Reinforcement Learning for Automous Building Energy Management

  • Biemann, Marco (PhD Student)
  • Garcia, Davide Astiaso (Examiner)
  • Liu, Yang (Examiner)
  • Liu, Xiufeng (Main Supervisor)
  • Huang, Lizhen (Supervisor)

Project Details


In the gradually digitized energy systems, the cutting-edge technologies including smart meters, information and communication technologies (ICT), and Internet-of-things (IoT) have increasingly used to make energy systems smarter. There is a broad range of applications that are helping smart buildings to become a reality. IoT generates an enormous amount of data that can be analyzed in depth to reveal the impact of building operation on energy consumption, greenhouse gas emission, users and owners. The innovation brought by big data can change the landscape of traditional building management. For example, online data-driven models generated by novel algorithms can enable building operation quickly adapting to the needs of users and energy grids. Machine and deep learning provide new opportunities through implementation into building energy management systems.

The objective of this project is to develop methods, tools and theories for optimizing building energy systems through machine and deep learning methods, in particular, reinforcement learning. A multi-agent based model will be created and applied to buildings to improve indoor environment and energy efficiency, to reduce greenhouse gas emission, and to make energy demand flexible.
Effective start/end date01/12/201910/07/2023

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

  • SDG 7 - Affordable and Clean Energy


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.