Air conditioner and method thereof

Abstract

The present invention relates to an air conditioner and a method of operating the same. An air conditioner according to one embodiment of the present invention comprises: an outdoor unit including a compressor for compressing a refrigerant; at least one indoor unit; a storage unit storing a previously learned control algorithm in relation to the control of a component included in the air conditioner; and a control unit. The control unit, when the operating mode of the air conditioner is set to a first mode, controls at least one of the outdoor unit and the at least one indoor unit regardless of the control algorithm, and learns a power consumption learning model related to the actual power consumption of the air conditioner while the first mode is set based on first data acquired while the first mode is set, and when the operating mode of the air conditioner is set to a second mode, controls at least one of the outdoor unit and the at least one indoor unit based on the control algorithm, and calculates a predicted power consumption corresponding to the second mode based on second data acquired while the second mode is set and the power consumption learning model, and the actual power consumption of the air conditioner while the second mode is set, respectively.

Description

Technology Field

[0001] The present invention relates to an air conditioner and a method of operating the same, and more specifically, to an air conditioner and a method of operating the same capable of providing the amount of power consumed by the air conditioner to a user. Background Technology

[0002] An air conditioner is installed to provide a more comfortable indoor environment for humans by discharging hot and cold air into the room to regulate the indoor temperature and purify the indoor air, thereby creating a pleasant indoor environment. Generally, an air conditioner includes an indoor unit composed of a heat exchanger and installed indoors, and an outdoor unit composed of a compressor and a heat exchanger, which supplies refrigerant to the indoor unit.

[0003] Recently, electronic devices used in homes are becoming increasingly diverse for user convenience, and various automation systems are being implemented across diverse industrial sectors to boost productivity. Furthermore, as temperatures gradually rise due to climate change, such as global warming, the frequency and duration of air conditioner operation are also increasing. For these reasons, electricity consumption is on the rise not only in households but across industries as a whole, leading to a growing burden from electricity bills.

[0004] To address these issues, active research is being conducted to provide a comfortable indoor environment while reducing the power consumption of air conditioners. For example, in an operation mode that prioritizes cooling and heating capacity, the air conditioner operates according to a target temperature set by the user, while in an operation mode that prioritizes power consumption reduction, it can operate by varying the target temperature depending on the situation.

[0005] Meanwhile, generally, a user can check the amount of power consumed by an air conditioner by repeatedly checking the readings of a power meter installed in a home or building, similar to Prior Art 1 (Korean Published Patent Application No. 10-2020-0089196), or by using a system that manages the accumulated amount of power consumed by the air conditioner in conjunction with a power meter. In this case, the user can only check the actual amount of power consumed by the air conditioner during a predetermined period in a specific operating mode, and there is a problem in that it is difficult to accurately determine how much power consumption a specific operating mode can reduce compared to other operating modes under the same conditions. Prior art literature

[0006] (Patent Document 0001) KR 10-2020-0089196 A The problem to be solved

[0007] The present disclosure aims to solve the aforementioned problems and other problems.

[0008] Another objective is to provide an air conditioner and a method of operation thereof that, when the operating mode is set to smart operating mode, can calculate together the actual power consumption in the currently set smart operating mode and the power consumption expected to be used in the currently unset normal operating mode under the same conditions.

[0009] Another objective is to provide an air conditioner and a method of operation thereof that can provide the user with information regarding the amount of power saved compared to the normal operation mode when set to smart operation mode. Another objective is to provide an air conditioner and a method of operation thereof that can improve the accuracy of the result of calculating the expected power consumption in normal operation mode by training a power consumption learning model based on data acquired while set to normal operation mode.

[0010] Another objective is to provide an air conditioner and a method of operation thereof that can correct the result of calculating the power consumption expected to be used in a normal operating mode by considering the error range of the result value calculated through a power consumption learning model.

[0011] Another objective is to provide an air conditioner and a method of operation thereof that can calculate the actual amount of power consumed by using data received from an external device such as a power meter and / or data corresponding to an operation of a predetermined configuration.

[0012] Another objective is to provide an air conditioner and a method of operation thereof that can manage the history of power consumption by updating a database of power consumption expected to be used and actual consumed in a predetermined operating mode.

[0013] Another objective is to provide an air conditioner and a method of operation thereof that can regulate the flow rate of refrigerant supplied to an indoor unit by utilizing various control algorithms when set to smart operation mode.

[0014] Another objective is to provide an air conditioner and a method of operation thereof that can provide various user interfaces related to power consumption depending on the currently set operating mode.

[0015] The problems of the present invention are not limited to those mentioned above, and other unmentioned problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0016] An air conditioner according to various embodiments of the present invention for achieving the above objective can learn a power consumption learning model related to the actual power consumption of the air conditioner while the operating mode is set to a first mode.

[0017] According to one embodiment of the present invention, while the operating mode is set to a second mode different from the first mode, the air conditioner can calculate the predicted amount of power expected to be consumed when the air conditioner is set to the first mode by using the power amount learning model.

[0018] According to one embodiment of the present invention, the air conditioner can compare the predicted amount of power expected to be consumed when set to the first mode with the actual amount of power consumed by the air conditioner while set to the second mode.

[0019] According to one embodiment of the present invention, the air conditioner may include: an outdoor unit comprising a compressor for compressing a refrigerant; at least one indoor unit; a storage unit storing a control algorithm learned in relation to the control of a component included in the air conditioner; and a control unit.

[0020] According to one embodiment of the present invention, when the operating mode of the air conditioner is set to the first mode, the control unit can control at least one of the outdoor unit and the at least one indoor unit independently of the control algorithm.

[0021] According to one embodiment of the present invention, when the operating mode of the air conditioner is set to the second mode, the control unit can control at least one of the outdoor unit and the at least one indoor unit based on the control algorithm.

[0022] According to one embodiment of the present invention, the control unit can calculate the actual amount of power consumed by the air conditioner based on either data regarding the amount of power consumed by the air conditioner received from an external device or the operating frequency of the compressor.

[0023] According to one embodiment of the present invention, when the operating mode of the air conditioner is set to the first mode, the control unit can calculate a predicted power amount corresponding to the first mode by using the first data acquired for a predetermined time and the power amount learning model.

[0024] According to one embodiment of the present invention, the control unit can learn the power amount learning model based on the first data acquired during the predetermined time when the difference between the predicted power amount corresponding to the first mode and the actual power amount consumed by the air conditioner during the predetermined time is greater than or equal to a preset standard.

[0025] According to one embodiment of the present invention, the control unit can determine the weight and bias of the power consumption learning model by learning the correlation between the first data acquired during the predetermined time and the actual power consumption of the air conditioner during the predetermined time.

[0026] According to one embodiment of the present invention, the storage unit stores a database, and the control unit can add to the database a first predicted power amount calculated based on the first data acquired during a predetermined time and an actual power amount consumed by the air conditioner during the predetermined time when the operating mode of the air conditioner is set to the first mode.

[0027] According to one embodiment of the present invention, when the operating mode of the air conditioner is set to the second mode, the control unit may add to the database a second predicted power amount calculated based on the second data acquired during the predetermined time and an actual power amount consumed by the air conditioner during the predetermined time.

[0028] According to one embodiment of the present invention, the control unit can delete data included in the database that was added to the database earlier than a preset period from the current time.

[0029] According to one embodiment of the present invention, when the operating mode of the air conditioner is set to the first mode, the control unit can calculate the first predicted power amount calculated based on the first data acquired during the predetermined time period as a value equal to the actual power amount consumed by the air conditioner during the predetermined time period.

[0030] According to one embodiment of the present invention, the control unit can determine the minimum and maximum values ​​of the predicted power amount in response to the pressure of the refrigerant flowing into the compressor while set to the second mode.

[0031] According to one embodiment of the present invention, if the calculated predicted power amount is less than the minimum value, the control unit may determine the minimum value as the predicted power amount corresponding to the second mode.

[0032] According to one embodiment of the present invention, if the calculated predicted power amount exceeds the maximum value, the control unit may determine the maximum value as the predicted power amount corresponding to the second mode.

[0033] According to one embodiment of the present invention, when the operating mode of the air conditioner is set to the second mode, the control unit can determine an indoor unit cluster for each of the at least one indoor unit.

[0034] According to one embodiment of the present invention, the control unit can determine the flow rate of the refrigerant supplied to the at least one indoor unit based on the indoor unit cluster and the second data.

[0035] According to one embodiment of the present invention, the control unit can determine the total flow rate of the refrigerant supplied by the outdoor unit based on the flow rate of the refrigerant supplied to the at least one indoor unit.

[0036] According to one embodiment of the present invention, the control unit can determine whether to perform initial operation when the operating mode of the air conditioner is set to the second mode.

[0037] According to one embodiment of the present invention, when performing the initial operation, the control unit can determine the flow rate of the refrigerant supplied to the at least one indoor unit based on a first control algorithm using an exponential smoothing method.

[0038] According to one embodiment of the present invention, when the initial operation is not performed, the control unit can determine the flow rate of the refrigerant supplied to the at least one indoor unit based on a second control algorithm that has been learned regarding the correlation between the second data and the flow rate of the refrigerant.

[0039] Meanwhile, an air conditioner according to one embodiment of the present invention may include an outdoor unit comprising a compressor for compressing a refrigerant; at least one indoor unit; a storage unit storing a previously learned control algorithm in relation to the control of a component included in the air conditioner; a display; and a control unit.

[0040] Meanwhile, according to various embodiments of the present invention for achieving the above objective, the control unit may output a screen through the display that includes at least one of the actual amount of power consumed by the air conditioner, the predicted amount of power, and the reduction rate while the second mode is set.

[0041] Meanwhile, according to various embodiments of the present invention for achieving the above objective, the control unit may output a first screen related to the actual amount of power consumed by the air conditioner through the display while set to the first mode, and output a second screen related to the actual amount of power consumed by the air conditioner and the predicted amount of power through the display while set to the second mode.

[0042] Meanwhile, a method of operating an air conditioner according to various embodiments of the present invention for achieving the above objective may include a first control operation that controls at least one of an outdoor unit and at least one indoor unit regardless of a previously stored control algorithm when the operating mode of the air conditioner is set to a first mode.

[0043] According to one embodiment of the present invention, the method of operating the air conditioner may include a learning operation of learning a power amount learning model related to the actual power amount consumed by the air conditioner while it is set to the first mode, based on first data acquired while it is set to the first mode.

[0044] According to one embodiment of the present invention, the method of operating the air conditioner may include a second control operation that controls at least one of the outdoor unit and at least one indoor unit based on the control algorithm when the operating mode of the air conditioner is set to a second mode.

[0045] According to one embodiment of the present invention, the method of operating the air conditioner may include a result calculation operation for each calculating a predicted power amount corresponding to the second mode based on second data acquired while the second mode is set and a power amount learning model, and an actual power amount consumed by the air conditioner while the second mode is set.

[0046] According to one embodiment of the present invention, the result calculation operation may be an operation of calculating the actual amount of power consumed by the air conditioner based on either data regarding the amount of power consumed by the air conditioner received from an external device or the operating frequency of the compressor.

[0047] According to one embodiment of the present invention, the learning operation may include acquiring the first data for a predetermined period of time when the operating mode of the air conditioner is set to the first mode.

[0048] According to one embodiment of the present invention, the learning operation may include an operation of calculating a predicted power amount corresponding to the first mode using the first data acquired during the predetermined time and the power amount learning model.

[0049] According to one embodiment of the present invention, the learning operation may include an operation of learning the power amount learning model based on the first data acquired during the predetermined time when the difference between the predicted power amount corresponding to the first mode and the actual power amount consumed by the air conditioner during the predetermined time is greater than or equal to a preset standard.

[0050] According to one embodiment of the present invention, the operation of learning the power consumption learning model may be an operation of determining the weight and bias of the power consumption learning model by learning the correlation between the first data acquired during the predetermined time and the actual power consumption consumed by the air conditioner during the predetermined time.

[0051] According to one embodiment of the present invention, the method of operating the air conditioner may include, when the operating mode of the air conditioner is set to the first mode, adding to a database a first predicted power amount calculated based on the first data acquired during a predetermined time and an actual power amount consumed by the air conditioner during the predetermined time.

[0052] According to one embodiment of the present invention, the method of operating the air conditioner may include, when the operating mode of the air conditioner is set to the second mode, adding to the database a second predicted power amount calculated based on the second data acquired during the predetermined time and an actual power amount consumed by the air conditioner during the predetermined time.

[0053] According to one embodiment of the present invention, the method of operating the air conditioner may include the operation of deleting data added to the database earlier than a preset period from the current time, among the data included in the database.

[0054] According to one embodiment of the present invention, the operation of adding to a database considering the above time may include, when the operating mode of the air conditioner is set to the first mode, the operation of calculating the first predicted power amount calculated based on the first data acquired during the above predetermined time period as a value equal to the actual power amount consumed by the air conditioner during the above predetermined time period.

[0055] According to one embodiment of the present invention, the result calculation operation may include an operation of determining the minimum and maximum values ​​of the predicted power amount in response to the pressure of the refrigerant flowing into the compressor equipped in the outdoor unit while the second mode is set.

[0056] According to one embodiment of the present invention, the result calculation operation may include, when the calculated predicted power amount is less than the minimum value, the operation of determining the minimum value as the predicted power amount corresponding to the second mode.

[0057] According to one embodiment of the present invention, the result calculation operation may include, when the calculated predicted power amount exceeds the maximum value, an operation of determining the maximum value as the predicted power amount corresponding to the second mode.

[0058] According to one embodiment of the present invention, the first control operation may include an operation of determining an indoor unit cluster for each of the at least one indoor unit when the operating mode of the air conditioner is set to the second mode.

[0059] According to one embodiment of the present invention, the first control operation may include an operation to determine the flow rate of the refrigerant supplied to the at least one indoor unit based on the indoor unit cluster and the second data.

[0060] According to one embodiment of the present invention, the second control operation may include an operation to determine whether to perform initial operation when the operating mode of the air conditioner is set to the second mode.

[0061] According to one embodiment of the present invention, the second control operation may include, when performing the initial operation, an operation to determine the flow rate of the refrigerant supplied to the at least one indoor unit based on a first control algorithm using an exponential smoothing method.

[0062] According to one embodiment of the present invention, the second control operation may include, when the initial operation is not performed, an operation to determine the flow rate of the refrigerant supplied to the at least one indoor unit based on a second control algorithm that has been learned regarding the correlation between the second data and the flow rate of the refrigerant.

[0063] According to one embodiment of the present invention, the second control operation may include an operation to determine the total flow rate of the refrigerant supplied by the outdoor unit based on the flow rate of the refrigerant supplied to the at least one indoor unit.

[0064] Meanwhile, a method of operating an air conditioner according to various embodiments of the present invention for achieving the above objective may include an operation of outputting, through a display, a screen including at least one of the actual amount of power consumed by the air conditioner, the predicted amount of power, and the reduction rate while the second mode is set.

[0065] Meanwhile, a method of operating an air conditioner according to various embodiments of the present invention for achieving the above objective may include: an operation of outputting a first screen related to the actual amount of power consumed by the air conditioner through the display while the first mode is set; and an operation of outputting a second screen related to the actual amount of power consumed by the air conditioner and the predicted amount of power through the display while the second mode is set.

[0066] Specific details of other embodiments are included in the detailed description and drawings. Effects of the invention

[0067] According to various embodiments of the present invention, one or more of the following effects are present.

[0068] According to various embodiments of the present invention, when the air conditioner is set to a smart operation mode, there is an advantage in that the power consumption expected in the normal operation mode and the actual power consumption in the smart operation mode can be calculated and compared under the same conditions by using a power consumption learning model related to the actual power consumption in the normal operation mode.

[0069] In addition, according to various embodiments of the present invention, there is also an advantage of being able to provide the user with information regarding the amount of power saved compared to the normal driving mode when set to smart driving mode.

[0070] In addition, according to various embodiments of the present invention, there is an advantage in that the accuracy of the result of calculating the power consumption expected to be used in normal mode can be improved while the operating mode is set to smart operating mode, by repeatedly retraining the power consumption learning model based on the difference between the power consumption calculated using the power consumption learning model and the actual power consumption consumed by the air conditioner while the operating mode is set to normal operating mode.

[0071] In addition, according to various embodiments of the present invention, there is an advantage in that the result of calculating the power consumption expected to be used in a general operating mode can be corrected by considering the error range of the result value calculated through the power consumption learning model.

[0072] In addition, according to various embodiments of the present invention, there is also an advantage in that the actual amount of power consumed by the air conditioner can be calculated using data received from an external device such as a power meter and / or data corresponding to an operation of a predetermined configuration.

[0073] In addition, according to various embodiments of the present invention, there is an advantage in being able to manage the history regarding the use of power by updating a database of the power amount expected to be used in a predetermined operating mode and the power amount actually consumed.

[0074] In addition, according to various embodiments of the present invention, when set to smart operation mode, there is an advantage in that the flow rate of the refrigerant supplied to the indoor unit can be controlled by utilizing various control algorithms.

[0075] In addition, according to various embodiments of the present invention, there is also an advantage of being able to provide various user interfaces related to power consumption depending on the currently set operating mode.

[0076] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description in the claims. Brief explanation of the drawing

[0077] FIG. 1 is a drawing illustrating the configuration of an air conditioner according to one embodiment of the present invention. Figure 2 is a schematic diagram of the outdoor unit and indoor unit of Figure 1. FIG. 3 is a block diagram of an air conditioner according to one embodiment of the present invention. FIG. 4 is a drawing referenced in the description of deep learning according to one embodiment of the present invention. FIGS. 5 to 7 are flowcharts illustrating a method of operation of an air conditioner according to an embodiment of the present invention. FIGS. 8 to 12b are drawings referenced in the description of the operation of an air conditioner. FIGS. 13 to 21 are drawings referenced in the description of a control algorithm used to control a component included in an air conditioner. Specific details for implementing the invention

[0078] The present invention will be described in detail below with reference to the drawings. In order to clearly and concisely explain the invention, parts unrelated to the description have been omitted from the drawings, and the same reference numerals are used throughout the specification for identical or extremely similar parts.

[0079] The suffixes "module" and "part" for components used in the following description are assigned solely for the ease of drafting this specification and do not inherently confer any particularly significant meaning or role. Accordingly, the terms "module" and "part" may be used interchangeably.

[0080] In this application, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0081] Additionally, in this specification, terms such as first, second, etc. may be used to describe various elements, but these elements are not limited by these terms. These terms are used only to distinguish one element from another.

[0082] Hereinafter, the present invention will be described with reference to the drawings for explaining a control method of an air conditioner according to embodiments of the present invention.

[0083] FIG. 1 is a drawing illustrating the configuration of an air conditioner according to one embodiment of the present invention.

[0084] Referring to FIG. 1, an air conditioner (100) according to one embodiment of the present invention may include an outdoor unit (21) and at least one indoor unit (31) connected to the outdoor unit (21). A plurality of indoor units (31) may be connected to one outdoor unit (21), and the number of indoor units (31) connected to one outdoor unit (21) is not limited to the drawing.

[0085] The indoor unit (31) may include at least one of a stand-type indoor unit (31a), a wall-mounted indoor unit (31b), and a ceiling-type indoor unit (31c).

[0086] Meanwhile, the air conditioner (100) may further include at least one of a ventilation device, an air purifier, a humidifier, and a heater, and may operate in conjunction with the operation of the indoor unit (31) and the outdoor unit (21).

[0087] The outdoor unit (21) may include a compressor (not shown) that receives and compresses refrigerant, an outdoor heat exchanger (not shown) that exchanges heat between the refrigerant and outdoor air, an accumulator (not shown) that extracts gaseous refrigerant from the supplied refrigerant and supplies it to the compressor, and a four-way valve (not shown) that selects the flow path of the refrigerant according to the heating operation. Additionally, the outdoor unit (21) may further include a plurality of sensors, valves, and oil recovery devices.

[0088] The outdoor unit (21) can operate the provided compressor and outdoor heat exchanger to compress or heat exchange the refrigerant according to the settings and supply the refrigerant to the indoor unit (31). The outdoor unit (21) can be driven by a central controller (not shown) or by the demand of the indoor unit (31). At this time, it is also possible to vary the number of outdoor units and the number of compressors installed in the outdoor unit as the cooling / heating capacity varies in response to the driven indoor unit (31).

[0089] At this time, the outdoor unit (21) can supply compressed refrigerant to the connected indoor unit (31).

[0090] The indoor unit (31) can receive refrigerant from the outdoor unit (21) and discharge cold and hot air into the room. The indoor unit (31) may include an indoor heat exchanger (not shown), an indoor unit fan (not shown), an expansion valve (not shown) through which the supplied refrigerant expands, and a plurality of sensors (not shown).

[0091] At this time, the outdoor unit (21) and the indoor unit (31) can be connected via a communication line to transmit and receive data to and from each other, and the outdoor unit (21) and the indoor unit (31) can be connected to a central controller via a wired or wireless connection and operate according to the control of the central controller.

[0092] The remote control (41) is connected to the indoor unit (31) and can transmit control commands from the user to the indoor unit (31) and receive and display status information of the indoor unit (31). At this time, the remote control (41) can communicate via wired or wireless connection depending on the connection type with the indoor unit (31).

[0093] Meanwhile, the air conditioner (100) may further include at least one sensor (not shown) capable of detecting the condition of indoor air. For example, the air conditioner (100) may further include a temperature sensor for detecting indoor temperature, a humidity sensor for detecting indoor humidity, a pressure sensor for detecting indoor air pressure, a sensor for measuring the amount of dust in indoor air, and may also include a sensor capable of collecting various data such as temperature, humidity, air pressure, and the amount of dust in the air.

[0094] Meanwhile, the air conditioner (100) can communicate with an external device (10) and transmit and receive data to and from each other. For example, the outdoor unit (21) can receive data regarding the amount of power consumed by the air conditioner (100) in real time from an external device (10) that measures the amount of power consumed by the air conditioner (100).

[0095] Figure 2 is a schematic diagram of the outdoor unit and indoor unit of Figure 1.

[0096] Referring to FIG. 2, an air conditioner (100) according to one embodiment of the present invention may be divided into an outdoor unit (21) and an indoor unit (31). The air conditioner (100) may include a plurality of indoor units (31a to 31c).

[0097] The outdoor unit (21) may include a compressor (110) that compresses the refrigerant, a compressor motor (not shown) that drives the compressor (110), an outdoor heat exchanger (120) that dissipates heat from the compressed refrigerant, an accumulator (130) that temporarily stores the gasified refrigerant to remove moisture and foreign substances and then supplies the refrigerant at a constant pressure to the compressor, a cooling / heating switching valve (140) that changes the path of the compressed refrigerant, an oil separator (150), an outdoor fan (161) that is positioned on one side of the outdoor heat exchanger (120) to promote heat dissipation of the refrigerant, an outdoor fan motor (162) that rotates the outdoor fan (161), and at least one expansion mechanism (e.g., electronic expansion valves (EEV)) that expands the condensed refrigerant.

[0098] More specifically, the outdoor unit (21) may include a gas pipe service valve (113) to which a gas pipe (182) is connected and a liquid pipe service valve (114) to which a liquid pipe (112) is connected. The gas pipe service valve (113) and the liquid pipe service valve (114) may be connected to an indoor unit (31) and may circulate the refrigerant of the outdoor unit (21).

[0099] At least one of an inverter compressor and a constant speed compressor may be used for the compressor (110). High temperature, high pressure refrigerant discharged from the compressor (110) may flow to an oil separator (150) through the discharge side pipe (151) of the compressor (110).

[0100] The outdoor unit (21) may include a first oil recovery pipe (131) connecting the lower side of the accumulator (130) and the suction side pipe (135) of the compressor (110). An oil return valve (132) for controlling the flow of oil may be provided in the first oil recovery pipe (131).

[0101] The outdoor unit (21) may include a second oil recovery pipe (152) through which oil flows from the oil separator (150) to the compressor (11). A check valve (153) that restricts the flow of oil to one side may be provided in the second oil recovery pipe (152).

[0102] The refrigerant discharged from the oil separator (150) can flow to the cooling / heating switching valve (140) through the refrigerant discharge pipe (181).

[0103] The outdoor heat exchanger (120) can exchange heat between the outdoor air and the refrigerant, and may be composed of a plurality of units (122, 124) according to the embodiment. The outdoor heat exchanger (120) can operate as a condenser during cooling operation and as an evaporator during heating operation.

[0104] A variable pass valve (186) may be positioned between the first outdoor heat exchanger (122) and the variable pass pipe (185). When the variable pass valve (186) is opened, the refrigerant flowing through the first outdoor heat exchanger (122) may flow to the cooling / heating switching valve (140) via the variable pass valve (186), the variable pass pipe (185), and the check valve (187). When the variable pass valve (186) is closed, the refrigerant flowing through the first outdoor heat exchanger (122) during cooling operation may flow to the first heat exchanger-expansion valve connecting pipe (123), and the refrigerant flowing through the first heat exchanger-expansion valve connecting pipe (123) during heating operation may flow to the first outdoor heat exchanger (122).

[0105] The outdoor expansion valve (170) can expand the refrigerant flowing to the outdoor heat exchanger (120) during heating operation, and can pass the refrigerant without expansion during cooling operation. The outdoor expansion valve (170) may use an electronic expansion valve (EEV) that can adjust the opening value according to an input signal.

[0106] The outdoor expansion valve (170) may include a first outdoor expansion valve (172) that expands the refrigerant flowing to the first outdoor heat exchanger (122) and a second outdoor expansion valve (174) that expands the refrigerant flowing to the second outdoor heat exchanger (174).

[0107] The first outdoor heat exchanger (122) can be connected to a cooling / heating switching valve (140) through a heat exchanger-switching valve connecting pipe (183a). The first outdoor heat exchanger (122) can be connected to an outdoor expansion valve (170) through a first heat exchanger-expansion valve connecting pipe (123).

[0108] The second outdoor heat exchanger (124) can be connected to the second outdoor expansion valve (174) through the second heat exchanger-expansion valve connecting pipe (125).

[0109] The first outdoor expansion valve (172) may be positioned between the first heat exchanger-expansion valve connecting pipe (123) and the supercooled liquid pipe (112'). The second outdoor expansion valve (174) may be positioned between the second heat exchanger-expansion valve connecting pipe (125) and the supercooled liquid pipe (112').

[0110] The outdoor unit (21) may further include a hot gas unit (190) for bypassing the refrigerant supplied to the outdoor heat exchanger (120) to the indoor unit (31) during heating operation. The hot gas unit (90) may include a hot gas bypass pipe (191, 192) for bypassing the refrigerant and a hot gas valve (193, 194). At this time, the first hot gas valve (193) and the second hot gas valve (194) may be operated selectively. For example, only the first hot gas valve (193) may be opened / closed, or only the second hot gas valve (194) may be opened / closed. Meanwhile, in this embodiment, a bonding valve (195) for bonding the first hot gas bypass pipe (191) and the second hot gas bypass pipe (192) may be provided.

[0111] The outdoor unit (21) may further include a supercooling unit (200) placed in the liquid pipe (112). The subcooling unit (200) comprises a subcooling heat exchanger (201), a subcooling bypass pipe (202) that is bypassed from the liquid pipe (112) and connected to the subcooling heat exchanger (201), a first subcooling expansion valve (203) that selectively expands the refrigerant flowing through the subcooling bypass pipe (202), a subcooling-compressor connecting pipe (204) that connects the subcooling heat exchanger (201) and the compressor (110), a second subcooling expansion valve (205) that is placed in the subcooling-compressor connecting pipe (204) and selectively expands the refrigerant flowing through it, an accumulator bypass pipe (206) that connects the accumulator (130) and the subcooling-compressor connecting pipe (204), and / or a refrigerant flowing through the accumulator bypass pipe (206). It may include a supercooling bypass valve (107) that controls the refrigerant.

[0112] The outdoor unit (21) may further include a receiver (210) disposed in the liquid pipe (112). The receiver (210) may store liquid refrigerant to regulate the amount of circulating refrigerant. The receiver (210) may store liquid refrigerant separately from the liquid refrigerant stored in the accumulator (30). For example, the receiver (210) may supply refrigerant to the accumulator (130) when the amount of circulating refrigerant is insufficient, and may recover and store refrigerant when the amount of circulating refrigerant is large.

[0113] The receiver (210) may include a receiver tank (211) for storing refrigerant and a receiver valve (213, 215) for controlling the flow of refrigerant.

[0114] The first receiver connecting pipe (112) can connect the receiver tank (211) and the supercooled liquid pipe (112') to each other. A first receiver valve (213) for controlling the flow of refrigerant can be disposed in the first receiver connecting pipe (112).

[0115] The second receiver connecting pipe (114) can connect the receiver tank (211) and the accumulator (130) to each other. A second receiver valve (215) for controlling the flow of refrigerant can be disposed in the second receiver connecting pipe (114).

[0116] The indoor unit (31a to 31c) may include an indoor heat exchanger (33a to 33c) that is placed indoors and performs cooling / heating functions, an indoor expansion valve (35a to 35c) in which the supplied refrigerant expands, an indoor fan (not shown) that is placed on one side of the indoor heat exchanger (33a to 33c) to promote heat dissipation of the refrigerant, an indoor blower (not shown) composed of an indoor fan motor (not shown) that rotates the indoor fan, and a plurality of sensors (not shown). At least one indoor heat exchanger (33a to 33c) may be installed in each of the indoor units (31a to 31c).

[0117] The air conditioner (100) may include a gas pipe connecting pipe (241) connecting a gas pipe service valve (113) and a first distributor (242), and a liquid pipe connecting pipe (251) connecting a liquid pipe service valve (114) and a second distributor (252).

[0118] The first distributor (245) can be connected to indoor heat exchangers (33a to 33c) through first to third gas branch pipes (243, 244, 245). The second distributor (252) can be connected to indoor heat exchangers (33a to 33c) through first to third liquid branch pipes (253, 254, 255).

[0119] The air conditioner (100) may be composed of a cooling device that cools the indoor space, or may be composed of a heat pump that cools or heats the indoor space.

[0120] FIG. 3 is a block diagram of an air conditioner according to one embodiment of the present invention.

[0121] Referring to FIG. 3, the air conditioner (100) may include a sensor unit (310), a communication unit (320), a fan driving unit (330), a compressor driving unit (340), a storage unit (350), an output unit (360), and / or a control unit (370). An air conditioner (100) according to various embodiments of the present invention may further include various components not shown in FIG. 3.

[0122] The communication unit (310) may include at least one communication module. The communication unit (310) may be provided in each of the outdoor unit (21) and the indoor unit (31), and the outdoor unit (21) and the indoor unit (31) may transmit and receive data to and from each other. For example, the communication method between the outdoor unit (21) and the indoor unit (31) may be a communication method using power lines, a serial communication method (e.g., RS-485 communication), a wired communication method through refrigerant pipes, as well as a wireless communication method such as Wi-Fi, Bluetooth, Beacon, or Zigbee.

[0123] Meanwhile, the communication unit (310) can transmit and receive data with an external device. For example, the communication unit (310) can establish a wireless communication channel with an external device (e.g., a mobile terminal) and can transmit and receive data regarding the status of each component equipped in the air conditioner (100), whether an error has occurred, etc., through the established wireless communication channel. The communication unit (310) can also transmit and receive data by connecting to a server connected to an external network.

[0124] The sensor unit (320) may be equipped with a plurality of sensors and may transmit data regarding the detected values ​​detected through the plurality of sensors to the control unit (370). For example, the sensor unit (320) may include a heat exchanger temperature sensor (not shown) for detecting the temperature of an outdoor heat exchanger (120) and / or an indoor heat exchanger (33), a pressure sensor (not shown) for detecting the pressure of a refrigerant flowing through each pipe of the air conditioner (100), a pipe temperature sensor (not shown) for detecting the temperature of a refrigerant flowing through each pipe of the air conditioner (100), an indoor temperature sensor (not shown) for detecting the indoor temperature, an outdoor temperature sensor (not shown) for detecting the outdoor temperature, etc.

[0125] The storage unit (330) may store programs for each signal processing and control within the control unit (370), or may store signal-processed voice or data signals. For example, the storage unit (330) may store application programs designed for the purpose of performing various tasks that can be processed by the control unit (370), and may selectively provide some of the stored application programs upon request by the control unit (370). The programs stored in the storage unit (330) are not specifically limited as long as they can be executed by the control unit (370).

[0126] Although the storage unit (330) of FIG. 3 is illustrated in an embodiment in which it is provided separately from the control unit (370), the scope of the present invention is not limited thereto, and the storage unit (330) may be included within the control unit (370).

[0127] The storage unit (330) can store data related to each component provided in the air conditioner (100). For example, the storage unit (330) can store data regarding detection values ​​detected from a plurality of sensors provided in the sensor unit (320). For example, the storage unit (330) can store data regarding the operating frequency of the compressor (110), the pressure of the refrigerant flowing into the compressor (110) (hereinafter referred to as low pressure of the compressor), the pressure of the refrigerant discharged from the compressor (110) (hereinafter referred to as high pressure of the compressor), etc. For example, the storage unit (330) can store data regarding the rotational speed of the fan (351), the opening amount of each electronic expansion valve (EEV), the degree of superheating, the degree of subcooling, etc. For example, the storage unit (330) can store at least one database regarding the amount of power consumed by the air conditioner (100), etc.

[0128] The compressor drive unit (340) can drive the compressor (110). For example, the compressor drive unit (340) may include a rectifier (not shown) that rectifies and outputs AC power into DC power, a DC terminal capacitor that stores the pulsating voltage from the rectifier, an inverter (not shown) that converts and outputs the smoothed DC power into a three-phase AC power of a predetermined frequency by having a plurality of switching elements, and / or a compressor motor (not shown) that drives the compressor (110) according to the three-phase AC power output from the inverter.

[0129] The compressor drive unit (340) can change the operating frequency of the compressor (110) according to the control of the control unit (370). For example, the compressor drive unit (340) can change the operating frequency of the compressor (110) by changing the frequency of the three-phase AC power output to the compressor motor according to the control of the control unit (370).

[0130] The fan driving unit (350) can drive a fan (351) provided in an air conditioner (100). For example, the fan driving unit (350) can drive an outdoor fan (161) and / or an indoor fan (not shown). For example, the fan driving unit (350) may include a rectifier (not shown) that rectifies and outputs AC power into DC power, a DC terminal capacitor that stores a pulsating voltage from the rectifier, an inverter (not shown) that converts and outputs smoothed DC power into three-phase AC power of a predetermined frequency by having a plurality of switching elements, and / or a motor that drives the fan according to the three-phase AC power output from the inverter.

[0131] Meanwhile, the fan drive unit (350) may be provided with separate configurations for driving the outdoor fan (161) and the indoor fan.

[0132] The fan drive unit (350) can change the rotational speed of the fan (351) according to the control of the control unit (370). For example, the fan drive unit (350) can change the rotational speed of the outdoor fan (161) by changing the frequency of the three-phase AC power output to the outdoor fan motor according to the control of the control unit (370). For example, the fan drive unit (350) can change the rotational speed of the indoor fan by changing the frequency of the three-phase AC power output to the indoor fan motor according to the control of the control unit (370).

[0133] The output unit (360) may be equipped with a display device such as a display (not shown) or a light-emitting diode (LED), and may display an operation state related to the operation status of the air conditioner (100), such as the occurrence of an error, through the display device.

[0134] The output unit (360) may be equipped with an audio device such as a speaker or a buzzer, and may output an effect sound regarding the operating status of the air conditioner (100) through the audio device, and may output a predetermined warning sound when an error occurs.

[0135] The control unit (370) can be connected to each component provided in the air conditioner (100) and can control the overall operation of each component. The control unit (370) can transmit and receive data to and from each component provided in the air conditioner (100). The control unit (370) may be provided in at least one of the outdoor unit (21), as well as the indoor unit (31) and / or the central controller. For example, the outdoor unit (21), the indoor unit (31), and the central controller may each include a control unit (370) that controls the operation.

[0136] The control unit (370) may include at least one processor. Here, the processor may be a general processor such as a CPU (central processing unit). Of course, the processor may be a dedicated device such as an ASIC or a processor based on other hardware.

[0137] The control unit (370) can generate a learning model by learning data related to each component provided in the air conditioner (100) through machine learning, such as deep learning. The control unit (370) can control each component provided in the air conditioner (100) using the data related to each component provided in the air conditioner (100) and the previously learned learning model. Hereinafter, deep learning will be explained in detail with reference to FIG. 4.

[0138] FIG. 4 is a drawing referenced in the description of deep learning according to one embodiment of the present invention.

[0139] Machine learning refers to a process where a computer learns from data and solves problems without requiring direct human instructions for logic.

[0140] Deep learning refers to an artificial intelligence technology that enables computers to learn like humans on their own, based on Artificial Neural Networks (ANNs) and other methods of teaching computers human ways of thinking. Artificial Neural Networks (ANNs) can be implemented in the form of software or in the form of hardware, such as chips. For example, Artificial Neural Networks (ANNs) can include various types of algorithms, such as Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Deep Belief Networks (DBNs).

[0141] Referring to FIG. 4, an artificial neural network (ANN) may include an input layer, a hidden layer, and an output layer. Each layer may include multiple nodes, and each layer may be connected to the next layer, and nodes between adjacent layers may be connected to each other with weights.

[0142] A computer can discover a certain pattern from data to form a feature map, extract features ranging from lower-level to intermediate and upper-level features to recognize an object and output the result.

[0143] In addition, each node can operate based on an activation model, and an output value corresponding to an input value can be determined according to the activation model.

[0144] The output value of an arbitrary node, for example, a low-level feature, can be input to the next layer connected to that node, for example, a node of an intermediate-level feature. The node of the next layer, for example, a node of an intermediate-level feature, can receive values ​​output from multiple nodes of the low-level feature.

[0145] In this case, the input value of each node may be the output value of the node in the previous layer with a weight applied. The weight can represent the strength of the connection between nodes. Additionally, the deep learning process can be viewed as a process of finding appropriate weights and biases.

[0146] Meanwhile, the output value of an arbitrary node, for example, an intermediate-level feature, can be input to the next layer connected to that node, for example, a node of a higher-level feature. The node of the next layer, for example, a node of a higher-level feature, can receive values ​​output from multiple nodes of the intermediate-level feature.

[0147] An artificial neural network (ANN) can extract feature information corresponding to each level by using learned layers corresponding to each level. An artificial neural network (ANN) can recognize a specific object by sequentially abstracting and utilizing feature information from the highest level.

[0148] Meanwhile, the training of an Artificial Neural Network (ANN) can be achieved by adjusting the weights of the connections between nodes to produce a desired output for the input data, and bias values ​​can also be adjusted if necessary. Furthermore, the weight values ​​of an ANN can be continuously updated through learning. Additionally, methods such as back-propagation can be used for the training of an ANN.

[0149] The storage unit (330) can store data obtained from each component equipped in the air conditioner (100), data for training an artificial neural network (ANN), etc. For example, the storage unit (330) can store a database containing data for each component equipped in the air conditioner (100) for training an artificial neural network (ANN), weights, biases, etc. that form the structure of an artificial neural network (ANN).

[0150] Meanwhile, the control unit (370) may include a data acquisition unit (not shown), a model learning unit (not shown) and / or a result output unit (not shown).

[0151] The data acquisition unit can acquire data for each component provided in the air conditioner (100) and determine the input data to be learned among the acquired data.

[0152] The model learning unit can learn input data and generate a learning model. The model learning unit can update the generated learning model based on data for each component provided in the air conditioner (100).

[0153] The result output unit can produce result data corresponding to the input data by using the input data and a previously learned learning model among the data for each component provided in the air conditioner (100).

[0154] FIGS. 5 to 7 are flowcharts illustrating a method of operation of an air conditioner according to an embodiment of the present invention, and FIGS. 8 to 12 are drawings referenced for an explanation of the operation of the air conditioner.

[0155] Referring to FIG. 5, the air conditioner (100) can determine whether the operating mode is the first mode in operation S510. Here, the first mode may mean a mode that controls at least one of the components included in the air conditioner (100) regardless of a previously learned learning model (hereinafter, control algorithm) regarding the control of the components included in the air conditioner (100). In one embodiment, the first mode may be named the general operating mode.

[0156] In operation S520, when the operating mode is the first mode, the air conditioner (100) can control at least one of the outdoor unit (21) and the indoor unit (31) regardless of the control algorithm. For example, the air conditioner (100) can adjust the operating frequency of the compressor (110) according to the difference between the target temperature set by the user and the indoor temperature detected by the indoor temperature sensor. At this time, the air conditioner (100) can reduce the operating frequency of the compressor (110) as the difference between the target temperature and the indoor temperature becomes smaller.

[0157] The air conditioner (100) can learn a learning model (hereinafter, power consumption learning model) related to the actual power consumption of the air conditioner (100) based on data for each component equipped in the air conditioner (100) obtained while the operating mode is set to the first mode during operation S530. Here, the data for each component obtained by the air conditioner (100) while the operating mode is set to the first mode may be named the first data. Here, the power consumption learning model may be a learning model that learns the correlation between the first data and the power consumption output layer of the air conditioner (100) using an artificial neural network (ANN), by setting the first data as an input layer parameter and the power consumption of the air conditioner (100) as a parameter. In this regard, it will be explained with reference to FIG. 6.

[0158] Referring to FIG. 6, the air conditioner (100) can acquire first data for a predetermined time during operation S610. For example, the air conditioner (100) can acquire the operating frequency of the compressor (110), the low pressure of the compressor, the high pressure of the compressor, the temperature of the outdoor heat exchanger (120), the temperature of the indoor heat exchanger (33), the outdoor temperature, the indoor temperature, the rotational speed of the outdoor fan (161), the rotational speed of the indoor fan, and the ratio of the number of indoor units in operation to the total number of indoor units (31) provided in the air conditioner (100) (hereinafter, the operating rate) as first data.

[0159] The air conditioner (100) can determine whether a power consumption learning model has already been created during operation S620. For example, when the air conditioner (100) creates a power consumption learning model, it can store the created power consumption learning model in the storage unit (330). At this time, the air conditioner (100) can determine whether a power consumption learning model has already been created by checking whether a power consumption learning model is stored in the storage unit (330).

[0160] In operation S630, if a power consumption learning model has already been generated, the air conditioner (100) can calculate the amount of power consumed by the air conditioner (100) during a predetermined time based on the first data acquired during a predetermined time and the power consumption learning model. Here, the amount of power calculated using the power consumption learning model may be named the predicted amount of power. Additionally, the predicted amount of power calculated based on the first data acquired by the air conditioner (100) while the operating mode is set to the first mode may be named the first predicted amount of power. For example, the air conditioner (100) can calculate the predicted amount of power based on the outdoor temperature, indoor temperature, the temperature of the outdoor heat exchanger (120), the operating rate, and the rotational speed of the indoor fan among the first data acquired during a predetermined time of 10 minutes.

[0161] Meanwhile, the air conditioner (100) can monitor the actual amount of power consumed by the air conditioner (100) for a predetermined period of time. For example, the air conditioner (100) can determine the actual amount of power consumed by the air conditioner (100) based on data received from an external device (10) that measures the amount of power consumed by the air conditioner (100). For example, the air conditioner (100) can determine the actual amount of power consumed by the air conditioner (100) based on the operating frequency of the compressor (110). At this time, as the operating frequency of the compressor (110) increases, the actual amount of power consumed by the air conditioner (100) can also increase.

[0162] In operation S640, the air conditioner (100) can determine whether the difference between the calculated predicted power amount and the actual power amount consumed by the air conditioner (100) is greater than or equal to a preset standard. For example, the air conditioner (100) can determine that the difference between the calculated predicted power amount and the actual power amount consumed by the air conditioner (100) is greater than or equal to 1% of the actual power amount.

[0163] In operation S650, if the difference between the calculated predicted power amount and the actual power amount consumed by the air conditioner (100) is greater than or equal to a preset standard, the air conditioner (100) can retrain a power amount learning model based on the first data acquired during a predetermined time.

[0164] Meanwhile, in the S660 operation, the air conditioner (100) can check whether the database stored in the storage unit (330) contains data exceeding a predetermined standard when the power consumption learning model has not been generated, that is, when the power consumption learning model has not been stored in the storage unit (330). For example, the air conditioner (100) can determine that data exceeding a predetermined standard is contained in the database if data corresponding to a period of one week or more, which is a pre-set minimum period, is accumulated in the database.

[0165] In operation S670, if data exceeding a predetermined standard is included in the database, the air conditioner (100) can generate a power consumption learning model based on the data included in the database. For example, the air conditioner (100) can calculate the amount of power consumed by the air conditioner (100) for a predetermined period based on the outdoor temperature, indoor temperature, the temperature of the outdoor heat exchanger (120), the operating rate, and the rotational speed of the indoor fan among the data included in the database.

[0166] The air conditioner (100) can update the database of the storage unit (330) in operation S680. The first data acquired during a predetermined time and the actual amount of power consumed by the air conditioner (100) during a predetermined time can be added to the database, taking into account the time. At this time, the air conditioner (100) can delete data that was added to the database earlier than a preset period (e.g., 2 years) from the current time among the data included in the database.

[0167] Meanwhile, the air conditioner (100) may further include a database (hereinafter referred to as the power consumption database) composed of data in which the actual power consumption and the predicted power consumption consumed by the air conditioner (100) during a predetermined period are mapped. At this time, when the operating mode is the first mode, the air conditioner (100) may determine the predicted power consumption mapped to the actual power consumption to be the same value as the actual power consumption. That is, while the operating mode is the first mode, data in which the predicted power consumption and the actual power consumption are the same may be added to the power consumption database.

[0168] Referring to FIG. 8, data may be added to the power consumption database in chronological order. For example, the data included in the power consumption database may include the time (810, 820, 830) when the data was added, the actual power consumption (840) consumed by the air conditioner (100), and the predicted power consumption (850). In this case, for the data added to the power consumption database while the operating mode is the first mode, the actual power consumption (840) and the predicted power consumption (850) having the same value may be mapped to each other.

[0169] Referring again to FIG. 5, the air conditioner (100) can control at least one of the outdoor unit (21) and the indoor unit (31) using a control algorithm when the operating mode is a second mode rather than a first mode in operation S540. Here, the second mode may refer to a mode in which at least one of the components included in the air conditioner (100) is controlled using a control algorithm that has been learned in relation to the control of the components included in the air conditioner (100). In one embodiment, the second mode may be named a smart operating mode. Meanwhile, the predicted power amount calculated based on the second data acquired by the air conditioner (100) while the operating mode is set to the second mode may be named a second predicted power amount.

[0170] The details regarding controlling the outdoor unit (21) and / or indoor unit (31) using a control algorithm will be described later with reference to FIGS. 13 to 21.

[0171] The air conditioner (100) can calculate the reduction rate of power consumption for the amount of power saved over a predetermined period based on the data for each component equipped in the air conditioner (100) obtained while the operating mode is set to the second mode in operation S550, and the power consumption learning model. Here, the data for each component obtained by the air conditioner (100) while the operating mode is set to the second mode may be referred to as the second data. In this regard, it will be explained with reference to FIG. 7.

[0172] Referring to FIG. 7, the air conditioner (100) can acquire second data for a predetermined time during operation S710. For example, the air conditioner (100) can acquire the operating frequency of the compressor (110), the low pressure of the compressor, the high pressure of the compressor, the temperature of the outdoor heat exchanger (120), the temperature of the indoor heat exchanger (33), the outdoor temperature, the indoor temperature, the rotational speed of the outdoor fan (161), the rotational speed of the indoor fan, the operating rate, etc. as second data.

[0173] The air conditioner (100) can calculate the predicted power amount based on the second data acquired during a predetermined time period and the power amount learning model during operation S720. For example, the air conditioner (100) can calculate the predicted power amount based on the outdoor temperature, indoor temperature, the temperature of the outdoor heat exchanger (120), the operating rate, and the rotational speed of the indoor fan among the second data acquired during a predetermined time period of 10 minutes.

[0174] The air conditioner (100) can correct the predicted power consumption based on data regarding the compressor (110). For example, the air conditioner (100) can monitor the compressor low pressure for the refrigerant flowing into the compressor (110) while set to a second mode, and can determine the minimum and maximum values ​​of the predicted power consumption corresponding to the compressor low pressure. At this time, the air conditioner (100) can correct the predicted power consumption to the minimum value if the predicted power consumption calculated based on the power consumption learning model is less than the minimum value, and can correct the predicted power consumption to the maximum value if the predicted power consumption calculated based on the power consumption learning model exceeds the maximum value.

[0175] The air conditioner (100) can check whether data for a predetermined period or longer has been accumulated in the power consumption database in operation S730. For example, the air conditioner (100) can check whether data for one day or longer has been accumulated in the power consumption database when the user sets the predetermined period to one day to check the amount of power saved during the day.

[0176] In operation S740, if data for a predetermined period or longer is accumulated in the power consumption database, the air conditioner (100) can calculate the reduction rate of power consumption saved during a predetermined period based on the actual power consumption and predicted power consumption accumulated during a predetermined period. For example, the air conditioner (100) can calculate the difference between the predicted power consumption accumulated during a predetermined period and the actual power consumption consumed by the air conditioner (100) during a predetermined period, based on the predicted power consumption and actual power consumption calculated in operation S720 and the data included in the power consumption database, as the amount of power consumption saved. At this time, the air conditioner (100) can calculate the reduction rate of power consumption by dividing the amount of power consumption saved by the actual power consumption consumed by the air conditioner (100) during a predetermined period.

[0177] In operation S750, the air conditioner (100) can output a screen including the actual amount of power consumed by the air conditioner (100) during a predetermined period, the predicted amount of power, and / or the reduction rate of power consumption through the output unit (360). For example, the air conditioner (100) can output a screen including a graph corresponding to the actual amount of power consumed by the air conditioner (100) during a predetermined period, a graph corresponding to the predicted amount of power accumulated during a predetermined period, and an indicator indicating the reduction rate of power consumption through a display.

[0178] Referring to FIG. 9, the air conditioner (100) can output the actual amount of power consumed by the air conditioner (100) and the amount of power saved (930) for a plurality of periods through a display (910) included in the remote control (900).

[0179] The actual amount of power consumed by the air conditioner (100) (920) may include the daily consumption (921), weekly consumption (922), monthly consumption (923), and annual consumption (924) of the air conditioner (100). The amount of power saved (930) may include the daily saving (931), weekly saving (932), monthly saving (933), and annual saving (934) of the air conditioner (100).

[0180] Meanwhile, although the present disclosure describes outputting a screen through the display (910) of the remote control (900), the present invention is not limited thereto, and the screen may be output through a display provided in the outdoor unit (21), indoor unit (31), etc.

[0181] Referring again to FIG. 7, the air conditioner (100) can update the power consumption database in operation S760. The air conditioner (100) can add data to the power consumption database in which the actual power consumption and the predicted power consumption consumed by the air conditioner (100) are mapped during a predetermined time when the operating mode is set to the second mode.

[0182] Referring again to FIG. 5, the air conditioner (100) can check whether operation is terminated in operation S560. At this time, the air conditioner (100) can check the operation mode before operation is terminated and perform an operation corresponding to the first mode or second mode set as the operation mode.

[0183] Meanwhile, according to one embodiment of the present invention, the air conditioner (100) can output various user interface (UI) screens through a display (910) included in a remote control (900) depending on the operating mode. For example, when the operating mode is a first mode, which is a general operating mode, the air conditioner (100) can output a screen related to the actual amount of power consumed by the air conditioner (100). For example, when the operating mode is a second mode, which is a smart operating mode, the air conditioner (100) can output a screen related to the actual amount of power consumed by the air conditioner (100) and the predicted amount of power calculated based on a power amount learning model.

[0184] Referring to FIG. 10, the air conditioner (100) can output a UI screen (1000) for setting an operating mode through a display included in the remote control (900). At this time, the air conditioner (100) can determine the operating mode according to a user input selecting one of a screen area (1010) corresponding to a normal operating mode and a screen area (1020) corresponding to a smart operating mode.

[0185] Referring to FIG. 11a, the air conditioner (100) can output a UI screen (1100) corresponding to the normal operation mode when the operation mode is determined to be the normal operation mode according to user input.

[0186] A UI screen (1100) corresponding to a general operating mode may include a screen area (1110) corresponding to a setting related to air conditioning in a general operating mode, such as a set temperature; a screen area (1120) corresponding to a setting to reduce the amount of power consumed by the air conditioner (100) in a general operating mode; a screen area (1130) corresponding to monitoring the amount of power consumed by the air conditioner (100) in a general operating mode; and / or a screen area (1140) corresponding to other settings related to the air conditioner (100).

[0187] Referring to FIG. 11b, when a user selects a screen area (1130) corresponding to monitoring the amount of power consumed by the air conditioner (100) in normal operation mode, the air conditioner (100) can output a UI screen (1131) (hereinafter, the first UI screen) for monitoring the amount of power consumed by the air conditioner (100) in normal operation mode.

[0188] The first UI screen (1131) may include at least one indicator for the actual amount of power consumed by the air conditioner (100). For example, the first UI screen (1131) may include, in normal operation mode, an indicator (1132) for the actual amount of power consumed monthly by the air conditioner (100), an indicator (1133) for the actual amount of power consumed weekly, and / or an indicator (1134) for the actual amount of power consumed daily.

[0189] Meanwhile, referring to FIG. 12a, the air conditioner (100) can output a UI screen (1200) corresponding to the smart operation mode when the operation mode is determined to be a smart operation mode according to user input.

[0190] A UI screen (1200) corresponding to a smart driving mode may include a screen area (1210) corresponding to settings related to air conditioning in the smart driving mode, such as a set temperature; a screen area (1220) corresponding to settings for reducing the amount of power consumed by the air conditioner (100) in the smart driving mode; a screen area (1230) corresponding to monitoring the amount of power consumed by the air conditioner (100) in the smart driving mode; and / or a screen area (1240) corresponding to other settings related to the air conditioner (100).

[0191] Referring to FIG. 12b, when a user selects a screen area (1230) corresponding to monitoring the amount of power consumed by the air conditioner (100) in smart operation mode, the air conditioner (100) can output a UI screen (1231) (hereinafter referred to as the second UI screen) for monitoring the amount of power consumed by the air conditioner (100) in smart operation mode.

[0192] The second UI screen (1231) may include at least one indicator for the predicted amount of power that the air conditioner (100) is expected to consume in normal operation mode. For example, the second UI screen (1231) may include an indicator (1232) for the amount of power that the air conditioner (100) is expected to consume monthly in normal operation mode, an indicator (1234) for the amount of power that is expected to be consumed weekly, and an indicator (1236) for the amount of power that is expected to be consumed daily.

[0193] The second UI screen (1231) may include at least one indicator for the actual amount of power consumed by the air conditioner (100) in smart operation mode. For example, the second UI screen (1231) may include an indicator (1233) for the actual amount of power consumed monthly by the air conditioner (100) in smart operation mode, an indicator (1235) for the actual amount of power consumed weekly, and / or an indicator (1237) for the actual amount of power consumed daily.

[0194] The second UI screen (1231) may include an indicator for the reduction rate of the amount of electricity saved during a predetermined period set in smart operation mode. For example, the second UI screen (1231) may include the reduction rate of the amount of electricity saved during one month set in smart operation mode, the reduction rate of the amount of electricity saved during one week set in smart operation mode, and / or the reduction rate of the amount of electricity saved during one day set in smart operation mode.

[0195] FIGS. 13 to 21 are drawings referenced in the description of a control algorithm used to control a component included in an air conditioner.

[0196] Referring to FIGS. 13 and 14, a plurality of air conditioners (100) are installed in various environments and can transmit data regarding indoor temperature, indoor humidity, outdoor temperature, outdoor humidity, and a target temperature (hereinafter, set temperature) set by a user, which are measured or input by the air conditioners (100), to a server (60).

[0197] The server (60) can organize data obtained from multiple air conditioners (100) into a database and, using the data included in the database, can cluster the environment of the indoor space (hereinafter, indoor environment) in which each indoor unit (31) included in the air conditioner (100) is placed into multiple clusters. Here, multiple clusters may refer to a group of sets classified based on the temperature, humidity, and the difference between the set temperature and the indoor temperature of the indoor environment. For example, the server (60) can cluster the indoor environment into multiple clusters based on the difference between the set temperature and the indoor temperature. At this time, since the data collected from multiple air conditioners (100) may have a high proportion of data that has converged to the set temperature, the server (60) may sample data by state of the indoor environment and cluster it.

[0198] If there is no data regarding indoor humidity among the data received from multiple air conditioners (100), the server (60) can calculate indoor humidity from indoor temperature and outdoor humidity.

[0199] Referring to FIG. 14, the server (60) can cluster the indoor environment into six clusters using indoor temperature, indoor humidity, and the difference between the indoor temperature and the set temperature as input values. At this time, the six clusters can be distinguished based on sensible heat load and latent heat load. That is, the indoor environment can be clustered into a space where the sensible heat load and latent heat load are well processed, a space where only some of the sensible heat load and latent heat load are well processed, a space where processing for both the sensible heat load and latent heat load is required, etc.

[0200] A method for clustering indoor environments can be used in which data with similar characteristics are grouped together. That is, a learning method can be used in which ranges with similar load ranges required for indoor units (31) are grouped together based on similar temperature / humidity or the difference between indoor temperature and set temperature. Since the method for dividing indoor environments generally involves grouping unlabeled data, an unsupervised learning method can be used.

[0201] The server (60) may use K-means algorithm clustering to divide data into multiple partitions to cluster indoor environments. K-means algorithm clustering may mean a method of plotting n center points, finding the location of center point n where the sum of the distances between each point from this center point is minimized, and grouping points close to this center point based on the center point to classify them.

[0202] Referring to FIGS. 15a and 15b, the indoor environment can be clustered into a first cluster level (LV1) where both sensible heat load and latent heat load are well handled, a second cluster level (LV2) where sensible heat load is well handled but latent heat load needs to be removed, a third cluster level (LV3) where latent heat load is well handled but sensible heat load needs to be handled, a fourth cluster level (LV4) where both sensible heat load and latent heat load need to be handled, and a fifth cluster level (LV5) where a large amount of load needs to be handled.

[0203] Referring to FIG. 12a, as the cluster level increases, the degree of discomfort felt by the user in the corresponding indoor space may increase. Additionally, since the first cluster level (LV1) and the second cluster level (LV2) are formed at an indoor temperature below the set temperature, the user may feel less discomfort compared to the third cluster level (LV3) to the fifth cluster level (LV5).

[0204] Meanwhile, a higher cluster level may require a greater load. However, this is based on one embodiment, and it is also possible to classify that a lower cluster level requires a greater load.

[0205] FIG. 12a is a classification of the indoor environment in cooling mode, and FIG. 12b is a classification of the indoor environment in heating mode. Even in a heating mode like FIG. 12b, the degree of discomfort felt by the user may increase as the cluster level increases. In FIG. 12b as well, the first cluster level (LV1) and the second cluster level (LV2) may be a range where the user feels less discomfort compared to the third cluster level (LV3) to the fifth cluster level (LV5) because the indoor temperature is formed above the set temperature.

[0206] The server (60) can generate a learning model for clustering indoor environments (hereinafter referred to as a clustering learning model) and transmit it to the air conditioner (100). The air conditioner (100) can determine a cluster corresponding to the indoor unit (31) based on the clustering learning model received from the server (60). For example, the air conditioner (100) can determine the indoor temperature, indoor humidity, and the difference between the set temperature and the indoor temperature of the indoor space where the indoor unit (31) is placed, and use the clustering learning model to determine a cluster corresponding to the indoor unit (31).

[0207] The air conditioner (100) can correct the cluster corresponding to the indoor unit (31) by taking into account the change in the indoor environment corresponding to the indoor unit (31).

[0208] Referring to FIG. 16, the air conditioner (100) can perform control regarding the operation of the indoor unit (31) according to a cluster corresponding to the indoor unit (31) that has been set in operation S1610. For example, if the cluster corresponding to the indoor unit (31) has been set to a first cluster level (LV1), the air conditioner (100) can control at least some of the components included in the air conditioner (100) based on a control algorithm corresponding to the first cluster level (LV1). The control algorithm corresponding to the cluster level will be described later with reference to FIG. 15 to 18.

[0209] The air conditioner (100) can acquire data regarding the indoor environment while performing operation in operation S1620. For example, the air conditioner (100) can acquire data regarding the indoor temperature, indoor humidity, and the difference between the set temperature and the indoor temperature of the indoor space while the indoor unit (31) is operating.

[0210] At this time, the air conditioner (100) can preprocess the data to adjust the influence of the acquired data on the determination of the cluster to a certain level. For example, considering the scale difference between each data, the air conditioner (100) can perform min-max scaling using the following mathematical formula 1 on the input value (x) of the data to convert multiple data into a single data.

[0211]

[0212] The air conditioner (100) can determine a cluster level corresponding to the current state of the indoor environment in which the indoor unit (31) is placed among a plurality of clusters while performing control regarding the operation of the indoor unit (31) in the S1630 operation and the S1640 operation. The air conditioner (100) can determine a cluster level corresponding to the current state of the indoor environment according to a predetermined period based on data acquired during operation and a clustering learning model.

[0213] For example, the air conditioner (100) can determine the degree of proximity between the acquired data and a plurality of clusters by performing a Manhattan distance calculation using the following mathematical formula 2, and can determine the cluster level corresponding to the current state of the indoor environment using the determined degree of proximity and a clustering model.

[0214]

[0215] The air conditioner (100) can correct the cluster corresponding to the indoor unit (31) when the operation of the indoor unit (31) ends in the S1650 operation.

[0216] The air conditioner (100) can correct the cluster corresponding to the indoor unit (31) by considering the proportion of the third cluster level (LV3) to the fifth cluster level (LV5) relative to the total number of times the cluster level is determined during operation. For example, if the proportion of the third cluster level (LV3) to the fifth cluster level (LV5) is 50% or more, the air conditioner (100) can correct the cluster that is pre-set as corresponding to the indoor unit (31) to a cluster with a higher cluster level. That is, if the proportion of the third cluster level (LV3) to the fifth cluster level (LV5) is large, it can be determined that the user feels discomfort for a long time while the air conditioner (100) is operating, and that the user's comfort level does not change quickly even when the indoor unit (31) is in operation. Therefore, the cluster level of the cluster corresponding to the indoor unit (31) can be raised so that the comfort level of the indoor space can be quickly changed to the comfort level desired by the user when the indoor unit (31) is in operation.

[0217] Meanwhile, the air conditioner (100) can improve the accuracy of the correction for the cluster based on the results of previous operation. The air conditioner (100) can correct the cluster corresponding to the indoor unit (31) by considering the proportion of the third cluster level (LV3) to the fifth cluster level (LV5) measured in multiple operating cycles of the indoor unit (31). Here, the operating cycle of the indoor unit (31) may mean the time from when the operation of the indoor unit (31) begins until when the operation of the indoor unit (31) ends. Accordingly, multiple operating cycles may mean that the start and end of the operation of the indoor unit (31) proceed multiple times.

[0218] Referring to FIG. 17, the operation that was recently completed can be set as the first operation cycle (d0) of the indoor unit (31), the operation completed before the first operation cycle (d0) as the second operation cycle (d1) of the indoor unit (31), and the operation completed before the second operation cycle (d1) as the third operation cycle (d2) of the indoor unit (31).

[0219] A maximum weight may be assigned to the ratio (d0) in which the third cluster level (LV3) to the fifth cluster level (LV5) is measured during the first operating cycle (d0) of the indoor unit (31), and a minimum weight may be assigned to the ratio (d2) in which the third cluster level (LV3) to the fifth cluster level (LV5) is measured during the third operating cycle (d2) of the indoor unit (31). Additionally, an intermediate weight may be assigned to the ratio (d1) in which the third cluster level (LV3) to the fifth cluster level (LV5) is measured during the second operating cycle (d2) of the indoor unit (31).

[0220] The air conditioner (100) can determine the indoor condition (dt) during multiple operating cycles based on the result of assigning weights to each operating cycle, similar to Equation 3 below. In this embodiment, the description is based on three operating cycles, but the present invention is not limited thereto.

[0221]

[0222] The air conditioner (100) can correct the cluster corresponding to the indoor unit (31) to a cluster with a higher cluster level when the indoor condition (dt) during multiple operating cycles is 0.5 or higher.

[0223] In another embodiment, the air conditioner (100) may collect results of determining clusters at predetermined time intervals while the indoor unit (31) is operating, and correct the clusters if the average value of the cluster level corresponding to the collected clusters is higher than a predetermined standard.

[0224] For example, when the value of the fifth cluster level (LV5), which is the highest cluster level area, is set to 1, the value of the first cluster level (LV1), which is the lowest cluster level area, is set to 0, and the values ​​of the second to fourth cluster levels (LV2 to LV4) are evenly distributed, a predetermined standard can be set to 0.5. At this time, when the average value of the cluster is higher than the predetermined standard of 0.5, the cluster of the indoor unit (31) can be corrected.

[0225] The air conditioner (100) can determine and correct clusters for each of the multiple indoor spaces in which multiple indoor units (31a, 31b, 31c) are installed.

[0226] Referring to FIGS. 18 and 19, an embodiment of a method for controlling at least one of an outdoor unit (21) and at least one indoor unit (31) using at least one control algorithm corresponding to a cluster will be described. Hereinafter, according to one embodiment, a case in which an air conditioner (100) includes a plurality of indoor units (31a, 31b, 31c) will be described, but the present invention is not limited thereto.

[0227] Referring to FIG. 18, the air conditioner (100) can determine a cluster for each of the plurality of indoor units (31a, 31b, 31c) when the operating mode is set to the second mode in operation S1810.

[0228] The air conditioner (100) can obtain data for each indoor unit for each indoor space in which a plurality of indoor units (31a, 31b, 31c) are arranged during operation S1820. For example, the air conditioner (100) can obtain data regarding the number of indoor units currently in operation among the plurality of indoor units (31a, 31b, 31c) connected to the outdoor unit (21), the indoor temperature of the indoor space, the indoor humidity, the set temperature, etc. For example, the air conditioner (100) can obtain data regarding the number of occupants present in each indoor space in which a plurality of indoor units (31a, 31b, 31c) are arranged through at least one sensor, camera, etc.

[0229] The air conditioner (100) can control the operation of each indoor unit for a plurality of indoor units (31a, 31b, 31c) in S1830 operation.

[0230] The air conditioner (100) can determine the total load required by the plurality of indoor units (31a, 31b, 31c) based on the operating rate of the plurality of indoor units (31a, 31b, 31c), and can adjust the amount of refrigerant discharged from the compressor (110) according to the determined total load.

[0231] The air conditioner (100) can control the indoor expansion valves (35a to 35c) included in the plurality of indoor units (31a, 31b, 31c) according to the indoor unit cluster. For example, a control unit (370) provided in the outdoor unit (21) can transmit data for a preset cluster to the plurality of indoor units (31a, 31b, 31c). At this time, the plurality of indoor units (31a, 31b, 31c) can control the indoor expansion valves (35a to 35c) so that the amount of refrigerant flowing increases as the cluster level increases, and control the indoor expansion valves (35a to 35c) so that the amount of refrigerant flowing decreases as the cluster level decreases.

[0232] The air conditioner (100) can control the indoor fans and / or vanes included in the plurality of indoor units (31a, 31b, 31c) according to the indoor unit cluster.

[0233] The air conditioner (100) can determine whether a preset setting time is achieved in the operation of S1840. Here, the setting time may refer to a time corresponding to a cycle for updating changes to the settings for a plurality of indoor units (31a, 31b, 31c).

[0234] The air conditioner (100) can check for a change in the indoor unit cluster for each of the plurality of indoor units (31a, 31b, 31c) in the S1850 operation. For example, the air conditioner (100) can check whether at least one of the indoor unit clusters changes as at least one of the plurality of indoor units (31a, 31b, 31c) completes an operation cycle for a set time.

[0235] The air conditioner (100) can check for a change in superheating degree for each of the plurality of indoor units (31a, 31b, 31c) in operation S1860. Here, a change in superheating degree may refer to an amount of heat that is additionally required or reduced depending on a change in the number of occupants present in the indoor space. For example, the air conditioner (100) can check whether the number of occupants changes during a set time in at least one of the indoor spaces where the plurality of indoor units (31a, 31b, 31c) are arranged.

[0236] Referring to FIG. 19, the variation in superheating can be determined based on the variation in the number of people. In FIG. 19, A0 is the maximum required superheating, and A4 is the minimum required superheating.

[0237] The higher the cluster level of the cluster corresponding to the indoor unit (31), the higher the degree of overheating can be formed. Also, even at the same cluster level, the degree of overheating can vary depending on the increase or decrease in the number of people. Also, the lower the cluster level, the more easily the target degree of overheating can change according to the change in the number of people.

[0238] The air conditioner (100) can control the operation of each indoor unit (31a, 31b, 31c) by taking into account the variation of the cluster and / or the variation of the superheating degree for each indoor unit in the operation of S1870. For example, a control unit (370) provided in the outdoor unit (21) can transmit data regarding the changed cluster to each of the indoor units (31a, 31b, 31c) where the cluster has changed. For example, a control unit (370) provided in the outdoor unit (21) can transmit data regarding the changed superheating degree to each of the indoor units (31a, 31b, 31c) where the superheating degree has changed.

[0239] At this time, the plurality of indoor units (31a, 31b, 31c) can adjust the indoor expansion valves (35a to 35c) according to the changed cluster and / or changed superheat. Additionally, the plurality of indoor units (31a, 31b, 31c) can adjust the indoor fans and / or vanes according to the changed cluster and / or changed superheat.

[0240] The air conditioner (100) can determine whether the operation using the control algorithm is terminated in the operation of S1880. For example, the air conditioner (100) can determine that the operation using the control algorithm is terminated when the operation of all of the multiple indoor units (31a, 31b, 31c) is stopped, or when the operation mode is changed from the second mode to the first mode.

[0241] Meanwhile, the air conditioner (100) may add the amount of power consumed by each of the plurality of indoor units (31a, 31b, 31c) to a power consumption database. For example, the air conditioner (100) may distribute the actual amount of power and / or predicted amount of power consumed by the air conditioner (100) to each of the plurality of indoor units (31a, 31b, 31c) according to the cluster level, operating time, rotational speed of the indoor fan, etc. At this time, the air conditioner (100) may determine the actual amount of power and / or predicted amount of power distributed to each of the plurality of indoor units (31a, 31b, 31c) as the amount of power consumed by each of the plurality of indoor units (31a, 31b, 31c).

[0242] Meanwhile, with reference to FIGS. 20 and 21, an embodiment of a method for controlling at least one of an outdoor unit (21) and at least one indoor unit (31) using at least one control algorithm related to determining the flow rate of a refrigerant will be described. Hereinafter, according to one embodiment, a case in which an air conditioner (100) includes a plurality of indoor units (31a, 31b, 31c, 31d) will be described, but the present invention is not limited thereto.

[0243] Referring to FIG. 20, the environment of a plurality of indoor spaces (S1 to S4) in which a plurality of indoor units (31a, 31b, 31c, 31d) are each arranged may differ from one indoor space to another.

[0244] In the case of the first indoor space (S1) where the first indoor unit (31a) is installed, windows (2000) that communicate with the outside may be placed on two of the walls constituting the first indoor space (S1). In contrast, in the case of the second and third indoor spaces (S2, S3) where the second and third indoor units (31b, 31c) are installed, windows (2000) may be placed on only one wall, and in the case of the fourth indoor space (S4) where the fourth indoor unit (31d) is installed, windows (2000) may not be placed.

[0245] Meanwhile, when examining the amount of solar radiation for multiple indoor spaces (S1 to S4), depending on the arrangement of the windows (2000), the amount of solar radiation in the first indoor space (S1) may be the highest, and the amount of solar radiation in the fourth indoor space (S4) may be the lowest. In addition, corresponding to the amount of solar radiation for multiple indoor spaces (S1 to S4), the amount of power consumed by multiple indoor units (31a, 31b, 31c, 31d) may differ from one another. For example, in the case of the first indoor space (S1), since the amount of solar radiation is relatively higher than that of other indoor spaces, the amount of power consumed by the first indoor unit (31a) during cooling operation may be higher than that of other indoor units (31b, 31c, 31d).

[0246] In this way, the amount of power consumed by the indoor unit (31) may vary depending on the indoor environment of the multiple indoor spaces where the indoor unit (31) is actually placed, so the air conditioner (100) can control at least one of the outdoor unit (21) and at least one indoor unit (31) by using a control algorithm that takes into account the indoor environment of the multiple indoor spaces where the indoor unit (31) is actually placed.

[0247] Referring to FIG. 21, the air conditioner (100) can determine whether to perform initial operation when the operating mode is set to the second mode in operation S2110. For example, the air conditioner (100) can perform initial operation from the time when the operation of the compressor (110) of the outdoor unit (21) begins until a predetermined time has elapsed.

[0248] The air conditioner (100) can determine the initial total flow rate of the refrigerant supplied to a plurality of indoor units (31a, 31b, 31c, 31d) when performing an initial operation in operation S2120.

[0249] According to one embodiment, the air conditioner (100) can calculate the amount of power expected to be consumed by the air conditioner (100) based on data accumulated in the power amount database of the storage unit (330). For example, a control unit (370) provided in the outdoor unit (21) can calculate the amount of power expected to be consumed by the air conditioner (100) corresponding to the data accumulated in the power amount database based on a first control algorithm related to the flow rate of the refrigerant learned in advance. At this time, the air conditioner (100) can determine the initial total flow rate of the refrigerant corresponding to the amount of power expected to be consumed by the air conditioner (100).

[0250] According to one embodiment, the air conditioner (100) can determine an initial total flow rate of refrigerant based on the total flow rate of refrigerant supplied to a plurality of indoor units (31a, 31b, 31c, 31d) during a previous operation stored in a storage unit (330). For example, a control unit (370) provided in an outdoor unit (21) can determine an initial total flow rate of refrigerant corresponding to the total flow rate of refrigerant supplied to a plurality of indoor units (31a, 31b, 31c, 31d) during a previous operation based on a previously learned first control algorithm. Meanwhile, the first control algorithm may be a previously learned algorithm using an exponential smoothing method. Here, the exponential smoothing method may mean a method that gives the greatest weight to recent data and geometrically decreases the weight as the time point accumulated in the database moves further away from the current time point.

[0251] Meanwhile, when determining the initial total flow rate of the refrigerant, the air conditioner (100) may determine the initial total flow rate of the refrigerant based on the current indoor temperature, the current outdoor temperature, the indoor temperature and / or outdoor temperature after the current time point, etc. For example, the air conditioner (100) may connect to a server that provides weather data through a communication unit (310) to receive data regarding the indoor temperature and / or outdoor temperature after the current time point, and may determine the initial total flow rate of the refrigerant based on the received data. At this time, the higher the indoor temperature and / or outdoor temperature after the current time point, the higher the initial total flow rate of the refrigerant may be.

[0252] The air conditioner (100) can determine the initial individual flow rate of the refrigerant supplied to each of the plurality of indoor units (31a, 31b, 31c, 31d) based on the initial total flow rate of the refrigerant in operation S2130. At this time, the air conditioner (100) can determine the initial individual flow rate of the refrigerant for each of the indoor units (31a, 31b, 31c, 31d) that are in operation.

[0253] According to one embodiment, the air conditioner (100) can determine an initial individual flow rate of refrigerant based on the difference between the indoor temperature and the outdoor temperature of each indoor space in which a plurality of indoor units (31a, 31b, 31c, 31d) are arranged. For example, if the difference between the indoor temperature and the outdoor temperature of the first indoor space (S1) is greater than the difference between the indoor temperature and the outdoor temperature of the fourth indoor space (S4), the control unit (370) provided in the outdoor unit (21) can determine an initial individual flow rate of refrigerant such that the flow rate of refrigerant supplied to the first indoor unit (31a) installed in the first indoor space (S1) is greater than the flow rate of refrigerant supplied to the fourth indoor unit (31d) installed in the fourth indoor space (S4).

[0254] According to one embodiment, the air conditioner (100) can calculate the amount of power expected to be consumed by each of the plurality of indoor units (31a, 31b, 31c) based on data accumulated in the power consumption database of the storage unit (330). For example, the control unit (370) provided in the outdoor unit (21) can calculate the amount of power expected to be consumed by each of the plurality of indoor units (31a, 31b, 31c) corresponding to the data accumulated in the power consumption database based on a previously learned first control algorithm. At this time, the air conditioner (100) can determine the initial individual flow rate of the refrigerant corresponding to the amount of power expected to be consumed by each of the plurality of indoor units (31a, 31b, 31c).

[0255] According to one embodiment, the air conditioner (100) can determine an initial individual flow rate of refrigerant based on the individual flow rates of refrigerant supplied to a plurality of indoor units (31a, 31b, 31c, 31d) during a previous operation stored in a storage unit (330). For example, a control unit (370) provided in an outdoor unit (21) can determine an initial individual flow rate of refrigerant corresponding to the individual flow rates of refrigerant supplied to a plurality of indoor units (31a, 31b, 31c, 31d) during a previous operation based on a previously learned first control algorithm.

[0256] Meanwhile, when the plurality of indoor units (31a, 31b, 31c, 31d) of the air conditioner (100) are not performing initial operation in operation S2140, they can each determine the individual flow rate of the refrigerant supplied to the plurality of indoor units (31a, 31b, 31c, 31d). For example, the plurality of indoor units (31a, 31b, 31c, 31d) can transmit data regarding the determined individual flow rate of the refrigerant to a control unit (370) provided in the outdoor unit (21).

[0257] According to one embodiment, the air conditioner (100) can calculate the amount of power consumed by each of the plurality of indoor units (31a, 31b, 31c) based on the actual amount of power consumed in the second mode. At this time, the control unit (370) provided in each of the plurality of indoor units (31a, 31b, 31c, 31d) can determine the individual flow rate of the refrigerant based on a second control algorithm related to the previously learned flow rate of the refrigerant. For example, a control unit (370) provided in each of the plurality of indoor units (31a, 31b, 31c, 31d) can determine the individual flow rate of the refrigerant based on the second control algorithm, corresponding to the amount of power consumed by each of the plurality of indoor units (31a, 31b, 31c), the difference between the indoor temperature and the outdoor temperature of each indoor space where the plurality of indoor units (31a, 31b, 31c, 31d) are placed, the set temperature, the rotation speed of the indoor fan, etc.

[0258] Meanwhile, the second control algorithm may be a previously learned algorithm in which the input value is set to the actual power consumption and / or predicted power consumption of the air conditioner (100), the power consumption of each of the plurality of indoor units (31a, 31b, 31c), indoor temperature, outdoor temperature, set temperature, rotational speed of the indoor fan, etc., and the output value is set to the total flow rate of the refrigerant or the individual flow rate of the refrigerant.

[0259] The air conditioner (100) can determine the total flow rate and / or individual flow rate of the refrigerant supplied to the plurality of indoor units (31a, 31b, 31c, 31d) based on the individual flow rates of the refrigerant determined in the plurality of indoor units (31a, 31b, 31c, 31d) in operation S2150.

[0260] According to one embodiment, a control unit (370) provided in an outdoor unit (21) can receive data on individual flow rates of refrigerant from a plurality of indoor units (31a, 31b, 31c, 31d) and can sum the individual flow rates of refrigerant received from the plurality of indoor units (31a, 31b, 31c, 31d). At this time, the control unit (370) provided in the outdoor unit (21) can correct the result of summing the individual flow rates of refrigerant by considering the actual power consumption and / or predicted power consumption of the air conditioner (100), the operating rate of the plurality of indoor units (31a, 31b, 31c, 31d), the indoor temperature of each indoor space where the plurality of indoor units (31a, 31b, 31c, 31d) are placed, the outdoor temperature, etc. For example, the control unit (370) provided in the outdoor unit (21) can determine the result of correcting the sum of the individual flow rates of the refrigerant based on the second control algorithm as the total flow rate of the refrigerant.

[0261] According to one embodiment, a control unit (370) provided in an outdoor unit (21) can determine the individual flow rate of refrigerant supplied to each of a plurality of indoor units (31a, 31b, 31c, 31d) in correspondence with the total flow rate of refrigerant. For example, the control unit (370) provided in an outdoor unit (21) can determine the individual flow rate of refrigerant supplied to each of a plurality of indoor units (31a, 31b, 31c, 31d) by using a second control algorithm, taking into account the actual power consumption and / or predicted power consumption of the air conditioner (100), the operating rate of a plurality of indoor units (31a, 31b, 31c, 31d), the indoor temperature of each indoor space where a plurality of indoor units (31a, 31b, 31c, 31d) are placed, the outdoor temperature, etc.

[0262] That is, the air conditioner (100) can adjust the individual flow rate of the refrigerant determined by the plurality of indoor units (31a, 31b, 31c, 31d) according to the indoor environment of the indoor space, the actual amount of power consumed by the air conditioner (100) and / or the predicted amount of power, the operating rate of the plurality of indoor units (31a, 31b, 31c, 31d), etc.

[0263] The air conditioner (100) can control the operation of each indoor unit for a plurality of indoor units (31a, 31b, 31c, 31d) in operation S2160. For example, a control unit (370) provided in the outdoor unit (21) can adjust the amount of refrigerant discharged from the compressor (110) based on the total flow rate of the refrigerant. For example, a control unit (370) provided in the outdoor unit (21) can transmit data regarding the individual flow rates of the refrigerant determined for the plurality of indoor units (31a, 31b, 31c, 31d) to each of the plurality of indoor units (31a, 31b, 31c, 31d). At this time, the plurality of indoor units (31a, 31b, 31c, 31d) can control the indoor expansion valves (35a to 35d) based on data regarding the individual flow rates of the refrigerant received from the outdoor unit (21).

[0264] The air conditioner (100) can check whether operation is terminated in S2170 operation.

[0265] The air conditioner (100) may update at least one control algorithm related to determining the flow rate of the refrigerant when operation ends in operation S2180. For example, the air conditioner (100) may update the first control algorithm based on the difference between the initial total flow rate of the refrigerant determined in operation S2120 and the total flow rate of the refrigerant determined in operation S2160. For example, the air conditioner (100) may update the first control algorithm based on the difference between the initial individual flow rate of the refrigerant determined in operation S2130 and the individual flow rate of the refrigerant determined in operation S2160. As described above, according to various embodiments of the present invention, the air conditioner (100) may use a power amount learning model related to the actual power amount consumed in the first mode to calculate and compare the power amount expected to be used in the first mode and the actual power amount consumed in the second mode under the same conditions.

[0266] In addition, according to various embodiments of the present invention, while the operating mode is set to the first mode, the power consumption learning model is repeatedly retrained based on the difference between the power consumption calculated using the power consumption learning model and the actual power consumption of the air conditioner, thereby improving the accuracy of the result of calculating the power consumption expected to be used in the first mode while the operating mode is set to the second mode.

[0267] The attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings; it should be understood that all modifications, equivalents, and substitutions included within the concept and technical scope of the present invention are included.

[0268] Likewise, although operations are depicted in a specific order in the drawings, this should not be understood to mean that such operations must be performed in that specific or sequential order depicted to obtain a desirable result, or that all depicted operations must be performed. In certain cases, multitasking and parallel processing may be advantageous.

[0269] Furthermore, although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the invention as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention.

Claims

Claim 1 An air conditioner comprising: an outdoor unit including a compressor for compressing refrigerant; at least one indoor unit; a storage unit storing a previously learned control algorithm in relation to the control of a configuration included in the air conditioner; and a control unit, wherein the control unit, when the operating mode of the air conditioner is set to a first mode, controls at least one of the outdoor unit and at least one indoor unit regardless of the control algorithm, and learns a power consumption learning model related to the actual power consumption of the air conditioner while the first mode is set based on first data acquired while the first mode is set, and when the operating mode of the air conditioner is set to a second mode, controls at least one of the outdoor unit and at least one indoor unit based on the control algorithm, and calculates a predicted power consumption corresponding to the second mode based on second data acquired while the second mode is set and the power consumption learning model, and the actual power consumption of the air conditioner while the second mode is set, respectively. Claim 2 An air conditioner according to claim 1, wherein the control unit calculates the actual amount of power consumed by the air conditioner based on either data regarding the amount of power consumed by the air conditioner received from an external device or the operating frequency of the compressor. Claim 3 An air conditioner according to claim 1, wherein the control unit acquires the first data for a predetermined time when the operating mode of the air conditioner is set to the first mode, calculates a predicted power amount corresponding to the first mode using the first data acquired for the predetermined time and the power amount learning model, and when the difference between the predicted power amount corresponding to the first mode and the actual power amount consumed by the air conditioner during the predetermined time is greater than or equal to a preset standard, learns the power amount learning model based on the first data acquired for the predetermined time. Claim 4 In paragraph 3, the air conditioner is characterized in that the control unit learns the correlation between the first data acquired during the predetermined time and the actual amount of power consumed by the air conditioner during the predetermined time, and determines the weight and bias of the power amount learning model. Claim 5 An air conditioner according to claim 1, wherein the storage unit stores a database, and the control unit adds to the database a first predicted power amount calculated based on the first data acquired during a predetermined time and an actual power amount consumed by the air conditioner during the predetermined time when the operating mode of the air conditioner is set to the first mode, and adds to the database a second predicted power amount calculated based on the second data acquired during the predetermined time and an actual power amount consumed by the air conditioner during the predetermined time when the operating mode of the air conditioner is set to the second mode, and deletes from the database data among the data included in the database data that was added to the database prior to a predetermined period from the current time. Claim 6 An air conditioner according to claim 5, wherein the control unit calculates the first predicted power amount, calculated based on the first data acquired during the predetermined time period, as the same value as the actual power amount consumed by the air conditioner during the predetermined time period when the operating mode of the air conditioner is set to the first mode. Claim 7 An air conditioner according to claim 1, wherein the control unit determines a minimum value and a maximum value of the predicted power amount in response to the pressure of the refrigerant flowing into the compressor while set to the second mode, and if the calculated predicted power amount is less than the minimum value, determines the minimum value as the predicted power amount corresponding to the second mode, and if the calculated predicted power amount exceeds the maximum value, determines the maximum value as the predicted power amount corresponding to the second mode. Claim 8 An air conditioner according to claim 1, wherein the control unit determines an indoor unit cluster for each of the at least one indoor unit when the operating mode of the air conditioner is set to the second mode, and determines the flow rate of the refrigerant supplied to the at least one indoor unit based on the indoor unit cluster and the second data. Claim 9 An air conditioner according to claim 8, wherein the control unit determines the total flow rate of the refrigerant supplied by the outdoor unit based on the flow rate of the refrigerant supplied to the at least one indoor unit. Claim 10 An air conditioner according to claim 1, wherein the control unit determines whether to perform an initial operation when the operating mode of the air conditioner is set to the second mode, and when the initial operation is performed, determines the flow rate of the refrigerant supplied to the at least one indoor unit based on a first control algorithm using an exponential smoothing method, and when the initial operation is not performed, determines the flow rate of the refrigerant supplied to the at least one indoor unit based on a second control algorithm that has been learned regarding the correlation between the second data and the flow rate of the refrigerant. Claim 11 An air conditioner comprising: an outdoor unit including a compressor for compressing a refrigerant; at least one indoor unit; a storage unit for storing a previously learned control algorithm in relation to the control of a component included in the air conditioner; and a display. An air conditioner comprising a control unit, wherein the control unit learns a power consumption learning model related to the actual power consumption of the air conditioner while the operating mode of the air conditioner is set to a first mode that controls at least one of the outdoor unit and at least one of the at least one indoor unit regardless of the control algorithm, and while the operating mode of the air conditioner is set to a second mode that controls at least one of the outdoor unit and at least one indoor unit based on the control algorithm, the control unit calculates a predicted power consumption based on the power consumption learning model and the actual power consumption of the air conditioner, respectively, and calculates a reduction rate for the power consumption reduced during a predetermined period based on the ratio of the actual power consumption of the air conditioner during a predetermined period to the predicted power consumption calculated during a predetermined period, and while the second mode is set, outputs a screen including at least one of the actual power consumption of the air conditioner, the predicted power consumption, and the reduction rate through the display. Claim 12 An air conditioner comprising: an outdoor unit including a compressor for compressing refrigerant; at least one indoor unit; a storage unit storing a previously learned control algorithm in relation to the control of a configuration included in the air conditioner; a display; and a control unit, wherein the control unit learns a power consumption learning model related to the actual power consumption of the air conditioner while the operating mode of the air conditioner is set to a first mode that controls at least one of the outdoor unit and at least one indoor unit independently of the control algorithm; outputs a first screen related to the actual power consumption of the air conditioner through the display while the operating mode of the air conditioner is set to a second mode that controls at least one of the outdoor unit and at least one indoor unit based on the control algorithm, respectively calculates a predicted power consumption based on the power consumption learning model and the actual power consumption of the air conditioner; and outputs a second screen related to the actual power consumption of the air conditioner and the predicted power consumption through the display while the operating mode of the air conditioner is set to a second mode that controls at least one of the outdoor unit and at least one indoor unit based on the control algorithm. Claim 13 A method of operation of an air conditioner comprising an outdoor unit and at least one indoor unit, wherein when the operating mode of the air conditioner is set to a first mode, a first control operation for controlling at least one of the outdoor unit and at least one indoor unit regardless of a previously learned control algorithm regarding control of a configuration included in the air conditioner; a learning operation for learning a power consumption learning model related to the actual power consumption of the air conditioner while it is set to the first mode based on first data acquired while it is set to the first mode; a second control operation for controlling at least one of the outdoor unit and at least one indoor unit based on the control algorithm when the operating mode of the air conditioner is set to a second mode; and a result calculation operation for calculating a predicted power consumption corresponding to the second mode based on second data acquired while it is set to the second mode and the power consumption learning model, and the actual power consumption of the air conditioner while it is set to the second mode, respectively. Claim 14 A method of operation of an air conditioner according to claim 13, wherein the above result calculation operation is an operation of calculating the actual amount of power consumed by the air conditioner based on either data regarding the amount of power consumed by the air conditioner received from an external device or the operating frequency of the compressor equipped in the outdoor unit. Claim 15 In claim 13, the above learning operation comprises: an operation of acquiring the first data for a predetermined time when the operating mode of the air conditioner is set to the first mode; an operation of calculating a predicted power amount corresponding to the first mode using the first data acquired for the predetermined time and the power amount learning model; and an operation of learning the power amount learning model based on the first data acquired for the predetermined time when the difference between the predicted power amount corresponding to the first mode and the actual power amount consumed by the air conditioner during the predetermined time is greater than or equal to a preset standard. Claim 16 A method of operation of an air conditioner according to claim 15, wherein the operation of learning the power consumption learning model is characterized by learning the correlation between the first data acquired during the predetermined time and the actual power consumption of the air conditioner during the predetermined time to determine the weight and bias of the power consumption learning model. Claim 17 A method of operation of an air conditioner according to claim 13, wherein, when the operating mode of the air conditioner is set to the first mode, a first addition operation of adding to a database a first predicted power amount calculated based on the first data acquired during a predetermined time and an actual power amount consumed by the air conditioner during the predetermined time; when the operating mode of the air conditioner is set to the second mode, a second addition operation of adding to a database a second predicted power amount calculated based on the second data acquired during the predetermined time and an actual power amount consumed by the air conditioner during the predetermined time; and further comprising an operation of deleting data included in the database that was added to the database prior to a predetermined period from the current time. Claim 18 A method of operation of an air conditioner according to claim 17, wherein the first additional operation comprises, when the operating mode of the air conditioner is set to the first mode, an operation of calculating the first predicted power amount calculated based on the first data acquired during the predetermined time period as a value equal to the actual power amount consumed by the air conditioner during the predetermined time period. Claim 19 A method of operation of an air conditioner according to claim 13, wherein the result calculation operation further comprises: an operation of determining a minimum value and a maximum value of the predicted power amount in response to the pressure of the refrigerant flowing into the compressor equipped in the outdoor unit while the second mode is set; an operation of determining the minimum value as the predicted power amount corresponding to the second mode when the calculated predicted power amount is less than the minimum value; and an operation of determining the maximum value as the predicted power amount corresponding to the second mode when the calculated predicted power amount exceeds the maximum value. Claim 20 A method of operating an air conditioner according to claim 13, wherein the second control operation comprises: an operation of determining an indoor unit-specific cluster for each of the at least one indoor unit when the operating mode of the air conditioner is set to the second mode; and an operation of determining the flow rate of a refrigerant supplied to the at least one indoor unit based on the indoor unit-specific cluster and the second data. Claim 21 A method of operation of an air conditioner according to claim 20, wherein the second control operation further includes an operation to determine the total flow rate of the refrigerant supplied by the outdoor unit based on the flow rate of the refrigerant supplied to the at least one indoor unit. Claim 22 A method of operation of an air conditioner according to claim 13, wherein the second control operation comprises: determining whether to perform an initial operation when the operating mode of the air conditioner is set to the second mode; determining the flow rate of the refrigerant supplied to the at least one indoor unit based on a first control algorithm using an exponential smoothing method when the initial operation is performed; and determining the flow rate of the refrigerant supplied to the at least one indoor unit based on a second control algorithm learned regarding the correlation between the second data and the flow rate of the refrigerant when the initial operation is not performed. Claim 23 A method of operation of an air conditioner comprising an outdoor unit and at least one indoor unit, comprising: an operation of learning a power consumption learning model related to the actual power consumption of the air conditioner while the operating mode of the air conditioner is set to a first mode that controls at least one of the outdoor unit and at least one indoor unit regardless of a control algorithm learned in relation to the control of a configuration included in the air conditioner; an operation of calculating a predicted power consumption based on the power consumption learning model and the actual power consumption of the air conditioner, respectively, while the operating mode of the air conditioner is set to a second mode that controls at least one of the outdoor unit and at least one indoor unit based on the control algorithm; an operation of calculating a reduction rate for the power consumption reduced during a predetermined period based on the ratio of the actual power consumption of the air conditioner during a predetermined period to the predicted power consumption calculated during a predetermined period; and an operation of outputting a screen through a display that includes at least one of the actual power consumption of the air conditioner, the predicted power consumption, and the reduction rate while the second mode is set. Claim 24 A method of operation of an air conditioner comprising an outdoor unit and at least one indoor unit, comprising: an operation of learning a power consumption learning model related to the actual power consumption of the air conditioner while the operating mode of the air conditioner is set to a first mode that controls at least one of the outdoor unit and at least one indoor unit regardless of a control algorithm previously learned in relation to the control of a configuration included in the air conditioner; an operation of outputting a first screen related to the actual power consumption of the air conditioner through a display while the operating mode of the air conditioner is set to a second mode that controls at least one of the outdoor unit and at least one indoor unit based on the control algorithm, respectively, a predicted power consumption based on the power consumption learning model and the actual power consumption of the air conditioner; and an operation of outputting a second screen related to the actual power consumption of the air conditioner and the predicted power consumption through the display while the operating mode of the air conditioner is set to a second mode.

Images