(Press-News.org)
Residential heating, ventilation, and air conditioning (HVAC) systems constitute a significant proportion of energy usage in buildings, necessitating energy management optimization. In this context, occupancy aware HVAC control is a promising option with 20-50% energy savings in homes. However, occupancy sensing technology suffers from long payback times, privacy issues, and poor comfort. Moreover, there is an increasing need for further advanced technologies that help regulate indoor air quality in addition to energy control.
To meet these expectations, scientists have recently turned to intelligent control methods such as quantum reinforcement learning (QRL) based on quantum computing principles. Such approaches can notably accelerate the machine learning process as well as handle the complexity of real-world building dynamics.
In a new breakthrough, a group of researchers from the Republic of Korea, led by Sangkeum Lee, Assistant Professor of Computer Engineering at Hanbat National University, have presented the first demonstration of continuous-variable, quantum-enhanced reinforcement learning for residential HVAC and home power management. Their innovative findings were made available online on 16 June 2025 and published in Volume 21 of the journal Energy and AI on 01 September 2025.
Dr. Lee highlights the novelty of their work. “Unlike conventional reinforcement learning techniques, QRL leverages quantum computing principles to efficiently handle high dimensional state and action spaces, enabling more precise HVAC control in multi-zone residential buildings. Our framework integrates real-time occupancy detection using deep learning with operational data, including power consumption patterns, air conditioner control data, and external temperature variations.”
Furthermore, the proposed technology integrates features such as multi-zone cooling—to control temperature of individual zones in building—and clustering—to group similar data points and adjust cooling. In this way, a single controller jointly optimizes comfort, energy cost, and carbon signals in real time.
The researchers performed simulations based on real world data from 26 residential households over a three-month period. They found that QRL HVAC control significantly outperforms deep deterministic policy gradient method as well as proximal policy optimization algorithm, while maintaining thermal comfort, achieving 63% and 62.4% reductions in power consumption, respectively, and 64.4% and 62.5% decrease in electricity costs, respectively.
The present approach comes with many more benefits. It is retrofit-friendly and works with standard temperature, occupancy, and CO₂ sensors and common HVAC equipment and thermostats. It is also robust to uncertainty, easily handling noisy forecasts on weather and occupancy and device constraints. In addition, it has a generalizable framework that can be extended from apartments to small buildings and microgrids.
Dr. Lee talks about the potential applications of their innovation. “It can be utilized in smart thermostats and autonomous home energy management systems that co-optimize comfort, bills, and emissions without manual tuning and rooftop photovoltaics and home battery scheduling. Our framework is also useful for utility demand-response and time-of-use programs with automated control.”
QRL based HVAC control can notably be applied at community or campus scale through grid-interactive efficient buildings and virtual power plants (VPPs). Herein, millions of homes can coordinate as VPPs to stabilize renewables-heavy grids. It can also ensure personalized indoor environmental quality within carbon budgets and integrate advanced intelligent control options.
As hardware matures in the coming years, quantum-accelerated policy search could facilitate faster training for complex multi-energy systems such as HVAC, electric vehicles, and energy storage systems. In the long term, this work is expected to guide the path toward standardized secure controllers that can be certified and deployed at a wide scale!
***
Reference
DOI: 10.1016/j.egyai.2025.100541
About the institute
Established in 1927, Hanbat National University (HBNU) is a university in Daejeon, South Korea. As a leading national university in the region, HBNU strives to take the lead in solving problems in the local community and solidifying its cooperation with industries. The university’s vision is to become “an Innovation Platform University integrating local community, industry, academia, and research.” With its focus on practical education and regional impact, HBNU continually advances technological solutions grounded in creative thinking and real-world relevance.
Website: https://www.hanbat.ac.kr/eng/index.do
About the author
Professor Sangkeum Lee is an Assistant Professor of Computer Engineering at Hanbat National University, South Korea, where he heads the EcoAI Lab. His research expertise lies in the integration of reinforcement learning, optimization, and quantum machine learning to improve energy efficiency and reliability in buildings, factories, and smart grids. He partners with both industry and national labs on projects ranging from factory energy management and anomaly detection to grid-interactive building control. His contributions in AI-driven energy systems and autonomous process control are documented in numerous peer-reviewed papers and patents.
END
HOUSTON – Oct. 2, 2025 – Obesity has long been acknowledged as a risk factor for a wide range of diseases, but a more precise link between obesity and Alzheimer’s disease has remained a mystery – until now.
A first-of-its-kind study from Houston Methodist found that adipose-derived extracellular vesicles, tiny cell-to-cell messengers in the body, can signal the buildup of amyloid-β plaque in obese individuals. These plaques are a key feature of Alzheimer’s disease.
The study, “Decoding Adipose–Brain Crosstalk: Distinct Lipid Cargo in Human Adipose-Derived ...
Kyoto, Japan -- With their massive flapping ears and long trunks, it isn't hard to believe that elephants tend to rely on acoustic and olfactory cues for communication. They use gestures and visual displays to communicate as well, but we don't really know how much. Visual communication research has mainly focused on species that are primarily visual, like nonhuman primates.
A previous study demonstrated that African savanna elephants can recognize human visual attention based on a person's face and body orientation, but this had yet to be investigated in their Asian cousins. Asian elephants split from African elephants millions of years ago, so their behavior and cognition differ ...
PHILADELPHIA— Researchers at Penn Medicine have identified specific brain circuits that are impacted by psilocybin—the active compound found in some psychedelic mushrooms—which could lead to new paths forward for pain and mental health management options. Chronic pain affects more than 1.5 billion people worldwide and is often deeply entangled with depression and anxiety, creating a vicious cycle that amplifies suffering and impairs quality of life. The study from the Perelman School of Medicine at the University of Pennsylvania- ...
A new study has found that UK Members of Parliament (MPs) and the public overestimated the time left to meet a critical deadline for limiting global warming.
Researchers at the University of East Anglia (UEA) surveyed a representative sample of the previous House of Commons, and the public in Britain, Canada, Chile and Germany, on their knowledge of a well-publicised statement from the UN’s Intergovernmental Panel on Climate Change (IPCC).
It related to when global ...
Semaglutide or tirzepatide should be the first line treatment for people living with obesity and most of its complications, according to a new framework for the pharmacological treatment of obesity and its complications from the European Association for the Study of Obesity (EASO) to be published in the journal Nature Medicine. “Even though there are several options on the market, the reality is that semaglutide and tirzepatide are so effective that they should be the first choice in almost all cases,” says co-first author Dr Andreea Ciudin.
The authors are an international team of obesity experts led by the co-chairs of the EASO Obesity Management Working Group who are Dr ...
Researchers at Integra Therapeutics, in collaboration with the Pompeu Fabra University (UPF) Department of Medicine and Life Sciences (MELIS) and the Center for Genomic Regulation (CRG), have designed and experimentally validated new synthetic proteins that can edit the human genome more efficiently than proteins provided by nature. This work, a global pioneer published today in the journal Nature Biotechnology, will be of great use in improving the current gene editing tools used in biotechnology research and personalized medicine by developing cellular (CAR-T) and gene therapies, especially to treat ...
Firms in the Gulf region are increasingly expected to align with environmental, social, and governance (ESG) standards. Yet the link between ESG performance and financial outcomes remains ambiguous. A new study examines whether publicly listed companies in GCC member states that achieve high ESG ratings also deliver superior financial performance.
The study “ESG and financial performance in the Gulf Cooperation Council” was authored by Catalina Stefanescu-Cuntze, professor of management science and faculty lead of the Master in Analytics and Artificial Intelligence Program at ESMT Berlin, together with Rodrigo Tavares and Catarina Sá from Nova School ...
University of Michigan researchers have developed a tool powered by artificial intelligence that can help them examine the behavior of a single molecule out of a sea of information in the blink of an eye—or at least overnight.
Understanding the behavior of single molecules is important: it can lead to knowledge of different cellular processes or track how diseases begin and progress. To track the behavior of single molecules, researchers tag the molecules with what's called a fluorophore. They excite these fluorophores with a laser, then use powerful microscopes to follow the behavior of the tagged molecules over time.
But ...
Western cultures tend to view teens as moody, irresponsible, and rebellious. However, in China and in other cultures, the teen years are viewed more positively and seen as a time of learning how to become responsible and fulfilling family obligations. Previous research shows that fulfilling family obligations is an important marker of maturity and that as adolescents continue to improve their skills, they can contribute more to their families.
Past studies also show that when teens are seen ...
A groundbreaking study published today in the European Geosciences Union (EGU) journal Earth System Dynamics provides a critical and previously underestimated connection between Antarctic sea ice, cloud cover, and global warming. This research is important because it shows that a greater extent of Antarctic sea ice today, compared to climate model predictions, means we can expect more significant global warming in the coming decades.
The study, led by Linus Vogt from Sorbonne University, utilized an emergent constraint based on data from 28 Earth system models and satellite observations ...