IP Library › Granted Patent US 12,560,347
Granted Patent B2
US 12,560,347 · App. 18/071,017 · Granted Feb 24, 2026

Electronic apparatus and operation method for predicting hvac energy consumption using machine learning

Inventors: Hyeonje Cho (Suwon-si, KR); Inhwan Hwang (Suwon-si, KR); Huijung Kim (Suwon-si, KR); Yunhu Ji (Suwon-si, KR); Sehoon Kim (Suwon-si, KR)
Assignee: Samsung Electronics Co., Ltd.
F24F11/46F24F11/52F24F11/63F24F2110/12F24F2110/22F24F2110/32F24F2110/52F24F2110/74F24F2130/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,560,347
App. No.
18/071,017
Granted
Feb 24, 2026
Kind
B2
Abstract

An operation method for reducing energy consumption and an electronic apparatus thereof are provided. The operation method includes obtaining, by the electronic apparatus, weather forecast information, inputting, by the electronic apparatus, the weather forecast information to an artificial intelligence model for predicting an amount of power to be consumed by a first air conditioner, and displaying, by the electronic apparatus, the predicted power consumption amount of the first air conditioner output from the artificial intelligence model, wherein the artificial intelligence model is trained to obtain correlation information between a weather condition and a power consumption amount of an air conditioner, based on a weather history and operations of a plurality of air conditioners related to the weather history, and predict the amount of power to be consumed by the first air conditioner based on the correlation information and the weather forecast information.

Claims (58)

1 . An operation method of an air conditioner, the operation method comprising:

receiving a user input of setting a target power amount;

obtaining weather information from a server;

obtaining a power consumption amount consumed by the air conditioner corresponding to the weather information;

obtaining air conditioner operational preference information of the user;

storing the obtained weather information and the obtained power consumption amount corresponding to the weather information as a training data for an artificial intelligence model;

training the artificial intelligence model such that, when the obtained weather information is inputted to the artificial intelligence model, the artificial intelligence model outputs the obtained power consumption amount corresponding to the weather information;

obtaining weather forecast information;

determining an output data outputted from the artificial intelligence model when the weather forecast information is inputted to the artificial intelligence model as a predicted power consumption amount to be consumed by the air conditioner corresponding to the weather forecast information;

displaying the predicted power consumption amount of the air conditioner output from the artificial intelligence model; and

performing a power saving operation by controlling a compressor of the air conditioner when the predicted power consumption amount of the air conditioner is within a predetermined range of the target power amount based on the preference information of the user, the target power amount, and the weather information.

2 . The operation method of claim 1 , wherein the weather information includes at least one of an outdoor temperature, an indoor/outdoor temperature difference, an outdoor humidity and a fine dust concentration.

3 . The operation method of claim 1 , further comprising:

displaying the target power amount with the predicted power consumption amount.

4 . The operation method of claim 1 , further comprising:

displaying the power consumption amount consumed by the air conditioner with the target power amount.

5 . The operation method of claim 1 , wherein the performing the power saving operation comprising:

performing the power saving operation by preventing the air conditioner from operating during a time for which the user is away from an indoor space of the air conditioner.

6 . The operation method of claim 1 , wherein the performing the power saving operation comprising:

obtaining motion information of the user in an indoor space of the air conditioner through a motion sensor; and

performing the power saving operation by lowering a wind speed of the air conditioner and increasing a desired temperature as a motion amount of the user is lower, based on the obtained motion information of the user.

7 . The operation method of claim 1 , further comprising:

performing a precooling operation based on schedule information of the user.

8 . The operation method of claim 1 , wherein the artificial intelligence model is trained, by the server, such that, when a weather condition of weather conditions is inputted to the artificial intelligence model, the artificial intelligence model outputs an amount of power consumed by the air conditioner obtained from feature information corresponding to the weather condition when the feature information on the usage patterns of the air conditioner according to the weather conditions has been used as the training data.

9 . The operation method of claim 1 , wherein the controlling the compressor includes at least one of controlling a number of rotations of the compressor of the air conditioner or controlling a discharge value through which a refrigerant is discharged from the compressor of the air conditioner.

10 . An air conditioner comprising:

memory, comprising one or more storage media, storing instructions;

a communication circuit;

a display; and

at least one processor coupled to the memory, the communication circuit, and the display,

wherein the instructions, when executed by the at least one processor individually or collectively, causes the air conditioner to:

receive a user input of setting a target power amount;

obtain, through the communication circuit, weather information from a server;

obtain a power consumption amount consumed by the air conditioner corresponding to the weather information;

obtain air conditioner operational preference information of the user;

store the obtained weather information and the obtained power consumption amount corresponding to the weather information as a training data for an artificial intelligence model;

train the artificial intelligence model such that, when the obtained weather information is inputted to the artificial intelligence model, the artificial intelligence model outputs the obtained power consumption amount corresponding to the weather information,

obtain, through the communication circuit, weather forecast information;

determine an output data outputted from the artificial intelligence model when the weather forecast information is inputted to the artificial intelligence model as a predicted power consumption amount to be consumed by the air conditioner corresponding to the weather forecast information;

display, through the display, the predicted power consumption amount of the air conditioner output from the artificial intelligence model; and

perform a power saving operation by controlling a compressor of the air conditioner when the predicted power consumption amount of the air conditioner is within a predetermined range of the target power amount based on the preference information of the user, the target power amount, and the weather information.

11 . The air conditioner of claim 10 , wherein the weather information includes at least one of an outdoor temperature, an indoor/outdoor temperature difference, an outdoor humidity and a fine dust concentration.

12 . The air conditioner of claim 10 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the air conditioner to display the target power amount with the predicted power consumption amount.

13 . The air conditioner of claim 10 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the air conditioner to display the power consumption amount consumed by the air conditioner with the target power amount.

14 . The air conditioner of claim 10 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the air conditioner to perform the power saving operation by preventing the air conditioner from operating during a time for which the user is away from an indoor space of the air conditioner.

15 . The air conditioner of claim 10 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the air conditioner to obtain motion information of the user in an indoor space of the air conditioner through a motion sensor, perform the power saving operation by lowering a wind speed of the air conditioner and increase a desired temperature as a motion amount of the user is lower, based on the obtained motion information of the user.

16 . The air conditioner of claim 10 , wherein the instructions, when executed by the at least one processor individually or collectively, further cause the air conditioner to perform a precooling operation based on schedule information of the user.

17 . One or more non-transitory computer-readable storage media storing one or more computer programs including computer-executable instructions that, when executed by one or more processors of an air conditioner individually or collectively, cause the air conditioner to perform operations, the operations comprising:

receiving a user input of setting a target power amount;

obtaining weather information from a server;

obtaining a power consumption amount consumed by the air conditioner corresponding to the weather information;

obtaining air conditioner operational preference information of the user;

storing the obtained weather information and the obtained power consumption amount corresponding to the weather information as a training data for an artificial intelligence model;

training the artificial intelligence model such that, when the obtained weather information is inputted to the artificial intelligence model, the artificial intelligence model outputs the obtained power consumption amount corresponding to the weather information;

obtaining weather forecast information;

determining an output data outputted from the artificial intelligence model when the weather forecast information is inputted to the artificial intelligence model as a predicted power consumption amount to be consumed by the air conditioner corresponding to the weather forecast information;

displaying the predicted power consumption amount of the air conditioner output from the artificial intelligence model; and

performing a power saving operation by controlling a compressor of the air conditioner when the predicted power consumption amount of the air conditioner is within a predetermined range of the target power amount based on the preference information of the user, the target power amount, and the weather information.

Priority Claims (1)
KR 10-2019-0115472 · Sep 19, 2019 · national
Continuity (2)
Continuation 17004445 · Aug 27, 2020
Related Publication 20230087048A1 · Mar 23, 2023
References Cited (55)
US 5996898A · Parker · 1999 [cited by examiner]
US 8396601B2 · Tomita et al. · 2013 [cited by applicant]
US 10001289B2 · Mowris · 2018 [cited by applicant]
US 10443873B1 · Johnson · 2019 [cited by examiner]
US 10885238B1 · Packer · 2021 [cited by examiner]
US 11397020B2 · Moon et al. · 2022 [cited by applicant]
US 20060031180A1 · Tamarkin · 2006 [cited by examiner]
US 20070203860A1 · Golden · 2007 [cited by examiner]
US 20090187445A1 · Barclay et al. · 2009 [cited by applicant]
US 20110313578A1 · Jones et al. · 2011 [cited by applicant]
US 20140249876A1 · Wu · 2014 [cited by examiner]
US 20150248118A1 · Li et al. · 2015 [cited by applicant]
US 20160018832A1 · Frank · 2016 [cited by examiner]
US 20160091904A1 · Horesh · 2016 [cited by examiner]
US 20160291622A1 · Al-Mohssen et al. · 2016 [cited by applicant]
US 20160305678A1 · Pavlovski et al. · 2016 [cited by applicant]
US 20170031429A1 · Miyazaki · 2017 [cited by examiner]
US 20170124466A1 · Li · 2017 [cited by examiner]
US 20170159956A1 · Lewis · 2017 [cited by examiner]
US 20170206615A1 · Sloop et al. · 2017 [cited by applicant]
US 20170211830A1 · Kosaka et al. · 2017 [cited by applicant]
US 20170261957A1 · Boettcher · 2017 [cited by examiner]
US 20180031264A1 · Atchison · 2018 [cited by examiner]
US 20180073760A1 · Smith · 2018 [cited by examiner]
US 20180195752A1 · Sasaki et al. · 2018 [cited by applicant]
US 20180209683A1 · Cho · 2018 [cited by examiner]
US 20190024928A1 · Li · 2019 [cited by examiner]
US 20190163215A1 · Cheng · 2019 [cited by examiner]
US 20190224928A1 · Danniger et al. · 2019 [cited by applicant]
US 20190271483A1 · Joo et al. · 2019 [cited by applicant]
US 20200124308A1 · Ota et al. · 2020 [cited by applicant]
US 20200143491A1 · Turney · 2020 [cited by examiner]
US 20200209820A1 · Kochar · 2020 [cited by examiner]
US 20200355387A1 · Samuni · 2020 [cited by examiner]
US 20210116874A1 · Murugesan et al. · 2021 [cited by applicant]
US 20210215370A1 · Moon et al. · 2021 [cited by applicant]
US 20210356161A1 · Chen · 2021 [cited by examiner]
US 20250012479A1 · Mun · 2025 [cited by examiner]
JP 08322147A · 1996 [cited by applicant]
JP 2012211738A · 2012 [cited by applicant]
JP 2018091560A · 2018 [cited by applicant]
JP 6372684B2 · 2018 [cited by applicant]
JP 2019007632A · 2019 [cited by applicant]
KR 1020160150156A · 2016 [cited by applicant]
KR 1020180065601A · 2018 [cited by applicant]
KR 1020190096878A · 2019 [cited by applicant]
WO 2017062896A1 · 2017 [cited by applicant]
Household Electricity Demand Forecasting-Benchmarking State-of-the-Art Methods; Apr. 1, 2014. [cited by applicant]
Electricity forecasting on the individual household level enhanced based on activity patterns; Apr. 19, 2017. [cited by applicant]
Nonintrusive Appliance Load Monitoring - Review and Outlook; Feb. 21, 2011. [cited by applicant]
Identifying trends in the use of domestic appliances from household; Dec. 2008. [cited by applicant]
International Search Report, dated Dec. 2, 2020, issued in International Patent Application No. PCT/KR2020/011493. [cited by applicant]
European Search Report dated May 24, 2022; European AppIn No. 20864481.5-1016 / 3966775 PCT/KR2020011493. [cited by applicant]
European Office Action dated Sep. 30, 2024, issued in European Application No. 20864481.5. [cited by applicant]
Korean Office Action dated Apr. 17, 2025, issued in Korean Patent Application No. 10-2019-0115472. [cited by applicant]