A Vehicle Carbon Emission Safety Calculation Method and System Based on the Internet of Vehicles

Abstract

The present invention discloses a method and system for calculating vehicle carbon emissions safety based on the vehicle networking, which relates to the technical field of carbon emission monitoring. Through the in-vehicle carbon measurement terminal deployed on each vehicle, the carbon emissions are calculated based on the embedded local carbon measurement model, ensuring the real-time and high-precision of carbon emission monitoring; through traditional encryption algorithms and homomorphic encryption technology, strong security guarantees are provided during the data transmission process to ensure the privacy and security of carbon data. The carbon measurement operation platform calculates and optimizes the global carbon emission model for the encrypted data uploaded by multiple in-vehicle terminals based on federated learning technology, effectively improving the efficiency and precision of large-scale data processing. In addition, the system supports multiple communication networks and can perform data interaction with external systems, providing support for the generation of carbon emission reports and carbon assetization applications, meeting the application requirements in different scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission monitoring, and particularly relates to a method and system for safely calculating vehicle carbon emissions based on the Internet of Vehicles (IoV). Background Art

[0002] Currently, the systems for vehicle carbon emission monitoring on the market mainly rely on the extraction and analysis of later-stage data, suffering from problems such as poor real-time performance and low accuracy. Especially for new energy vehicles, due to the unclear baseline and undefined accounting methods for calculating their carbon emission reduction amounts, the implementation operability of carbon emission reduction assetization is relatively poor. Most of the existing monitoring systems rely on vehicle charging data for statistics, with a relatively large granularity, unable to achieve precise segmented metering and real-time monitoring, and it is difficult to meet the dynamic carbon emission monitoring requirements under different working conditions.

[0003] With the rapid development of the Internet of Vehicles (IoV) technology, it has become possible to collect and analyze vehicle operation data in real time using in-vehicle devices. The IoV technology can obtain the instantaneous operation data of vehicles in real time through the vehicle CAN bus, providing a basis for the accurate calculation of vehicle carbon emissions. However, most of the carbon emission calculation models of traditional systems rely on cloud centralized processing. This centralized calculation mode is prone to system performance bottlenecks when facing a large amount of vehicle data, and it is difficult to achieve real-time processing with high concurrency and multiple scenarios. Secondly, there are also relatively large risks in data security. Especially, the energy consumption data of vehicles is vulnerable to theft or tampering during the transmission process, seriously affecting the credibility and reliability of the data.

[0004] In addition, the existing carbon metering methods are also difficult to support various different types of transportation vehicles, including traditional fuel vehicles, plug-in hybrid vehicles, pure electric vehicles, etc. In order to meet the carbon emission monitoring requirements of different types of vehicles, there is an urgent need for a system that can dynamically adjust the calculation model to ensure accurate and safe calculation of vehicle operation data under various working conditions. Summary of the Invention

[0005] Aiming at the problems existing in the current calculation of vehicle carbon emissions, such as unclear accounting baseline, undefined accounting method, poor operability, and insufficient security in the data collection and transmission process, the present invention proposes a method and system for safely calculating vehicle carbon emissions based on the Internet of Vehicles. Starting from the actual energy consumption of vehicles, it calculates the mileage traveled per unit time of energy consumption, accurate to individual vehicles, and accurately calculates the carbon emission reduction amount by benchmarking against the standard baseline, thereby promoting the assetization of carbon emission reduction for new energy vehicle travel.

[0006] To achieve the above object, the present invention is realized through the following technical solutions:

[0007] A method for safely calculating vehicle carbon emissions based on the Internet of Vehicles, the method comprising:

[0008] Deploy in-vehicle carbon measurement terminals on each vehicle, and connect them to the carbon measurement operation platform in the cloud through the IoV network;

[0009] The in-vehicle carbon measurement terminal is embedded with a local carbon measurement model, obtains the real-time operation data of the vehicle from the vehicle CAN bus, and calculates the real-time operation data through the local carbon measurement model to obtain the carbon data of the vehicle;

[0010] Use traditional encryption algorithms to encrypt the real-time operation data, use homomorphic encryption technology to encrypt the carbon data, and transmit the encrypted real-time operation data and carbon data to the carbon measurement operation platform;

[0011] The carbon measurement operation platform obtains the CAN message information of the vehicle from the vehicle enterprise, combines the encrypted real-time operation data and carbon data uploaded by multiple in-vehicle carbon measurement terminals, and performs the calculation and optimization of the global carbon emission model based on the federated learning technology to generate the global calculation result of carbon emissions.

[0012] As a preferred solution of the present invention, the real-time operation data includes instantaneous voltage, instantaneous current, driving mileage, speed, acceleration, vehicle VIN code and other relevant data; the carbon data of the vehicle includes the carbon emission, carbon emission reduction and vehicle energy consumption of each vehicle.

[0013] As a preferred solution of the present invention, calculating the real-time operation data through the local carbon measurement model further includes: reviewing the operation data and carbon data calculation results of the vehicle within the historical time through the local experience replay mechanism, and comparing with the current operation state of the vehicle, so as to adjust the weights and parameters of the current local carbon measurement model. The formula is:

[0014] ;

[0015] In the formula, is the local replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents the probability of the occurrence of event under the given historical hidden state during the local experience replay process; represents the probability distribution of the occurrence of event under the given historical hidden state under the current local carbon measurement model parameters .

[0016] As a preferred solution of the present invention, the traditional encryption algorithms include symmetric encryption algorithm AES, triple data encryption algorithm 3DES, asymmetric encryption algorithm RSA, stream cipher algorithm ChaCha20 and elliptic curve encryption algorithm ECC.

[0017] As a preferred solution of the present invention, the carbon data is encrypted using homomorphic encryption technology, specifically including:

[0018] Weight matrix for local carbon accounting model Encoding processing, the formula is:

[0019] ;

[0020] In the formula, is the encoded weight matrix; Represents the weight matrix Fill, 0 represents the filling value, is the size of the matrix after encoding; Represents a flattening operation, which is used to convert a multi-dimensional matrix into a one-dimensional vector;

[0021] Using Public Key The encoded weight matrix To encrypt, the formula is:

[0022] ;

[0023] In the formula, represents the encrypted weight matrix, is the encryption function.

[0024] As a preferred solution of the present invention, the carbon metering operation platform calculates and optimizes the global carbon emission model based on the federated learning technology, and also includes: performing global experience playback based on the CAN message information of different vehicles, the formula is:

[0025] ;

[0026] In the formula, is the global playback loss function; is the qth relevant event in historical time; Hidden state for history; Indicates that during the global playback process, given the historical hidden state The following events occurred The probability of Indicates the current global carbon emission model parameters Under the given historical hidden state Events occur under the conditions The probability distribution of .

[0027] As a preferred solution of the present invention, the carbon accounting operation platform uses a weighted aggregation algorithm to optimize and update the global carbon emission model, and the update formula is:

[0028] ;

[0029] In the formula, represents the parameters of the updated global carbon emission model; is the parameter of the local carbon accounting model of the nth vehicle, is the number of vehicles participating in federated learning; is the parameter of the global carbon emission model used in the current iteration on the server side; represents the current iteration round of federated learning; represents the addition operation of matrices; represents the multiplication operation of matrices.

[0030] As a preferred solution of the present invention, the method further includes: the carbon accounting operation platform generates a carbon emission report according to the global calculation result of carbon emissions, and conducts data interaction with an external system. At the same time, the globally optimized carbon emission model after federated learning is fed back to each on-vehicle carbon accounting terminal to improve the local carbon accounting model and achieve dynamic adjustment and optimization.

[0031] A vehicle carbon emission safety calculation system based on the Internet of Vehicles, the system includes on-vehicle carbon accounting terminals deployed on each vehicle and a carbon accounting operation platform;

[0032] The on-vehicle carbon accounting terminal includes:

[0033] A CAN communication module for data transmission between the vehicle CAN bus and the MCU module;

[0034] The MCU module, as the core processing unit of the on-vehicle carbon accounting terminal, is embedded with a local carbon accounting model, obtains the real-time operation data of the vehicle from the vehicle CAN bus through the CAN communication module, and calculates the carbon data of the vehicle through the local carbon accounting model;

[0035] A storage module for temporarily storing the real-time operation data and carbon data of the vehicle when the network is unstable or disconnected;

[0036] A data encryption module for encrypting the real-time operation data using a traditional encryption algorithm and encrypting the carbon data using homomorphic encryption technology;

[0037] An external communication module for transmitting the encrypted real-time operation data and carbon data to the carbon accounting operation platform through 4G CAT1, 5G or 6G;

[0038] The carbon measurement operation platform obtains the CAN message information of vehicles from vehicle manufacturers, combines the encrypted real-time operation data and carbon data uploaded by multiple in-vehicle carbon measurement terminals, calculates and optimizes the global carbon emission model based on federated learning technology, generates the global calculation result of carbon emissions, and generates a carbon emission report according to the global calculation result, and conducts data interaction with external systems.

[0039] As a preferred solution of the present invention, the MCU module calculates the real-time operation data through the local carbon measurement model, and further includes: reviewing the operation data and carbon data calculation results of the vehicle within a historical time through a local experience replay mechanism, and comparing them with the current operation state of the vehicle, so as to adjust the weights and parameters of the current local carbon measurement model. The formula is:

[0040] ;

[0041] In the formula, is the local replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents the probability of the occurrence of event under the given historical hidden state during the local experience replay process; represents the probability distribution of the occurrence of event under the given historical hidden state under the condition of the current local carbon measurement model parameters ;

[0042] The carbon measurement operation platform calculates and optimizes the global carbon emission model based on federated learning technology, and further includes: performing global experience replay based on the CAN message information of different vehicles. The formula is:

[0043] ;

[0044] In the formula, is the global replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents the probability of the occurrence of event under the given historical hidden state during the global replay process; represents the probability distribution of the occurrence of event under the given historical hidden state under the condition of the current global carbon emission model parameters ;

[0045] The beneficial effects of the present invention are as follows: Through the in-vehicle carbon measurement terminal deployed on each vehicle, real-time operation data is obtained from the vehicle CAN bus, and the carbon emissions are accurately calculated through the embedded local carbon measurement model, ensuring the real-time and high-precision of carbon emissions monitoring. At the same time, the system has the function of storing data when the network is unstable or disconnected, ensuring the integrity of the data. Through traditional encryption algorithms and homomorphic encryption technologies, the system provides strong security guarantees during data transmission, ensuring the privacy and security of carbon data. The carbon measurement operation platform is based on federated learning technology to calculate and optimize the global carbon emission model for the encrypted data uploaded by multiple in-vehicle terminals, effectively improving the efficiency and accuracy of large-scale data processing. In addition, the system supports multiple communication networks and can interact with external systems, providing support for the generation of carbon emission reports and carbon assetization applications, meeting the application requirements in different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them:

[0047] Figure 1 is the method flow chart of the present invention;

[0048] Figure 2 is the system modular structure diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the embodiments of the present invention in conjunction with the drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the described embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present invention.

[0050] As Figure 1 shown, it is an embodiment of the present invention. This embodiment provides a method for securely calculating vehicle carbon emissions based on the Internet of Vehicles. The method includes the following steps:

[0051] S1: Deploy in-vehicle carbon measurement terminals on each vehicle to form distributed nodes, and connect to the carbon measurement operation platform in the cloud through the IoV (Internet of Vehicles) network to achieve independent and distributed collection of carbon data;

[0052] Different from the traditional regular statistical method of carbon emission data and the method of collecting data through discrete and shared links, the present invention adopts an independent and secure data collection link to establish the real-time collection ability of carbon data;

[0053] S2: The in-vehicle carbon measurement terminal is embedded with a local carbon measurement model, obtains the real-time operation data of the vehicle from the vehicle CAN bus, and calculates the real-time operation data through the local carbon measurement model to obtain the carbon data of the vehicle;

[0054] Specifically, the real-time operation data may include instantaneous voltage, instantaneous current, driving mileage (single trip and total driving mileage), speed, acceleration, vehicle VIN code (vehicle identification code), and other relevant data (such as battery status, vehicle load), etc.; after collection, preliminary preprocessing is carried out, including outlier processing, noise filtering, and data standardization to ensure the accuracy of subsequent calculations.

[0055] The carbon data of the vehicle includes carbon emissions, carbon emission reduction, vehicle energy consumption, etc.

[0056] The calculation of carbon emissions can combine the electrical energy consumption of the vehicle (the power obtained by multiplying the instantaneous voltage and current), and then combine the mileage traveled by the vehicle and the battery efficiency to convert it into carbon emissions; the baseline carbon emissions can be estimated according to the fuel consumption and mileage data of traditional vehicles, and compared with the current carbon emissions of the vehicle to obtain the value of carbon emission reduction; the vehicle energy consumption can be calculated by the power consumption of the vehicle (the product of instantaneous voltage and current), and then combined with the driving distance and load conditions.

[0057] Starting from the actual energy consumption of the vehicle in use, calculate the mileage traveled per unit time of energy consumption, accurately accurate to the individual vehicle, and accurately calculate the carbon emission reduction by benchmarking against the standard baseline, so as to promote the assetization of carbon emission reduction of new energy vehicle travel.

[0058] The calculated carbon data is temporarily stored in the storage module; if the network connection is unstable or interrupted, the data will be temporarily stored and uploaded after the network is restored.

[0059] Further, in one embodiment, calculating the real-time operation data through the local carbon measurement model further includes: reviewing historical data through a local experience replay mechanism to obtain the carbon emission calculation experience of early driving behaviors from it, and avoiding the model forgetting important historical information. The specific method is to review the vehicle operation data and carbon data calculation results within the local historical time, and compare them with the current operation state of the vehicle, so as to adjust the weights and parameters of the current local carbon measurement model. The formula is:

[0060] ;

[0061] In the formula, is a local replay loss function, which is used to measure the difference between the historical data distribution and the current model output distribution during the local experience replay process; is the q-th relevant event within the historical time, representing a possible state or output in the historical data; is the historical hidden state, which represents the state of the system over a past period of time, used to represent the historical behavior or characteristics of the system, and helps the model learn from past experiences during local replay; represents the conditional probability distribution of the historical data, specifically, during the local experience replay process, given the historical hidden state the probability of the occurrence of event This probability represents the historical data distribution, reflecting the frequency or likelihood of a certain event occurring under the same conditions in the past; represents the conditional probability distribution of the output of the current local carbon accounting model, specifically, under the current local model parameters given the historical hidden state the probability distribution of the occurrence of event It represents the prediction probability of the model under the current conditions. By using logarithmic operations, the difference between the historical data distribution and the current model output distribution is measured. The larger this difference is, the further the output of the current model deviates from the historical experience. By minimizing this difference, the model can better adapt to historical experience and prevent forgetting important information from the past.

[0062] S3: Encrypt the real-time operation data using a traditional encryption algorithm, encrypt the carbon data using homomorphic encryption technology, and transmit the encrypted real-time operation data and carbon data to the carbon accounting operation platform;

[0063] Before the data is prepared for uploading, encrypt these data through an encryption module to ensure that they will not be leaked or tampered with during the data transmission process.

[0064] Specifically, traditional encryption algorithms include the symmetric encryption algorithm AES (Advanced Encryption Standard), triple data encryption algorithm 3DES (Triple Data Encryption Standard), asymmetric encryption algorithm RSA (Rivest-Shamir-Adleman), stream cipher algorithm ChaCha20, elliptic curve encryption algorithm ECC (Elliptic Curve Cryptography), etc. Since the amount of real-time running data is large and high-efficiency encryption is required, AES is the best choice. In particular, AES-256 can provide high security and encryption speed. If the system has higher requirements for computing resources and lower power consumption, ChaCha20 is also a good choice.

[0065] In one embodiment, homomorphic encryption technology is used to encrypt carbon data, specifically including:

[0066] Encoding the weight matrix of the local carbon measurement model The formula is:

[0067] ;

[0068] In the formula, is the encoded weight matrix; represents padding the weight matrix with 0 representing the padded value, is the size of the encoded matrix; the purpose of this operation is to ensure that the matrix size is suitable for subsequent encryption processing; represents the flattening operation, which is used to convert a multi-dimensional matrix into a one-dimensional vector;

[0069] Using the public key to encrypt the encoded weight matrix The formula is:

[0070] ;

[0071] In the formula, is the encrypted weight matrix, is the encryption function.

[0072] By using the public key , it is ensured that the data can still be homomorphically computed without decryption after encryption. Even if intercepted during transmission, the data is secure.

[0073] S4: The carbon measurement operation platform obtains the CAN message information of the vehicle from the vehicle enterprise, combines the encrypted real-time operation data and carbon data uploaded by multiple on-vehicle carbon measurement terminals, and calculates and optimizes the global carbon emission model based on the federated learning technology to generate the global calculation result of carbon emissions;

[0074] The CAN message information includes the historical operation data and system performance parameters of the vehicle, which are used to supplement and correct the real-time operation data uploaded by the on-vehicle carbon measurement terminal;

[0075] The traditional method usually aggregates the data of multiple vehicles to the cloud and then performs centralized calculation. However, this centralized calculation method is prone to privacy risks. Therefore, the present invention introduces the federated learning technology, enabling each vehicle to calculate local carbon emission data locally. Each on-vehicle carbon measurement terminal can learn the vehicle's operation mode locally and optimize the carbon emission model through its own computing resources (such as the MCU module), and upload the encrypted model parameters of each vehicle to the carbon measurement operation platform through the federated learning method. The carbon measurement operation platform performs weighted aggregation on the model parameters of different vehicles to generate a globally optimized model, and then distributes this model back to the on-vehicle carbon measurement terminal, thereby improving the accuracy of the carbon measurement model and avoiding the impact of centralized data processing on vehicle privacy.

[0076] This distributed computing mode not only enhances data privacy protection but also enables personalized carbon emission modeling according to different types of vehicles and different driving environments.

[0077] Further, the carbon measurement operation platform calculates and optimizes the global carbon emission model based on the federated learning technology, and also includes: performing global experience replay based on the CAN message information of different vehicles, and the formula is:

[0078] ;

[0079] In the formula, is the global replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents that during the global replay process, given the historical hidden state the probability of the occurrence of event ; represents that under the current global carbon emission model parameters given the historical hidden state the probability distribution of the occurrence of event under the condition.

[0080] The carbon measurement operation platform supports the dynamic learning and continuous optimization of vehicle carbon data. By adopting the experience replay technology, it ensures that the platform can maintain the long-term stability and accuracy of the carbon emission model according to different driving scenarios and long-term usage conditions. It can also be set to automatically adjust the carbon emission calculation weights according to changes in different driving environments (such as rainy days, mountainous areas, etc.) to meet the carbon emission calculation requirements in complex scenarios.

[0081] Through the federated learning algorithm, the carbon measurement operation platform aggregates the local model parameters of different vehicles to form a global carbon emission model. The local experience replay data of each vehicle will be uploaded to the platform through federated learning, and the carbon measurement operation platform forms a more accurate global model by aggregating the encrypted local model parameters.

[0082] In one specific embodiment, the carbon measurement operation platform uses a weighted aggregation algorithm to optimize and update the global carbon emission model. The update formula is:

[0083] ;

[0084] In the formula, represents the updated global carbon emission model parameters, which are the global model weights obtained after each round of training in the federated learning process and are used for the next round of model training and optimization; is the local carbon measurement model parameter of the nth vehicle. These vehicles perform model training based on their own data locally, and the obtained parameters are encrypted to protect privacy; is the number of vehicles participating in the federated learning; is the global carbon emission model parameter used in the current iteration on the server side; represents the current iteration round of the federated learning; represents the addition operation of matrices; represents the multiplication operation of matrices.

[0085] S5: The carbon measurement operation platform generates a carbon emission report based on the global calculation results of carbon emissions and conducts data interaction with external systems (such as carbon trading platforms). At the same time, it feeds back the globally optimized carbon emission model by federated learning to each on-vehicle carbon measurement terminal to improve the local carbon measurement model and achieve dynamic adjustment and optimization.

[0086] The carbon emission report contains accurate carbon emission reduction amounts calculated based on the local and global replay mechanisms, and the transparency and immutability of the data can be ensured through blockchain technology.

[0087] As Figure 2 shown, in another embodiment of the present invention, there is provided a secure calculation system for vehicle carbon emissions based on the vehicle networking, including an on-vehicle carbon measurement terminal and a carbon measurement operation platform;

[0088] The in-vehicle carbon measurement terminal includes:

[0089] A CAN communication module for data transmission between the vehicle CAN bus and the MCU module;

[0090] An MCU module, serving as the core processing unit of the in-vehicle carbon measurement terminal, with a local carbon measurement model embedded. It obtains the real-time operation data of the vehicle from the vehicle CAN bus through the CAN communication module, and calculates the real-time operation data through the local carbon measurement model to obtain the carbon data of the vehicle;

[0091] A storage module for temporarily storing the real-time operation data and carbon data of the vehicle when the network is unstable or disconnected;

[0092] A data encryption module for encrypting the real-time operation data using a traditional encryption algorithm and encrypting the carbon data using homomorphic encryption technology;

[0093] An external communication module for transmitting the encrypted real-time operation data and carbon data to the carbon measurement operation platform through 4G CAT1, 5G or 6G;

[0094] The carbon measurement operation platform obtains the CAN message information of the vehicle from the vehicle enterprise, combines the encrypted real-time operation data and carbon data uploaded by multiple in-vehicle carbon measurement terminals, calculates and optimizes the global carbon emission model based on federated learning technology, generates the global calculation result of carbon emissions, and generates a carbon emission report according to the global calculation result for data interaction with external systems.

[0095] 4G CAT1 is a specific 4G standard. While maintaining the basic 4G network characteristics, it focuses on low power consumption, low cost and moderate data transmission performance. The 4G CAT1 module is designed with energy efficiency in mind, and has lower power consumption in standby and transmission states compared to traditional 4G modules. It can provide relatively low network latency, which is beneficial for applications with high real-time requirements.

[0096] Using a low-cost MCU module combined with a 4G CAT1 communication module and CAN bus to access the vehicle, obtaining real-time operation data from the vehicle's entire vehicle CAN communication protocol, ensuring the independence and authority of data collection, and being able to adapt to different types of new energy vehicles (plug-in hybrid, fuel vehicle, etc.).

[0097] Furthermore, when the MCU module calculates the real-time operation data through the local carbon measurement model, it also includes: reviewing the operation data and carbon data calculation results of the vehicle within the historical time through the local experience replay mechanism, and comparing them with the current operation state of the vehicle, so as to adjust the weights and parameters of the current local carbon measurement model. The formula is:

[0098] ;

[0099] In the formula, is the local replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents that during the local experience replay process, given the historical hidden state the probability of the occurrence of event ; represents the probability distribution of the occurrence of event under the condition of the given historical hidden state under the current local carbon accounting model parameters ;

[0100] The carbon accounting operation platform calculates and optimizes the global carbon emission model based on federated learning technology, and also includes: performing global experience replay based on the CAN message information of different vehicles, and the formula is:

[0101] ;

[0102] In the formula, is the global replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents that during the global replay process, given the historical hidden state the probability of the occurrence of event ; represents the probability distribution of the occurrence of event under the condition of the given historical hidden state under the current global carbon emission model parameters ;

[0103] To sum up, through the in-vehicle carbon accounting terminal deployed on each vehicle, the present invention can obtain the operation data of the vehicle from the CAN bus of the vehicle in real time, and perform real-time calculation on these data through the embedded local carbon accounting model to generate the carbon emissions of the vehicle. This design ensures the immediacy and high precision of the carbon emission data, and is particularly suitable for the dynamic monitoring requirements of different types of vehicles. Compared with the traditional method that relies on extracting data afterwards, this system significantly improves the real-time calculation ability of carbon emissions and ensures the accuracy and timeliness of the data.

[0104] Equipped with a storage module, it can temporarily store the real-time operation data and carbon data of the vehicle when the network is unstable or disconnected. This function effectively guarantees the integrity of the data, and even when the transmission is interrupted, key data will not be lost. After the network is restored, the system can automatically re-transmit this data to the carbon measurement operation platform, thus ensuring the continuity and reliability of the entire data stream. This redundant design greatly improves the stability of the system under harsh network conditions.

[0105] By using traditional encryption algorithms (such as AES, RSA, etc.) to encrypt the real-time operation data of the vehicle, and adopting homomorphic encryption technology for carbon data, the system provides strong security protection during data transmission. The use of homomorphic encryption allows for computational processing of encrypted data without decryption, ensuring the security and privacy of carbon data during cloud transmission and processing. This design not only effectively prevents the risk of data tampering and theft during transmission, but also enhances the protection ability of the entire system in terms of data security, meeting the high standards of current data privacy protection requirements.

[0106] The carbon measurement operation platform can obtain the encrypted real-time operation data and carbon data from multiple in-vehicle carbon measurement terminals, and calculate and optimize the global carbon emission model based on federated learning technology. Federated learning allows multiple data sources to collaboratively train a global model without sharing raw data. This distributed learning method protects data privacy while ensuring that the system can process carbon emission data from a large number of vehicles to generate a more accurate global carbon emission model. Compared with the traditional centralized data processing mode, this system greatly improves the efficiency and accuracy of large-scale carbon data processing and can achieve dynamic optimization of carbon emission models among different vehicles.

[0107] Through the external communication module, it supports high-speed data transmission of 4G CAT1, 5G or 6G networks, can quickly upload the encrypted data to the carbon measurement operation platform, and conduct data interaction with external systems. This flexible communication method ensures the application expansion ability of the system under different future network conditions, and at the same time supports data sharing with various external systems, such as the generation of carbon emission reports and carbon asset management. This provides a technical basis for cross-industry and cross-regional data sharing and certification, and has important application value especially in the field of international carbon emission reduction data mutual recognition.

[0108] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of various changes or substitutions, and these should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A vehicle carbon emission safety calculation method based on the vehicle networking, characterized in that The method includes: Deploy an on-vehicle carbon measurement terminal on each vehicle, and connect it to the carbon measurement operation platform in the cloud through the IoV network; The on-vehicle carbon measurement terminal is embedded with a local carbon measurement model, obtains the real-time operation data of the vehicle from the vehicle CAN bus, and calculates the real-time operation data through the local carbon measurement model to obtain the carbon data of the vehicle; Calculating the real-time operation data through the local carbon measurement model further includes: reviewing the operation data and carbon data calculation results of the vehicle within the historical time through the local experience replay mechanism, and comparing them with the current operation state of the vehicle, so as to adjust the weights and parameters of the current local carbon measurement model. The formula is: ； In the formula, is the local replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents that during the local experience replay process, given the historical hidden state the probability of the occurrence of event ; represents the probability distribution of the occurrence of event under the current local carbon accounting model parameters given the historical hidden state ; Use an encryption algorithm to encrypt the real-time operation data, use homomorphic encryption technology to encrypt the carbon data, and transmit the encrypted real-time operation data and carbon data to the carbon measurement operation platform; The carbon measurement operation platform obtains the CAN message information of the vehicle from the vehicle enterprise, combines the encrypted real-time operation data and carbon data uploaded by multiple on-vehicle carbon measurement terminals, and performs the calculation and optimization of the global carbon emission model based on the federated learning technology to generate the global calculation result of carbon emissions.

2. The vehicle carbon emission safety calculation method based on the vehicle networking according to claim 1, characterized in that, The real-time operation data includes instantaneous voltage, instantaneous current, driving mileage, speed, acceleration, and vehicle VIN code; the carbon data of the vehicle includes the carbon emission, carbon emission reduction, and vehicle energy consumption of each vehicle.

3. The vehicle carbon emission safety calculation method based on the vehicle networking according to claim 1, wherein The encryption algorithm includes the symmetric encryption algorithm AES, the triple data encryption algorithm 3DES, the asymmetric encryption algorithm RSA, the stream cipher algorithm ChaCha20, and the elliptic curve encryption algorithm ECC.

4. The vehicle carbon emission safety calculation method based on the vehicle networking according to claim 1, characterized in that The use of homomorphic encryption technology to encrypt the carbon data specifically includes: The weight matrix of the local carbon accounting model is encoded with the formula: ； In the formula, is the encoded weight matrix; represents padding the weight matrix with 0 representing the padding value, is the size of the encoded matrix; represents a flattening operation used to convert a multi-dimensional matrix into a one-dimensional vector; Using the public key to encrypt the encoded weight matrix with the formula: ； In the formula, represents the encrypted weight matrix, is the encryption function.

5. A vehicle carbon emission safety calculation method based on the vehicle Internet of Things according to claim 1, characterized in that, The carbon measurement operation platform performing the calculation and optimization of the global carbon emission model based on the federated learning technology further includes: performing global experience replay based on the CAN message information of different vehicles. The formula is: ； In the formula, is the global replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents that during the global replay process, given the historical hidden state the probability of the occurrence of event ; represents the probability distribution of the occurrence of event under the current global carbon emission model parameters given the historical hidden state .

6. The vehicle carbon emission safety calculation method based on the vehicle networking according to claim 1, wherein, The carbon measurement operation platform uses a weighted aggregation algorithm to optimize and update the global carbon emission model. The update formula is: ； wherein, represents the updated global carbon emission model parameters; is the local carbon measurement model parameter of the nth vehicle, is the number of vehicles participating in federated learning; is the global carbon emission model parameter used in the current iteration on the server side; represents the current iteration round of federated learning; represents the addition operation of matrices; represents the multiplication operation of matrices.

7. A method for calculating the safe carbon emissions of a vehicle based on the vehicle Internet of Things according to claim 1, characterized in that, The method further includes: the carbon measurement operation platform generates a carbon emission report according to the global calculation result of carbon emissions, performs data interaction with an external system, and at the same time, feeds back the globally optimized carbon emission model by federated learning to each on-vehicle carbon measurement terminal to improve the local carbon measurement model and achieve dynamic adjustment and optimization.

8. A vehicle carbon emission safety calculation system for a vehicle carbon emission safety calculation method based on the Internet of Vehicles according to any one of claims 1-7, characterized in that, The system includes an on-vehicle carbon measurement terminal deployed on each vehicle and a carbon measurement operation platform; The on-vehicle carbon measurement terminal includes: A CAN communication module for data transmission between the vehicle CAN bus and the MCU module; The MCU module, as the core processing unit of the on-vehicle carbon measurement terminal, is embedded with a local carbon measurement model, obtains the real-time operation data of the vehicle from the vehicle CAN bus through the CAN communication module, and calculates the real-time operation data through the local carbon measurement model to obtain the carbon data of the vehicle; A storage module for temporarily storing the real-time operation data and carbon data of the vehicle when the network is unstable or disconnected; A data encryption module for encrypting the real-time operation data using an encryption algorithm and encrypting the carbon data using homomorphic encryption technology; An external communication module for transmitting the encrypted real-time operation data and carbon data to the carbon measurement operation platform via 4G CAT1, 5G or 6G; The carbon measurement operation platform obtains the CAN message information of the vehicle from the vehicle enterprise, combines the encrypted real-time operation data and carbon data uploaded by multiple in-vehicle carbon measurement terminals, calculates and optimizes the global carbon emission model based on the federated learning technology, generates the global calculation result of carbon emissions, and generates a carbon emission report according to the global calculation result, and conducts data interaction with external systems.

9. The vehicle carbon emission safety calculation system according to claim 8, characterized in that, The MCU module calculates the real-time operation data through the local carbon measurement model, and further includes: reviewing the operation data and carbon data calculation results of the vehicle within the historical time through the local experience replay mechanism, and comparing them with the current operation state of the vehicle, so as to adjust the weights and parameters of the current local carbon measurement model. The formula is: ； Wherein, is the local replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents that during the local experience replay process, given the historical hidden state the probability of the occurrence of event ; represents the probability distribution of the occurrence of event under the current local carbon accounting model parameters, given the historical hidden state and the condition of event ; The carbon measurement operation platform calculates and optimizes the global carbon emission model based on the federated learning technology, and further includes: performing global experience replay based on the CAN message information of different vehicles. The formula is: ； In the formula, is the global replay loss function; is the q-th relevant event within the historical time; is the historical hidden state; represents that during the global replay process, given the historical hidden state the probability of the occurrence of event ; represents the probability distribution of the occurrence of event under the current global carbon emission model parameters given the historical hidden state .

Images