AI Based Electric Automobile Battery Drain Forecasting System

• Published in: 2023 4th International Conference on Smart Electronics and Communication (ICOSEC) pp. 756 - 761
• Main Authors: J, Santhosh B, Benvin, Shalet, R, Arvind, V, Aswini, Maranan, Ramya, Thrinath, B.V. Sai
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.09.2023
• Subjects: artificial intelligence; battery drain; Electric vehicles; Error analysis; Machine learning; Machine learning algorithms; prediction; Predictive models; Support Vector Machine (SVM); Support vector machines; Transportation
• DOI: 10.1109/ICOSEC58147.2023.10276243

While electric vehicles (EVs) are gaining appeal as a sustainable mode of transportation, issues like range anxiety and battery depletion prevent them from being widely adopted. To better plan for charging stops, we created a model that takes into account the time of day, the length of the trip, and the temperature outside. We constructed an accurate battery drain prediction model using machine learning methods, specifically the Support Vector Machine (SVM) algorithm. With strong correlation and low error rates, our findings show that the SVM algorithm is ideal for this job. Our findings might be useful to EV owners and fleet managers as a resource for reducing wasteful driving and maximizing range. Future work might examine the effect of battery deterioration on electric vehicle performance, leading to more nuanced models for maximizing EV efficiency and reducing transportation emissions.