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...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Frederik Ruelens, Bert J. Claessens, Peter Vrancx, Fred Spiessens, Geert Deconinck
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	China electric power research institute 2019-12-01
Saila:	CSEE Journal of Power and Energy Systems
Gaiak:	convolutional networks deep reinforcement learning long short-term memory residential demand response
Sarrera elektronikoa:	https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8928284
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!