检索结果-南通市图书馆

An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems

引用

Building Simulation 2024年第5期17卷 739-770页

作者： Davide Coraci Silvio Brandi Tianzhen Hong alfonso capozzoli Politecnico di Torino Department of EnergyTEBE research groupBAEDA Lab.Corso Duca degli Abruzzi 24Torino10129Italy Building Technology and Urban Systems Division Lawrence Berkeley National LaboratoryOne Cyclotron RoadBerkeleyCA 94720USA

Deep Reinforcement Learning(DRL)-based control shows enhanced performance in the management of integrated energy systems when compared with Rule-Based Controllers(RBCs),but it still lacks scalability and generalisation due to the necessity of using tailored models for the training *** Learning(TL)is a potential solution to address this ***,existing TL applications in building control have been mostly tested among buildings with similar features,not addressing the need to scale up advanced control in real-world scenarios with diverse energy *** paper assesses the performance of an online heterogeneous TL strategy,comparing it with RBC and offline and online DRL controllers in a simulation setup using EnergyPlus and *** study tests the transfer in both transductive and inductive settings of a DRL policy designed to manage a chiller coupled with a Thermal Energy Storage(TES).The control policy is pre-trained on a source building and transferred to various target buildings characterised by an integrated energy system including photovoltaic and battery energy storage systems,different building envelope features,occupancy schedule and boundary conditions(e.g.,weather and price signal).The TL approach incorporates model slicing,imitation learning and fine-tuning to handle diverse state spaces and reward functions between source and target *** show that the proposed methodology leads to a reduction of 10% in electricity cost and between 10% and 40% in the mean value of the daily average temperature violation rate compared to RBC and online DRL ***,online TL maximises self-sufficiency and self-consumption by 9% and 11% with respect to ***,online TL achieves worse performance compared to offline DRL in either transductive or inductive ***,offline Deep Reinforcement Learning(DRL)agents should be trained at least for 15 episodes to reach the same level of performance as the online

关键词： transfer learning reinforcement learning building control building energy management

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A data analytics-based tool for the detection and diagnosis of anomalous daily energy patterns in buildings

引用

Building Simulation 2021年第1期14卷 131-147页

作者： Marco Savino Piscitelli Silvio Brandi alfonso capozzoli Fu Xiao Department of Energy“Galileo Ferraris” TEBE research groupPolitecnico di TorinoTurinItaly Department of Building Services Engineering The Hong Kong Polytechnic UniversityHong KongChina

In this paper,a tool for the detection and diagnosis of anomalous electrical daily energy patterns relative to a transformer substation of a university campus was developed and *** an innovative pattern recognition analysis consisting in a multi-step clustering process,six clusters of anomalous daily load profiles were identified and isolated in two-year historical data of total electrical energy *** infrequent electrical load profiles were found to be strongly affected,in terms of both shape and magnitude,by the energy consumption behaviour related to the heating/cooling mechanical ***,a fault-free predictive model,which uses artificial neural network(ANN)in combination with a Regression Tree,was developed to detect anomalous trends of the electrical energy *** model was able to detect the 93.7%of the anomalous profiles and only the 5%of fault-free days were wrongly predicted as ***,a diagnosis phase was conceived and validated with a testing data set.A number of daily abnormal load profiles were detected and compared with the centroids of the anomalous clusters identified in the pattern-recognition *** work led to the development of a flexible intelligent tool useful for operating a continuous commissioning of the campus facilities.

关键词： anomaly detection data analytics energy management pattern recognition prediction models

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Leveraging graph convolutional networks for semi-supervised fault diagnosis of HVAC systems in data-scarce contexts

引用

建筑模拟(英文) 2023年第8期16卷 1499-1517页

作者： Cheng Fan Yiwen Lin Marco Savino Piscitelli Roberto Chiosa Huilong Wang alfonso capozzoli Yuanyuan Ma Key Laboratory for Resilient Infrastructures of Coastal Cities Ministry of EducationShenzhen UniversityShenzhenChina Sino-Australia Joint Research Center in BIM and Smart Construction Shenzhen UniversityShenzhenChina College of Civil and Transportation Engineering Shenzhen UniversityShenzhenChina Department of Energy TEBE research groupBAEDA LabPolitecnico di TorinoTorinoItaly

The continuous accumulation of operational data has provided an ideal platform to devise and implement customized data analytics for smart HVAC fault detection and *** practice,the potentials of advanced supervised learning algorithms have not been fully realized due to the lack of sufficient labeled *** tackle such data challenges,this study proposes a graph neural network-based approach to effectively utilizing both labeled and unlabeled operational data for optimum *** specifically,a graph generation method is proposed to transform tabular building operational data into association graphs,based on which graph convolutions are performed to derive useful insights for fault *** experiments have been designed to evaluate the values of the methods *** datasets on HVAC air-side operations have been used to ensure the generalizability of results *** data scenarios,which vary in training data amounts and imbalance ratios,have been created to comprehensively quantify behavioral patterns of representative graph convolution networks and their *** research results indicate that graph neural networks can effectively leverage associations among labeled and unlabeled data samples to achieve an increase of 2.86%–7.30%in fault classification accuracies,providing a novel and promising solution for smart building management.

关键词： fault detection and diagnosis graph convolutional networks semi-supervised learning HVAC systems machine learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：