Artificial Intelligence based Machine Learning with data, Optimization and Prediction
MOEV AI™uses real time and historical data gathered from EV chargers, fleet telematics, driver preferences and driving history, duty cycle needs, vehicle information, routes, weather, terrain, traffic and various other types of information to perform prediction of energy needs of the EV so as to guide the driver and fleet operator on how many miles they have remaining throughout the day, when, where and for how long recharge and subsequently to precisely manage and control the charging of the vehicle to optimize around fleet needs of minimum cost, optimize fleet operations and dispatch, maximize EV battery life and achieve maximum utilization of the EV charging infrastructure.
Our technology is unique and it uses a combination of machine learning, deep learning, neural networks, regression, clustering, data science, dynamic optimization and several other AI and data science technologies to achieve these objectives. Our system operates on the Internet Cloud, is offered as a software as a service (SaaS), and functions independent of the charging hardware by supporting the OCPP (MOEV AI™ supports both Versions 1.6 and 2.01) standard, is independent of the vehicle telematics by way of using an API (application programming interface), and is independent of the vehicle manufacturer.
The MOEV founders have been researchers and faculty members from UCLA Samueli School of Engineering from where the company was spun out, and, who collectively have deep technical expertise and knowledge in the field of electric vehicles, AI, Machine Learning and smart charging infrastructure, and have published over 300 technical publications/patents. All members of the technical team have a masters degree and half of them have PhDs in engineering/software/data science/etc.