: A distributed and low-overhead protocol for traffic congestion control using vehicular networks
Naresh et al. Link prediction algorithm for efficient routing in VANETs
Saad et al. MDP-based vehicular network connectivity model for VCC management
Farsi et al. Optimal deployment of Road Side Units in urban environments
Ahmed et al. Probabilistic coverage methods in people-centric sensing
Li et al. Seer: trend-prediction-based geographic message forwarding in sparse vehicular networks

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
GR01 Patent grant
GR01 Patent grant