Smart Contract Centric Inference Engine For Intelligent Electric Vehicle Transportation System.

Area of Science:

• Computer Science
• Electrical Engineering
• Artificial Intelligence

Background:

• Increasing adoption of electric vehicles (EVs) necessitates advanced transportation systems beyond traditional cloud-based models.
• Existing systems face privacy and security challenges due to personal data disclosure during vehicle and driver information transmission.
• The need for a secure, intelligent, and decentralized solution for managing EV data and operations is paramount.

Purpose of the Study:

• To propose a secure and intelligent electric vehicle transportation system leveraging blockchain and machine learning.
• To enhance data privacy and security in EV transportation systems.
• To develop a robust system for managing EV data, decision-making, and operational control.

Main Methods:

• Utilized blockchain's smart contract module to construct an inference engine for decision-making.
• Integrated sensor data from EV control units, storing it securely on the blockchain.
• Employed a double-layer optimized long short-term memory (LSTM) algorithm for predicting EV stator temperature.

Main Results:

• The proposed system effectively processes EV sensor data, enabling intelligent decision-making and execution via actuators.
• The blockchain integration ensures secure storage and management of sensitive vehicle and driver information.
• The LSTM model demonstrated accurate prediction of EV stator temperature, contributing to operational efficiency and safety.

Conclusions:

• The developed blockchain and machine learning-based system offers a robust solution for secure and intelligent EV transportation.
• The system effectively resolves critical security and privacy issues in information and energy interactions within EVs.
• The proposed architecture enhances the reliability and robustness of intelligent electric vehicle transportation systems.