Title:
機械学習装置、デマンド制御システム、及び、空調制御システム
Document Type and Number:
Japanese Patent JP7078873
Kind Code:
B2
Abstract:
There is provided a machine learning device capable of determining a set temperature for implementing a predetermined demand target value. A machine learning device (100) learns a set temperature, in a target space, for achieving a demand target value that is an upper-limit value of a power consumption of an air conditioner (110) in the target space in a predetermined period. The machine learning device (100) includes a learning unit (103), a state variable acquisition unit (101), an evaluation data acquisition unit (105), and a function updating unit (104). The state variable acquisition unit (101) acquires a state variable including at least one of the power consumption of the air conditioner (110) and an indoor state value correlated with a state in the target space. The evaluation data acquisition unit (105) acquires evaluation data for evaluating a control result of the air conditioner (110). The function updating unit (104) updates, by using the evaluation data, a learning state of the learning unit (103). The learning unit (103) performs learning in accordance with an output of the function updating unit (104). The evaluation data includes at least the power consumption of the air conditioner (110).
Inventors:
Nishimura Tadashi
Application Number:
JP2020196258A
Publication Date:
June 01, 2022
Filing Date:
November 26, 2020
Export Citation:
Assignee:
Daikin Industries, Ltd.
International Classes:
H02J13/00; F24F11/47; F24F11/62; F24F11/755; H02J3/00; H02J3/14
Domestic Patent References:
| JP2019060514A | ||||
| JP2016170647A | ||||
| JP2017142595A |
Foreign References:
| WO2018199167A1 |
Attorney, Agent or Firm:
Shinki Global IP Patent Corporation