A vehicle-borne signal intelligent routing method based on 5G+WLAN technology

Abstract

The present invention relates to the technical field of vehicle signal routing, and discloses a vehicle signal intelligent routing method based on 5G+WLAN technology, the method comprising: real-time collection of 5G and WLAN network status information and smoothing; communication parameter constraints for different vehicle applications; building a multi-objective vehicle application network loss objective function; and optimizing and solving using an improved particle swarm algorithm to obtain an optimal vehicle network switching strategy for vehicle network switching. The present invention combines network delay, jitter, and the frequency of packet loss rate deviation from communication parameter constraints and the discrete variation degree of signal strength to calculate the network quality of vehicle applications under different vehicle networks, and weights the allocation weights of vehicle applications in combination with network bandwidth to achieve a network quality quantification method for vehicle applications in a 5G+WLAN network environment, and then solves the optimal vehicle network switching strategy for improving the network quality of vehicle applications, thereby achieving intelligent routing for vehicle applications.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-mounted signal routing, and in particular to a vehicle-mounted signal intelligent routing method based on 5G+WLAN technology. Background Art

[0002] With the development of intelligent transportation systems and the increasing popularity of the Internet of Vehicles (IoV), vehicle network communication technology has become an important cornerstone for promoting the development of emerging technologies such as autonomous driving and smart transportation. The IoV greatly improves the intelligence level of vehicles and driving safety by providing vehicles with efficient, stable, and low-latency communication services. Traditional in-vehicle communication systems mainly rely on cellular networks (such as 3G / 4G) for data transmission. However, with the rapid development of mobile Internet and the sharp increase in vehicle data volume, traditional cellular networks have been unable to meet the low-latency, high-bandwidth, and high-stability communication requirements of intelligent driving vehicles. The emergence of 5G technology has brought a huge breakthrough in in-vehicle communications. 5G has technical advantages such as high speed (up to 10Gbps), low latency (<1ms), and large connections (millions of connections per square kilometer). It can effectively support in-vehicle scenarios with extremely high communication requirements such as autonomous driving, real-time monitoring, and remote driving. At the same time, WLAN (Wireless Local Area Network) technology has also become an important supplementary technology in in-vehicle communications due to its low cost and easy deployment. During the driving process, the vehicle system can dynamically select 5G or WLAN network according to different scenarios, such as cities, highways, tunnels, underground parking lots, etc., to provide more stable, fast and economical network communication. However, how to efficiently and intelligently select routes between 5G and WLAN has become one of the key issues in the current research on vehicle network communication technology. Route selection not only involves network switching, but also affects the stability of vehicle communication, the continuity of data transmission and the user experience of vehicle applications. Summary of the invention

[0003] In view of this, the present invention provides an intelligent routing method for vehicle signals based on 5G+WLAN technology, which regularly calculates the current network status information of 5G and WLAN, combines the network resources required by different vehicle applications, calculates the network quality of vehicle applications under different vehicle networks, constructs a multi-objective vehicle application network loss objective function, and solves the strategy with the goal of maximizing the dynamically weighted vehicle application network quality, obtains the optimal vehicle network switching strategy, switches the vehicle network for different vehicle applications, and realizes intelligent routing for vehicle applications.

[0004] To achieve the above object, the present invention provides a vehicle-mounted signal intelligent routing method based on 5G+WLAN technology, comprising the following steps:

[0005] S1: Deploy a network monitoring module in the vehicle system to collect 5G and WLAN network status information in real time, and use the sliding window technology to smooth the collected network status information to obtain smoothed network status information, where the network status information includes signal strength, delay, bandwidth, jitter and packet loss rate;

[0006] S2: constrain communication parameters for different in-vehicle applications and determine the value range of signal strength, delay, bandwidth, jitter and packet loss rate for each in-vehicle application;

[0007] S3: Based on the smoothed network status information and the vehicle application communication parameter constraints, a multi-objective vehicle application network loss objective function is constructed, wherein the multi-objective vehicle application network loss objective function uses the vehicle network selected by different vehicle applications as an independent variable and aims to maximize the dynamically weighted vehicle application network quality;

[0008] S4: Use the improved particle swarm algorithm to optimize and solve the multi-objective vehicle application network loss objective function to obtain the optimal vehicle network switching strategy;

[0009] S5: Perform vehicle network switching for different vehicle applications according to the optimal vehicle network switching strategy obtained by solving.

[0010] As a further improvement method of the present invention:

[0011] Optionally, in step S1, a network monitoring module is deployed in the vehicle system to collect network status information of 5G and WLAN in real time, including:

[0012] A network monitoring module is deployed in the vehicle system, and the network status information of 5G and WLAN is collected in real time using the network monitoring module. The network status information includes signal strength, delay, bandwidth, jitter and packet loss rate. The collection and calculation process of network status information is as follows:

[0013] The signal strengths of 5G and WLAN in the car at N consecutive moments are calculated, where the signal strengths of 5G and WLAN in the car at the nth moment are :

[0014] ;

[0015] ;

[0016] in:

[0017] Indicates the signal strength of 5G in the car at the nth moment, represents the signal strength of the WLAN in the car at the nth moment, , the Nth moment is the real time;

[0018] Indicates the distance between the vehicle and the base station at the nth moment;

[0019] Indicates the carrier frequency of the wireless access point in the car;

[0020] The delays of 5G and WLAN in the car at N consecutive moments are calculated, where the delays of 5G and WLAN in the car at the nth moment are :

[0021] ;

[0022] ;

[0023] in:

[0024] represents the delay of 5G in the car at the nth moment;

[0025] represents the delay of the in-car WLAN at the nth moment;

[0026] Indicates the timestamp corresponding to the nth moment;

[0027] Indicates the data packet sending timestamp of the data packet received by the 5G in the car at the nth moment;

[0028] Indicates the data packet sending timestamp of the data packet received by the in-vehicle WLAN at the nth time;

[0029] The bandwidths of 5G and WLAN in the car at N consecutive moments are collected, where the bandwidths of 5G and WLAN in the car at the nth moment are ;

[0030] The jitters of 5G and WLAN in the car at N consecutive moments are calculated, where the jitters of 5G and WLAN in the car at the nth moment are :

[0031] ;

[0032] ;

[0033] in:

[0034] represents the jitter of 5G in the car at the nth moment; in the embodiment of the present invention, They are the preset minimum jitter for 5G and the minimum jitter for WLAN;

[0035] Indicates the jitter of the in-car WLAN at the nth moment;

[0036] The packet loss rates of 5G and WLAN in the car at N consecutive moments are collected, where the packet loss rates of 5G and WLAN in the car at the nth moment are ;

[0037] The network status information of 5G and WLAN collected in real time:

[0038] ;

[0039] ;

[0040] ;

[0041] ;

[0042] in:

[0043] Indicates the real-time collected in-car 5G network status information. Indicates the network status information of the in-vehicle WLAN collected in real time;

[0044] Indicates the network status of the 5G in the car at the nth moment, Indicates the network status of the in-car WLAN at the nth moment;

[0045] Use sliding window technology to collect network status information Perform smoothing processing to obtain smoothed network status information.

[0046] Optionally, the collected network status information is processed using a sliding window technique. Perform smoothing to obtain smoothed network status information, including:

[0047] S11: Set the smoothing coefficient ;

[0048] S12: Calculate and obtain network status information The initial smoothing term and the initial trend term of Network status information The initial smoothing term is Network status information The initial trend term of:

[0049] ;

[0050] ;

[0051] ;

[0052] S13: Iterate the initial smooth term and the initial trend term to obtain the smooth term and the trend term at N moments, where the initial smooth term The smoothing terms at the nth moment are , initial trend term The trend terms at the nth moment are :

[0053] ;

[0054] ;

[0055] ;

[0056] ;

[0057] ;

[0058] ;

[0059] in:

[0060] Represent the initial trend terms The trend coefficient to be iterated at the nth moment;

[0061] S14: Based on the smoothing terms and trend terms at N moments, the smoothed network states of 5G and WLAN at each moment are calculated, where the smoothed network state of 5G at the nth moment is , the smoothed network state of WLAN at the nth moment is ;

[0062] S15: Smoothed in-vehicle 5G network status information , and the network status information of the in-car WLAN .

[0063] Optionally, in step S2, constraining communication parameters for different vehicle-mounted applications includes:

[0064] Communication parameter constraints are imposed on different vehicle-mounted applications to determine the value range of signal strength, delay, bandwidth, jitter, and packet loss rate for each vehicle-mounted application. The communication parameter constraint set for M vehicle-mounted applications is:

[0065] ;

[0066] ;

[0067] in:

[0068] Indicates the communication parameter constraints of the mth in-vehicle application; in-vehicle applications include navigation systems, entertainment systems, voice assistants, communication systems, safety systems, remote diagnosis, autonomous driving systems, payment systems, etc.;

[0069] Indicates the parameter constraints of the mth vehicle-mounted application in terms of signal strength, delay, bandwidth, jitter, and packet loss rate; if the network resources obtained by the vehicle-mounted application are within the parameter constraints, it means that the vehicle-mounted application can operate normally;

[0070] represents the minimum and maximum signal strength of the mth vehicle-mounted application;

[0071] represents the minimum and maximum delay of the mth vehicle application respectively;

[0072] represents the minimum and maximum bandwidth of the mth vehicle application respectively;

[0073] represents the minimum and maximum jitter values ​​of the mth vehicle-mounted application respectively;

[0074] They represent the minimum and maximum packet loss rates of the m-th vehicle-mounted application respectively.

[0075] Optionally, in the step S3, a multi-objective vehicle application network loss objective function is constructed based on the smoothed network state information and the vehicle application communication parameter constraints, including:

[0076] Based on the smoothed network status information and the vehicle application communication parameter constraints, a multi-objective vehicle application network loss objective function is constructed. The multi-objective vehicle application network loss objective function takes the vehicle network selected by different vehicle applications as the independent variable and aims to maximize the dynamically weighted vehicle application network quality. The constructed multi-objective vehicle application network loss objective function is:

[0077] ;

[0078] ;

[0079] ;

[0080] ;

[0081] ;

[0082] ;

[0083] ;

[0084] in:

[0085] represents the multi-objective vehicle application network loss objective function;

[0086] For the vehicle network switching strategy, represents the vehicle network selected by M vehicle applications, This means that the mth in-vehicle application selects the 5G network. This means that the mth in-vehicle application selects the WLAN network;

[0087] represents the network quality of the mth in-vehicle application in the 5G network, Indicates the network quality of the mth in-vehicle application in the WLAN network;

[0088] Indicates the dynamic 5G network bandwidth weight of the mth vehicle application after the vehicle network is switched according to the vehicle network switching strategy;

[0089] Indicates the dynamic WLAN network bandwidth weight of the mth vehicle application after the vehicle network is switched according to the vehicle network switching strategy;

[0090] Indicates network status information In the example, delay, jitter and packet loss rate are all within the parameter constraints. The number of moments in the range;

[0091] Indicates network status information In the example, delay, jitter and packet loss rate are all within the parameter constraints. The number of moments in the range;

[0092] Indicates network status information The mean signal strength, Indicates network status information The mean signal intensity in

[0093] Indicates network status information The standard deviation of the signal intensity, Indicates network status information The standard deviation of the signal intensity in

[0094] represents an exponential function with a natural constant as base;

[0095] A control parameter representing signal strength;

[0096] Indicates the dynamic network bandwidth weight threshold;

[0097] Indicates network status information The mean bandwidth in Indicates network status information The average bandwidth.

[0098] Optionally, in step S4, the improved particle swarm algorithm is used to optimize and solve the multi-objective vehicle application network loss objective function, including:

[0099] The improved particle swarm algorithm is used to optimize and solve the multi-objective vehicle application network loss objective function to obtain the optimal vehicle network switching strategy. The optimization solution process is as follows:

[0100] S41: Initialize and generate U groups of particles, where each group of particles includes particle position and particle velocity. The particle position is a binary sequence of length M, corresponding to the vehicle network switching strategy. The particle position of the uth group of particles generated by initialization is , the particle speed is ;

[0101] S42: Set the current iteration number of the particle to t, the initial value of t is 0, and the maximum value is Max. Then the tth iteration result of the uth group of particles is ;

[0102] S43: using the particle position as an independent variable of the multi-objective vehicle application network loss objective function, and using the multi-objective vehicle application network loss objective function value as the fitness value of the particle position;

[0103] S44: Select the particle position with the highest fitness value after the tth iteration as the optimal position of the tth iteration ; and update the historical optimal position and historical worst position of each particle, where the historical optimal position of the u-th particle is , the worst position in history is The best historical position of a particle is the iteration result with the highest fitness value among the t-times position iteration results; the worst historical position of a particle is the iteration result with the lowest fitness value among the t-times position iteration results;

[0104] S45: Iterate the particle velocity and particle position in combination with the neighbor information of each particle position;

[0105] S46: Order , return to step S43 until the maximum number of iterations is reached, and extract the historical optimal position of each particle, and select the historical optimal position with the highest fitness value among the U historical optimal positions as the optimal vehicle network switching strategy .

[0106] Optionally, in step S45, the particle velocity and particle position are iterated in combination with the neighbor information of each particle position, including:

[0107] S451: Gaussian mapping is performed on the historical optimal position of each particle, where the historical optimal position of the uth particle is The Gaussian mapping result is :

[0108] ;

[0109] ;

[0110] in:

[0111] represents the Gaussian mapping parameter of the u-th particle;

[0112] S452: Calculate the neighbor information of each particle position, where the particle position The neighbor information of :

[0113] ;

[0114] in:

[0115] It means that the fitness value ratio of the particle position in group U after t iterations is The average of all particle positions of the highest; in the embodiment of the present invention, the distance is calculated as the Euclidean distance;

[0116] Represents a random number between 0 and 1;

[0117] S453: Based on the Gaussian mapping result and the neighbor information, iterate the particle velocity and particle position, where the particle velocity The iteration formula is:

[0118] ;

[0119] in:

[0120] , is an iterative control parameter; in the embodiment of the present invention, set is 0.4, is 0.6;

[0121] Particle Position The iteration formula is: .

[0122] Optionally, in step S5, performing vehicle network switching for different vehicle applications according to the optimal vehicle network switching strategy includes:

[0123] According to the optimal vehicle network switching strategy , switch the vehicle network for different vehicle applications, represents the optimal vehicle network switching strategy The vehicle network selected by the mth vehicle application in This means that the mth in-vehicle application selects the 5G network. It means that the mth in-vehicle application selects the WLAN network; and after a preset time range, the in-vehicle application network quality of each current in-vehicle application is calculated. If the number of in-vehicle applications whose in-vehicle application network quality is lower than the preset quality threshold is higher than 30%, then according to steps S1 to S4, the optimal in-vehicle network switching strategy is regenerated to perform in-vehicle network switching.

[0124] In order to solve the above problem, the present invention provides an electronic device, the electronic device comprising:

[0125] A memory storing at least one instruction;

[0126] Communication interface, enabling electronic equipment to communicate; and

[0127] The processor executes the instructions stored in the memory to implement the above-mentioned vehicle signal intelligent routing method based on 5G+WLAN technology.

[0128] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned vehicle signal intelligent routing method based on 5G+WLAN technology.

[0129] Compared with the prior art, the present invention proposes an intelligent vehicle signal routing method based on 5G+WLAN technology, which has the following advantages:

[0130] First, this scheme proposes a method for quantifying the network quality of in-vehicle applications. The current network status information of 5G and WLAN is calculated periodically. The network quality of in-vehicle applications under different in-vehicle networks is calculated based on the network resources required by different in-vehicle applications, the frequency of network delay, jitter, and packet loss rate deviation from communication parameter constraints, and the discrete change degree of signal strength. The dynamic network bandwidth weight is constructed based on the allocation weight of network bandwidth to in-vehicle applications, thereby constructing a multi-objective in-vehicle application network loss objective function with the goal of maximizing the dynamically weighted in-vehicle application network quality, realizing the network quality quantification method of in-vehicle applications in the 5G+WLAN network environment, and then solving the optimal in-vehicle network switching strategy to improve the network quality of in-vehicle applications, performing in-vehicle network switching for different in-vehicle applications, and realizing intelligent routing of in-vehicle applications.

[0131] At the same time, this scheme proposes a method for solving the objective function, which uses a Gaussian function to perform Gaussian mapping on the historical optimal position of the particle, and then adjusts the historical optimal position to improve the diversity of the particle position and expand the search space of the particle position to help the particle jump out of the local optimal solution. The mean of all particle positions in the same batch of particle positions that are better than the particle position to be iterated is used to form neighbor information to stimulate the particle position, further improve the diversity of the particle position, and thus solve a more effective optimal vehicle network switching strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0132] Figure 1 A flowchart of a vehicle signal intelligent routing method based on 5G+WLAN technology provided by an embodiment of the present invention;

[0133] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0134] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0135] The embodiment of the present application provides a method for intelligent routing of vehicle-mounted signals based on 5G+WLAN technology. The execution subject of the method for intelligent routing of vehicle-mounted signals based on 5G+WLAN technology includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for intelligent routing of vehicle-mounted signals based on 5G+WLAN technology can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0136] A vehicle-mounted signal intelligent routing method based on 5G+WLAN technology includes the following steps:

[0137] S1: Deploy a network monitoring module in the vehicle system to collect network status information of 5G and WLAN in real time, and use the sliding window technology to smooth the collected network status information to obtain smoothed network status information, where the network status information includes signal strength, delay, bandwidth, jitter and packet loss rate.

[0138] In step S1, a network monitoring module is deployed in the vehicle system to collect network status information of 5G and WLAN in real time, including:

[0139] A network monitoring module is deployed in the vehicle system, and the network status information of 5G and WLAN is collected in real time using the network monitoring module. The network status information includes signal strength, delay, bandwidth, jitter and packet loss rate. The collection and calculation process of network status information is as follows:

[0140] The signal strengths of 5G and WLAN in the car at N consecutive moments are calculated, where the signal strengths of 5G and WLAN in the car at the nth moment are :

[0141] ;

[0142] ;

[0143] in:

[0144] Indicates the signal strength of 5G in the car at the nth moment, represents the signal strength of the WLAN in the car at the nth moment, , the Nth moment is the real time;

[0145] Indicates the distance between the vehicle and the base station at the nth moment;

[0146] Indicates the carrier frequency of the wireless access point in the car;

[0147] The delays of 5G and WLAN in the car at N consecutive moments are calculated, where the delays of 5G and WLAN in the car at the nth moment are :

[0148] ;

[0149] ;

[0150] in:

[0151] represents the delay of 5G in the car at the nth moment;

[0152] represents the delay of the in-car WLAN at the nth moment;

[0153] Indicates the timestamp corresponding to the nth moment;

[0154] Indicates the data packet sending timestamp of the data packet received by the 5G in the car at the nth moment;

[0155] Indicates the data packet sending timestamp of the data packet received by the in-vehicle WLAN at the nth time;

[0156] The bandwidths of 5G and WLAN in the car at N consecutive moments are collected, where the bandwidths of 5G and WLAN in the car at the nth moment are ;

[0157] The jitters of 5G and WLAN in the car at N consecutive moments are calculated, where the jitters of 5G and WLAN in the car at the nth moment are :

[0158] ;

[0159] ;

[0160] in:

[0161] represents the jitter of 5G in the car at the nth moment; in the embodiment of the present invention, They are the preset minimum jitter for 5G and the minimum jitter for WLAN;

[0162] Indicates the jitter of the in-car WLAN at the nth moment;

[0163] The packet loss rates of 5G and WLAN in the car at N consecutive moments are collected, where the packet loss rates of 5G and WLAN in the car at the nth moment are ;

[0164] The network status information of 5G and WLAN collected in real time:

[0165] ;

[0166] ;

[0167] ;

[0168] ;

[0169] in:

[0170] Indicates the real-time collected in-car 5G network status information. Indicates the network status information of the in-vehicle WLAN collected in real time;

[0171] Indicates the network status of the 5G in the car at the nth moment, Indicates the network status of the in-car WLAN at the nth moment;

[0172] Use sliding window technology to collect network status information Perform smoothing processing to obtain smoothed network status information.

[0173] The network status information collected by using the sliding window technology Perform smoothing to obtain smoothed network status information, including:

[0174] S11: Set the smoothing coefficient ;

[0175] S12: Calculate and obtain network status information The initial smoothing term and the initial trend term of Network status information The initial smoothing term is Network status information The initial trend term of:

[0176] ;

[0177] ;

[0178] ;

[0179] S13: Iterate the initial smooth term and the initial trend term to obtain the smooth term and the trend term at N moments, where the initial smooth term The smoothing terms at the nth moment are , initial trend term The trend terms at the nth moment are :

[0180] ;

[0181] ;

[0182] ;

[0183] ;

[0184] ;

[0185] ;

[0186] in:

[0187] Represent the initial trend terms The trend coefficient to be iterated at the nth moment;

[0188] S14: Based on the smoothing terms and trend terms at N moments, the smoothed network states of 5G and WLAN at each moment are calculated, where the smoothed network state of 5G at the nth moment is , the smoothed network state of WLAN at the nth moment is ;

[0189] S15: Smoothed in-vehicle 5G network status information , and the network status information of the in-car WLAN .

[0190] S2: Constrain communication parameters for different vehicle-mounted applications and determine the value range of signal strength, delay, bandwidth, jitter, and packet loss rate for each vehicle-mounted application.

[0191] In step S2, communication parameter constraints are imposed on different vehicle-mounted applications, including:

[0192] Communication parameter constraints are imposed on different vehicle-mounted applications to determine the value range of signal strength, delay, bandwidth, jitter, and packet loss rate for each vehicle-mounted application. The communication parameter constraint set for M vehicle-mounted applications is:

[0193] ;

[0194] ;

[0195] in:

[0196] Indicates the communication parameter constraints of the mth in-vehicle application; in-vehicle applications include navigation systems, entertainment systems, voice assistants, communication systems, safety systems, remote diagnosis, autonomous driving systems, payment systems, etc.;

[0197] Indicates the parameter constraints of the mth vehicle-mounted application in terms of signal strength, delay, bandwidth, jitter, and packet loss rate; if the network resources obtained by the vehicle-mounted application are within the parameter constraints, it means that the vehicle-mounted application can operate normally;

[0198] represents the minimum and maximum signal strength of the mth vehicle-mounted application;

[0199] represents the minimum and maximum delay of the mth vehicle application respectively;

[0200] represents the minimum and maximum bandwidth of the mth vehicle application respectively;

[0201] represents the minimum and maximum jitter values ​​of the mth vehicle-mounted application respectively;

[0202] They represent the minimum and maximum packet loss rates of the m-th vehicle-mounted application respectively.

[0203] S3: Based on the smoothed network status information and the vehicle application communication parameter constraints, a multi-objective vehicle application network loss objective function is constructed.

[0204] In the step S3, a multi-objective vehicle application network loss objective function is constructed based on the smoothed network state information and the vehicle application communication parameter constraints, including:

[0205] Based on the smoothed network status information and the vehicle application communication parameter constraints, a multi-objective vehicle application network loss objective function is constructed. The multi-objective vehicle application network loss objective function takes the vehicle network selected by different vehicle applications as the independent variable and aims to maximize the dynamically weighted vehicle application network quality. The constructed multi-objective vehicle application network loss objective function is:

[0206] ;

[0207] ;

[0208] ;

[0209] ;

[0210] ;

[0211] ;

[0212] ;

[0213] in:

[0214] represents the multi-objective vehicle application network loss objective function;

[0215] For the vehicle network switching strategy, represents the vehicle network selected by M vehicle applications, This means that the mth in-vehicle application selects the 5G network. This means that the mth in-vehicle application selects the WLAN network;

[0216] represents the network quality of the mth in-vehicle application in the 5G network, Indicates the network quality of the mth in-vehicle application in the WLAN network;

[0217] Indicates the dynamic 5G network bandwidth weight of the mth vehicle application after the vehicle network is switched according to the vehicle network switching strategy;

[0218] Indicates the dynamic WLAN network bandwidth weight of the mth vehicle application after the vehicle network is switched according to the vehicle network switching strategy;

[0219] Indicates network status information In the example, delay, jitter and packet loss rate are all within the parameter constraints. The number of moments in the range;

[0220] Indicates network status information In the example, delay, jitter and packet loss rate are all within the parameter constraints. The number of moments in the range;

[0221] Indicates network status information The mean signal strength, Indicates network status information The mean signal intensity in

[0222] Indicates network status information The standard deviation of the signal intensity, Indicates network status information The standard deviation of the signal intensity in

[0223] represents an exponential function with a natural constant as base;

[0224] A control parameter representing signal strength;

[0225] Indicates the dynamic network bandwidth weight threshold;

[0226] Indicates network status information The mean bandwidth in Indicates network status information The average bandwidth.

[0227] S4: Use the improved particle swarm algorithm to optimize and solve the multi-objective vehicle application network loss objective function to obtain the optimal vehicle network switching strategy.

[0228] In the step S4, the improved particle swarm algorithm is used to optimize and solve the multi-objective vehicle application network loss objective function, including:

[0229] The improved particle swarm algorithm is used to optimize and solve the multi-objective vehicle application network loss objective function to obtain the optimal vehicle network switching strategy. The optimization solution process is as follows:

[0230] S41: Initialize and generate U groups of particles, where each group of particles includes particle position and particle velocity. The particle position is a binary sequence of length M, corresponding to the vehicle network switching strategy. The particle position of the uth group of particles generated by initialization is , the particle speed is ;

[0231] S42: Set the current iteration number of the particle to t, the initial value of t is 0, and the maximum value is Max. Then the tth iteration result of the uth group of particles is ;

[0232] S43: using the particle position as an independent variable of the multi-objective vehicle application network loss objective function, and using the multi-objective vehicle application network loss objective function value as the fitness value of the particle position;

[0233] S44: Select the particle position with the highest fitness value after the tth iteration as the optimal position of the tth iteration ; and update the historical optimal position and historical worst position of each particle, where the historical optimal position of the u-th particle is , the worst position in history is The best historical position of a particle is the iteration result with the highest fitness value among the t-times position iteration results; the worst historical position of a particle is the iteration result with the lowest fitness value among the t-times position iteration results;

[0234] S45: Iterate the particle velocity and particle position in combination with the neighbor information of each particle position;

[0235] S46: Order , return to step S43 until the maximum number of iterations is reached, and extract the historical optimal position of each particle, and select the historical optimal position with the highest fitness value among the U historical optimal positions as the optimal vehicle network switching strategy .

[0236] In the step S45, the particle velocity and particle position are iterated in combination with the neighbor information of each particle position, including:

[0237] S451: Gaussian mapping is performed on the historical optimal position of each particle, where the historical optimal position of the uth particle is The Gaussian mapping result is :

[0238] ;

[0239] ;

[0240] in:

[0241] represents the Gaussian mapping parameter of the u-th particle;

[0242] S452: Calculate the neighbor information of each particle position, where the particle position The neighbor information of :

[0243] ;

[0244] in:

[0245] It means that the fitness value ratio of the particle position in group U after t iterations is The average of all particle positions of the highest; in the embodiment of the present invention, the distance is calculated as the Euclidean distance;

[0246] Represents a random number between 0 and 1;

[0247] S453: Based on the Gaussian mapping result and the neighbor information, iterate the particle velocity and particle position, where the particle velocity The iteration formula is:

[0248] ;

[0249] in:

[0250] , is an iterative control parameter; in the embodiment of the present invention, set is 0.4, is 0.6;

[0251] Particle Position The iteration formula is: .

[0252] S5: Perform vehicle network switching for different vehicle applications according to the optimal vehicle network switching strategy obtained by solving.

[0253] In the step S5, the vehicle network switching for different vehicle applications is performed according to the optimal vehicle network switching strategy, including:

[0254] According to the optimal vehicle network switching strategy , switch the vehicle network for different vehicle applications, represents the optimal vehicle network switching strategy The vehicle network selected by the mth vehicle application in This means that the mth in-vehicle application selects the 5G network. It means that the mth in-vehicle application selects the WLAN network; and after a preset time range, the in-vehicle application network quality of each current in-vehicle application is calculated. If the number of in-vehicle applications whose in-vehicle application network quality is lower than the preset quality threshold is higher than 30%, then according to steps S1 to S4, the optimal in-vehicle network switching strategy is regenerated to perform in-vehicle network switching.

[0255] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0256] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0257] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0258] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A vehicle-borne signal intelligent routing method based on 5G+WLAN technology, characterized in that: The method comprises: S1: Deploy a network monitoring module in the vehicle system to collect 5G and WLAN network status information in real time, and use the sliding window technology to smooth the collected network status information to obtain smoothed network status information, where the network status information includes signal strength, delay, bandwidth, jitter and packet loss rate; Network status information includes signal strength, delay, bandwidth, jitter and packet loss rate. The collection and calculation process of network status information is as follows: The signal strengths of 5G and WLAN in the car at N consecutive moments are calculated, where the signal strengths of 5G and WLAN in the car at the nth moment are ; The delays of 5G and WLAN in the car at N consecutive moments are calculated, where the delays of 5G and WLAN in the car at the nth moment are ; The bandwidths of 5G and WLAN in the car at N consecutive moments are collected, where the bandwidths of 5G and WLAN in the car at the nth moment are ; The jitters of 5G and WLAN in the car at N consecutive moments are calculated, where the jitters of 5G and WLAN in the car at the nth moment are ; The packet loss rates of 5G and WLAN in the car at N consecutive moments are collected, where the packet loss rates of 5G and WLAN in the car at the nth moment are ; The network status information of 5G and WLAN collected in real time: ； ； ； ； in: Indicates the real-time collected in-car 5G network status information. Indicates the network status information of the in-vehicle WLAN collected in real time; Indicates the network status of the 5G in the car at the nth moment, Indicates the network status of the in-car WLAN at the nth moment; Use sliding window technology to collect network status information Perform smoothing processing to obtain smoothed network status information; S2: constrain communication parameters for different vehicle applications and determine the value range of signal strength, delay, bandwidth, jitter and packet loss rate for each vehicle application; The set of communication parameter constraints for M vehicle applications is: ； ； in: represents the communication parameter constraints of the mth vehicle application; represents the parameter constraints of the mth vehicle application in terms of signal strength, delay, bandwidth, jitter and packet loss rate; represents the minimum and maximum signal strength of the mth vehicle-mounted application; represents the minimum and maximum delay of the mth vehicle application respectively; represents the minimum and maximum bandwidth of the mth vehicle application respectively; represents the minimum and maximum jitter values ​​of the mth vehicle-mounted application respectively; represents the minimum and maximum packet loss rate of the m-th vehicle application respectively; S3: Based on the smoothed network state information and the vehicle application communication parameter constraints, a multi-objective vehicle application network loss objective function is constructed; The multi-objective vehicle application network loss objective function takes the vehicle network selected by different vehicle applications as the independent variable and takes maximizing the dynamically weighted vehicle application network quality as the goal. The constructed multi-objective vehicle application network loss objective function is: ； ； ； ； ； ； ； in: represents the multi-objective vehicle application network loss objective function; For the vehicle network switching strategy, represents the vehicle network selected by M vehicle applications, This means that the mth in-vehicle application selects the 5G network. This means that the mth in-vehicle application selects the WLAN network; represents the network quality of the mth in-vehicle application in the 5G network, Indicates the network quality of the mth in-vehicle application in the WLAN network; Indicates the dynamic 5G network bandwidth weight of the mth vehicle application after the vehicle network is switched according to the vehicle network switching strategy; Indicates the dynamic WLAN network bandwidth weight of the mth vehicle application after the vehicle network is switched according to the vehicle network switching strategy; Indicates network status information In the example, delay, jitter and packet loss rate are all within the parameter constraints. The number of moments in the range; Indicates network status information In the example, delay, jitter and packet loss rate are all within the parameter constraints. The number of moments in the range; Indicates network status information The mean signal strength, Indicates network status information The mean signal intensity in Indicates network status information The standard deviation of the signal intensity, Indicates network status information The standard deviation of the signal intensity in represents an exponential function with a natural constant as base; A control parameter representing signal strength; Indicates the dynamic network bandwidth weight threshold; Indicates network status information The mean bandwidth in Indicates network status information The mean value of the bandwidth; S4: Use the improved particle swarm algorithm to optimize and solve the multi-objective vehicle application network loss objective function to obtain the optimal vehicle network switching strategy; S5: Perform vehicle network switching for different vehicle applications according to the optimal vehicle network switching strategy obtained by solving.

2. The method for intelligent vehicle signal routing based on 5G+WLAN technology according to claim 1, characterized in that: The network status information collected by using the sliding window technology Perform smoothing to obtain smoothed network status information, including: S11: Set the smoothing coefficient ; S12: Calculate and obtain network status information The initial smoothing term and the initial trend term of Network status information The initial smoothing term is Network status information The initial trend term of S13: Combined smoothing coefficient The initial smooth term and the initial trend term are iterated to obtain the smooth term and the trend term at N moments, where the initial smooth term The smoothing terms at the nth moment are , initial trend term The trend terms at the nth moment are ; S14: Based on the smoothing terms and trend terms at N moments, the smoothed network states of 5G and WLAN at each moment are calculated, where the smoothed network state of 5G at the nth moment is , the smoothed network state of WLAN at the nth moment is ; S15: Smoothed in-vehicle 5G network status information , and the network status information of the in-car WLAN .

3. The method for intelligent vehicle signal routing based on 5G+WLAN technology as claimed in claim 1, characterized in that: In the step S4, the improved particle swarm algorithm is used to optimize and solve the multi-objective vehicle application network loss objective function, including: The improved particle swarm algorithm is used to optimize and solve the multi-objective vehicle application network loss objective function to obtain the optimal vehicle network switching strategy. The optimization solution process is as follows: S41: Initialize and generate U groups of particles, where each group of particles includes particle position and particle velocity. The particle position is a binary sequence of length M, corresponding to the vehicle network switching strategy. The particle position of the uth group of particles generated by initialization is , the particle speed is ; S42: Set the current iteration number of the particle to t, the initial value of t is 0, and the maximum value is Max. Then the tth iteration result of the uth group of particles is ; S43: using the particle position as an independent variable of the multi-objective vehicle application network loss objective function, and using the multi-objective vehicle application network loss objective function value as the fitness value of the particle position; S44: Select the particle position with the highest fitness value after the tth iteration as the optimal position of the tth iteration ; and update the historical optimal position and historical worst position of each particle, where the historical optimal position of the u-th particle is , the worst position in history is The best historical position of a particle is the iteration result with the highest fitness value among the t-times position iteration results; the worst historical position of a particle is the iteration result with the lowest fitness value among the t-times position iteration results; S45: Iterate the particle velocity and particle position in combination with the neighbor information of each particle position; S46: Order , return to step S43 until the maximum number of iterations is reached, and extract the historical optimal position of each particle, and select the historical optimal position with the highest fitness value among the U historical optimal positions as the optimal vehicle network switching strategy .

4. The method for intelligent vehicle signal routing based on 5G+WLAN technology as claimed in claim 3, characterized in that: In the step S45, the particle velocity and particle position are iterated in combination with the neighbor information of each particle position, including: S451: Gaussian mapping is performed on the historical optimal position of each particle, where the historical optimal position of the uth particle is The Gaussian mapping result is ; S452: Calculate the neighbor information of each particle position, where the particle position The neighbor information of ; S453: Iterate the particle velocity and particle position based on the Gaussian mapping result and neighbor information.

5. The method for intelligent vehicle signal routing based on 5G+WLAN technology according to claim 1, characterized in that: In step S5, the vehicle network switching for different vehicle applications is performed according to the optimal vehicle network switching strategy, including: According to the optimal vehicle network switching strategy , switch the vehicle network for different vehicle applications, represents the optimal vehicle network switching strategy The vehicle network selected by the mth vehicle application in This means that the mth in-vehicle application selects the 5G network. It means that the mth in-vehicle application selects the WLAN network; and after a preset time range, the in-vehicle application network quality of each current in-vehicle application is calculated. If the number of in-vehicle applications whose in-vehicle application network quality is lower than the preset quality threshold is higher than 30%, then according to steps S1 to S4, the optimal in-vehicle network switching strategy is regenerated to perform in-vehicle network switching.

Images