Internet of vehicles data grading and classifying method based on probabilistic neural network and reinforcement learning
By using probabilistic neural networks and reinforcement learning methods in the Internet of Vehicles system, and combining the actual situation of Internet of Vehicles data, the problem of limited data upload bandwidth and difficult to adjust the fixed model is solved, and priority uploading of emergency data and bandwidth resources are realized efficient use.
Patent Information
- Application Number
- CN202410810133.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-21
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-06-21
AI Technical Summary
The data upload bandwidth in the Internet of Vehicles system is limited, which is difficult to process in a timely manner in an emergency, and it is difficult for fixed models to adjust the classification standards according to real-time road conditions, resulting in low bandwidth utilization.
Using a method based on probability neural network and reinforcement learning, by obtaining data samples in the Internet of Vehicles scenario, calculating road conditions vectors, deploying agents to make decisions, sorting data using probability neural networks, and uploading data according to the decisions of agents. Implement hierarchical classification of data and priority upload of emergency data.
Effectively classify and classify data based on actual conditions, give priority to uploading emergency data, improve the utilization rate of bandwidth resources, ensure that emergency data can be uploaded to the cloud in a timely manner, and better utilize bandwidth resources in non-congestion situations.
Smart Images

Figure BDA0004905935420000032 
Figure BDA0004905935420000033 
Figure BDA0004905935420000052
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle networking data classification and grading, and in particular to a vehicle networking data classification and grading method based on probabilistic neural network and reinforcement learning. Background Art
[0002] With the development of communication technology and mobile networks, cars are no longer just a simple means of transportation. Vehicles equipped with wireless sensors, on-board computers, GPS antennas, radars and other intelligent devices can collect and process large amounts of data, while enabling information exchange between vehicles. However, in the Internet of Vehicles system, the upload bandwidth is limited. It takes a lot of time to upload all information to the cloud for analysis, and it is difficult to handle emergency situations. Therefore, it is necessary to classify the uploaded data and give priority to uploading emergency data.
[0003] In the Internet of Vehicles system, information such as traffic flow, vehicle speed and traffic accidents changes over time. It is difficult for fixed models to adjust themselves according to real-time road conditions. Therefore, the model needs to adjust the grading and classification standards based on current road conditions to achieve better bandwidth utilization. Summary of the invention
[0004] The purpose of the present invention is to provide a method for grading and classifying Internet of Vehicles data based on probabilistic neural networks and reinforcement learning, which can not only grade and classify Internet of Vehicles data in combination with actual conditions, but also better allocate broadband resources and ensure that urgent data is uploaded to the cloud first.
[0005] To achieve the above object, the present invention provides a method for grading and classifying Internet of Vehicles data based on probabilistic neural network and reinforcement learning, comprising the following steps:
[0006] S1. Obtain data samples in the Internet of Vehicles scenario and establish a sample data set;
[0007] S2. Calculate the road condition vector of each road side according to the established sample data set;
[0008] S3. Deploy an agent on each roadside, and each agent makes decisions based on the road condition vectors of itself and the adjacent roadside:
[0009] S4. Use probabilistic neural network to sort the data in the sample data set;
[0010] S5. The sorted data is uploaded according to the decision of the intelligent agent to achieve hierarchical classification of Internet of Vehicles data.
[0011] Preferably, step S2 specifically comprises:
[0012] The traffic volume, number of vehicles, and accident conditions are obtained from the sample data set, and these data are processed and merged into a road condition vector, where the traffic volume is a normalized real number between 0 and 1, which means the average traffic volume in the 1 / 2 sampling moments before and after the current moment divided by the maximum traffic volume; the number of vehicles is a real number between 0 and 1, calculated using the following formula:
[0013] N = sigmoid(nn m )
[0014] Where N represents the number of vehicles after calculation; n represents the current number of vehicles; n m Indicates the number of vehicles in the sample data set; the accident situation is a real number between 0 and 1, which means the proportion of normal lanes to all lanes. In particular, an accident situation of 0 indicates that all lanes are normally accessible, and an accident situation of 1 indicates that a serious traffic accident or emergency has occurred, making all lanes impassable.
[0015] Preferably, in step S3, the agent calculates the decision value based on the road condition vector of itself and the adjacent road side, using the following formula:
[0016] p=π(a|s)
[0017] Among them, p is a percentage between 0 and 1, indicating that the data in the sample data set needs to be uploaded to the cloud, and the rest of the data is processed locally; π represents the decision network of the intelligent agent; is a 9-dimensional vector, which contains three 3D vectors, namely the road condition vectors of the previous road side, the current road side and the next road side; a represents the action space taken by the agent when the observation is s.
[0018] Preferably, in step S4, the model parameters are first estimated using a semi-parametric approximation method in GRNN:
[0019]
[0020] Therefore, the overall calculation process of the model is expressed by the following formula:
[0021]
[0022] in, x represents the input vector; x i Represents other vectors besides the current calculation vector; c i represents the center vector of each class; c k represents the center vector of the kth class; f k Indicates that it corresponds to c k The kernel learning function of Z k Represents the center c k The number of data points; fi (x,σ) represents the kernel learning function with center x and smoothing parameter σ; y i is the output value, indicating the importance of the current data; Represents the predicted output of the model; Z i Indicates the center is c i The number of data points; i Z i =NV represents the total number of data points in the data set;
[0023] After calculating the importance of each data, all the data in the sample data set are sorted in order from large to small.
[0024] Preferably, the percentage p is obtained according to step S3, and the first p data among the data obtained in step S4 are uploaded to the cloud of the Internet of Vehicles, and the remaining data are processed locally, so as to realize the hierarchical classification of the Internet of Vehicles data during data upload.
[0025] Therefore, the present invention adopts the above-mentioned vehicle network data classification method based on probabilistic neural network and reinforcement learning, which has the following beneficial effects:
[0026] By selecting traffic volume, number of vehicles, and accident conditions as evaluation indicators of the current road conditions, and using road condition vectors to describe the current road condition information, the actual situation can be better combined when performing subsequent data grading and classification.
[0027] Data is sorted through a probabilistic neural network, which can effectively evaluate the urgency of the data and sort it from urgent to non-urgent to ensure that urgent data can be uploaded to the cloud first.
[0028] At the same time, using intelligent agents to choose the proportion of data uploaded to the cloud according to current road conditions can better allocate broadband resources and ensure that emergency data can be uploaded to the cloud first. At the same time, in non-congested conditions, broadband resources can be better utilized to upload more data.
[0029] The technical solution of the present invention is further described in detail below through embodiments. DETAILED DESCRIPTION
[0030] The technical solution of the present invention is further illustrated by the following examples.
[0031] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.
[0032] Embodiment 1
[0033] The present invention provides a method for grading and classifying Internet of Vehicles data based on probabilistic neural network and reinforcement learning, comprising the following steps:
[0034] S1. Obtain data samples in the Internet of Vehicles scenario and establish a sample data set;
[0035] S2. Under the sample data set, calculate the road condition vector of each road side, obtain the traffic flow, number of vehicles, and accident situation in the sample data set, and merge these data into a road condition vector after processing, where the traffic flow is a normalized real number between 0 and 1, which means the average traffic flow within 1 / 2 sampling moments before and after the current moment divided by the maximum traffic flow; the number of vehicles is a real number between 0 and 1, calculated using the following formula:
[0036] N = sigmoid(nn m )
[0037] Where N represents the number of vehicles after calculation; n represents the current number of vehicles; n m Indicates the number of vehicles in the sample data set; accident situation is a real number between 0 and 1, which means the proportion of normal lanes to all lanes. In particular, an accident situation of 0 means that all lanes are normally accessible, and an accident situation of 1 means that a serious traffic accident or emergency has caused all lanes to be blocked.
[0038] S3. An agent is deployed on each roadside. Each agent makes a decision based on the road condition vectors of itself and the adjacent roadside. The following formula is used:
[0039] p=π(a|s)
[0040] Among them, p is a percentage between 0 and 1, indicating that the data in the sample data set needs to be uploaded to the cloud, and the rest of the data is processed locally; π represents the decision network of the intelligent agent; is a 9-dimensional vector, which contains three 3D vectors, namely the road condition vectors of the previous road side, the current road side and the next road side; a represents the action space taken by the agent when the observation is s.
[0041] S4. All the data in the sample data set are used as the information to be uploaded and sorted using a boost-based probabilistic neural network. First, the semi-parametric approximation method in GRNN is used to estimate the model parameters:
[0042]
[0043] Therefore, the overall calculation process of the model is expressed by the following formula:
[0044]
[0045] in,x represents the input vector; x i Represents other vectors besides the current calculation vector; c i Represents the center vector of each class; c k represents the center vector of the kth class; f k Indicates that it corresponds to c k The kernel learning function of Z k Represents the center c k The number of data points; f i (x,σ) represents the kernel learning function with center x and smoothing parameter σ; y i is the output value, indicating the importance of the current data; Represents the predicted output of the model; Z i Indicates the center is c i The number of data points; i Z i =NV represents the total number of data points in the data set.
[0046] After calculating the importance of each data, all the data in the data set are sorted in order from large to small.
[0047] S5. The sorted data is uploaded according to the decision of the intelligent agent to realize the hierarchical classification of the Internet of Vehicles data. Specifically, the percentage p is obtained according to step S3, and the first p data of the data obtained in step S4 are uploaded to the cloud of the Internet of Vehicles. The remaining data is processed locally to realize the hierarchical classification of the Internet of Vehicles data during data upload.
[0048] The present invention adopts the above-mentioned vehicle network data grading and classification method based on probabilistic neural network and reinforcement learning, which can not only grade and classify the vehicle network data according to the actual situation, but also better allocate broadband resources and ensure that urgent data is uploaded to the cloud first.
[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.
Claims
1. A method for grading and classifying Internet of Vehicles data based on probabilistic neural network and reinforcement learning, characterized in that: The following steps are involved: S1. Obtain data samples in the Internet of Vehicles scenario and establish a sample data set; S2. Calculate the road condition vector of each road side according to the established sample data set; S3, deploying agents in each roadside, each agent makes decisions based on the road condition vectors of itself and the adjacent roadside; S4. Use a probabilistic neural network to sort the data in the sample data set; S5. The sorted data is uploaded according to the decision of the intelligent agent to achieve hierarchical classification of Internet of Vehicles data.
2. The method for classifying Internet of Vehicles data based on probabilistic neural network and reinforcement learning according to claim 1, characterized in that: Step S2 is specifically as follows: The traffic volume, number of vehicles, and accident conditions are obtained from the sample data set, and these data are processed and merged into a road condition vector, where the traffic volume is a normalized real number between 0 and 1, which means the average traffic volume in the 1 / 2 sampling moments before and after the current moment divided by the maximum traffic volume; the number of vehicles is a real number between 0 and 1, calculated using the following formula: N=sigmoid(n-n m ) Where N represents the number of vehicles after calculation; n represents the current number of vehicles; n m Represents the number of vehicles in the sample data set; the accident situation is a real number between 0 and 1, which means the proportion of normal traffic lanes to all lanes.
3. The method for grading and classifying Internet of Vehicles data based on probabilistic neural network and reinforcement learning according to claim 2 is characterized in that: In step S3, the agent calculates the decision value based on the road condition vectors of itself and the adjacent road sides, using the following formula: p=π(a|s) Among them, p is a percentage between 0 and 1, indicating that the data in the sample data set needs to be uploaded to the cloud, and the rest of the data is processed locally; π represents the decision network of the intelligent agent; is a 9-dimensional vector, which contains three 3D vectors, namely the road condition vectors of the previous road side, the current road side and the next road side; a represents the action space taken by the agent when the observation is s.
4. The method for grading and classifying Internet of Vehicles data based on probabilistic neural network and reinforcement learning according to claim 3 is characterized in that: In step S4, the model parameters are first estimated using the semi-parametric approximation method in GRNN: Therefore, the overall calculation process of the model is expressed by the following formula: in, x represents the input vector; x i Represents other vectors besides the current calculation vector; c i Represents the center vector of each class; c k represents the center vector of the kth class; f k Indicates that it corresponds to c k The kernel learning function of Z k Represents the center c k The number of data points; f i (x,σ) represents the kernel learning function with center x and smoothing parameter σ; y i is the output value, indicating the importance of the current data; Represents the predicted output of the model; Z i Indicates the center is c i The number of data points; i Z i =NV represents the total number of data points in the data set; After calculating the importance of each data, all the data in the sample data set are sorted in order from large to small.
5. The method for grading and classifying Internet of Vehicles data based on probabilistic neural network and reinforcement learning according to claim 4 is characterized in that: According to step S3, the percentage p is obtained, and the first p data of the data obtained in step S4 are uploaded to the cloud of the Internet of Vehicles, and the remaining data are processed locally, so as to realize the hierarchical classification of the Internet of Vehicles data during data upload.
Citation Information
Patent Citations
Traffic signal control system and method based on road condition traffic big data
CN105390000A
Intelligent road system for traffic dispersion
CN109615867A
Vehicle trust evaluation method combining entity trust and social trust
CN112887986A
Internet of vehicles spectrum sharing method based on multi-agent reinforcement learning
CN113613207A
Road traffic real-time road condition information analysis system and method based on vehicle-road cooperation
CN116844337A
