Effectiveness of neural networks and transfer learning for indoor air-temperature forecasting

Bellagarda, Andrea; Césari, Silvia N.; Aliberti, Alessandro; Ugliotti, Francesca Maria; Bottaccioli, Lorenzo; Macii, Enrico; Patti, Edoardo

doi:10.1016/j.autcon.2022.104314

Cited by 18 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Validation primarily focuses on temperature and building energy consumption due to the continuous interplay between indoor air temperature and energy demands (Chong et al, 2021). Key parameters influencing simulation results include weather data (Beagon et al, 2020), building envelope, internal gains, zone set points, and HVAC system settings (heating and cooling set points) (Al-Shargabi et al, 2022;Afroz et al, 2018;Beagon et al, 2020;Bellagarda et al, 2022). Internal gains encompass occupant profiles and density, lighting, equipment, and operational schedules, significantly impacting energy end-users (Koulamas et al, 2018).…”

Section: Sasbementioning

confidence: 99%

A systematic approach to manual calibration and validation of building energy simulation

Tomrukcu,

Kizildag,

Avgan

et al. 2024

SASBE

View full text Add to dashboard Cite

PurposeThis study aims to create an efficient approach to validate building energy simulation models amidst challenges from time-intensive data collection. Emphasizing precision in model calibration through strategic short-term data acquisition, the systematic framework targets critical adjustments using a strategically captured dataset. Leveraging metrics like Mean Bias Error (MBE) and Coefficient of Variation of Root Mean Square Error (CV(RMSE)), this methodology aims to heighten energy efficiency assessment accuracy without lengthy data collection periods.Design/methodology/approachA standalone school and a campus facility were selected as case studies. Field investigations enabled precise energy modeling, emphasizing user-dependent parameters and compliance with standards. Simulation outputs were compared to short-term actual measurements, utilizing MBE and CV(RMSE) metrics, focusing on internal temperature and CO2 levels. Energy bills and consumption data were scrutinized to verify natural gas and electricity usage against uncertain parameters.FindingsDiscrepancies between initial simulations and measurements were observed. Following adjustments, the standalone school 1’s average internal temperature increased from 19.5 °C to 21.3 °C, with MBE and CV(RMSE) aiding validation. Campus facilities exhibited complex variations, addressed by accounting for CO2 levels and occupancy patterns, with similar metrics aiding validation. Revisions in lighting and electrical equipment schedules improved electricity consumption predictions. Verification of natural gas usage and monthly error rate calculations refined the simulation model.Originality/valueThis paper tackles Building Energy Simulation validation challenges due to data scarcity and time constraints. It proposes a strategic, short-term data collection method. It uses MBE and CV(RMSE) metrics for a comprehensive evaluation to ensure reliable energy efficiency predictions without extensive data collection.

show abstract

Section: Sasbementioning

confidence: 99%

A systematic approach to manual calibration and validation of building energy simulation

Tomrukcu,

Kizildag,

Avgan

et al. 2024

SASBE

View full text Add to dashboard Cite

show abstract

“…A few examples of application of the transfer learning method are listed herein: the detection of faults in chillers [6,7], the forecasting of building energy demand [8,9], the control of HVAC systems [10,11], the detection of faults in solar photovoltaic modules [12], the detection of gas path faults across the turbine fleet [13], the forecasting of indoor air temperature [14], and the building information extraction [15]. The detailed literature review of applications of transfer learning to HVAC systems is beyond the scope of this paper.…”

Section: Transfer Learningmentioning

confidence: 99%

“…Bellagarda et al [14] tested different TL methods applied to neural network models for the forecasting of indoor air temperature in existing buildings. The results indicate that the implementation of TL contributed to an extension of the forecast horizon by 13.4 hours on average.…”

Section: Transfer Learningmentioning

confidence: 99%

Transfer Learning Prediction Performance of Chillers for Neural Network Models

Dou,

Zmeureanu

2023

Energies

View full text Add to dashboard Cite

Building automation systems installed in large commercial buildings record sub-hourly measurements from hundreds of sensors. The use of such large datasets are challenging because of missing and erroneous data, which can prevent the development of accurate prediction models of the performance of heating, ventilation, and air-conditioning equipment. The use of the transfer learning (TL) method for building applications attracted researchers to solve the problems created by small and incomplete datasets. This paper verifies the hypothesis that the deep neural network models that are pre-trained for one chiller (called the source chiller) with a small dataset of measurements from July 2013 could be applied successfully, by using TL strategies, for the prediction of the operation performance of another chiller (called the target chiller) with different datasets that were recorded during the cooling season of 2016. Measurements from a university campus are used as a case study. The results show that the initial hypothesis of this paper is confirmed.

show abstract

“…Para (Bellagarda et al, 2022), las Tecnologías de la Información y Comunicaciones brindan oportunidades innovadoras para que la previsión e integración de nuevas políticas de control, sin embargo, dichas tecnologías deben superar desafíos como la falta de datos históricos precisos necesarios para las predicciones. La aplicabilidad de redes neuronales innovadoras para predicciones de series temporales, han permitido con efectividad establecer un pronóstico de la temperatura del aire interior, mostrando niveles constantes de precisión y comodidad.…”

Section: Trabajos Relacionadosunclassified

Modelo de serie temporal para pronosticar la temperatura superficial del mar en la zona costera de Paita (Perú)

Cáceres

Nima

et al. 2022

revTECHNO

View full text Add to dashboard Cite

Las técnicas de inteligencia artificial han evolucionado y fortalecido permitiendo desarrollar propuestas transversales que velen y salvaguarden la integridad del ser humano. El presente estudio tiene como objetivo, elaborar una serie de tiempo que pronostique la Temperatura Superficial del Mar (TSM) a escala promedio diaria en la zona costera de Paita, Perú. La metodología empleada se centró en cinco fases, desde la recolección de datos hasta la validación del modelo. Los resultados obtenidos dan a conocer que existe un margen de error del 3.96% sobre la TSM a escala promedio semanal y una diferencia de 0.05 a 1.42, de manera diaria.

show abstract

Effectiveness of neural networks and transfer learning for indoor air-temperature forecasting

Cited by 18 publications

References 28 publications

A systematic approach to manual calibration and validation of building energy simulation

A systematic approach to manual calibration and validation of building energy simulation

Transfer Learning Prediction Performance of Chillers for Neural Network Models

Modelo de serie temporal para pronosticar la temperatura superficial del mar en la zona costera de Paita (Perú)

Contact Info

Product

Resources

About