Vehicle network data transmission system and method

Abstract

The present invention provides a vehicle-to-vehicle (IoV) data transmission system and method. The system includes vehicles, roads, edge servers located at intersections, and cloud servers. The vehicles include a data-sending vehicle, a destination vehicle, and multiple intermediate vehicles. The edge servers include a first edge server, a second edge server, and multiple intermediate edge servers. The edge servers collect beacons sent by the vehicles, obtain local traffic flow information at each intersection, establish multi-hop links based on the local traffic flow information, and upload the local traffic flow information and multi-hop links to the cloud server. The cloud server generates global traffic flow information, determines road quality, and determines a global optimal transmission path based on the global traffic flow information, a reinforcement learning algorithm, the multi-hop links, and the road quality. The edge server modifies the global optimal transmission path to obtain a target transmission path. The present invention improves the transmission speed of data packets.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a vehicle network data transmission system and method. Background Art

[0002] The increasing number of cars on urban roads poses a significant challenge to the resilience of urban transportation. Faced with massive traffic flows, such as during morning and evening rush hours, urban transportation systems must be able to make responsive decisions. For example, when a traffic jam or accident occurs somewhere in the city, the message needs to be transmitted quickly and accurately throughout the city, radiating from the incident site to other nearby roads, and advising potentially affected vehicles to change lanes. Furthermore, in real-world urban scenarios, a large number of vehicles are constantly sending data packets. Therefore, designing an efficient routing algorithm for multi-packet transmission scenarios to ensure that packets are delivered quickly and accurately to their intended destinations is crucial.

[0003] As the number of terminals continues to increase, the data generated by the traffic flow environment is also increasing. The existing technology uses cloud servers to receive global traffic flow information and complete computing tasks through cloud servers, which consumes a lot of bandwidth and brings data transmission delays, resulting in a slow speed at which data packets are sent to the destination vehicle.

[0004] Therefore, there is an urgent need to provide a vehicle network data transmission system and method to increase the speed at which data packets are sent to the destination vehicle. Summary of the Invention

[0005] In view of this, it is necessary to provide a vehicle network data transmission system and method to solve the technical problem in the existing technology that the cloud server is used to receive global traffic information and complete computing tasks, resulting in a slow speed in sending data packets to the destination vehicle.

[0006] The present invention provides a vehicle network data transmission system, comprising a plurality of vehicles, a road, a plurality of edge servers arranged at a plurality of intersections, and a cloud server. The plurality of vehicles include a data-sending vehicle, a destination vehicle, and a plurality of intermediate vehicles. The plurality of edge servers include a first edge server closest to the data-sending vehicle, a second edge server closest to the destination vehicle, and a plurality of intermediate edge servers.

[0007] The edge server is configured to collect beacons sent by the vehicles, obtain local traffic flow information at each intersection, establish a multi-hop link with adjacent edge servers adjacent to the edge server based on the local traffic flow information, and upload the local traffic flow information and the multi-hop link to the cloud server;

[0008] The cloud server is configured to generate global traffic flow information based on the local traffic flow information and determine road quality, determine a global optimal transmission path for data packets between the first edge server, the multiple intermediate edge servers, and the second edge server based on the global traffic flow information, a reinforcement learning algorithm, the multi-hop link, and the road quality, and send the global optimal transmission path to each of the edge servers;

[0009] The edge server is further configured to modify the global optimal transmission path based on the reinforcement learning algorithm to obtain a target transmission path. The data packet is sent from the data sending vehicle to the destination vehicle via the first edge server, the target transmission path, and the second edge server.

[0010] In some possible implementations, the edge server includes a vehicle location determination module, a candidate base construction module, a base determination module, and a multi-hop link establishment module;

[0011] The vehicle position determination module is used to determine the vehicle positions of multiple vehicles within the transmission range of the edge server in a preset coordinate system based on the local traffic flow information;

[0012] The candidate base construction module is used to determine multiple target vehicles traveling away from the intersection among the multiple vehicles, establish multiple groups of preliminary bases corresponding to the multiple target vehicles, and determine multiple groups of candidate bases in the multiple groups of preliminary bases based on vehicle positions and preset screening rules;

[0013] The basis determination module is used to determine the link lifetime of each group of candidate bases and use the candidate base with the longest link lifetime as the basis, wherein the vehicles in the basis are relay vehicles, and the relay vehicles include the previous hop relay vehicle and multiple relay vehicles to be selected;

[0014] The multi-hop link establishment module is used to determine the link lifespans of the multiple candidate relay vehicles and the previous-hop relay vehicle, and use the candidate relay vehicle with the longest link lifespan as the next-hop relay vehicle. When the link between the previous-hop relay vehicle and the edge server is disconnected, the next-hop relay vehicle is linked to the previous-hop relay vehicle to obtain the multi-hop link.

[0015] In some possible implementations, the vehicle position is:

[0016]

[0017]

[0018]

[0019]

[0020] Where x is the horizontal coordinate of the vehicle's position; y is the vertical coordinate of the vehicle's position; t is the time when the vehicle establishes a connection with the edge server; t0 is the time when the vehicle receives the beacon; x0 is the horizontal coordinate of the vehicle at time t0; y0 is the initial vertical coordinate of the vehicle at time t0; v is the speed of the vehicle when the connection is established with the edge server; a is the acceleration of the vehicle when the connection is established with the edge server; θ is the angle between the vehicle's moving direction and the positive axis of the horizontal coordinate of the preset coordinate system; V0 is the speed of the vehicle at time t0; ΔD is the distance between the vehicle and the edge server when the edge server sends the beacon; R is the maximum communication distance of the vehicle; X R Y is the horizontal coordinate of the edge server; R is the vertical coordinate of the edge server.

[0021] In some possible implementations, the link lifetime of the preparation base is:

[0022]

[0023]

[0024] Where MLET(P) is the link lifetime of the preparation base; min is the minimum value symbol; len is the number of vehicles in the multi-hop link; LET(P[i],P[i+1]) is the link lifetime between the i-th vehicle and the i+1-th vehicle; S i is the distance between the i-th vehicle and the edge sensor; S i+1 is the distance between the i+1th vehicle and the edge sensor; V i is the speed of the i-th vehicle; V i+1 is the speed of the i+1th vehicle; || is the absolute value operator.

[0025] In some possible implementations, the substrate determination module includes a first screening unit, a second screening unit, and a third screening unit;

[0026] The first screening unit is used to screen the multiple groups of preliminary bases based on the speeds and accelerations of the multiple target vehicles to obtain multiple groups of first candidate preliminary bases;

[0027] The second screening unit is configured to screen the plurality of first candidate preparatory bases based on the vehicle positions when the first candidate preparatory bases include two target vehicles, and to screen the plurality of first candidate preparatory bases based on a linking manner to obtain a plurality of second candidate preparatory bases when the first candidate preparatory bases include at least three target vehicles;

[0028] The third screening unit is configured to screen the plurality of groups of second candidate bases based on the number of target vehicles in each group of the second candidate bases to obtain the plurality of groups of candidate bases.

[0029] In some possible implementations, the edge server further includes a link break processing module and a multi-hop link maintenance module;

[0030] The link break processing module is used to generate a new multi-hop link when the multi-hop link is broken;

[0031] The multi-hop link maintenance module is used to determine whether the new multi-hop link can be connected to the multi-hop link, and when the new multi-hop link can be connected to the multi-hop link, connect the new multi-hop link to the multi-hop link.

[0032] In some possible implementations, the edge server further includes a multi-hop link storage module;

[0033] The multi-hop link storage module is used to determine the first relay vehicle and the last relay vehicle in the multi-hop link, and determine the effectiveness time of the multi-hop link according to the distance between the first relay vehicle and the edge server, and determine the expiration time of the multi-hop link according to the distance between the last relay vehicle and the edge server, and store the multi-hop link based on the effectiveness time, the expiration time and the life of the multi-hop link.

[0034] In some possible implementations, the road quality is:

[0035] Q=αDr ij +βPr ij

[0036]

[0037]

[0038] α+β=1

[0039] Where Q is the road quality; α is the first proportional coefficient; Dr ii is the road section r ij The number of vehicles on the road and the road section r ij length ratio; β is the second proportional coefficient; Pr ij is the ratio of relay vehicles in multiple links; Nr ij is the road section r ij The number of vehicles on board; Lr ij is the road section r ij Length; Nh ij is the road section r ij The number of relay vehicles.

[0040] In some possible implementations, the vehicle includes a data packet transmission module and a retransmission module;

[0041] The data packet transmission module is used to transmit the data packet to the edge server;

[0042] The retransmission module is configured to retransmit the data packet to the edge server with a preset number of retransmissions when the data packet transmission fails.

[0043] On the other hand, the present invention further provides a method for transmitting data in an Internet of Vehicles (IoV) network, which is applicable to the IoV IoV data transmission system described in any one of the possible implementations above. The IoV IoV data transmission method includes:

[0044] Controlling the edge server to collect beacons sent by the vehicles, obtaining local traffic flow information at each intersection, establishing a multi-hop link with adjacent edge servers adjacent to the edge server based on the local traffic flow information, and uploading the local traffic flow information and the multi-hop link to the cloud server;

[0045] controlling the cloud server to generate global traffic flow information based on the local traffic flow information and determine road quality, determining a global optimal transmission path for data packets between the first edge server, the multiple intermediate edge servers, and the second edge server based on the global traffic flow information, a reinforcement learning algorithm, the multi-hop link, and the road quality, and sending the global optimal transmission path to each of the edge servers;

[0046] The edge server is controlled to modify the global optimal transmission path based on the reinforcement learning algorithm to obtain a target transmission path, and the data packet is sent from the data sending vehicle to the destination vehicle through the first edge server, the target transmission path, and the second edge server.

[0047] The beneficial effect of adopting the above-mentioned implementation method is: the vehicle network data transmission system provided by the present invention realizes a three-layer architecture of cloud-edge-end by setting up a vehicle network data transmission system including multiple vehicles, roads, multiple edge servers set at multiple intersections, and cloud servers, that is: some computing tasks can be processed by the edge server, the transmission delay of the data packet can be reduced, and the computing pressure of the cloud server can be reduced, thereby improving the transmission speed of the data packet.

[0048] Furthermore, the present invention sets a cloud server to determine the global optimal transmission path of data packets between a first edge server, multiple intermediate edge servers, and a second edge server based on global traffic flow information, a reinforcement learning algorithm, multi-hop links, and road quality, and sets an edge server to modify the global optimal transmission path based on the reinforcement learning algorithm to obtain a target transmission path. This can implement two-stage reinforcement learning, speed up the determination efficiency of the target transmission path, and thus further improve the transmission speed of data packets.

[0049] Furthermore, the present invention takes road quality into consideration when determining the global optimal transmission path, and can determine a more reasonable and reliable global optimal transmission path on road sections with high vehicle density, thereby further improving the speed of data packet transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A schematic structural diagram of an embodiment of the vehicle network data transmission system provided by the present invention;

[0052] Figure 2 A schematic diagram of the structure of an embodiment of the edge server provided by the present invention;

[0053] Figure 3 A schematic structural diagram of an embodiment of a base determination module provided by the present invention;

[0054] Figure 4 A schematic structural diagram of an embodiment of a vehicle provided by the present invention;

[0055] Figure 5 A schematic flow chart of an embodiment of the vehicle network data transmission method provided by the present invention; DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0057] In the description of the embodiments of the present application, unless otherwise specified, “plurality” means two or more.

[0058] The terms "including" and "having" and any variations thereof in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or device comprising a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products or devices.

[0059] The naming or numbering of the steps in the embodiments of the present invention does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The execution order of the named or numbered process steps can be changed according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0060] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0061] The present invention provides a vehicle network data transmission system and method, which are described below.

[0062] Figure 1 This is a schematic diagram of an embodiment of the vehicle network data transmission system provided by the present invention, as shown in FIG. Figure 1 As shown, the vehicle network data transmission system 10 includes multiple vehicles 100, a road 200, multiple edge servers 300 set at multiple intersections, and a cloud server 400. The multiple vehicles 100 include a data sending vehicle, a destination vehicle, and multiple intermediate vehicles. The multiple edge servers 300 include a first edge server closest to the data sending vehicle, a second edge server closest to the destination vehicle, and multiple intermediate edge servers.

[0063] The edge server 300 is used to collect beacons sent by the vehicle 100, obtain local traffic flow information at each intersection, establish a multi-hop link with adjacent edge servers adjacent to the edge server 300 based on the local traffic flow information, and upload the local traffic flow information and the multi-hop link to the cloud server 400;

[0064] The cloud server 400 is configured to generate global traffic flow information based on the local traffic flow information and determine road quality. The cloud server 400 determines a global optimal transmission path for data packets between a first edge server, multiple intermediate edge servers, and a second edge server based on the global traffic flow information, a reinforcement learning algorithm, multi-hop links, and road quality, and sends the global optimal transmission path to each edge server 300.

[0065] The edge server 300 is also used to modify the global optimal transmission path based on the reinforcement learning algorithm to obtain the target transmission path. The data packet is sent from the data sending vehicle to the destination vehicle through the first edge server, the target transmission path and the second edge server.

[0066] Compared with the prior art, the Internet of Vehicles data transmission system 10 provided in an embodiment of the present invention realizes a three-layer architecture of cloud-edge-end by setting up the Internet of Vehicles data transmission system 10 to include multiple vehicles 100, roads 200, multiple edge servers 300 set at multiple intersections, and a cloud server 400. That is, part of the computing tasks can be processed by the edge server 300, the transmission delay of the data packet can be reduced, and the computing pressure of the cloud server 400 can be reduced, thereby improving the transmission speed of the data packet.

[0067] Furthermore, the embodiment of the present invention sets a cloud server 400 to determine the global optimal transmission path of the data packet between the first edge server, multiple intermediate edge servers and the second edge server based on global traffic flow information, reinforcement learning algorithm, multi-hop links and road quality, and sets the edge server 300 to modify the global optimal transmission path based on the reinforcement learning algorithm to obtain the target transmission path, thereby realizing two-stage reinforcement learning, accelerating the efficiency of determining the target transmission path, and further improving the transmission speed of the data packet.

[0068] Furthermore, the embodiments of the present invention take road quality into consideration when determining the global optimal transmission path, and can determine a more reasonable and reliable global optimal transmission path on road sections with high vehicle density, thereby further improving the speed of data packet transmission.

[0069] The specific process of sending a data packet from a data-sending vehicle to a destination vehicle through a first edge server, a target transmission path, and a second edge server is as follows: first, the data packet is transmitted from the data-sending vehicle to the first edge server, and then the data packet is transmitted from the first edge server to the next edge server receiving the data packet through a multi-hop link between the first edge server and the next edge server receiving the data packet, and so on, until the data packet is transmitted to the second edge server and then transmitted to the destination vehicle based on the second edge server.

[0070] In some embodiments of the present invention, Figure 2 As shown, the edge server 300 includes a vehicle position determination module 310, a candidate base construction module 320, a base determination module 330, and a multi-hop link establishment module 340;

[0071] The vehicle position determination module 310 is used to determine the vehicle positions of multiple vehicles 100 in a preset coordinate system within the transmission range of the edge server based on the local traffic flow information;

[0072] The candidate base construction module 320 is used to determine multiple target vehicles traveling away from the intersection among the multiple vehicles 100, establish multiple groups of preliminary bases corresponding to the multiple target vehicles, and determine multiple groups of candidate bases in the multiple groups of preliminary bases based on the vehicle positions and preset screening rules;

[0073] The basis determination module 330 is used to determine the link lifetime of each group of candidate bases and use the candidate base with the longest link lifetime as the basis. The vehicles in the basis are relay vehicles, which include the previous hop relay vehicle and multiple relay vehicles to be selected.

[0074] The multi-hop link establishment module 340 is used to determine the link life of multiple candidate relay vehicles and the previous-hop relay vehicle, and use the candidate relay vehicle with the longest link life as the next-hop relay vehicle. When the link between the previous-hop relay vehicle and the edge server 300 is disconnected, the next-hop relay vehicle is linked to the previous-hop relay vehicle to obtain a multi-hop link.

[0075] When obtaining a multi-hop link, the embodiment of the present invention selects the link with the longest link life, thereby improving the durability of the multi-hop link.

[0076] The preset coordinate system is a coordinate system established with the upper left corner of the road 200 as the coordinate origin, the south direction as the positive direction of the vertical axis, and the east direction as the positive direction of the horizontal axis.

[0077] Because the communication capabilities of the edge server 300 and the vehicle 100 are not equal, the edge server 300 has a stronger communication capability and can transmit farther. Therefore, after receiving the beacon from the edge server 300, the vehicle 100 cannot immediately respond to the beacon. In other words, it takes time for the vehicle 100 to establish a connection with the edge server 300, and this time must be calculated before the location of the vehicle 100 can be determined. In a specific embodiment of the present invention, the vehicle location is:

[0078]

[0079]

[0080]

[0081]

[0082] Wherein, x is the horizontal coordinate of the vehicle position; y is the vertical coordinate of the vehicle position; t is the time when the vehicle 100 establishes a connection with the edge server 300; t0 is the time when the vehicle 100 receives the beacon; x0 is the horizontal coordinate of the vehicle 100 at time t0; y0 is the initial vertical coordinate of the vehicle 100 at time t0; v is the speed of the vehicle 100 when the connection is established with the edge server 300; a is the acceleration of the vehicle 100 when the connection is established with the edge server 300; θ is the angle between the vehicle's moving direction and the positive axis of the horizontal coordinate of the preset coordinate system; V0 is the speed of the vehicle 100 at time t0; ΔD is the distance between the vehicle 100 and the edge server 300 when the edge server 300 sends the beacon; R is the maximum communication distance of the vehicle 100; X R Y is the horizontal coordinate of the edge server 300; R is the vertical coordinate of the edge server 300.

[0083] The embodiment of the present invention can improve the accuracy of the position of the vehicle 100 by calculating the time when the vehicle 100 establishes a connection with the edge server 300 and determining the position of the vehicle 100 based on this time, thereby improving the accuracy and reliability of data packet transmission.

[0084] In a specific embodiment of the present invention, the link lifetime of the preparation base is:

[0085]

[0086]

[0087] Where MLET(P) is the link lifetime of the preparation base; min is the minimum value symbol; len is the number of vehicles in the multi-hop link; LET(P[i],P[i+1]) is the link lifetime between the i-th vehicle and the i+1-th vehicle; S i is the distance between the i-th vehicle and the edge sensor; S i+1 is the distance between the i+1th vehicle and the edge sensor; V i is the speed of the i-th vehicle; V i+1 is the speed of the i+1th vehicle; || is the absolute value operator.

[0088] In some embodiments of the present invention, Figure 3 As shown, the base determination module 330 includes a first screening unit 331, a second screening unit 332 and a third screening unit 333;

[0089] The first screening unit 331 is used to screen multiple groups of preliminary bases based on the speeds and accelerations of multiple target vehicles to obtain multiple groups of first candidate preliminary bases;

[0090] The second screening unit 332 is configured to screen multiple groups of first candidate preparatory bases based on vehicle positions when the first candidate preparatory base includes two target vehicles, and to screen multiple groups of first candidate preparatory bases based on a linking manner when the first candidate preparatory base includes at least three target vehicles, to obtain multiple groups of second candidate preparatory bases;

[0091] The third screening unit 333 is configured to screen multiple groups of second candidate bases based on the number of target vehicles in each group of second candidate bases to obtain multiple groups of candidate bases.

[0092] In the embodiment of the present invention, the first screening unit 331, the second screening unit 332 and the third screening unit 333 are provided to screen multiple groups of preliminary bases to obtain multiple groups of candidate bases, which can further reduce the computational complexity of the edge server 300 and further improve the data packet transmission efficiency.

[0093] Specifically, the specific screening process of the first screening unit 331 is: excluding target vehicles with too large differences in speed and acceleration, so that the target vehicles in the first candidate preparation base meet the principle of similar kinematic information.

[0094] The specific screening process of the second screening unit 332 is: when the first candidate preparatory base includes two target vehicles, determine whether the distance between the two target vehicles is greater than the transmission range of the target vehicle. If it is greater, disband the first candidate preparatory base. When the first candidate preparatory base includes at least three target vehicles, for example: when the first candidate preparatory base includes three target vehicles a, b, and c, if target vehicle a can skip target vehicle b and directly establish a connection with target vehicle c, then target vehicle b will be eliminated from the first candidate preparatory base and the second candidate preparatory base will be obtained.

[0095] The specific screening process of the third screening unit 333 is: disbanding the second candidate preparation base in which the number of target vehicles is less than or equal to 2, to obtain multiple groups of candidate bases.

[0096] Due to the highly dynamic characteristics of vehicle mobility and traffic flow, multi-hop links may be broken. In order to solve this technical problem, in some embodiments of the present invention, such as Figure 2 As shown, the edge server 300 further includes a link break processing module 350 and a multi-hop link maintenance module 360;

[0097] The link break processing module 350 is used to generate a new multi-hop link when a multi-hop link is broken;

[0098] The multi-hop link maintenance module 360 ​​is configured to determine whether the new multi-hop link can be connected to the multi-hop link, and connect the new multi-hop link to the multi-hop link if the new multi-hop link can be connected to the multi-hop link.

[0099] By providing a link break processing module 350, the embodiments of the present invention can address the situation where a multi-hop link breaks, thereby improving the ability of the vehicle network data transmission system 10 to cope with link breaks. Furthermore, by providing a multi-hop link maintenance module 360 ​​to connect a new multi-hop link to a multi-hop link, the embodiments of the present invention can resolve the link window period caused by establishing a new multi-hop link, achieve link reuse, and increase the service life of the multi-hop link.

[0100] There are two types of link breakage. The first is when the edge server 300 receives the beacon from the vehicle 100 and finds that the distance between the previous relay vehicle and itself has exceeded the transmission range of the relay vehicle, but still cannot find a suitable next-hop relay vehicle. Once this happens, the edge server 300 will build a new multi-hop link after a certain period of time. The specific time value is determined by the distance between the last-hop link and the edge server 300. The second is when the subsequent edge server 300 does not receive the beacon from the remaining vehicles. When the edge server 300 modifies the multi-hop link (including establishing the base and selecting the next-hop relay vehicle to join the multi-hop link), it saves the time at that time, recorded as pretime, and sets a periodic check to see if it is overdue. When the difference between the current time curtime and the time pretime of the last modification of the multi-hop link is too large, the multi-hop link is broken and a new multi-hop link is immediately built.

[0101] It should be noted that when the multi-hop link maintenance module 360 ​​determines whether a new multi-hop link can establish a connection with a multi-hop link, it does not consider whether the motion information is similar. That is, even if the motion information of the first-hop relay vehicle in the new multi-hop link is not similar to that of the last-hop relay vehicle in the multi-hop link, a connection can be successfully established.

[0102] In order to ensure the timeliness of multi-hop links, in some embodiments of the present invention, such as Figure 2 As shown, the edge server 300 further includes a multi-hop link storage module 370;

[0103] The multi-hop link storage module 370 is used to determine the first relay vehicle and the last relay vehicle in the multi-hop link, and determine the effectiveness time of the multi-hop link based on the distance between the first relay vehicle and the edge server, determine the expiration time of the multi-hop link based on the distance between the last relay vehicle and the edge server, and store the multi-hop link based on the effectiveness time, expiration time and the life of the multi-hop link.

[0104] In a specific embodiment of the present invention, the road quality is:

[0105] Q=αDr ij +βPr ij

[0106]

[0107]

[0108] α+β=1

[0109] Where Q is the road quality; α is the first proportional coefficient; Dr ij is the road section r ij The number of vehicles on the road and the road section r ij length ratio; β is the second proportional coefficient; Pr ij is the ratio of relay vehicles in multiple links; Nr ij is the road section r ij The number of vehicles on board; Lr ij is the road section r ij Length; Nh ij is the road section r ij The number of relay vehicles.

[0110] In a specific embodiment of the present invention, the specific principle of the reinforcement learning algorithm (Q-learning) is:

[0111] Each edge server 300 is regarded as an intelligent agent. In each time step, each available agent takes an action ai to indicate its transmission direction. The action space of the agent is set here to include a total of 4 actions, namely transmitting data packets to the east, west, south, and north. The action space of the agent is represented by A, where ai∈A, and the set of states S represents the ID and geographical location of each agent. In each state s, the agent also needs to clarify the relationship between the next possible state s_next and the corresponding action. The state transfer function P(s|s_next, ai) represents the probability of reaching the state s_next after executing action ai in state s. It is used by the agent to decide the next action to take. After each action is completed, the agent will reward or punish the action according to the set reward function, and directly affect the probability of the state transfer function P(s|s_next, ai). The reward function is defined as reward(s, a) to represent the reward for executing action ai in state s. The reward is defined as r t .

[0112] In a specific embodiment of the present invention, the specific steps of the reinforcement learning algorithm are as follows: first, a weighted directed graph is established, the directed graph G = (V, E), V is the edge server 300 at the intersection, E is the road segment ri j The weight refers to the road segment r ij The weight of road segment r ij The weight is related to the level of the road section. Specifically, the road sections are divided into four levels:

[0113] (1) There are available multi-hop links;

[0114] (2) There is no available multi-hop link but there are more relay vehicles on the road, which can form a valid link (fewer handshake mechanisms are required to establish a V2V communication connection in order to successfully establish a connection with the neighboring RSU);

[0115] (3) There is no multi-hop link, and multiple handshake mechanisms need to be executed or even rely entirely on the handshake mechanism to establish a V2V communication connection to transmit messages;

[0116] (4) There are no multi-hop links and traffic vacuum zones appear at both ends of the road, which requires vehicles to carry and forward.

[0117] Specifically, where r t =ω1Dr ij +ω2Level i，j +ω3Pr ij

[0118] Where, Level i，j is the reward value corresponding to the road quality, and ω1, ω2, and ω3 are all proportional factors.

[0119] After establishing a weighted directed graph, a 3x3 small grid is established with each edge server 300 as the center. A determination is made as to whether the second edge server is within the small grid of the first edge server. If the second edge server is not within the small grid of the first edge server, a global optimal transmission path is determined based on global traffic flow information, a reinforcement learning algorithm, multi-hop links, and road quality. Because the edge server at the end of the global optimal transmission path may not be the second edge server, the edge server 300 modifies the global optimal transmission path based on the reinforcement learning algorithm to obtain the target transmission path.

[0120] It's important to note that reinforcement learning algorithms generate a Q-value table, which stores the value rewards generated by different actions under all conditions. In special circumstances, such as when all roads can successfully establish multi-hop links, the transmission task may face the same value reward for all actions. In this case, combined with road quality assessment, the globally optimal transmission path can be selected.

[0121] That is, by considering the road quality to obtain the global optimal transmission path, the reliability and rationality of the global optimal transmission path can be improved.

[0122] In particular, in an embodiment of the present invention, when there is no multi-hop link on a road and a traffic vacuum zone appears at both ends of the road, the vehicle-carried forwarding can provide a guarantee for the successful transmission of data packets.

[0123] It should be noted that once a multi-hop link is established, it includes multiple relay vehicles. The edge server periodically broadcasts the relay vehicles that make up the multi-hop link in a beacon. Vehicles receiving these broadcasts check whether they have been designated as relay vehicles. Furthermore, if a relay vehicle discovers that its location is too far from the edge server that assigned it relay status, it will automatically cancel its relay status and become a normal vehicle. When a vehicle learns its own identity, it also learns the IDs of its previous and next-hop relay vehicles. Since the relay vehicle selection process is entirely handled by the edge server, which cannot obtain real-time information about every vehicle, much of this work is imprecise, making it difficult to prevent link disconnections. Therefore, once a vehicle is assigned relay status by an edge server, it will autonomously collect beacons containing kinematic information periodically transmitted by other vehicles on the road and store them in its neighbor table, particularly information about its previous and next-hop relay vehicles, to address special circumstances.

[0124] The embodiment of the present invention can provide a guarantee for the successful transmission of data packets by generating a neighbor table.

[0125] In order to further ensure the success of data packet transmission, in some embodiments of the present invention, such as Figure 4 As shown, the vehicle 100 includes a data packet transmission module 110 and a retransmission module 120;

[0126] The data packet transmission module 110 is used to transmit the data packet to the edge server 300;

[0127] The retransmission module 120 is configured to retransmit the data packet to the edge server 300 with a preset number of retransmission times when the data packet transmission fails.

[0128] In the embodiment of the present invention, the retransmission module 120 is configured to retransmit the data packet to the edge server 300 when the data packet transmission fails, thereby improving the transmission success rate of the data packet.

[0129] The preset number of times can be set or adjusted according to actual application scenarios or experience values. In a specific embodiment of the present invention, the preset number of retransmissions is 2.

[0130] It should be noted that the specific workflow of retransmission module 120 is as follows: a handshake mechanism is introduced. When vehicle 100 transmits a beacon, a timer begins. If the timer times out and no confirmation beacon (reply1) is received, periodic retransmissions will be performed to avoid transmission failures caused by beacon or confirmation beacon loss. After vehicle 100 confirms the next-hop relay vehicle, it will periodically transmit data packets until it receives a confirmation beacon (reply2) from the next-hop relay vehicle. If no confirmation beacon is received after more than two retransmissions, the transmission is considered a failure and the data packet is lost.

[0131] It should also be noted that in order to further improve the success rate of data packet transmission, in some embodiments of the present invention, when the next-hop relay vehicle leaves the communication range of the edge server 300, the following protection mechanisms are executed in sequence from top to bottom to reselect the next-hop relay vehicle. The proposed triple protection mechanisms are:

[0132] (1) Select the appropriate next-hop relay vehicle based on the neighbor table;

[0133] (2) Send beacons to sense surrounding traffic flow information;

[0134] (3) Forwarding by vehicle.

[0135] Through the triple protection mechanism, the embodiment of the present invention can successfully find the next-hop relay vehicle again when the next-hop relay vehicle leaves the communication range of the edge server 300, thereby ensuring the successful transmission of the data packet.

[0136] The embodiment of the present invention further provides a vehicle network data transmission method, which is applicable to the vehicle network data transmission system 10 in any of the above embodiments. Figure 5 As shown, the vehicle network data transmission method includes:

[0137] S501: Control the edge server 300 to collect beacons sent by the vehicle 100, obtain local traffic flow information at each intersection, establish a multi-hop link with adjacent edge servers based on the local traffic flow information, and upload the local traffic flow information and the multi-hop link to the cloud server 400.

[0138] S502: Control the cloud server 400 to generate global traffic flow information based on the local traffic flow information and determine road quality. Based on the global traffic flow information, the reinforcement learning algorithm, the multi-hop links, and the road quality, determine a global optimal transmission path for data packets between the first edge server, the multiple intermediate edge servers, and the second edge server, and send the global optimal transmission path to each edge server 300.

[0139] S503: Control the edge server 300 to modify the global optimal transmission path based on the reinforcement learning algorithm to obtain the target transmission path. The data packet is sent from the data sending vehicle to the destination vehicle through the first edge server, the target transmission path, and the second edge server.

[0140] Those skilled in the art will appreciate that all or part of the process steps of the above-described embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0141] The above is a detailed introduction to the vehicle network data transmission system and method provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A vehicle network data transmission system, characterized in that: The method comprises a plurality of vehicles, a road, a plurality of edge servers arranged at a plurality of intersections, and a cloud server, wherein the plurality of vehicles include a data sending vehicle, a destination vehicle, and a plurality of intermediate vehicles, and the plurality of edge servers include a first edge server closest to the data sending vehicle, a second edge server closest to the destination vehicle, and a plurality of intermediate edge servers; The edge server is configured to collect beacons sent by the vehicles, obtain local traffic flow information at each intersection, establish a multi-hop link with adjacent edge servers adjacent to the edge server based on the local traffic flow information, and upload the local traffic flow information and the multi-hop link to the cloud server; The cloud server is configured to generate global traffic flow information based on the local traffic flow information and determine road quality, determine a global optimal transmission path for data packets between the first edge server, the multiple intermediate edge servers, and the second edge server based on the global traffic flow information, a reinforcement learning algorithm, the multi-hop link, and the road quality, and send the global optimal transmission path to each of the edge servers; The edge server is further configured to modify the global optimal transmission path based on the reinforcement learning algorithm to obtain a target transmission path. The data packet is sent from the data sending vehicle to the destination vehicle via the first edge server, the target transmission path, and the second edge server.

2. The vehicle network data transmission system according to claim 1, characterized in that: The edge server includes a vehicle position determination module, a candidate base construction module, a base determination module, and a multi-hop link establishment module; The vehicle position determination module is used to determine the vehicle positions of multiple vehicles within the transmission range of the edge server in a preset coordinate system based on the local traffic flow information; The candidate base construction module is used to determine multiple target vehicles traveling away from the intersection among the multiple vehicles, establish multiple groups of preliminary bases corresponding to the multiple target vehicles, and determine multiple groups of candidate bases in the multiple groups of preliminary bases based on vehicle positions and preset screening rules; The basis determination module is used to determine the link lifetime of each group of candidate bases and use the candidate base with the longest link lifetime as the basis, wherein the vehicles in the basis are relay vehicles, and the relay vehicles include the previous hop relay vehicle and multiple relay vehicles to be selected; The multi-hop link establishment module is used to determine the link lifespans of the multiple candidate relay vehicles and the previous-hop relay vehicle, and use the candidate relay vehicle with the longest link lifespan as the next-hop relay vehicle. When the link between the previous-hop relay vehicle and the edge server is disconnected, the next-hop relay vehicle is linked to the previous-hop relay vehicle to obtain the multi-hop link.

3. The vehicle network data transmission system according to claim 2, characterized in that: The vehicle position is: Where x is the horizontal coordinate of the vehicle's position; y is the vertical coordinate of the vehicle's position; t is the time when the vehicle establishes a connection with the edge server; t0 is the time when the vehicle receives the beacon; x0 is the horizontal coordinate of the vehicle at time t0; y0 is the initial vertical coordinate of the vehicle at time t0; v is the speed of the vehicle when it establishes a connection with the edge server; a is the acceleration of the vehicle when it establishes a connection with the edge server; θ is the angle between the vehicle's moving direction and the positive axis of the horizontal coordinate of the preset coordinate system; V0 is the speed of the vehicle at time t0; ΔD is the distance between the vehicle and the edge server when the edge server sends a beacon; R is the maximum communication distance of the vehicle; X R Y is the horizontal coordinate of the edge server; R is the vertical coordinate of the edge server.

4. The vehicle network data transmission system according to claim 2, characterized in that: The link lifetime of the preparation base is: Where MLET(P) is the link lifetime of the preparation base; min is the minimum value symbol; len is the number of vehicles in the multi-hop link; LET(P[i],P[i+1]) is the link lifetime between the i-th vehicle and the i+1-th vehicle; S i is the distance between the i-th vehicle and the edge sensor; S i+1 is the distance between the i+1th vehicle and the edge sensor; V i is the speed of the i-th vehicle; V i+1 is the speed of the i+1th vehicle; | | is the absolute value operator.

5. The vehicle network data transmission system according to claim 2, characterized in that: The base determination module includes a first screening unit, a second screening unit, and a third screening unit; The first screening unit is used to screen the multiple groups of preliminary bases based on the speeds and accelerations of the multiple target vehicles to obtain multiple groups of first candidate preliminary bases; The second screening unit is configured to screen the plurality of first candidate preparatory bases based on the vehicle positions when the first candidate preparatory bases include two target vehicles, and to screen the plurality of first candidate preparatory bases based on a linking manner to obtain a plurality of second candidate preparatory bases when the first candidate preparatory bases include at least three target vehicles; The third screening unit is configured to screen the plurality of groups of second candidate bases based on the number of target vehicles in each group of the second candidate bases to obtain the plurality of groups of candidate bases.

6. The vehicle network data transmission system according to claim 2, characterized in that: The edge server also includes a link break processing module and a multi-hop link maintenance module; The link break processing module is used to generate a new multi-hop link when the multi-hop link is broken; The multi-hop link maintenance module is used to determine whether the new multi-hop link can be connected to the multi-hop link, and when the new multi-hop link can be connected to the multi-hop link, connect the new multi-hop link to the multi-hop link.

7. The vehicle network data transmission system according to claim 2, characterized in that: The edge server also includes a multi-hop link storage module; The multi-hop link storage module is used to determine the first relay vehicle and the last relay vehicle in the multi-hop link, and determine the effectiveness time of the multi-hop link according to the distance between the first relay vehicle and the edge server, and determine the expiration time of the multi-hop link according to the distance between the last relay vehicle and the edge server, and store the multi-hop link based on the effectiveness time, the expiration time and the life of the multi-hop link.

8. The vehicle network data transmission system according to claim 2, characterized in that: The road quality is: Q=αDr ij +βPr ij α+β＝1 Where Q is the road quality; α is the first proportional coefficient; Dr ij is the road section r ij The number of vehicles on the road and the road section r ij length ratio; β is the second proportional coefficient; Pr ij is the ratio of relay vehicles in multiple links; Nr ij is the road section r ij The number of vehicles on board; Lr ij is the road section r ij Length; Nh ij is the road section r ij The number of relay vehicles.

9. The vehicle network data transmission system according to claim 1, characterized in that: The vehicle includes a data packet transmission module and a retransmission module; The data packet transmission module is used to transmit the data packet to the edge server; The retransmission module is configured to retransmit the data packet to the edge server with a preset number of retransmissions when the data packet transmission fails.

10. A vehicle network data transmission method, characterized in that: The vehicle network data transmission system according to any one of claims 1 to 9, wherein the vehicle network data transmission method comprises: Controlling the edge server to collect beacons sent by the vehicles, obtaining local traffic flow information at each intersection, establishing a multi-hop link with adjacent edge servers adjacent to the edge server based on the local traffic flow information, and uploading the local traffic flow information and the multi-hop link to the cloud server; controlling the cloud server to generate global traffic flow information based on the local traffic flow information and determine road quality, determining a global optimal transmission path for data packets between the first edge server, the multiple intermediate edge servers, and the second edge server based on the global traffic flow information, a reinforcement learning algorithm, the multi-hop link, and the road quality, and sending the global optimal transmission path to each of the edge servers; The edge server is controlled to modify the global optimal transmission path based on the reinforcement learning algorithm to obtain a target transmission path, and the data packet is sent from the data sending vehicle to the destination vehicle through the first edge server, the target transmission path, and the second edge server.

Images