Electric Vehicles & ZEV Technologies

White Paper on Zero Emission Vehicles performance through Artificial Intelligence

Electrical Vehicles Energy Performance and Optimal Charging

For maximizing energy efficiency of electrical vehicles, maintaining optimal charging schedule for fixed or flexible driving ranges, and reducing the maintenance costs, Netsity proposes artificial intelligence based data analysis / classification, system control / monitoring, and design / performance optimization for zero emissions vehicles, by capturing millions of miles of data points relating to engine telemetry, real-world traffic conditions, topology of the road, weight, temperature, and many other parameters, the battery status, vehicle speed, driving cycle, payloads, tyre and rolling resistance, driver behavior, with other contextual data.

White Paper Abstract

Zero emission vehicles are becoming increasingly prominent, especially electric vehicles (EVs) with mobility applications in transit buses, last mile delivery, transportation, logistics, medium, heavy duty trucks, people movers, and passenger cars. With ZEVs adoption increasing, electrical vehicle OEMs are facing challenges with regards to building more energy efficient propulsion systems, reducing the cost of ownership of EVs with Li-ion battery packs forming the major chunk of those costs, getting higher efficiency in regenerative braking system, helping the fleet owners extract more mileage in varying conditions, and run their fleets with maximum uptime and minimum maintenance costs. EV charging infrastructure is still in early stages, and with only a small number of charging stations for the growing fleet of vehicles, EV charging poses bigger challenges for fleet owners who are trying to maximise their operating profits and ensure stability with grid connectivity and transformer loads.

Updated On: June 2021

    White Paper Topics

    In this Zero Emission Vehicles White Paper, we have attempted to address ZEV challenges with focus on five key objectives for EV OEMs and Fleet Owners:

    • Minimizing energy consumption
    • Reducing the maintenance costs & operating expenses
    • Higher profitability through efficient charging schedule
    • Lower capital costs for batteries
    • Driver safety
    White Paper References
    1. High-Dimensional Data-Driven Energy Optimization for Multi-Modal Transit Agencies, Project Report November 2020. Philip Pugliese, Abhishek Dubey, Aron Laszka, Yuche Chen.
    2. A Decision Support Framework for Grid-Aware Electric Bus Charge Scheduling. Geoffrey Pettet, Malini Ghosal, Shant Mahserejian, Sarah Davis, Siddharth Sridhar, Abhishek Dubey, and Michael Kintner-Meyer.
    3. A Machine Learning Method for Predicting Driving Range of Battery Electric Vehicles. Shuai Sun, Jun Zhang, Jun Bi,, Yongxing Wang.
    4. A Review and Outlook of Energy Consumption Estimation Models for Electric Vehicles. Yuche Chen, Guoyuan Wu, Ruixiao Sun, Abhishek Dubey, Aron Laszka, Philip Pugliese.
    5. An Approach of Applying Machine Learning for Range Prediction for LD, HD Commercial Electrical Trucks Energy Management. Balaji Srinivasan, J. Devi Shree.
    6. Data-Driven Prediction and Optimization of Energy Use for Transit Fleets of Electric and ICE Vehicles. Afiya Ayman, Amutheezan Sivagnanam, Michael Wilbur, Philip Pugliese, Aron Laszka.
    7. Deep Reinforcement Learning for the Electric Vehicle Routing Problem with Time Windows. Bo Lin, Bissan Ghaddar, Jatin Nathwani.
    8. Efficient Data Management for Intelligent Urban Mobility Systems. Michael Wilbur, Philip Pugliese, Aron Laszka, Abhishek Dubey.
    9. Time-Dependent Electric Vehicle Routing Problem with Time Windows and Path Flexibility. Li Wang, Shuai Gao, Kai Wang, Tong Li, Lin Li, and Zhiyuan Chen.