当前位置: X-MOL 学术Soft Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Type-2 fuzzy wavelet neural network for estimation energy performance of residential buildings
Soft Computing ( IF 3.1 ) Pub Date : 2021-05-15 , DOI: 10.1007/s00500-021-05873-4
Rahib Abiyev , Sanan Abizada

The estimation of the energy performance of residential buildings has gained importance because of the significant consumption of electricity in housing estate areas. For this aim, different approaches were utilized for robust and accurate prediction of the energy load in buildings. The use of different kind of construction materials, timely change in building parameters lead to imprecise and vague evaluation of energy consumption. For such kind of problems that are characterized with uncertainties, the use of fuzzy set theory is a more suitable approach for the modeling of energy consumption. This paper proposes a novel type-2 fuzzy wavelet neural network (T2FWNN) for modeling the energy performance of residential buildings. Based on the type-2 fuzzy rules, the multi-input multi-output T2FWNN model is proposed. For the construction of the T2FWNN model, the learning algorithm has been designed using cross-validation approach, clustering and gradient descent algorithms. During construction, the adaptive learning procedure was developed to stabilize and speed up the learning process. The proposed model is used for the solution of two problems. At the first stage, based on statistical data, the T2FWNN model has been designed for modeling the cooling and heating load of residential buildings. In the second stage, using T2FWNN the prediction model was designed for the energy consumption of residential buildings in Northern Cyprus. Comparative results have been provided to prove the efficiency of using the designed model in the prediction of the energy load of residential buildings. The obtained results indicated the suitability of using the T2FWNN system for estimation of the energy performance and prediction of the energy consumption of residential buildings.



中文翻译:

用于估计住宅建筑能源性能的 2 类模糊小波神经网络

由于住宅区的大量电力消耗,住宅建筑的能源性能评估变得越来越重要。为此,使用了不同的方法来对建筑物中的能量负荷进行稳健和准确的预测。使用不同种类的建筑材料,建筑参数的及时变化导致能耗评估不准确和模糊。对于这类具有不确定性特征的问题,使用模糊集理论是一种更适合建模能耗的方法。本文提出了一种新型的 2 类模糊小波神经网络 (T2FWNN),用于对住宅建筑的能源性能进行建模。基于二类模糊规则,提出了多输入多输出T2FWNN模型。为了构建 T2FWNN 模型,使用交叉验证方法、聚类和梯度下降算法设计了学习算法。在施工期间,开发了自适应学习程序以稳定和加速学习过程。所提出的模型用于解决两个问题。在第一阶段,基于统计数据,设计了 T2FWNN 模型,用于对住宅建筑的冷热负荷进行建模。在第二阶段,使用 T2FWNN 为北塞浦路斯住宅建筑的能源消耗设计预测模型。已经提供了比较结果来证明使用设计的模型在住宅建筑的能量负荷预测中的效率。

更新日期:2021-07-24
down
wechat
bug