Application of adaptive neuro-fuzzy methodology for estimating building energy consumption

Naji, Sareh; Shamshirband, Shahaboddin; Basser, Hossein; Keivani, Afram; Alengaram, U. Johnson; Jumaat, Mohd Zamin; Petković, Dalibor

doi:10.1016/j.rser.2015.09.062

Cited by 57 publications

(23 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For this reason, an ANN is one of the most appropriate machine-learning methods for the current dataset. According to Table 1, some papers specifically applied ANN to the dataset (Ahmed et al [20]; Nwulu [28]), while others applied the ensemble approach by incorporating ANNs (Chou and Bui [18]; Sonmez et al [21]; Naji et al [25]; Nilashi et al [27]). To the best of the authors' knowledge, Sekha et al [4] is the only paper that applied DNNs to forecast HL and CL.…”

Section: Literature Reviewmentioning

confidence: 99%

An Intelligent Model to Predict Energy Performances of Residential Buildings Based on Deep Neural Networks

et al. 2020

View full text Add to dashboard Cite

As the level of greenhouse gas emissions increases, so does the importance of the energy performance of buildings (EPB). One of the main factors to measure EPB is a structure’s heating load (HL) and cooling load (CL). HLs and CLs depend on several variables, such as relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution. This research uses deep neural networks (DNNs) to forecast HLs and CLs for a variety of structures. The DNNs explored in this research include multi-layer perceptron (MLP) networks, and each of the models in this research was developed through extensive testing with a myriad number of layers, process elements, and other data preprocessing techniques. As a result, a DNN is shown to be an improvement for modeling HLs and CLs compared to traditional artificial neural network (ANN) models. In order to extract knowledge from a trained model, a post-processing technique, called sensitivity analysis (SA), was applied to the model that performed the best with respect to the selected goodness-of-fit metric on an independent set of testing data. There are two forms of SA—local and global methods—but both have the same purpose in terms of determining the significance of independent variables within a model. Local SA assumes inputs are independent of each other, while global SA does not. To further the contribution of the research presented within this article, the results of a global SA, called state-based sensitivity analysis (SBSA), are compared to the results obtained from a traditional local technique, called sensitivity analysis about the mean (SAAM). The results of the research demonstrate an improvement over existing conclusions found in literature, which is of particular interest to decision-makers and designers of building structures.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An Intelligent Model to Predict Energy Performances of Residential Buildings Based on Deep Neural Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Nikolić et al [34] also used the ANFIS technique for enhancing the performance of the wind turbines. Naji et al [35] later designed and adapted the ANFIS technique to estimate the energy consumption of buildings based on some parameters, including line insulation, K-value, and material thickness. The results of this paper showed that the ANFIS results are more accurate than the results of the artificial neural network (ANN) and genetic programming (GP) techniques.…”

Section: Sustainability and Fuzzy Neural Networkmentioning

confidence: 99%

Measuring Country Sustainability Performance Using Ensembles of Neuro-Fuzzy Technique

et al. 2018

View full text Add to dashboard Cite

Global warming is one of the most important challenges nowadays. Sustainability practices and technologies have been proven to significantly reduce the amount of energy consumed and incur economic savings. Sustainability assessment tools and methods have been developed to support decision makers in evaluating the developments in sustainable technology. Several sustainability assessment tools and methods have been developed by fuzzy logic and neural network machine learning techniques. However, a combination of neural network and fuzzy logic, neuro-fuzzy, and the ensemble learning of this technique has been rarely explored when developing sustainability assessment methods. In addition, most of the methods developed in the literature solely rely on fuzzy logic. The main shortcoming of solely using the fuzzy logic rule-based technique is that it cannot automatically learn from the data. This problem of fuzzy logic has been solved by the use of neural networks in many real-world problems. The combination of these two techniques will take the advantages of both to precisely predict the output of a system. In addition, combining the outputs of several predictors can result in an improved accuracy in complex systems. This study accordingly aims to propose an accurate method for measuring countries' sustainability performance using a set of real-world data of the sustainability indicators. The adaptive neuro-fuzzy inference system (ANFIS) technique was used for discovering the fuzzy rules from data from 128 countries, and ensemble learning was used for measuring the countries' sustainability performance. The proposed method aims to provide the country rankings in term of sustainability. The results of this research show that the method has potential to be effectively implemented as a decision-making tool for measuring countries' sustainability performance.

show abstract

“…Эти параметры в процессе моделирования генерируются автоматически и обладают при этом всеми необходимыми статистическими характеристиками. Отметим еще, что модели, использующие вероятностно-статистический подход, особенно полезны для расчета годового энергопотребления здания при оценке его класса энергосбережения, что имеет существенное значение в настоящее время в условиях исчерпания запасов ископаемого органического топлива и повышенного внимания к энергоресурсосбережению, наблюдающегося сейчас в большинстве европейских и других стран [11][12][13][14][15][16][17][18][19][20].…”

Section: обзор литературыunclassified

Probabilistic-Statistical Modeling of Annual Variation of Outside Air Temperature and Its Values in the Warm Season

Dmitrievich¹

2018

Vestnik MGSU

View full text Add to dashboard Cite

Предмет исследования: рассматриваются способы получения массивов климатических данных для моделирования воздушно-теплового режима помещений здания и оценки его годового энергопотребления. Отмечено, что большинство современных подходов в этой области опираются на понятие «типового года» и поэтому малопригодны для инженерной практики, так как требуют поиска, накопления и отбора большого объема значений климатических параметров. Цели: обобщение вероятностного подхода к получению массивов климатических данных на случай исследования годового хода среднесуточной температуры наружного воздуха и создания массива наружных температур в теплый период. Материалы и методы: в работе использована программная генерация массивов климатических данных методом Монте-Карло с применением датчика псевдослучайных чисел на основе линейного конгруэнтного алгоритма. Учет закономерного сезонного хода наружной температуры при этом осуществляется за счет использования «плавающих» математического ожидания и среднего квадратического отклонения. Реализована численная модель нестационарного теплового режима вентилируемого помещения на основе решения системы дифференциальных уравнений теплопроводности и теплообмена на поверхностях помещения. Результаты: приведены некоторые результаты расчета срочной температуры наружного воздуха в течение года и в теплый период с применением метода Монте-Карло для климатических условий Москвы. Выполнено сравнение результатов оценки нестационарного теплового режима вентилируемого помещения при использовании среднесуточных температур наружного воздуха в течение месяца по климатическим данным и по результатам программной генерации. Выводы: показано принципиальное совпадение статистического распределения наружных температур и поведения температуры внутреннего воздуха по обоим сравниваемым вариантам. Отмечено, что метод Монте-Карло дает результаты, не отличимые с точки зрения инженерных потребностей от применения «типового года», и выявлена возможность практической реализации вероятностно-статистического принципа формирования климатических данных для некоторых расчетов, касающихся систем климатизации и теплового режима здания. Предложено применять предлагаемую методику при оценке годового энергопотребления зданий и оценки эффективности энергоресурсосбережения.

show abstract

Application of adaptive neuro-fuzzy methodology for estimating building energy consumption

Cited by 57 publications

References 33 publications

An Intelligent Model to Predict Energy Performances of Residential Buildings Based on Deep Neural Networks

An Intelligent Model to Predict Energy Performances of Residential Buildings Based on Deep Neural Networks

Measuring Country Sustainability Performance Using Ensembles of Neuro-Fuzzy Technique

Probabilistic-Statistical Modeling of Annual Variation of Outside Air Temperature and Its Values in the Warm Season

Contact Info

Product

Resources

About