检索结果-南通市图书馆

Deep reinforcement learning with planning guardrails for building energydemand response

Energy and AI 2023年第1期11卷 12-25页

作者： doseok jang Lucas Spangher Selvaprabu Nadarajah Costas Spanos Department of Electrical Engineering and Computer Science University of California at BerkeleyBerkeley94704CAUSA Department of Information and Decision Sciences University of Illinois at ChicagoChicago60607ILUSA

Building energy demand response is projected to be important in decarbonizing energy use. A demand responseprogram that communicates ‘‘artificial’’ hourly price signals to workers as part of a social game has the potentialto elicit energy consumption changes that simultaneously reduce energy costs and emissions. The efficacy ofsuch a program depends on the pricing agent’s ability to learn how workers respond to prices and mitigatethe risk of high energy costs during this learning process. We assess the value of deep reinforcement learning(RL) for mitigating this risk. Specifically, we explore the value of combining: (i) a model-free RL method thatcan learn by posting price signals to workers, (ii) a supervisory ‘‘planning model’’ that provides a syntheticlearning environment, and (iii) a guardrail method that determines whether a price should be posted to realworkers or the planning environment for feedback. In a simulated medium-sized office building, we compareour pricing agent against existing model-free and model-based deep RL agents, and the simpler strategy ofpassing on the time-of-use price signal to workers. We find that our controller eliminates 175,000 US Dollarsin initial investment, decreases by 30% the energy cost, and curbs emissions by 32% compared to energyconsumption under the time-of-use rate. In contrast, the model-free and model-based deep RL benchmarksare unable to overcome initial learning costs. Our results bode well for risk-aware deep RL facilitating thedeployment of building demand response.

关键词： Deep reinforcement learning Risk-aware planning Demand response Energy Decarbonization

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

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

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：