MOEV.AI™
Electric Fleet Optimization, Charging Management and Yard Management
MOEV AI ™
AI software predicts throughout the day the energy needed and miles available for the vehicle’s duty cycle needs, and uses data fleet telematics, real-time traffic, driving routes, weather, electricity pricing, EV metering, driver behavior and vehicle/battery data. It uses this information to ensure that duty cycle needs of route/block/run/dispatch/delivery are met. This reduces stress of the drivers and operators and gives them confidence to use their EVs more than they are currently.
AI based charging management optimizes when and how much to charge to minimize electric bill while ensuring that charging needs are met by reducing demand charges and optimizing around time of use pricing. Using machine learning software on real time data from OCPP chargers (MOEV.AI™ supports both Versions 1.6 and 2.01) in combination with historical behavior, we help our customer improve reliability of charging.
MOEV.AI™ dashboard provided to the customer has an interactive touch screen that displays real-time information predicted remaining miles of each EV, the current and future predicted state of charge (SOC), predicted energy consumption of each vehicle through the day, charging scheduling including whether a vehicle needs to return in the middle of the day to recharge, where, when and how much to recharge, and all this data feeds into their real time dispatch and operations.
This dashboard fully manages and displays where and how much each vehicle is charging and predicts when it will complete charging so as to make it available for operations.
MOEV.AI™ Dashboard
- DISPATCH capability
The dispatch shows the current and future status of the EV battery, and actual miles available for travel. Every morning it maps the most optimal vehicle to service the energy needs of each route. Throughout the day it continues to monitor real-time changes to traffic, weather, road conditions, etc., and keeps the driving mileage projections up to date and even recommends if a bus should be brought back to the yard or replaced.
In the yard, the system guides the driver as to which charger and parking spot the vehicle should be parked at to ensure that adequate levels of charge are provided, and predicts when it will be ready to serve the next duty cycle. It ensures that the vehicle that needs to leave first is parked in a spot that minimizes the need for an operator to move other vehicles. It solves complex triple energy-time-space problems using data and machine learning to simplify yard management.