Comparison of model-based and data-driven approaches for modeling energy and comfort management systems, with a case study

Maccarana, Yamuna; Panza, Angela; Maroni, Gabriele; Sarto, Luca; Carta, Marco Francesco; Reggiani, Sandro

doi:10.1109/eeeic.2019.8783703

Cited by 2 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…development: a pilot plant has been chosen to practically test the data-driven multi-step approach [22]. Iterative testing led to improve the data-driven model until its final design was obtained; 3.…”

Section: Methodsmentioning

confidence: 99%

“…Premised that, to fully exploit their potentiality, all the methodological approaches require to model the thermal dynamics of the building. Reference [22] shows that a data-driven approach based on a Random Forest regression model performs better than a standard model-based approach on the winter period for the same building that has been used in this research. Hence, this paper focuses on the data-driven approach.…”

Section: The Data-driven Ecms Modelmentioning

confidence: 99%

“…Even if [22] unveiled that data-driven approaches are more accurate than model-based approaches, it has to be raised that a static, time invariant approach was adopted, not exploiting the advantage that derives from updating the prediction with real time data. Indeed, in recent years the interest on the prediction of the inner temperature of a building through dynamic data-driven approaches is constantly growing.…”

Section: Machine Learning Models For Predicting the Inner Temperaturementioning

confidence: 99%

“…Once the data-driven model has been chosen to the detriment of the model-based one, the focus shifted on the improvement of the data-driven approach. In particular, in the step between development and validation, the model has been evaluated comparing its results with its previous version from [22]. Here, the application of the model on different boundary conditions, also considering other regression models, and the consequent introduction of real time data to progressively improve the solution while the time advances, makes the two versions qualitatively different.…”

Section: Model Evolutionmentioning

confidence: 99%

See 3 more Smart Citations

The Data-Driven Multi-Step Approach for Dynamic Estimation of Buildings’ Interior Temperature

Villa¹,

Sassanelli

2020

Energies

View full text Add to dashboard Cite

Buildings are among the main protagonists of the world’s growing energy consumption, employing up to 45%. Wide efforts have been directed to improve energy saving and reduce environmental impacts to attempt to address the objectives fixed by policymakers in the past years. Meanwhile, new approaches using Machine Learning regression models surged in the modeling and simulation research context. This research develops and proposes an innovative data-driven black box predictive model for estimating in a dynamic way the interior temperature of a building. Therefore, the rationale behind the approach has been chosen based on two steps. First, an investigation of the extant literature on the methods to be considered for tests has been conducted, shrinking the field of investigation to non-recursive multi-step approaches. Second, the results obtained on a pilot case using various Machine Learning regression models in the multi-step approach have been assessed, leading to the choice of the Support Vector Regression model. The prediction mean absolute error on the pilot case is 0.1 ± 0.2 °C when the offset from the prediction instant is 15 min and grows slowly for further future instants, up to 0.3 ± 0.8 °C for a prediction horizon of 8 h. In the end, the advantages and limitations of the new data-driven multi-step approach based on the Support Vector Regression model are provided. Relying only on data related to external weather, interior temperature and calendar, the proposed approach is promising to be applicable to any type of building without needing as input specific geometrical/physical characteristics.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: The Data-driven Ecms Modelmentioning

confidence: 99%

Section: Machine Learning Models For Predicting the Inner Temperaturementioning

confidence: 99%

Section: Model Evolutionmentioning

confidence: 99%

See 2 more Smart Citations

The Data-Driven Multi-Step Approach for Dynamic Estimation of Buildings’ Interior Temperature

Villa¹,

Sassanelli

2020

Energies

View full text Add to dashboard Cite

show abstract

“…Nevertheless, the construction of this model requires detailed knowledge about the system and, in spite of it, may present a gap in the actual building due to uncertainties and inaccuracies in the construction [8]. In this context, the application of Artificial Intelligence (AI) provides a reliable alternative in terms of speed and accuracy [9]. There is a wide variety of applications, overall using Machine Learning and Deep Learning algorithms, where these models have proved their effectiveness learning complex patterns and modelling non-linear relationships [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Feasibility of Different Weather Data Sources Applied to Building Indoor Temperature Estimation Using LSTM Neural Networks

Pensado-Mariño

Garrido²,

Eguía

et al. 2021

Sustainability

View full text Add to dashboard Cite

The use of Machine Learning models is becoming increasingly widespread to assess energy performance of a building. In these models, the accuracy of the results depends largely on outdoor conditions. However, getting these data on-site is not always feasible. This article compares the temperature results obtained for an LSTM neural network model, using four types of meteorological data sources. The first is the monitoring carried out in the building; the second is a meteorological station near the site of the building; the third is a table of meteorological data obtained through a kriging process and the fourth is a dataset obtained using GFS. The results are analyzed using the CV(RSME) and NMBE indices. Based on these indices, in the four series, a CV(RSME) slightly higher than 3% is obtained, while the NMBE is below 1%, so it can be deduced that the sources used are interchangeable.

show abstract

Comparison of model-based and data-driven approaches for modeling energy and comfort management systems, with a case study

Cited by 2 publications

References 9 publications

The Data-Driven Multi-Step Approach for Dynamic Estimation of Buildings’ Interior Temperature

The Data-Driven Multi-Step Approach for Dynamic Estimation of Buildings’ Interior Temperature

Feasibility of Different Weather Data Sources Applied to Building Indoor Temperature Estimation Using LSTM Neural Networks

Contact Info

Product

Resources

About