Evaluation of advanced control strategies of electric thermal storage systems in residential building stock

Buttitta, Giuseppina; Jones, Colin N.; Finn, Donal

doi:10.1016/j.jup.2021.101178

Cited by 10 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Input layer: For the high-frequency part of the load, the input features are filtered using the Boruta method to establish key feature vectors, and then the historical 4-h load data are used to predict the load changes in the next 10 min, and the input features with data dimension (24,7) are constructed and input to the CNN layer; for the low-frequency part of the load, it is directly entered into the ARIMA model.…”

Section: Predictive Model Structurementioning

confidence: 99%

“…Input layer: For the high-frequency part of the load, the input features are filtered using the Boruta method to establish key feature vectors, and then the historical 4-h load CNN layer: Extract the input feature matrix information by setting the two-layer CNN layer. After passing through the first layer, the data dimension becomes (24,7,15); through the pooling layer pooling, the data dimension is transformed into (24,3,15), and then input to the second layer convolution layer. The data dimension is transformed into (24, 3, 1), then a single layer Squeeze layer is added, the data dimension to (24,3) and input to the BiLSTM layer.…”

Section: Predictive Model Structurementioning

confidence: 99%

“…However, as the available data increase, these models face performance limitations [6]. Research has shown that MPC methods using black-box models can achieve energy savings of 8.4%, higher than the energy savings of 7.4% for white-box models and 7.2% for grey-box models [7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of Heat and Cold Loads of Factory Mushroom Houses Based on EWT Decomposition

Zuo,

Zheng,

Wang

et al. 2023

Sustainability

View full text Add to dashboard Cite

Load forecasting has significant implications on optimizing the operation of air conditioning systems for industrial mushroom houses and energy saving. This research paper presents a novel approach for short-term load forecasting in mushroom houses, which face challenges in accurately modeling cold and heat loads due to the complex interplay of various factors, including climatic conditions, mushroom growth, and equipment operation. The proposed method combines empirical wavelet transform (EWT), hybrid autoregressive integrated moving average (ARIMA), convolutional neural network (CNN), and bi-directional long short-term memory (BiLSTM) with an attention mechanism (CNN-BiLSTM-Attention) to address these challenges. The first step of this method was to select input features via the Boruta algorithm. Then, the EWT method was used to decompose the load data of mushroom houses into four modal components. Subsequently, the Lempel–Ziv method was introduced to classify the modal components into high-frequency and low-frequency classes. CNN-BiLSTM-Attention and ARIMA prediction models were constructed for these two classes, respectively. Finally, the predictions from both classes were combined and reconstructed to obtain the final load forecasting value. The experimental results show that the Boruta algorithm selects key influential feature factors effectively. Compared to the Spearman and Pearson correlation coefficient methods, the mean absolute error (MAE) of the prediction results is reduced by 14.72% and 3.75%, respectively. Compared to the ensemble empirical mode decomposition (EEMD) method, the EWT method can reduce the decomposition reconstruction error by an order of magnitude of 103, effectively improving the accuracy of the prediction model. The proposed model in this paper exhibits significant advantages in prediction performance compared to the single neural network model, with the MAE, root mean square error (RMSE), and mean absolute percentage error (MAPE) of the prediction results reduced by 31.06%, 26.52%, and 39.27%, respectively.

show abstract

“…Input layer: For the high-frequency part of the load, the input features are filtered using the Boruta method to establish key feature vectors, and then the historical 4-h load data are used to predict the load changes in the next 10 min, and the input features with data dimension (24,7) are constructed and input to the CNN layer; for the low-frequency part of the load, it is directly entered into the ARIMA model.…”

Section: Predictive Model Structurementioning

confidence: 99%

“…Input layer: For the high-frequency part of the load, the input features are filtered using the Boruta method to establish key feature vectors, and then the historical 4-h load CNN layer: Extract the input feature matrix information by setting the two-layer CNN layer. After passing through the first layer, the data dimension becomes (24,7,15); through the pooling layer pooling, the data dimension is transformed into (24,3,15), and then input to the second layer convolution layer. The data dimension is transformed into (24, 3, 1), then a single layer Squeeze layer is added, the data dimension to (24,3) and input to the BiLSTM layer.…”

Section: Predictive Model Structurementioning

confidence: 99%

See 1 more Smart Citation

Prediction of Heat and Cold Loads of Factory Mushroom Houses Based on EWT Decomposition

Zuo,

Zheng,

Wang

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…Alrwashdeh et al, 2018;Alrwashdeh and Ammari, 2019;Alrwashdeh et al, 2022;Alrwashdeh et al, 2017a). Other studies have focused on developing building windows through the use of double and triple glazing, and some studies have gone into window frames and the types of materials that can be used to manufacture window frames, such as wood, aluminum, and other materials (Tsagarakis et al, 2012;Ammari et al, 2015;Cuce and Riffat, 2015;Alrwashdeh et al, 2016a;Alrwashdeh et al, 2016b;Alrwashdeh et al, 2017b;Alrwashdeh et al, 2017c;Aburas et al, 2019;Altarawneh et al, 2022). Studies have also emerged about the doors used in buildings, and today, there are wooden and iron doors and others (Mahajan et al, 2015;Sun et al, 2016;Saraireh et al, 2017;Sun et al, 2017;Göbel et al, 2018;Ince et al, 2018;Markötter et al, 2019;Henman et al, 2021;Hsu et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Investigation of the Effect of Roof Color on the Energy Use of a Selected House in Amman, Jordan

2022

View full text Add to dashboard Cite

Energy consumption in the buildings sector is considered one of the most important sources of energy consumption in Jordan, as the reason for this is due to the traditional building pattern and the buildings’ lack of various energy saving and rationalization systems. The development of the buildings sector in terms of the capacity of buildings to save and produce energy is one of the most important reasons that lead to saving energy consumption at the national level in Jordan. In this study, the effect of paint colors on the roofs of buildings was studied by studying three different colors, which are blue, white, and black, where it was confirmed that the best colors in energy conservation is black, and white is the opposite of it, which is considered the worst in energy conservation.

show abstract

“…Although it is rather common to find studies claiming that advanced building control techniques paired with new-fashioned machine learning models can enhance the system operation and attain important monetary savings, it is considerably harder to find significant experimental evidence supporting these statements [1][2][3][4]. Instead, the validation of complex analysis and control techniques is usually performed with the aid of simulation models calibrated either on real data or on construction parameters [5][6][7][8][9]. Some investigations adopt a middle ground approach, whereby novel strategies are tested through extensive simulations followed by scaled-down experiments acting simply as a proof of concept [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Experimental Data-Driven Model Predictive Control of a Hospital HVAC System During Regular Use

Maddalena¹,

Muller²,

Santos³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Herein we report a multi-zone, heating, ventilation and air-conditioning (HVAC) control case study of an industrial plant responsible for cooling a hospital surgery center. The adopted approach to guaranteeing thermal comfort and reducing electrical energy consumption is based on a statistical non-parametric, non-linear regression technique named Gaussian processes. Our study aimed at assessing the suitability of the aforementioned technique to learning the building dynamics and yielding models for our model predictive control (MPC) scheme. Experimental results gathered while the building was under regular use showcase the final controller performance while subject to a number of measured and unmeasured disturbances. Finally, we provide readers with practical details and recommendations on how to manage the computational complexity of the on-line optimization problem and obtain high-quality solutions from solvers.

show abstract

Evaluation of advanced control strategies of electric thermal storage systems in residential building stock

Cited by 10 publications

References 24 publications

Prediction of Heat and Cold Loads of Factory Mushroom Houses Based on EWT Decomposition

Prediction of Heat and Cold Loads of Factory Mushroom Houses Based on EWT Decomposition

Investigation of the Effect of Roof Color on the Energy Use of a Selected House in Amman, Jordan

Experimental Data-Driven Model Predictive Control of a Hospital HVAC System During Regular Use

Contact Info

Product

Resources

About