An Edge-Based Digital Twin Framework for Connected and Autonomous Vehicles: Design and Evaluation

Aim:

            The aim of this project is to design and implement an edge-based digital twin system for monitoring and controlling the performance of a connected vehicle. Using sensors like the LM35 for engine temperature, IR sensors for speed measurement, and push buttons for speed control, the system optimizes real-time vehicle operations. It integrates the vehicle’s real-time data into a digital twin for simulation, performance evaluation, and diagnostics. This approach enhances vehicle efficiency, safety, and real-time decision-making through continuous monitoring and control.

Introduction:

             The development of connected and autonomous vehicles (CAVs) relies heavily on real-time data for monitoring and control. Digital twin technology, which creates virtual replicas of physical systems, has emerged as a powerful tool to simulate and optimize vehicle performance. By integrating sensors and edge computing, vehicle systems can dynamically monitor engine health, speed, and other critical parameters. This project aims to leverage the ESP32 microcontroller, coupled with sensors like the LM35, IR sensors, and push buttons, to implement an edge-based digital twin system that enhances vehicle performance, efficiency, and safety.

Proposed Method:

          The proposed method introduces an edge-based digital twin framework for connected vehicles, utilizing the ESP32 microcontroller to process data locally, minimizing latency, and enhancing real-time decision-making. The system incorporates multiple sensors: the LM35 for monitoring engine temperature, IR sensors for speed measurement, and push buttons for speed control and LED activation. The digital twin is implemented as a virtual representation of the vehicle, continuously updated with real-time data from the sensors. By processing data on the edge (within the vehicle), the system allows for immediate analysis and feedback, improving vehicle control, safety, and energy efficiency. The motor speed is adjusted based on user input from the push buttons, while the IR sensors ensure speed is measured accurately. Additionally, the system features LED indicators that can be controlled through a separate push button, with LDRs monitoring their status. This data feeds into the digital twin, which simulates various driving conditions, allowing for continuous optimization of vehicle performance. The digital twin also provides a platform for real-time diagnostics and predictive maintenance, alerting the user to potential issues before they occur. This approach reduces reliance on cloud-based systems and enhances overall vehicle autonomy and efficiency.