Sample data selection method for improving the prediction accuracy of the heating energy consumption

Yuan, Tianhao; Zhu, Neng; Shi, Yong; Chen, Chang; Yang, Kun; Ding, Yan

doi:10.1016/j.enbuild.2017.10.006

Cited by 41 publications

(14 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Ding et al used Kmeans and hierarchical clustering methods to classify input variables to improve prediction accuracy [60]. Yuan et al proposed a sample data selection method based on a grey correlation method integrated with an entropy weight method; the result demonstrated that the accuracy of BPNN had improved [26]. Ding et al divided the sample data by tenfold cross-validation to improve the accuracy of the SVR model in shortterm and ultra-short-term predictions of cooling load [61].…”

Section: Improved Prediction Modelsmentioning

confidence: 99%

“…Improved prediction models use auxiliary algorithms or frameworks to make up for the deficiencies of the original prediction algorithm. There are generally three forms: (1) the pre-assisted algorithm, which improves the data quality to make up for the specific requirements of the prediction algorithm [26]; (2) the assisted optimization algorithm, which is used to perform hyperparameter tuning of a prediction algorithm [27]; and (3) nesting of an auxiliary improvement framework on the base prediction algorithm, to improve model performance [7]. Most of the existing research is based on single or integration models, which lack improvements in the essence of the algorithm.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A novel improved model for building energy consumption prediction based on model integration

2020

View full text Add to dashboard Cite

Building energy consumption prediction plays an irreplaceable role in energy planning, management, and conservation. Constantly improving the performance of prediction models is the key to ensuring the efficient operation of energy systems. Moreover, accuracy is no longer the only factor in revealing model performance, it is more important to evaluate the model from multiple perspectives, considering the characteristics of engineering applications. Based on the idea of model integration, this paper proposes a novel improved integration model (stacking model) that can be used to forecast building energy consumption. The stacking model combines advantages of various base prediction algorithms and forms them into "meta-features" to ensure that the final model can observe datasets from different spatial and structural angles. Two cases are used to demonstrate practical engineering applications of the stacking model. A comparative analysis is performed to evaluate the prediction performance of the stacking model in contrast with existing well-known prediction models including Random Forest, Gradient Boosted Decision Tree, Extreme Gradient Boosting, Support Vector Machine, and K-Nearest Neighbor. The results indicate that the stacking method achieves better performance than other models, regarding accuracy (improvement of 9.5%-31.6% for Case A and 16.2%-49.4% for Case B), generalization (improvement of 6.7%-29.5% for Case A and 7.1%-34.6% for Case B), and robustness (improvement of 1.5%-34.1% for Case A and 1.8%-19.3% for Case B). The proposed model enriches the diversity of algorithm libraries of empirical models.

show abstract

Section: Improved Prediction Modelsmentioning

confidence: 99%

mentioning

confidence: 99%

A novel improved model for building energy consumption prediction based on model integration

2020

View full text Add to dashboard Cite

show abstract

“…Energy consumption in residential buildings makes a significant contribution to the GHG emissions generated by the urbanization process in China [3]. As a result, the building industry has been a major obstacle in reducing energy consumption and GHG emissions from China [4,5]. The current situation with building energy efficiency levels is to ensure high energy efficiency standards for new construction [6].…”

Section: Research Backgroundmentioning

confidence: 99%

Energy-Saving Potential of Applying Prefabricated Straw Bale Construction (PSBC) in Domestic Buildings in Northern China

et al. 2020

View full text Add to dashboard Cite

The Prefabricated Straw Bale Construction (PSBC) has been proven as one of the most efficient construction methods to achieve low-energy buildings with low environmental impacts. This research presents analysis of the rationale for using straw bale constructions in northern China and a discussion of feasible constructions of PSBC to meet the local building codes following evaluations of potential energy performance of domestic buildings with PSBC in severe cold regions and cold regions in China. The results show that the buildings with PSBC reduce both heating and cooling energy uses, as well as heating intensities across the severe cold and cold regions, compared to the domestic buildings with conventional constructions. The findings of this research will contribute to reducing energy consumption in building industries in China.

show abstract

“…Energy consumption in China has increased from 1.4 × 10 9 tons of standard coal equivalent in 2000 to 4.1 × 10 9 tons of standard coal equivalent in 2017 [2]. Amongst all energy uses, the building sector accounts for 31.4% of the total [3]. The International Energy Agency (IEA) also announced that the total…”

Section: Overall Energy Consumptionmentioning

confidence: 99%

Energy Sustainability of Bio-Based Building Materials in the Cold and Severe Cold Regions of China—A Case Study of Residential Buildings

et al. 2020

View full text Add to dashboard Cite

The aim of this research is to investigate the energy sustainability of cross-laminated timber (CLT) and straw residential buildings in the Cold and Severe Cold Regions of China. In the study, three building materials, namely reinforced concrete (RC), CLT, and straw bale, are used separately to design the building envelope in reference residential buildings in different climate zones. The energy consumption during the operation phase of these buildings is then simulated using Integrated Environmental Solutions—Virtual Environment software (IES-VE). The results show that both CLT and straw buildings are more efficient than reinforced concrete with a reduction in energy consumption during the operational phase. Overall, the calculated heating energy-saving ratios for CLT buildings in Hailar, Harbin, Urumchi, Lanzhou, and Beijing are 3.04%, 7.39%, 7.43%, 12.69%, and 13.41%, respectively, when compared with RC. The calculated energy-saving ratios for heating in straw buildings in comparison with RC in these cities are 8.04%, 22.09%, 22.17%, 33.02%, and 34.28%, respectively. The results also reveal that a south orientation of the main building facade results in approximately 5% to 7% energy reduction in comparison with east or west orientations, and as the building height increases, energy consumption decreases gradually. Although RC is the most frequently used building material in Cold and Severe Cold regions in China, as bio-based building materials, there is great potential to promote CLT and straw bale construction in view of the energy sustainability features.

show abstract

Sample data selection method for improving the prediction accuracy of the heating energy consumption

Cited by 41 publications

References 41 publications

A novel improved model for building energy consumption prediction based on model integration

A novel improved model for building energy consumption prediction based on model integration

Energy-Saving Potential of Applying Prefabricated Straw Bale Construction (PSBC) in Domestic Buildings in Northern China

Energy Sustainability of Bio-Based Building Materials in the Cold and Severe Cold Regions of China—A Case Study of Residential Buildings

Contact Info

Product

Resources

About