Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning

Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning

This paper considers a demand response agent that must find a near-optimal sequence of decisions based on sparse observations of its environment. Extracting a relevant set of features from these observations is a challenging task and may require substantial domain knowledge. One way to tackle this p...

Full description

Bibliographic Details
Main Authors: Frederik Ruelens, Bert J. Claessens, Peter Vrancx, Fred Spiessens, Geert Deconinck
Format: Article
Language:English
Published: China electric power research institute 2019-12-01
Series:CSEE Journal of Power and Energy Systems
Subjects:
convolutional networks
deep reinforcement learning
long short-term memory
residential demand response
Online Access:https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8928284

Internet

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8928284

Similar Items