by Mike Szudarek, Marx Layne & Company

Originally Published: Automation Alley

June 12, 2024

“The ultimate purpose of collecting the data is to provide a basis for action or a recommendation.”

– W. Edwards Deming

As tasks grow in complexity and the volume of data increases, especially in real-time, the value of AI and predictive modeling becomes ever more apparent. Accumulating data is one thing; knowing what to do with it is quite another, as Deming suggested.

AI is poised to substantially accelerate the adoption of electric vehicles (EVs) across various sectors, including consumer, commercial, governmental, educational, industrial, agricultural, and specialty markets.

AI-augmented EV transportation will build on sophisticated vehicle management systems, such as telematics, fleet management software, and route scheduling, as well as preventive and predictive maintenance and traffic management systems. These advancements were present even before the growth of non-internal combustion engine vehicles.

AI will be crucial in managing the transition from all-ICE to hybrid and predominantly or all-EV fleets. For example, scheduling will need to accommodate mixed fleets with varying fueling requirements, ranges, and driver behaviors. Similarly, preventive and predictive maintenance will impact mechanic training, scheduled intervals, and parts ordering. More sophisticated information systems, with advanced sensors and real-time telemetry, will greatly enhance understanding and guidance of driving behaviors.

Focus on EV Charging and The Grid

EVs have introduced new technologies and operational challenges for transportation managers, particularly regarding EV battery charging and grid interaction. This evolving landscape employs AI and involves collaboration among various stakeholders, including EV charging infrastructure providers and electric utilities.

Kevin Kushman, CEO of Cincinnati-based Electrada, which has provided EV charging infrastructure to fleets since 2020, observes that “challenges such as depot charging capacity planning, scaling charging networks with fleet expansion, and optimizing charging demand to synch with utility infrastructure capacity represent engineering and economic use cases for AI. The most effective business model to address these challenges has been the emergence of Charging-as-a-Service (CaaS) providers, like Electrada, who develop necessary charging infrastructure and guarantee capacity, pricing, and performance for fleet operators.

Benefits of AI Support

Kushman also notes that the CaaS model incorporates critical partnerships that speed up EV adoption in fleet operations, improving costs and organizational efficiencies. AI-powered software solutions at fleet electrification depots enhance the efficiency of electric fleets while reducing the financial and operational risk to scaling EV usage.

These AI solutions reduce EV charger downtime and electric fuel costs. They integrate EV charging hardware and vehicle telematics to help fleet operators make real-time decisions, resulting in increased on-time departures, reduced energy costs, and fully charged vehicles, further accelerating electrification as the most cost-effective fleet strategy over time.

AI-guided fleets save costs by orchestrating battery charging based on route needs and electricity costs, contributing to grid stability by providing excess power back to the grid during peak times. As we work towards mitigating climate change and reducing dependence on fossil fuels, this grid coordination will become essential.

Future Prospects

EV-powered transportation parallels autonomous vehicles in completing complex tasks faster and with greater precision. AI will be critical to mastering new technologies and maximizing the potential of EV-powered transportation. While EVs can be simpler than ICE vehicles in some ways, they can also be more complex. Through AI, we can master both extremes of this spectrum.

Read Full Article