<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Batteries | LOOPS Research Group</title><link>https://p-quintanilla.github.io/tag/batteries/</link><atom:link href="https://p-quintanilla.github.io/tag/batteries/index.xml" rel="self" type="application/rss+xml"/><description>Batteries</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Fri, 28 Aug 2026 00:00:00 +0000</lastBuildDate><image><url>https://p-quintanilla.github.io/media/logo_hu3037203394763648603.png</url><title>Batteries</title><link>https://p-quintanilla.github.io/tag/batteries/</link></image><item><title>Presented at the IFAC World Congress 2026, Busan</title><link>https://p-quintanilla.github.io/post/ifac-busan-presentation/</link><pubDate>Fri, 28 Aug 2026 00:00:00 +0000</pubDate><guid>https://p-quintanilla.github.io/post/ifac-busan-presentation/</guid><description>&lt;p>How can batteries respond to markets in seconds while protecting their health for years? 🔋&lt;/p>
&lt;p>This is the question behind our work presented at the &lt;strong>23rd IFAC World Congress 2026&lt;/strong> in &lt;strong>Busan, Korea&lt;/strong> 🇰🇷&lt;/p>
&lt;p>Our hierarchical approach separates these two timescales: &lt;strong>model predictive control&lt;/strong> operates on a long timescale, accounting for battery health and future value, while &lt;strong>reinforcement learning&lt;/strong> handles fast market decisions. We will soon upload our arXiv preprint with more details! :)&lt;/p>
&lt;p>A special thank you to &lt;strong>Rasa Pourjam&lt;/strong>, whose hard work made this presentation possible. Ehecatl Antonio del Rio Chanona and I co-supervised Rasa&amp;rsquo;s MSc thesis at The Sargent Centre for Process Systems Engineering, and we are incredibly proud of how far he has taken the project.&lt;/p>
&lt;p>🔗 &lt;a href="https://www.linkedin.com/posts/paulinaquintanilla_mpc-rl-ugcPost-7499026620578648078-Kc4T/" target="_blank" rel="noopener">View the announcement on LinkedIn&lt;/a>&lt;/p></description></item></channel></rss>