Building energy consumption (BEC) prediction is very important for energy management and conservation. This paper presents a short-term energy consumption prediction method that integrates the Fuzzy Rough Set (FRS) theory and the Long Short-Term Memory (LSTM) model, and is thus named FRS-LSTM. Thismethod can find the most directly related factors from the complex and diverse factors influencing the energy consumption, which improves the prediction accuracy and efficiency. First, the FRS is used to reduce the redundancy of the input features by the attribute reduction of the factors affecting the energy consumption forecasting, and solves the data loss problem caused by the data discretization of a classical rough set. Then, the final attribute set after reduction is taken as the input of the LSTM networks to obtain the final prediction results. To validate the effectiveness of the proposed model, this study used the actual data of a public building to predict the building’s energy consumption, and compared the proposed model with the LSTM, Levenberg-Marquardt Back Propagation (LM-BP), and Support Vector Regression (SVR) models. The experimental results reveal that the presented FRS-LSTM model achieves higher prediction accuracy compared with other comparative models.

中文翻译：

---

一种基于模糊粗糙集的长短期记忆集成模型，用于公共建筑能耗预测

建筑能耗（BEC）预测对于能源管理和节约非常重要。本文提出了一种短期能耗预测方法，该方法结合了模糊粗糙集（FRS）理论和长短期记忆（LSTM）模型，因此被称为FRS-LSTM。该方法可以从影响能耗的复杂多样因素中找到最直接相关的因素，从而提高了预测的准确性和效率。首先，FRS用于通过减少影响能耗预测的因素的属性来减少输入特征的冗余，并解决了由经典粗糙集的数据离散化引起的数据丢失问题。然后，将归约后设置的最终属性作为LSTM网络的输入，以获得最终预测结果。为了验证所提出模型的有效性，本研究使用公共建筑的实际数据来预测建筑物的能耗，并将所提出的模型与LSTM，Levenberg-Marquardt反向传播（LM-BP）和支持向量回归进行比较（SVR）模型。实验结果表明，与其他比较模型相比，本文提出的FRS-LSTM模型具有更高的预测精度。