FCAI SIG

AI in energy

Coordination: Professor Zhengmao Li (Aalto University)

This SIG focuses on using AI techniques to optimize and transform current energy systems. With the massive integration of renewable energy sources, green hydrogen, power to X techniques, etc, the energy sector is at a critical juncture, undergoing transformations that require innovative and scalable solutions. In this context, AI technologies, capable of analyzing vast amounts of data, predicting energy demand, optimizing resource allocation, and managing real-time operations, are driving the global shift toward more economical, low-carbon, and intelligent energy systems.This page highlights how each of our research programs interacts with energy research within FCAI and lists the groups currently involved. 

This SIG will regularly organize online or in-person seminars to share the latest developments in AI applications for energy systems. It will provide a platform for exploring AI's role in the energy sector and promoting collaboration.

Goals

The goals of AI for Energy SIG are to foster a vibrant network and to facilitate in-depth research collaborations within the AI and energy communities. Through regular seminars, discussions, workshops, and hands-on sessionsas well as online groups in Linkedin, Slack, Github, etc, the SIG will offer members numerous opportunities for knowledge exchange and sharing of diverse insights across various subfields of AI and energy systems. By bringing together researchers, industry practitioners, and other stakeholders, the group aims to create a dynamic, collaborative platform where participants can discuss emerging trends, identify common challenges, and explore synergistic research partnerships.

Founding Event

We are hosting a funding event for our FCAI-SIG on AI for Energy. The event aims to introduce the group members and present brief 10–15-minute talks on various AI-related research topics in energy systems.The event will be held on 15th Jan. 2025 from 13:00 to 17:00 in a hybrid format (Teams+Klondyke in Dipoli, Aalto University). Everyone is welcome to join and listen to the talks, which will highlight the innovative role of AI in transforming energy systems.

Research Programs

AI for Smart Grids enables real-time monitoring and optimization by autonomously managing distributed energy resources, balancing supply and demand, and enhancing grid reliability. AI-driven solutions provide accurate demand forecasting, optimize power flow, and enable rapid responses to disturbances, making grid management more efficient. These capabilities benefit both energy providers and consumers by reducing operational costs, increasing flexibility, and facilitating the integration of renewable energy sources.

AI for Green Hydrogen optimizes the production, storage, and distribution of hydrogen as a clean energy resource. AI algorithms enhance the efficiency of electrolysis processes, predict renewable energy availability, and optimize hydrogen logistics, ensuring that hydrogen is produced and delivered at minimal cost with reduced energy losses. These innovations are critical to scaling the hydrogen economy and achieving decarbonization goals.

AI for Smart Buildings empowers energy management systems by optimizing heating, cooling, and lighting operations in realtime. By analyzing sensor data, AI adjusts building systems to reduce energy consumption, enhance occupant comfort, and lower operational costs. It can forecast energy demand, detect equipment faults, and optimize building networks, making buildings more efficient and environmentally friendly.

AI for Transportation/mobility improves energy efficiency in electric vehicles, mobile ships, and airports by optimizing battery performance, managing charging infrastructure, and reducing energy consumption. AI enhances route planning for electric vehicles and ships, contributing to reduced fuel consumption and emissions while making transportation systems more energy-efficient and sustainable.

AI for HVAC Systems optimizes heating, ventilation, and air conditioning by dynamically adjusting energy use based on building occupancy and external climate conditions. AI-driven predictive maintenance ensures that systems operate efficiently, reducing downtime and energy waste while maintaining comfort for building occupants.

AI for Water Management enhances the efficiency of water treatment and distribution by optimizing pump operations, reducing energy use, and preventing leaks. AI analyzes water usage patterns and environmental data to ensure that water is managed sustainably and energy efficiently, benefiting both water utilities and consumers.

AI for Battery Systems optimizes battery performance and lifecycle management by analyzing real-time data on usage patterns, temperature, and charge cycles. AI-driven solutions improve energy storage efficiency, predict battery health, and optimize charging and discharging processes, maximizing both battery lifespan and performance. These advancements lower maintenance costs, enhance reliability, and accelerate the widespread adoption of battery technologies in sustainable energy systems.

People

The following researchers have already taken part in the SIG. If you would like to join the SIG, please contact the coordinator.

Zhengmao Li, Assistant Professor, Aalto University – Coordinator

Simo Särkkä, Professor, Aalto University – Co-coordinator

  • Research topic: Multi-sensor data fusion, bayesian filtering and smoothing, machine learning, medical technology, AI

  • Personal Website: https://users.aalto.fi/~ssarkka/

Xueyong Jia, Doctoral Researcher, Aalto University – Co-coordinator

Marko Hinkkanen, Professor, Aalto University

Matti Lehtonen, Professor, Aalto University

Peter Lund, Professor, Aalto University

Risto Kosonen, Professor, Aalto University

Xiaozhi Gao, Professor, University of Eastern Finland

Pertti Järventausta, Professor, Tampere University

Pedro Juliano Nardelli, Full Professor, LUT University

Jouni Havukainen, Associate Professor, LUT University

Annukka Santasalo-Aarnio, Assistant Professor, Aalto University

Yaolin Xu, Assistant Professor, Aalto University

Mahdi Pourakbari Kasmaei, Assistant Professor, Aalto University

Dandan Zhao, Post-doctoral Researcher, Aalto University

Arun Narayanan, Post-doctoral Researcher, LUT University

Peng Mei, Visiting Post-doctoral Researcher, Aalto University 

Pengmin Hua, Doctoral Researcher, Aalto University

Issac Hsu, Doctoral Researcher, Helsinki GSE

  • Research topic: Energy Economics, Housing, GIS machine learning

Yinda Xu, Doctoral Researcher, Aalto University

Yang Xu, Doctoral Researcher, Aalto University

  • Research topic: Smart building, machine learning, HVAC

  • Personal Website: https://www.aalto.fi/en/people/xu-yang

Nauman Arshad, Junior Researcher, LUT University