AI in Charge: Large-Scale Experimental Evidence on Electric Vehicle Charging Demand

Robert D. Metcalfe; Andrew Schein; Cohen R. Simpson; Yixin Sun

doi:10.3386/w34709

AI in Charge: Large-Scale Experimental Evidence on Electric Vehicle Charging Demand

Robert D. Metcalfe, Andrew Schein, Cohen R. Simpson & Yixin Sun

Working Paper 34709

DOI 10.3386/w34709

Issue Date January 2026

One of the promising opportunities offered by AI to support the decarbonization of electricity grids is to align demand with low-carbon supply. We evaluated the effects of one of the world’s largest AI managed EV charging tariffs (a retail electricity pricing plan) using a large-scale natural field experiment. The tariff dynamically controlled vehicle charging to follow real-time wholesale electricity prices and coordinate and optimize charging for the grid and the consumer through AI. We randomized financial incentives to encourage enrollment onto the tariff. Over more than a year, we found that the tariff led to a 42% reduction in household electricity demand during peak hours, with 100% of this demand shifted to lower-cost and lower-carbon-intensity periods. The tariff generated substantial consumer savings, while demonstrating potential to lower producer costs, energy system costs, and carbon emissions through significant load shifting. Overrides of the AI algorithm were low, suggesting that this tariff was likely more efficient than a real-time-pricing tariff without AI, given our theoretical framework. We found similar plug-in and override behavior in several markets, including the UK, US, Germany, and Spain, implying the potential for comparable demand and welfare effects. Our findings highlight the potential for scalable AI managed charging and its substantial welfare gains for the electricity system and society. We also show that experimental estimates differed meaningfully from those obtained via non-randomized difference-in-differences analysis, due to differences in the samples in the two evaluation strategies, although we can reconcile the estimates with observables.

We thank Lucy Bourke and Joe Grainger, from Centre for Net Zero (CNZ), for their critical support with logistics and background research. We thank Jaye Cribb, from Octopus Energy Limited (OE), for devising the strategy used to detect ownership of an electric vehicle based on electricity usage, and Charlotte Avery, from CNZ, for further refining and implementing that strategy. We thank Francesca Corby, Geraldine De Boisse, and Katrin Weingartner, from OE, for their comments and collaboration regarding study design and implementation, in particular construction of the email-based treatments used for customer experimentation. We thank George Doucy, Ben Ferris, Lilla Hoddosy, Ryan Jenkinson, Will Reeves, Richard Sephton, and Henry Tagg, all from OE, for their guidance around operational aspects of the EV charging algorithms and associated data collection. We thank Andy Hackett, from CNZ, for specific comments on the text of the paper itself. We thank Navya Kumar for excellent research assistance. We thank Omar Asensio, Susanna Berkouwer, Louise Bernard, Daniel Björkegren, David Byrne, Gus Chadney, Sheng Chai, Sylvain Chassang, Daniel Lopez Garcia, Charlie Hutchinson, Alex Imas, Maria Jacob, Seung Min Kim, Justin Kirkpatrick, Alex Schoch, Ben Sprung-Keyser, Phil Steele, Chad Syverson, Arthur van Bentham, Casey Wichman, Izzy Woolgar, Lucy Yu, and seminar participants at Wharton, Manchester Workshop on the Economics of Energy Transition, and Harvard's Workshop on the Economics and Policy of Electric Transportation Charging Infrastructure for their valuable insights and comments. This work would not have been possible without financial support from the Abdul Latif Jameel Poverty Action Lab's (J-PAL) King Climate Action Initiative (K-CAI). Conflicts of Interest: Andrew Schein and Yixin Sun are paid employees of Centre for Net Zero (CNZ), a part of the Octopus Energy Group Limited (OEG), Robert Metcalfe is a consultant, and Cohen Simpson was a paid employee of CNZ at the time of the trial but is no longer employed by CNZ. The four authors made final decisions regarding experimental design, data analysis, and writing; all mistakes herein are ours alone.
Copy Citation

Robert D. Metcalfe, Andrew Schein, Cohen R. Simpson, and Yixin Sun, "AI in Charge: Large-Scale Experimental Evidence on Electric Vehicle Charging Demand," NBER Working Paper 34709 (2026), https://doi.org/10.3386/w34709.

Download Citation

MARC RIS BibTeΧ
- randomized controlled trials registry entry

AI in Charge: Large-Scale Experimental Evidence on Electric Vehicle Charging Demand

Related

Topics

Programs

More from the NBER