Unsupervised energy prediction in a Smart Grid context using reinforcement cross-building transfer learning
详细信息    查看全文
文摘
istitem" id="list_list0015">

id="p0005">We propose a new prediction method to model building energy consumption in Smart Grid.

id="p0010">It incorporates deep learning into reinforcement learning for continuous states estimation.

id="p0015">The learned model is transferred to a new building to predict energy consumption.

id="p0020">The method is validated on a real database recorded over seven years, with hourly resolution.

NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.