Abstract Description: The Air Force is rapidly replacing its 54,368 non-tactical ICE-powered vehicles with electric vehicles (EVs). This rapid transition poses pressing economic and operational challenges associated with the required infrastructural changes, related to both chargers and electricity distribution lines, and different scheduling due to longer charging times compared to refueling.
This paper presents a tool that smooths this transition by optimizing current operations and future purchases. Our methodology analyzes multiple data sources—vehicles’ and chargers’, usage patterns, utility rates, etc.— with our advanced ML algorithms to identify the optimal number and types of EVs and chargers, minimize peak utility demand, and maximize vehicle utilization through efficient shift scheduling.
Using the tool, we will present a case study for cargo handling equipment electrification, demonstrating at least 30% total cost of ownership (TCO) reduction compared to ICE equivalents, by minimizing capital expenditure on vehicles and infrastructure while reducing long-term operational costs. We will also demonstrate the emissions benefits in the case study, both in terms of climate pollution and criteria air pollutants. Based on the emissions benefits, we will estimate the health benefits for personnel at the base from the reduction of diesel exhaust.
Through the case study, we will demonstrate a practice-ready software tool that reduces the time for feasibility assessment, streamlines the procurement decisions of vehicles and chargers, and optimizes the daily scheduling of vehicle and charger use in operations.
