logo
ResearchBunny Logo
Enhancing Indoor Temperature Forecasting through Synthetic Data in Low-Data Environments

Engineering and Technology

Enhancing Indoor Temperature Forecasting through Synthetic Data in Low-Data Environments

Z. Thiry, M. Ruocco, et al.

In a groundbreaking study by Zachari Thiry, Massimiliano Ruocco, Alessandro Nocente, and Michail Spitieris, the potential of synthetic data generated through AI methods like GANs and VAEs to enhance indoor temperature forecasting is explored. This research demonstrates how augmenting real data can significantly boost forecasting accuracy and reduce training variance, addressing a critical challenge in HVAC system control.

00:00
00:00
Playback language: English
Abstract
Forecasting indoor temperatures is crucial for efficient HVAC system control. Data scarcity hinders this, as extreme scenarios are rarely recorded. This paper investigates using synthetic data generation via AI methods (GANs and VAEs) to augment real data and improve forecasting accuracy. The study assesses the synthesizers independently and then evaluates their utility in forecasting using a simple LSTM model. Results show that synthetic data augmentation enhances forecasting accuracy and mitigates training variance.
Publisher
Published On
Authors
Zachari Thiry, Massimiliano Ruocco, Alessandro Nocente, Michail Spitieris
Tags
indoor temperature forecasting
HVAC control
synthetic data
AI methods
GANs
VAEs
LSTM model

Related Publications

Explore these studies to deepen your understanding of the subject.

Enhancing Indoor Temperature Forecasting through Synthetic Data in Low-Data Environments
Engineering and Technology

Enhancing Indoor Temperature Forecasting through Synthetic Data in Low-Data Environments

Z. Thiry, M. Ruocco, et al.

Addressing gaps in data on drinking water quality through data integration and machine learning: evidence from Ethiopia
Environmental Studies and Forestry

Addressing gaps in data on drinking water quality through data integration and machine learning: evidence from Ethiopia

A. A. Ambel, R. Bain, et al.

Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing
Computer Science

Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing

D. Rankin, M. Black, et al.

Digital Disease Surveillance for Emerging Infectious Diseases: An Early Warning System Using the Internet and Social Media Data for COVID-19 Forecasting in Canada
Medicine and Health

Digital Disease Surveillance for Emerging Infectious Diseases: An Early Warning System Using the Internet and Social Media Data for COVID-19 Forecasting in Canada

Y. Yang, S. Tsao, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny