Sensitivity analysis to reduce duplicated features in ANN training for district heat demand
Sensitivity analysis to reduce duplicated features in ANN training for district heat demand
复制标题
DOI：
10.1016/j.egyai.2020.100028
复制
发表时间：
2020-11-01
期刊：
影响因子：
--
通讯作者：
Yu, James
中科院分区：
文献类型：
--
作者：
Chen, Si;Ren, Yaxing;Yu, James
人工神经网络（ANN）已成为模拟气象条件、建筑物特性与其热需求之间非线性关系的重要方法。由于人工神经网络训练需要大量的训练数据，数据约简和特征选择是简化训练的重要环节。然而，在建筑热需求预测中，许多与天气相关的输入变量包含重复的特征。本文提出了一种灵敏度分析方法来分析输入变量之间的相关性，并检测出具有高重要性但包含重复特征的变量。所提出的方法进行了验证，在一个案例研究，预测在一所大学校园的区域供热网络包含数十栋建筑物的热需求。结果表明，该方法检测并去除了一些不必要的输入变量，在保持预测精度的前提下，使神经网络模型的训练时间比传统方法减少了约20%。结果表明，该方法可用于分析大量输入变量，有助于提高人工神经网络的训练效率，并可用于区域供热量预测等应用。
Artificial neural network (ANN) has become an important method to model the nonlinear relationships between weather conditions, building characteristics and its heat demand. Due to the large amount of training data re-quired for ANN training, data reduction and feature selection are important to simplify the training. However, in building heat demand prediction, many weather-related input variables contain duplicated features. This paper develops a sensitivity analysis approach to analyse the correlation between input variables and to detect the variables that have high importance but contain duplicated features. The proposed approach is validated in a case study that predicts the heat demand of a district heating network containing tens of buildings at a university campus. The results show that the proposed approach detected and removed several unnecessary input variables and helped the ANN model to reduce approximately 20% training time compared with the traditional methods while maintaining the prediction accuracy. It indicates that the approach can be applied for analysing large num-ber of input variables to help improving the training efficiency of ANN in district heat demand prediction and other applications.