AIR-CONDITIONING SYSTEM, MACHINE LEARNING DEVICE, AND MACHINE LEARNING METHOD

Title:

AIR-CONDITIONING SYSTEM, MACHINE LEARNING DEVICE, AND MACHINE LEARNING METHOD

Document Type and Number:

WIPO Patent Application WO/2020/218219

Kind Code:

A1

Abstract:

Provided is an air-conditioning system such that the operating capacity of an outside air-conditioning device and an air-conditioning device can be optimized. This air-conditioning system, which has an outside air-conditioning device, an air-conditioning device, and a machine learning device, also has: a state variable acquisition unit for acquiring a state variable, which includes an outside air condition, an inside air condition, the operating condition of the outside air-conditioning device, the operating condition of the air-conditioning device, and a set temperature or set humidity for a subject space; a learning unit for carrying out learning by associating the state variable and the operating capacity of the outside air-conditioning device and/or the operating capacity of the air-conditioning device; and a reward calculation unit for calculating a reward correlated with the total energy consumption of the outside air-conditioning device and the air-conditioning device. The learning unit uses the reward to carry out learning.

More Like This:

WO/2007/110034	CONDENSER WHICH IS EXPOSED TO AIR
JPH1163580	HEAT STORAGE DEVICE
JP4140236	Outdoor unit for blower and air conditioner

Inventors:

OKAMOTO YASUNORI (JP)
FUJITA NAOTOSHI (JP)

Application Number:

PCT/JP2020/016968

Publication Date:

October 29, 2020

Filing Date:

April 17, 2020

Export Citation:

Click for automatic bibliography generation Help

Assignee:

DAIKIN IND LTD (JP)

International Classes:

F24F5/00; F24F11/43; F24F11/46; F24F11/63

Domestic Patent References:

WO2012049897A1

2012-04-19

Foreign References:

JP2012077948A	2012-04-19
JP2018173264A	2018-11-08
JP2018173264A	2018-11-08
JP2019086786A	2019-06-06
JP2020073804A	2020-05-14

Other References: