Enhancing Hourly Heat Demand Prediction through Artificial Neural Networks: A National Level Case Study-猫眼课题宝

DOI：

10.1016/j.egyai.2023.100315

发表时间：

2023-11

期刊：

Energy and AI

影响因子：

通讯作者：

中科院分区：

文献类型：

作者：

Meng Zhang;Michael-Allan Millar;Si Chen;Yaxing Ren;Zhibin Yu;James Yu

到2050年实现能源部门零排放的目标需要对能源消耗进行准确预测，这一点越来越重要。然而，传统的基于自下而上模型的热需求预测方法由于其复杂性和模型参数获取困难，不适合大规模、高分辨率和快速预测。本文提出了一种基于人工神经网络（ANN）的全国小时热需求预测模型，取代了传统的基于大量建筑模拟和计算的自下而上模型。人工神经网络模型通过特征选择减少模型输入类型的数量，大大减少了预测时间和复杂性，通过去除非必要的输入，使模型更加真实。改进后的模型可以使用较少的气象数据类型和不充分的数据进行训练，同时在可接受的误差范围内准确预测全年的小时热需求。该模型为获得大规模地区准确的热需求预测提供了一个框架，可作为利益相关者，特别是决策者做出明智决策的参考。

Meeting the goal of zero emissions in the energy sector by 2050 requires accurate prediction of energy consumption, which is increasingly important. However, conventional bottom-up model-based heat demand forecasting methods are not suitable for large-scale, high-resolution, and fast forecasting due to their complexity and the difficulty in obtaining model parameters. This paper presents an artificial neural network (ANN) model to predict hourly heat demand on a national level, which replaces the traditional bottom-up model based on extensive building simulations and computation. The ANN model significantly reduces prediction time and complexity by reducing the number of model input types through feature selection, making the model more realistic by removing non-essential inputs. The improved model can be trained using fewer meteorological data types and insufficient data, while accurately forecasting the hourly heat demand throughout the year within an acceptable error range. The model provides a framework to obtain accurate heat demand predictions for large-scale areas, which can be used as a reference for stakeholders, especially policymakers, to make informed decisions.

Enhancing Hourly Heat Demand Prediction through Artificial Neural Networks: A National Level Case Study

文献摘要

相似文献