Back to Blog
Electric Vehicle charging

Forecasting

EVentually EVs

May 14, 2024

The U.S. government set a goal to make 50% of all new vehicle sales zero-emissions by 2030. California took this a step further with “ Advanced Clean Cars II

The first scatter plot below depicts load vs. temperature, while the second scatter plot shows load vs. wind chill. Each point in the figures represents the 12:00 AM KW value and the corresponding temperature or wind chill from a particular day.


The horizontal scales are purposely identical to allow for easy comparison. The most salient feature is that the curve is extended further to the left with wind chill. From a modeling perspective, this is a useful attribute as it may clarify the relationship and provide additional information.


” and several states followed. This act mandates 100% of all new car sales to be zero-emissions by 2035. Agenda setting is necessary to propel us forward, but these strict agendas have large implications for not only the future, but for now. If you are like me, you might be thinking, “What does the future have in store for the combustion engine we all know?”   That seems great. Should we now jump in with both feet and commit to using wind chill as the basis for HDD variables in our models? 


Wait — there’s more!

From Combustion Engine to EV 

I don’t currently own any vehicle, but I might be in the market for one in the next few years. The current policies surrounding electric vehicles (EV) require us to be informed about the direction the auto/energy industry is headed. Luckily, a perk of being an energy forecaster is knowing the necessary questions. With every forecast there is error, so we must apply the art of forecasting. 

If I were to purchase a gas-powered vehicle, would I be stuck with this choice until I buy my next vehicle? The obvious answer is yes, but what if it doesn’t have to be? While listening to presentations at the

recent Annual Energy Forecasting Group Meeting

, I wondered if there was a way to convert a gas vehicle to an EV? And of course, someone else already thought about it because the solution already exists in the marketplace. The

describes the process. It simply requires one to remove the internal combustion engine, insert a battery pack, electric motor(s), and other necessary equipment. As someone who knows nothing about working on cars, this seems like a daunting process. I was curious how much this would cost, and of course it varies by vehicle. Nonetheless, the cost can be as much as a new vehicle, so while it is nice to have this as an option it is somewhat of a barrier. I feel this process could certainly appeal to car enthusiasts. My curiosity was a result of my qualms towards EV’s. Specifically, I was concerned about EV charging station availability. Each of the following two figures shows hourly DryBulb temperature and wind chill for one week. The most striking feature is that the wind chill is particularly volatile. More to the point, the wind chill is spiky, while the Drybulb temperature in these examples is smooth. The obvious explanation for the volatility in the wind chill is the variability in the wind speed itself. 

So where are EV chargers?  

Here is another thought to consider. Even if the historical observations of wind speed are smooth and well behaved, we are still using it in forecast models, which means we are dependent upon the wind speed forecast. Wind speed is infamously difficult to forecast well, especially as the forecast horizon extends further into the future (i.e., tomorrow is harder to forecast than today). This is not to denigrate the hard-working and skilled meteorologists who do this work; they are faced with the thankless task of forecasting a fundamentally chaotic series.


If you are using wind chill in hourly or sub-hourly models directly or indirectly as an HDD or Heating Degree Hour variable, your model and the resulting forecasts have the potential for volatility. This may manifest in interval-to-interval variability during a single forecast run. It may also manifest as instability from forecast iteration to forecast iteration, when comparing the forecast generated at 1:00 PM to the one generated at 2:00 PM, for instance.


The map above shows charging stations across the U.S. from These troubles may be ameliorated by using variables that aggregate across the day or groups of hours. Still, this is certainly something to consider when developing forecast models that incorporate wind chill as a driver variable. Most importantly, you should just chill.PlugShare

. This site currently shows there to be 1,444 charging stations in the U.S., primarily in metropolitan areas. I live in Chicago so finding a charger may not be difficult for in-city traveling, but I can imagine this would become an issue if I was to plan a road trip, as Midwesterners tend to do but the U.S. Department of Transportation is already working on that as well as part of the 2030 zero-emissions vehicles goal. While this still leaves me hesitant to purchase an EV for now, at least now I know what’s out there. After all, the future looks to have an increased number of charging stations and maybe there will be portable backup batteries for EV’s like they have for phones. So, I don’t have an answer to my original question “Gas or Electric?” but I can say is maybe EVentually I will buy an EV. 

By Brian Rissman

Forecasting Specialist

Mr. Brien Rissman Jr. is a Forecasting Specialist with Itron’s Forecasting Solutions division, where he works mainly with the Northeast office under Mike Russo. Brien started working with Itron in June 2023, and while he is relatively new to the team, he brings a strong background in economic modeling and forecasting. Under the direction of the forecasting team at Itron, Brien primarily assists and implements projects in the medium- term and long-term realm, consisting of long-term forecasts, internal revenue plans, rate case forecasts, weather variance reports, and monitoring Itron’s forecasting as a service (FaaS) solution.

energy