Communication resource scheduling method and system for wireless communication network

Abstract

The invention discloses a communication resource scheduling method and system for a wireless communication network, relates to the technical field of automatic driving, and ensures efficient communication of an automatic driving vehicle by monitoring and optimizing communication resources in real time. The method comprises the following steps: firstly, pre-dividing a communication network area and establishing a data set, and collecting network area data in real time; and then, monitoring the communication efficiency of each network area based on the data set, calculating and comparing the communication efficiency with a standard threshold value, and if the communication efficiency is not qualified, triggering an optimization strategy. And then, according to the load difference and the congestion risk, adjusting or rescheduling the unqualified area, sending an early warning instruction, and optimizing resource configuration. For optimization of conflict points, an automatic driving network model is established to simulate a communication path so as to adjust a communication resource allocation strategy in real time.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a communication resource scheduling method and system for a wireless communication network. Background Art

[0002] With the acceleration of urbanization, the application of autonomous driving technology in urban transportation is increasing, and autonomous driving vehicles are becoming more and more dependent on wireless communication networks. However, with the increase in traffic volume, traditional communication networks often cannot meet the real-time and stability requirements of autonomous driving systems when facing dynamically changing needs.

[0003] Currently, existing wireless communication resource scheduling methods mostly rely on static planning or simple load balancing, which often perform poorly in complex autonomous driving scenarios. Fluctuations in communication resource demand may lead to network congestion, communication delays and unbalanced resource allocation, thus affecting the performance and safety of the autonomous driving system.

[0004] Therefore, a dynamic and intelligent communication resource scheduling method is needed, which can monitor and optimize the communication path and resource allocation in real time. By comprehensively considering the coordinated scheduling of on-board computing, edge computing and network resources, the present invention provides a communication resource scheduling method based on real-time monitoring, data analysis and optimization to improve the utilization efficiency of network resources and ensure the stable operation of the autonomous driving system in complex environments. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a communication resource scheduling method and system for a wireless communication network to solve the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A communication resource scheduling method for a wireless communication network, comprising the following steps:

[0007] S1. Obtain the communication network area of ​​the autonomous driving path in advance, divide the communication network area into several network areas, conduct real-time monitoring, collect data from the network areas in real time and establish a data set;

[0008] S2. Based on the data set data, monitor the communication resource efficiency of the i-th network area and calculate the communication efficiency coefficient Txxs of the i-th network area i , and compare and analyze it with the first standard threshold, and after evaluation, issue the first warning instruction to the network area with unqualified communication efficiency and implement optimization strategy;

[0009] S3. When the first warning instruction is received, the network load difference of the network area with unqualified communication efficiency is optimized according to the data set data, and the network load difference coefficient R of the i-th network area is calculated. ci and compare and analyze it with the second standard threshold. After evaluation, adjust and optimize the communication resources in the first-level congestion risk network area; reschedule the communication resources in the second-level congestion risk network area, and issue a third warning instruction;

[0010] S4. When the third warning instruction is received, the conflict point of the rescheduled ith network area is monitored according to the data set data, and the optimized conflict coefficient Yhxs of the ith network area is calculated. i , and compare and analyze it with the third standard threshold, and after evaluation, optimize and adjust the resources of the i-th network area in the state of unbalanced communication resource allocation;

[0011] S5. By building an autonomous driving network model, a target communication path is established in the model to simulate autonomous driving, and the communication efficiency coefficient Txxs of the i-th network area is used. i , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area i The output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

[0012] Preferably, S1 comprises:

[0013] S11. Obtain the communication network area of ​​the autonomous driving path in advance, divide the communication network area into several network areas, and mark the several network areas on the distribution map as: Jcq 1 、Jcq 2 、...、Jcq n ; n represents the number of network areas for real-time monitoring;

[0014] S12, by installing wireless signal monitors in base stations within the network area, real-time collection of the load value L of the wireless communication resources in the network area load , the communication resource flow value W of the network area, the flow consumption value B of the conflict point, the load value L of the conflict point and the flow value G of the congested node in the network area; by installing computing resource monitoring sensors at the edge of the network area, the load value E of the edge computing resources of the network area is collected in real time load ; By installing an on-board computing monitor in the autonomous vehicle, the load value C of the on-board computing resources is collected in real time load; By installing delay monitoring sensors in the network area, the delay duration D of the conflict point is collected in real time and a data set is established.

[0015] Preferably, step S2 comprises:

[0016] S21. Based on the data set data, monitor the communication resource efficiency of the ith network area, and after dimensionless processing, calculate and obtain the communication efficiency coefficient Txxs of the ith network area i , the formula is as follows:

[0017]

[0018] Where n represents the total number of network regions. represents the load value of the wireless communication resources in the ith network area, represents the load value of the vehicle computing resources, E loadi It represents the load value of the edge computing resources in the i-th network area, α represents the impact coefficient of the on-board computing resources, obtained through experiments, 0.1<α<0.5, β represents the compensation coefficient of the edge computing resources, obtained through experiments, 0.05<β<0.2.

[0019] Preferably, step S2 further includes:

[0020] S22, by presetting the first standard threshold Q1 in advance, and setting the communication efficiency coefficient Txxs of the i-th network area i Compare and analyze with the first standard threshold Q1 to obtain a first evaluation result, including:

[0021] When the communication efficiency coefficient Txxs of the i-th network area i When ≥ the first standard threshold Q1, it means that the i-th network area is a network area with qualified communication efficiency, and no adjustment is required, and continuous monitoring is required;

[0022] When the communication efficiency coefficient Txxs of the i-th network area i When < the first standard threshold Q1, it indicates that the ith network area is a network area with unqualified communication efficiency, triggering the first early warning instruction, generating the first strategy, and optimizing the network load difference of the ith network area.

[0023] Preferably, step S3 includes:

[0024] S31. When the first warning instruction is received, the network load difference of the ith network area is optimized according to the data set data, and after dimensionless processing, the network load difference coefficient R of the ith network area is calculated. ci , the formula is as follows:

[0025]

[0026] Where, L max Indicates the maximum network load value, L min Indicates the minimum network load value, W i Indicates the communication resource flow value of the ith network area, Txxs i represents the communication efficiency coefficient of the ith network area, G i Represents the flow value of the congested node in the i-th network area.

[0027] Preferably, step S3 further includes:

[0028] S32, by setting the second standard threshold Q2 in advance and setting the network load difference coefficient R ci Compare and analyze with the first standard threshold value Q2 to obtain a first evaluation result, including:

[0029] When the network load difference coefficient R ci When the value is less than the second standard threshold Q2, it means that the communication resource load of the ith network area has no congestion risk and no adjustment is required, and continuous monitoring is required;

[0030] When the second standard threshold Q2 ≥ the network load difference coefficient R of the i-th network area ci When the second standard threshold Q2*150% is reached, it indicates that the communication resource load of the ith network area is at the first level of congestion risk, triggering the second warning instruction and generating the second strategy including: increasing the communication resource flow value of the ith network area by 10%-15%, increasing the communication resource flow value of the congested node in the ith network area by 5%-8%, and recalculating until the network load difference coefficient R of the ith network area is reached. ci Until the second standard threshold Q2;

[0031] When the network load difference coefficient R ci When ≥ the second standard threshold Q2*150%, it indicates that the communication resource load of the ith network area is at a level 2 congestion risk, triggering the third warning instruction, generating a third strategy, and rescheduling the communication resources of the ith network area at a level 2 congestion risk.

[0032] Preferably, step S4 comprises:

[0033] S41. When the third warning instruction is received, the conflict point of the rescheduled ith network area is monitored according to the data set data, and after dimensionless processing, the optimized conflict coefficient Yhxs of the ith network area is calculated. i , the formula is as follows:

[0034]

[0035] Where n represents the total number of network areas, m represents the total number of conflict points in the ith network area, and B i,j represents the traffic consumption value of the jth conflict point in the ith network area, B max Indicates the maximum flow value at the conflict point, D i,j represents the delay time of the jth conflict point in the ith network area, D max Indicates the maximum tolerable delay time of the conflict point, L i,j represents the load value of the jth conflict point in the ith network area, L max Indicates the maximum load value of the network, w1, w2 and w3 indicate weight coefficients.

[0036] Preferably, step S4 further includes:

[0037] S42, by presetting the third standard threshold Q3 in advance, and optimizing the conflict coefficient Yhxs of the i-th network area i Compare and analyze with the third standard threshold value Q3 to obtain a third evaluation result, including:

[0038] When the i-th network area optimizes the conflict coefficient Yhxs i When ≥ the third standard threshold Q3, it means that the communication resource allocation of the ith network area is qualified and in a balanced state, no adjustment is made and continuous monitoring is performed;

[0039] When the i-th network area optimizes the conflict coefficient Yhxs i When the value is less than the third standard threshold Q3, it indicates that the communication resource allocation of the ith network area is unqualified and unbalanced, triggering the second warning instruction and generating the fourth strategy including: reducing the traffic consumption value of the conflict point of the ith network area by 8%-10%, reducing the delay time of the conflict point of the ith network area by 10%-15%, increasing the load value of the conflict point of the ith network area by 10%-20%, and recalculating until the conflict coefficient Yhxs of the ith network area is optimized i ≥ the third standard threshold Q3.

[0040] Preferably, step S5 includes:

[0041] S51, by establishing an autonomous driving network model, establishing a target communication path in the model to simulate autonomous driving, and using the communication efficiency coefficient Txxs of the i-th network area i , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area iThe output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

[0042] Preferably, a communication resource scheduling system for a wireless communication network comprises a communication resource scheduling method for a wireless communication network as described in any one of claims 1 to 9, comprising:

[0043] A partitioning unit, used to obtain the communication resource adjustment network area of ​​the autonomous driving path in advance, divide the communication resource adjustment network area into several network areas, and perform real-time monitoring;

[0044] A collection unit, used to collect data in the network area in real time and establish a data set;

[0045] The first calculation unit is used to monitor the communication resource efficiency of the i-th network area according to the data set data, and calculate and obtain the communication efficiency coefficient Txxs of the i-th network area i ;

[0046] The second calculation unit is used to optimize the network load difference of the network area with unqualified communication efficiency according to the data set data, and calculate the network load difference coefficient R of the i-th network area. ci ;

[0047] The third calculation unit is used to monitor the conflict point of the rescheduled i-th network area according to the data set data, and calculate and obtain the optimized conflict coefficient Yhxs of the i-th network area i ;

[0048] The first evaluation unit is used to analyze and determine whether the communication resource efficiency of the i-th network area is qualified, and issue a first warning instruction to the network area with unqualified communication efficiency and perform an optimization strategy;

[0049] The second evaluation unit is used to analyze and determine whether the network in the network area with unqualified communication efficiency has a congestion risk, adjust and optimize the communication resources in the network area with the first-level congestion risk, reschedule the communication resources in the network area with the second-level congestion risk, and issue a third warning instruction;

[0050] The third evaluation unit is used to analyze and determine whether the i-th network area is in a balanced state after rescheduling, and to optimize and adjust the resources for the network area where the communication resources are allocated in an unbalanced state;

[0051] Establish a model unit for establishing an autonomous driving network model, establish a target communication path in the model to simulate autonomous driving, and use the communication efficiency coefficient Txxs of the i-th network areai , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area i The output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

[0052] The present invention provides a communication resource scheduling method and system for a wireless communication network, which has the following beneficial effects:

[0053] (1) A communication resource scheduling method and system for a wireless communication network, by real-time monitoring of the communication resource data of a network area and calculating the communication efficiency coefficient of the network area, effectively avoids excessively uniform distribution or excessive concentration of resources, ensures that the communication resources and delays of the wireless communication network are optimally utilized, and thus effectively improves the communication efficiency of the autonomous driving system.

[0054] (2) A communication resource scheduling method and system for a wireless communication network, which identifies and alleviates primary and secondary congestion risks by optimizing and adjusting network load differences in real time, avoids communication delays and packet loss caused by network congestion, and thus ensures the real-time response and stability of autonomous driving vehicles.

[0055] (3) A communication resource scheduling method and system for a wireless communication network improves the balance of communication resource allocation in the network area by calculating the optimized conflict coefficient of the network area, enhances the stability of the system under complex and high-load conditions, and ensures the security and reliability of the communication process.

[0056] (4) A communication resource scheduling method and system for wireless communication networks makes communication resource scheduling more intelligent and automated through real-time data analysis and training based on an autonomous driving network model, dynamically adjusts resource allocation according to communication efficiency, network load differences, and optimization conflict factors, and optimizes the communication demand prediction and response strategy of autonomous driving vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A schematic diagram of the steps of a communication resource scheduling method for a wireless communication network according to the present invention;

[0058] Figure 2 The present invention is a block diagram of a communication resource scheduling system for a wireless communication network. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] Example 1

[0061] See also Figure 1 The present invention provides a communication resource scheduling method for a wireless communication network, comprising the following steps:

[0062] S1. Obtain the communication network area of ​​the autonomous driving path in advance, divide the communication network area into several network areas, conduct real-time monitoring, collect data from the network areas in real time and establish a data set;

[0063] S2. Based on the data set data, monitor the communication resource efficiency of the i-th network area and calculate the communication efficiency coefficient Txxs of the i-th network area i , and compare and analyze it with the first standard threshold, and after evaluation, issue the first warning instruction to the network area with unqualified communication efficiency and implement optimization strategy;

[0064] S3. When the first warning instruction is received, the network load difference of the network area with unqualified communication efficiency is optimized according to the data set data, and the network load difference coefficient R of the i-th network area is calculated. ci and compare and analyze it with the second standard threshold. After evaluation, adjust and optimize the communication resources in the first-level congestion risk network area; reschedule the communication resources in the second-level congestion risk network area, and issue a third warning instruction;

[0065] S4. When the third warning instruction is received, the conflict point of the rescheduled ith network area is monitored according to the data set data, and the optimized conflict coefficient Yhxs of the ith network area is calculated. i , and compare and analyze it with the third standard threshold, and after evaluation, optimize and adjust the resources of the i-th network area in the state of unbalanced communication resource allocation;

[0066] S5. By building an autonomous driving network model, a target communication path is established in the model to simulate autonomous driving, and the communication efficiency coefficient Txxs of the i-th network area is used. i , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area iThe output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

[0067] In this embodiment, the communication network area is divided into several network areas for real-time monitoring, data of the network area is collected in real time and a data set is established, and the communication efficiency coefficient of the network area is calculated, so as to effectively avoid excessive uniform distribution or excessive concentration of resources, thereby effectively improving the communication efficiency of the autonomous driving system; by optimizing and adjusting the network load difference in real time, the risks of primary and secondary congestion are identified and alleviated, and communication delays and packet loss caused by network congestion are avoided, thereby ensuring the real-time response and stability of the autonomous driving vehicle; by calculating the network area optimization conflict coefficient, the balance of communication resource allocation in the network area is improved, the stability of the system under complex and high-load conditions is enhanced, and the security and reliability of the communication process are ensured; through real-time data analysis and training based on the autonomous driving network model, the communication resource scheduling is made more intelligent and automated, and the resource allocation is dynamically adjusted according to the communication efficiency, network load difference and optimization conflict factors, so as to optimize the communication demand prediction and response strategy of the autonomous driving vehicle.

[0068] Example 2

[0069] This embodiment is an explanation of the embodiment 1. Specifically, S1 includes:

[0070] S11. Obtain the communication network area of ​​the autonomous driving path in advance, divide the communication network area into several network areas, and mark the several network areas on the distribution map as: Jcq 1 、Jcq 2 、...、Jcq n ; n represents the number of network areas for real-time monitoring;

[0071] S12, by installing wireless signal monitors in base stations within the network area, real-time collection of the load value L of the wireless communication resources in the network area load , the communication resource flow value W of the network area, the flow consumption value B of the conflict point, the load value L of the conflict point and the flow value G of the congested node in the network area; by installing computing resource monitoring sensors at the edge of the network area, the load value E of the edge computing resources of the network area is collected in real time load ; By installing an on-board computing monitor in the autonomous vehicle, the load value C of the on-board computing resources is collected in real time load ; By installing delay monitoring sensors in the network area, the delay duration D of the conflict point is collected in real time and a data set is established.

[0072] In this embodiment, by deploying wireless signal monitors, computing resource monitoring sensors and delay monitoring sensors in the communication network area, it is possible to collect and monitor the load and flow data of various resources in real time. The real-time collection and monitoring of this data can provide accurate basic data and calculation basis for network resource optimization.

[0073] Example 3

[0074] This embodiment is an explanation of the embodiment 2. Specifically, step S2 includes:

[0075] S21. Based on the data set data, monitor the communication resource efficiency of the ith network area, and after dimensionless processing, calculate and obtain the communication efficiency coefficient Txxs of the ith network area i , the formula is as follows:

[0076]

[0077] Where n represents the total number of network regions. represents the load value of the wireless communication resources in the ith network area, represents the load value of the vehicle computing resources, E loadi It represents the load value of the edge computing resources in the i-th network area, α represents the impact coefficient of the on-board computing resources, obtained through experiments, 0.1<α<0.5, β represents the compensation coefficient of the edge computing resources, obtained through experiments, 0.05<β<0.2.

[0078] In this embodiment, by monitoring the communication resource efficiency of the i-th network area and calculating the communication efficiency coefficient, the load of wireless communication resources, vehicle computing resources and edge computing resources can be comprehensively considered, thereby accurately evaluating the communication efficiency of the network area. This method uses dimensionless processing and experimentally obtained influence coefficients to make the evaluation of communication efficiency more standardized and objective, providing a reliable basis for subsequent network load optimization and resource scheduling.

[0079] Example 4

[0080] This embodiment is explained in Embodiment 3. Specifically, step S2 further includes:

[0081] S22, by presetting the first standard threshold Q1 in advance, and setting the communication efficiency coefficient Txxs of the i-th network area i Compare and analyze with the first standard threshold Q1 to obtain a first evaluation result, including:

[0082] When the communication efficiency coefficient Txxs of the i-th network area i When ≥ the first standard threshold Q1, it means that the i-th network area is a network area with qualified communication efficiency, and no adjustment is required, and continuous monitoring is required;

[0083] When the communication efficiency coefficient Txxs of the i-th network area i When < the first standard threshold Q1, it indicates that the ith network area is a network area with unqualified communication efficiency, triggering the first early warning instruction, generating the first strategy, and optimizing the network load difference of the ith network area.

[0084] In this embodiment, by comparing and analyzing with the preset first standard threshold value Q1, the communication efficiency of the i-th network area can be effectively evaluated. If the communication efficiency is unqualified, the system can trigger an early warning and generate an optimization strategy in time to adjust the network load difference, thereby avoiding the waste of communication resources and network congestion. This mechanism ensures the communication stability of the autonomous driving system in complex environments, and can dynamically optimize the allocation of communication resources to improve the overall performance and real-time response capabilities of the network.

[0085] Example 5

[0086] This embodiment is an explanation of the embodiment 4. Specifically, step S3 includes:

[0087] S31. When the first warning instruction is received, the network load difference of the ith network area is optimized according to the data set data, and after dimensionless processing, the network load difference coefficient R of the ith network area is calculated. ci , the formula is as follows:

[0088]

[0089] Where, L max Indicates the maximum network load value, L min Indicates the minimum network load value, W i Indicates the communication resource flow value of the ith network area, Txxs i represents the communication efficiency coefficient of the ith network area, G i Represents the flow value of the congested node in the i-th network area.

[0090] In this embodiment, by calculating and optimizing the network load difference coefficient, the load status of the i-th network area can be accurately evaluated and adjusted to ensure a more balanced allocation of network resources. When the network load difference coefficient is too large, the system can adjust the communication resource flow in time, reduce the traffic burden of congested nodes, and optimize network load distribution. This process can not only effectively reduce network bottlenecks and improve communication efficiency, but also improve the response speed and stability of the autonomous driving system, ensuring efficient operation in complex environments.

[0091] Example 6

[0092] This embodiment is explained in Embodiment 5. Specifically, step S3 further includes:

[0093] S32, by setting the second standard threshold Q2 in advance and setting the network load difference coefficient R ci Compare and analyze with the first standard threshold value Q2 to obtain a first evaluation result, including:

[0094] When the network load difference coefficient R ci When the value is less than the second standard threshold Q2, it means that the communication resource load of the ith network area has no congestion risk and no adjustment is required, and continuous monitoring is required;

[0095] When the second standard threshold Q2 ≥ the network load difference coefficient R of the i-th network area ci When the second standard threshold Q2*150% is reached, it indicates that the communication resource load of the ith network area is at the first level of congestion risk, triggering the second warning instruction and generating the second strategy including: increasing the communication resource flow value of the ith network area by 10%-15%, increasing the communication resource flow value of the congested node in the ith network area by 5%-8%, and recalculating until the network load difference coefficient R of the ith network area is reached. ci Until the second standard threshold Q2;

[0096] When the network load difference coefficient R ci When ≥ the second standard threshold Q2*150%, it indicates that the communication resource load of the ith network area is at a level 2 congestion risk, triggering the third warning instruction, generating a third strategy, and rescheduling the communication resources of the ith network area at a level 2 congestion risk.

[0097] In this embodiment, by introducing the second standard threshold Q2 and accurately evaluating the network load difference coefficient, network congestion risks at different levels can be effectively identified and classified. When a primary or secondary congestion risk is found, the system can automatically trigger an early warning and take corresponding optimization strategies, such as adjusting the flow of communication resources and rescheduling resources to ensure the stability and efficient operation of the communication network. This method can respond to potential congestion problems in advance and avoid excessive load on communication resources.

[0098] Example 7

[0099] This embodiment is explained in Embodiment 6. Specifically, step S4 includes:

[0100] S41. When the third warning instruction is received, the conflict point of the rescheduled ith network area is monitored according to the data set data, and after dimensionless processing, the optimized conflict coefficient Yhxs of the ith network area is calculated. i , the formula is as follows:

[0101]

[0102] Where n represents the total number of network areas, m represents the total number of conflict points in the ith network area, and B i,j represents the traffic consumption value of the jth conflict point in the ith network area, B max Indicates the maximum flow value at the conflict point, D i,j represents the delay time of the jth conflict point in the ith network area, D max Indicates the maximum tolerable delay time of the conflict point, L i,j represents the load value of the jth conflict point in the ith network area, L max Indicates the maximum load value of the network, w1, w2 and w3 indicate weight coefficients.

[0103] In this embodiment, by calculating the optimized conflict coefficient and monitoring the conflict points in real time, this method can accurately identify and quantify potential bottlenecks and resource conflicts in the communication network. The traffic consumption, delay duration and load value of the conflict points are dimensionlessly processed, so that the optimization strategy can adapt to different network environments more flexibly. This technology can timely discover and optimize unbalanced resource allocation, reduce the impact of network conflicts, ensure communication quality and network stability, and improve the overall system's responsiveness and resource utilization efficiency.

[0104] Example 8

[0105] This embodiment is explained in Embodiment 7. Specifically, step S4 further includes:

[0106] S42, by presetting the third standard threshold Q3 in advance, and optimizing the conflict coefficient Yhxs of the i-th network area i Compare and analyze with the third standard threshold value Q3 to obtain a third evaluation result, including:

[0107] When the i-th network area optimizes the conflict coefficient Yhxs i When ≥ the third standard threshold Q3, it means that the communication resource allocation of the ith network area is qualified and in a balanced state, no adjustment is made and continuous monitoring is performed;

[0108] When the i-th network area optimizes the conflict coefficient Yhxs i When the value is less than the third standard threshold Q3, it indicates that the communication resource allocation of the ith network area is unqualified and unbalanced, triggering the second warning instruction and generating the fourth strategy including: reducing the traffic consumption value of the conflict point of the ith network area by 8%-10%, reducing the delay time of the conflict point of the ith network area by 10%-15%, increasing the load value of the conflict point of the ith network area by 10%-20%, and recalculating until the conflict coefficient Yhxs of the ith network area is optimized i≥ the third standard threshold Q3.

[0109] In this embodiment, by comparing and analyzing the optimized conflict coefficient with the third standard threshold value Q3, this method can achieve fine adjustment of communication resource allocation. When it is found that the resource allocation is unbalanced, the system can trigger an early warning in time and automatically generate an adjustment strategy to accurately optimize the traffic consumption, delay duration and load value of the conflict point to achieve the best balance of network load. This technology helps to reduce communication delays and resource waste, improve the efficiency of network resource utilization, and ensure that the network always maintains efficient and stable operation in a dynamically changing environment, thereby improving the communication quality and response speed of the autonomous driving system.

[0110] Example 9

[0111] This embodiment is explained in Embodiment 8. Specifically, step S5 includes:

[0112] S51, by establishing an autonomous driving network model, establishing a target communication path in the model to simulate autonomous driving, and using the communication efficiency coefficient Txxs of the i-th network area i , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area i The output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

[0113] In this embodiment, by establishing an autonomous driving network model and adjusting the communication path and resource allocation strategy in real time, this method can intelligently identify and predict the communication needs of autonomous driving vehicles based on key indicators such as the communication efficiency of the i-th network area, network load differences, and optimized conflict coefficients. This technology accurately predicts the scheduling needs of communication resources through dynamic training and testing models, thereby achieving optimal scheduling of communication paths and resource allocation for autonomous driving systems. This not only improves the utilization efficiency of network resources, but also ensures that autonomous driving vehicles can exchange data stably and quickly in complex communication environments, thereby improving the safety and real-time response capabilities of autonomous driving systems.

[0114] Example 10

[0115] A communication resource scheduling system for a wireless communication network, see Figure 2 ,include:

[0116] A partitioning unit, used to obtain the communication resource adjustment network area of ​​the autonomous driving path in advance, divide the communication resource adjustment network area into several network areas, and perform real-time monitoring;

[0117] A collection unit, used to collect data in the network area in real time and establish a data set;

[0118] The first calculation unit is used to monitor the communication resource efficiency of the i-th network area according to the data set data, and calculate and obtain the communication efficiency coefficient Txxs of the i-th network area i ;

[0119] The second calculation unit is used to optimize the network load difference of the network area with unqualified communication efficiency according to the data set data, and calculate the network load difference coefficient R of the i-th network area. ci ;

[0120] The third calculation unit is used to monitor the conflict point of the rescheduled i-th network area according to the data set data, and calculate and obtain the optimized conflict coefficient Yhxs of the i-th network area i ;

[0121] The first evaluation unit is used to analyze and determine whether the communication resource efficiency of the i-th network area is qualified, and issue a first warning instruction to the network area with unqualified communication efficiency and perform an optimization strategy;

[0122] The second evaluation unit is used to analyze and determine whether the network in the network area with unqualified communication efficiency has a congestion risk, adjust and optimize the communication resources in the network area with the first-level congestion risk, reschedule the communication resources in the network area with the second-level congestion risk, and issue a third warning instruction;

[0123] The third evaluation unit is used to analyze and determine whether the i-th network area is in a balanced state after rescheduling, and to optimize and adjust the resources for the network area where the communication resources are allocated in an unbalanced state;

[0124] Establish a model unit for establishing an autonomous driving network model, establish a target communication path in the model to simulate autonomous driving, and use the communication efficiency coefficient Txxs of the i-th network area i , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area i The output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

[0125] In this embodiment, the communication resource network area of ​​the autonomous driving path is accurately divided and monitored in real time through various units, the data of the network area is collected in real time and a data set is established, and the communication efficiency coefficient of the network area is calculated, so as to effectively avoid excessive uniform distribution or excessive concentration of resources, thereby effectively improving the communication efficiency of the autonomous driving system; by optimizing and adjusting the network load difference in real time, the risks of primary and secondary congestion are identified and alleviated, and communication delays and packet loss caused by network congestion are avoided, thereby ensuring the real-time response and stability of the autonomous driving vehicle; by calculating the optimization conflict coefficient of the network area, the balance of communication resource allocation in the network area is improved, the stability of the system under complex and high-load conditions is enhanced, and the safety and reliability of the communication process are ensured; through real-time data analysis and training based on the autonomous driving network model, the communication resource scheduling is made more intelligent and automated, and the resource allocation is dynamically adjusted according to the communication efficiency, network load difference and optimization conflict factors, so as to optimize the communication demand prediction and response strategy of the autonomous driving vehicle.

[0126] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0127] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. A communication resource scheduling method for a wireless communication network, characterized in that: The following steps are involved: S1. Obtain the communication network area of ​​the autonomous driving path in advance, divide the communication network area into several network areas, conduct real-time monitoring, collect data from the network areas in real time and establish a data set; S2. Based on the data set data, monitor the communication resource efficiency of the i-th network area and calculate the communication efficiency coefficient Txxs of the i-th network area i , and compare and analyze it with the first standard threshold, and after evaluation, issue the first warning instruction to the network area with unqualified communication efficiency and implement optimization strategy; S3. When the first warning instruction is received, the network load difference of the network area with unqualified communication efficiency is optimized according to the data set data, and the network load difference coefficient R of the i-th network area is calculated. ci , and compare and analyze it with the second standard threshold, and adjust and optimize the communication resources in the first-level congestion risk network area after evaluation; Re-schedule the communication resources in the secondary congestion risk network area and issue a third warning instruction; S4. When the third warning instruction is received, the conflict point of the rescheduled ith network area is monitored according to the data set data, and the optimized conflict coefficient Yhxs of the ith network area is calculated. i , and compare and analyze it with the third standard threshold, and after evaluation, optimize and adjust the resources of the i-th network area in the state of unbalanced communication resource allocation; S5. By building an autonomous driving network model, a target communication path is established in the model to simulate autonomous driving, and the communication efficiency coefficient Txxs of the i-th network area is used. i , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area i The output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

2. A communication resource scheduling method for a wireless communication network according to claim 1, characterized in that: S1 includes: S11. Obtain the communication network area of ​​the autonomous driving path in advance, divide the communication network area into several network areas, and mark the several network areas on the distribution map as: Jcq1, Jcq2, ..., Jcq n ; n represents the number of network areas for real-time monitoring; S12, by installing wireless signal monitors in base stations within the network area, real-time collection of the load value L of the wireless communication resources in the network area load , the communication resource flow value W of the network area, the flow consumption value B of the conflict point, the load value L of the conflict point and the flow value G of the congested node in the network area; By installing computing resource monitoring sensors at the edge of the network area, the load value E of the edge computing resources in the network area is collected in real time. load ; By installing an on-board computing monitor in the autonomous vehicle, the load value C of the on-board computing resources is collected in real time load ; By installing delay monitoring sensors in the network area, the delay duration D of the conflict point is collected in real time and a data set is established.

3. A communication resource scheduling method for a wireless communication network according to claim 2, characterized in that: Step S2 comprises: S21. Based on the data set data, monitor the communication resource efficiency of the ith network area, and after dimensionless processing, calculate and obtain the communication efficiency coefficient Txxs of the ith network area i , the formula is as follows: Where n represents the total number of network regions. represents the load value of the wireless communication resources in the ith network area, C load represents the load value of the vehicle computing resources, E loadi It represents the load value of the edge computing resources in the i-th network area, α represents the impact coefficient of the on-board computing resources, obtained through experiments, 0.1<α<0.5, β represents the compensation coefficient of the edge computing resources, obtained through experiments, 0.05<β<0.

2.

4. A communication resource scheduling method for a wireless communication network according to claim 3, characterized in that: Step S2 also includes: S22, by presetting the first standard threshold Q1 in advance, and setting the communication efficiency coefficient Txxs of the i-th network area i Compare and analyze with the first standard threshold value Q1 to obtain a first evaluation result, including: When the communication efficiency coefficient Txxs of the i-th network area i When ≥ the first standard threshold Q1, it means that the i-th network area is a network area with qualified communication efficiency, and no adjustment is required, and continuous monitoring is required; When the communication efficiency coefficient Txxs of the i-th network area i When < the first standard threshold Q1, it indicates that the ith network area is a network area with unqualified communication efficiency, triggering the first early warning instruction, generating the first strategy, and optimizing the network load difference of the ith network area.

5. A communication resource scheduling method for a wireless communication network according to claim 4, characterized in that: Step S3 includes: S31. When the first warning instruction is received, the network load difference of the ith network area is optimized according to the data set data, and after dimensionless processing, the network load difference coefficient R of the ith network area is calculated. ci , the formula is as follows: Where, L max Indicates the maximum network load value, L min Indicates the minimum network load value, W i Indicates the communication resource flow value of the ith network area, Txxs i represents the communication efficiency coefficient of the ith network area, G i Represents the flow value of the congested node in the i-th network area.

6. A communication resource scheduling method for a wireless communication network according to claim 5, characterized in that: Step S3 also includes: S32, by setting the second standard threshold Q2 in advance and setting the network load difference coefficient R ci Compare and analyze with the first standard threshold value Q2 to obtain a first evaluation result, including: When the network load difference coefficient R ci When the value is less than the second standard threshold Q2, it means that the communication resource load of the ith network area has no congestion risk and no adjustment is required, and continuous monitoring is required; When the second standard threshold Q2 ≥ the network load difference coefficient R of the i-th network area ci When the second standard threshold Q2*150% is reached, it indicates that the communication resource load of the ith network area is at the first level of congestion risk, triggering the second warning instruction and generating the second strategy including: increasing the communication resource flow value of the ith network area by 10%-15%, increasing the communication resource flow value of the congested node in the ith network area by 5%-8%, and recalculating until the network load difference coefficient R of the ith network area is reached. ci Until the second standard threshold Q2; When the network load difference coefficient R ci When ≥ the second standard threshold Q2*150%, it indicates that the communication resource load of the ith network area is at a level 2 congestion risk, triggering the third warning instruction, generating a third strategy, and rescheduling the communication resources of the ith network area at a level 2 congestion risk.

7. A communication resource scheduling method for a wireless communication network according to claim 6, characterized in that: Step S4 includes: S41. When the third warning instruction is received, the conflict point of the rescheduled ith network area is monitored according to the data set data, and after dimensionless processing, the optimized conflict coefficient Yhxs of the ith network area is calculated. i , the formula is as follows: Where n represents the total number of network areas, m represents the total number of conflict points in the ith network area, and B i,j represents the traffic consumption value of the jth conflict point in the ith network area, B max Indicates the maximum flow value at the conflict point, D i,j represents the delay time of the jth conflict point in the ith network area, D max Indicates the maximum tolerable delay time of the conflict point, L i,j represents the load value of the jth conflict point in the ith network area, L max Indicates the maximum load value of the network, w1, w2 and w3 indicate weight coefficients.

8. A communication resource scheduling method for a wireless communication network according to claim 7, characterized in that: Step S4 further includes: S42, by presetting the third standard threshold Q3 in advance, and optimizing the conflict coefficient Yhxs of the i-th network area i Compare and analyze with the third standard threshold value Q3 to obtain a third evaluation result, including: When the i-th network area optimizes the conflict coefficient Yhxs i When ≥ the third standard threshold Q3, it means that the communication resource allocation of the ith network area is qualified and in a balanced state, no adjustment is made and continuous monitoring is performed; When the i-th network area optimizes the conflict coefficient Yhxs i When the value is less than the third standard threshold Q3, it indicates that the communication resource allocation of the ith network area is unqualified and unbalanced, triggering the second warning instruction and generating the fourth strategy including: reducing the traffic consumption value of the conflict point of the ith network area by 8%-10%, reducing the delay time of the conflict point of the ith network area by 10%-15%, increasing the load value of the conflict point of the ith network area by 10%-20%, and recalculating until the conflict coefficient Yhxs of the ith network area is optimized i ≥ the third standard threshold Q3.

9. A communication resource scheduling method for a wireless communication network according to claim 8, characterized in that: Step S5 includes: S51, by establishing an autonomous driving network model, establishing a target communication path in the model to simulate autonomous driving, and using the communication efficiency coefficient Txxs of the i-th network area i , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area i The output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

10. A communication resource scheduling system for a wireless communication network, comprising a communication resource scheduling method for a wireless communication network as claimed in any one of claims 1 to 9, comprising: A partitioning unit, used to obtain the communication resource adjustment network area of ​​the autonomous driving path in advance, divide the communication resource adjustment network area into several network areas, and perform real-time monitoring; A collection unit, used to collect data in the network area in real time and establish a data set; The first calculation unit is used to monitor the communication resource efficiency of the i-th network area according to the data set data, and calculate and obtain the communication efficiency coefficient Txxs of the i-th network area i ; The second calculation unit is used to optimize the network load difference of the network area with unqualified communication efficiency according to the data set data, and calculate the network load difference coefficient R of the i-th network area. ci ; The third calculation unit is used to monitor the conflict point of the rescheduled i-th network area according to the data set data, and calculate and obtain the optimized conflict coefficient Yhxs of the i-th network area i ; The first evaluation unit is used to analyze and determine whether the communication resource efficiency of the i-th network area is qualified, and issue a first warning instruction to the network area with unqualified communication efficiency and perform an optimization strategy; The second evaluation unit is used to analyze and determine whether there is a congestion risk in the network area where the communication efficiency is unqualified, and adjust and optimize the communication resources in the network area with the first-level congestion risk; Rescheduling the communication resources in the network area with the risk of secondary congestion and issuing a third warning instruction; The third evaluation unit is used to analyze and determine whether the i-th network area is in a balanced state after rescheduling, and to optimize and adjust the resources for the network area where the communication resources are allocated in an unbalanced state; Establish a model unit for establishing an autonomous driving network model, establish a target communication path in the model to simulate autonomous driving, and use the communication efficiency coefficient Txxs of the i-th network area i , the network load difference coefficient R of the ith network area ci and the optimized conflict coefficient Yhxs of the i-th network area i The output of the middle layer is used as a feature vector to identify feature information, and the autonomous driving network model is trained and tested through the acquired feature information, and the communication path and communication resource allocation strategy are adjusted in real time to predict the real-time demand for communication resource scheduling of autonomous driving vehicles.

Images