KR20210078258A - Air conditioner and method for controlling thereof - Google Patents

Abstract

The present disclosure relates to an air conditioner controlled based on a solar radiation quantity, which comprises: a setting unit setting an operation condition of the air conditioner including set temperature; a load measurement unit for measuring a load amount processed by the air conditioner until reaching the set temperature; a time check unit for checking current time of a site where the air conditioner is installed; and a control unit communicating with the setting unit, the load measurement unit, and the time check unit to control operation of the air conditioner.

Description

AIR CONDITIONER AND METHOD FOR CONTROLLING THEREOF

The present invention relates to an air conditioner and a method for controlling the air conditioner, and more particularly, to a method of controlling an operation of the air conditioner based on an amount of insolation and a solar time of a location where an indoor unit of the air conditioner is installed.

The air conditioner has evolved in the direction of realizing an indoor environment that can improve the actual comfort and comfort that users feel beyond simply operating to meet the set temperature.

Since the air conditioner is installed and operated in various environments, the specificity of the installed space and the ability to operate according to the user's preference play a very important role in improving the user experience.

A system air conditioner is a system in which several indoor units are connected to one outdoor unit. Even if they are installed in the same building, the load varies depending on the installation location. Even if the settings are the same, the user will inevitably feel the heat during the time when solar radiation is coming in.

Accordingly, efforts have been made to control the operation of the air conditioner in consideration of the amount of insolation of the indoor space in which the air conditioner is installed.

Japanese Patent Laid-Open No. 2002-362129 is an invention related to an air conditioner for a vehicle, which is installed in a vehicle based on the amount of insolation detected from a solar detection device installed in front of the vehicle, the current location of the vehicle, solar location information, road information, and surrounding building information. Disclosed is a system that automatically calculates the set temperature of the air conditioner by calculating the presence or absence of sunlight and the direction of incidence, and correcting the sensor value.

In addition, U.S. Patent No. 9,417,638 is an invention related to an intelligent constant temperature control method for an air conditioner that sprays hot and cold air, indoor temperature, outdoor temperature, Disclosed is a method of controlling the operation of an air conditioner by measuring the intensity of sunlight and the like.

However, in order to directly detect the amount of insolation or sunlight, a separate sensor must be added to increase the installation cost, and problems such as continuously requiring more computational resources may occur.

In this regard, there is a need for an air conditioner and a control method of the air conditioner that can improve the user's comfort by operating in an optimal way according to the amount of insolation without adding a separate sensor and without excessively demanding computational resources there is

On the other hand, the above-mentioned prior art is technical information possessed by the inventor for the derivation of the present invention or acquired in the derivation process of the present invention, and it cannot be said that it is necessarily a known technique disclosed to the general public before the filing of the present invention. .

An embodiment of the present disclosure solves a problem in that the user's comfort level is deteriorated by simply operating the air conditioner according to a set temperature without considering the specificity of the place such as the amount of insolation of the place where the air conditioner is installed in the conventional air conditioner it is to do

In addition, the embodiment of the present disclosure further requires a separate sensor for detecting the amount of insolation in the conventional air conditioner that considers the amount of insolation, and to solve the problem that more continuous computational resources are needed to process the sensor value. it is for

In addition, an embodiment of the present disclosure is intended to solve the problem of wasting computational resources by continuously operating in consideration of the amount of insolation even in a time period in which detection of the amount of insolation is not required in a conventional conditioner that considers the amount of insolation.

The air conditioner according to an exemplary embodiment of the present disclosure may perform an air conditioning operation by identifying a solar radiation characteristic of a location where an indoor unit is installed, and calculating a set temperature based on an index including radiant heat during a time period when the amount of insolation is large.

In addition, the air conditioner according to the embodiment of the present disclosure collects the processing load of the indoor unit according to the set temperature for a certain period of time after initial installation and then extracts the effect of radiant heat from the load, thereby insolation characteristics of the place where the indoor unit of the air conditioner is installed. , and adjusting the set temperature in consideration of the insolation characteristics to perform an air conditioning operation.

In addition, the air conditioner according to the embodiment of the present disclosure determines the insolation characteristic of the space in which the indoor unit is installed based on the processing load characteristic of the indoor unit, and calculates the set temperature based on the index including radiant heat in the time period in which the insolation amount is greater than or equal to a certain amount Thus, an air conditioning operation can be performed.

In addition, in the air conditioner controlled based on solar radiation according to an embodiment of the present disclosure, a setting unit for setting an air conditioner operating condition including a set temperature, and a load processed by an indoor unit of the air conditioner until the set temperature is reached It may include a load measuring unit for measuring the air conditioner, a time checking unit for checking the current time of a place where the indoor unit is installed, a control unit communicating with the setting unit, the load measuring unit and the time checking unit and controlling the operation of the air conditioner have.

Here, the control unit determines the solar time of the space in which the indoor unit is located based on the load processed by the indoor unit to reach the set temperature for a predetermined period of time, and selects a set temperature determination method different from other times within the solar time. can be used to adjust the set temperature.

In addition, the controller may extract an effect of radiant heat based on data about a load processed by the indoor unit measured for a predetermined period, and determine a solar time of a space in which the indoor unit is located based on the extracted influence of radiant heat. .

Here, the effect of radiant heat may be calculated by excluding the amount of heat caused by internal heat generation of the space and the amount of heat lost through outer sheath conduction of the space from the load measured for the predetermined period.

The amount of heat lost by skin conduction may be a value standardized based on a difference value between an air temperature of a room in which the indoor unit is located and an outdoor air temperature obtained from the outdoor unit of the air conditioner.

The amount of heat generated by internal heat generation may be a standardized value based on the rated capacity of the indoor unit.

In addition, the control unit may be configured to input data about a processing load measured for a predetermined period to the first learning model to determine the solar type of the space, and to determine the solar time of the space according to the determined solar type.

Here, the first learning model may be a neural network model trained in advance to determine which solar radiation type the corresponding space belongs to among predetermined solar radiation types by inputting a load for each time period processed for temperature control of a certain space.

In addition, the controller may input data about a processing load measured for a predetermined period to the second learning model to determine the solar radiation time of the space.

Here, the second learning model may be a neural network model trained in advance to estimate a time period in which solar radiation is incident to a corresponding space by inputting a load for each time period processed for temperature control of a predetermined space.

In the method of determining the set temperature used within the solar time determined by the air conditioner according to the embodiment of the present disclosure, an optimum temperature for optimizing the comfort index is calculated based on the radiant temperature of the space in which the indoor unit is located, and the set temperature is set to the optimal temperature. It may be a method of adjusting the temperature.

The air conditioner according to an embodiment of the present disclosure may further include a communication unit for communicating with an external weather server, and the radiation temperature may be estimated based on the external horizontal plane solar radiation obtained from the external weather server and the measured indoor temperature.

Here, the comfort index is a predicted mean vote (PMV), and the comfort index may be optimized when the value is 0.

The air conditioner controlled based on solar radiation according to an embodiment of the present disclosure includes a memory for storing instructions and codes, and one or more processors connected to the memory, and the memory, when executed by the processor, causes the processor to: Measure and record the load processed by the indoor unit of the air conditioner to reach the set indoor temperature for a predetermined period, extract the effect of radiant heat based on the data about the load recorded for a period of time, and the effect of the extracted radiant heat Determine the solar time of the space where the indoor unit is located based on the information about the indoor unit, adjust the set temperature using the comfort index including the effect of radiant heat within the solar time, and control the air conditioner according to the adjusted set temperature code can be stored.

A method of controlling an air conditioner based on solar radiation according to an embodiment of the present disclosure includes measuring and recording a load processed by an indoor unit of the air conditioner for reaching a set indoor temperature for a predetermined period of time, and recording the load for a predetermined period of time. Extracting the influence of radiant heat based on the data on the recorded load, determining the solar time of the space where the indoor unit is located based on the information on the extracted influence of radiant heat, including the influence of radiant heat within the solar time The method may include adjusting the set temperature using the comfort index, and controlling the air conditioner according to the adjusted set temperature.

Here, the step of extracting the influence of radiant heat may include excluding the amount of heat due to internal heat generation of the space and the amount of heat lost through outer sheath conduction of the space from the processing load measured for a predetermined period of time.

In the air conditioner control method according to an embodiment of the present disclosure, the determining of the solar radiation time includes: inputting the recorded load-related data into the first learning model to determine the solar radiation type of the space, and according to the solar radiation type determining the insolation time of the space.

In the air conditioner control method according to an embodiment of the present disclosure, the determining of the solar radiation time may include inputting the recorded data on the load into the second learning model to determine the solar radiation time of the space.

In the air conditioner control method according to an embodiment of the present disclosure, the adjusting of the set temperature includes calculating an optimum temperature for optimizing the comfort index based on the radiant temperature of a space where the indoor unit is located, and setting the set temperature as the optimum temperature. It may include the step of adjusting to

In the air conditioner control method according to an embodiment of the present disclosure, the calculating of the optimum temperature includes: obtaining an external horizontal plane insolation from an external weather server; and calculating a radiant temperature based on the measured indoor temperature and the external horizontal plane insolation. It may include the step of estimating.

In the air conditioner control method according to an embodiment of the present disclosure, the extracting of the influence of radiant heat may include calculating a leveled load value obtained by leveling the load measured in the indoor unit using the indoor unit capacity and the indoor/outdoor temperature difference during measurement; and monitoring the change over time of the load value.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

The air conditioner controlled based on the amount of insolation according to the embodiment of the present disclosure improves the comfort of the indoor environment experienced by the user by operating the air conditioner in consideration of the specificity of the place, such as the amount of insolation of the place where the indoor unit of the air conditioner is installed. can do it

In addition, the air conditioner according to the embodiment of the present disclosure can provide efficient air conditioner operation by performing an operation in consideration of incident solar radiation for only necessary indoor units only for a time when solar radiation is incident without additional information input or manipulation. .

In addition, the air conditioner according to the embodiment of the present disclosure does not require a separate solar radiation detection sensor, and does not require more continuous computational resources for processing such sensor values, and air that can offset the effect of solar radiation It is possible to provide an optimal operation method of the harmonizer.

Effects of the present disclosure are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is an exemplary diagram of an environment in which an air conditioner according to an embodiment of the present disclosure is used.
2 shows a block diagram of an air conditioner according to an embodiment of the present disclosure.
3 is a view for explaining the effect of radiant heat on the load of the indoor unit of the air conditioner according to an embodiment of the present disclosure.
4 is a flowchart illustrating a method of controlling an air conditioner according to an exemplary embodiment of the present disclosure.
5 illustrates load graphs for each solar radiation type referenced to determine a solar radiation type of a space in which an indoor unit of the air conditioner is installed according to an embodiment of the present disclosure.
6 is a diagram for describing a neural network model for determining a characteristic of a space in which an indoor unit of an air conditioner is installed according to an embodiment of the present disclosure.

Advantages and features of the present invention, and methods for achieving them will become apparent with reference to the detailed description in conjunction with the accompanying drawings. However, it should be understood that the present invention is not limited to the embodiments presented below, but may be implemented in a variety of different forms, and includes all transformations, equivalents, and substitutes included in the spirit and scope of the present invention. . The embodiments presented below are provided to complete the disclosure of the present invention, and to fully inform those of ordinary skill in the art to the scope of the present invention. In describing the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof. Terms such as first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings, and in the description with reference to the accompanying drawings, the same or corresponding components are given the same reference numerals, and overlapping descriptions thereof are omitted. decide to do

1 is an exemplary diagram of an environment in which an air conditioner according to an embodiment of the present disclosure is used.

1 illustrates an environment in which different spaces exist in one building and an air conditioner system is installed in each space. Indoor units 120 and 220 and outdoor units 130 and 230 are installed in the first space 100 and the second space 200 in one building, respectively.

In addition, the first window 110 is present in the first space 100 , and sunlight is incident on the first space 100 through the first window 110 at the time point shown in FIG. 1 to the first space ( In 100 ), the amount of solar radiation may affect the sensible temperature of the user in the first space 100 .

Although the second window 210 is present in the second space 200, since the second window 210 is disposed at a position opposite to the direction in which the sun is present at the time shown in FIG. 1, the second space 200 The sunlight will be much less incident compared to the first space (100).

Accordingly, even if the indoor unit 120 of the first space 100 and the indoor unit 220 of the second space 200 operate by setting the same temperature as the target temperature, the user of the first space 100 can ) will have a feeling of being hotter than that of the user.

Meanwhile, although it is illustrated in FIG. 1 that a separate outdoor unit is arranged for each indoor unit arranged in each space, in another embodiment, the indoor units installed in the first space 100 and the second space 200 are connected to one outdoor unit. It will also be included in the scope of the embodiments of the present disclosure.

In an air conditioner environment in which several indoor units are connected to one outdoor unit, even if the indoor units are installed in the same building, the load varies depending on the installation location. Even if the settings are the same, the user cannot help but feel the heat during the time when solar radiation is coming in.

Therefore, it is necessary to differentially operate the air conditioner in consideration of the amount of solar radiation incident on each space.

On the other hand, in the case of insolation, there is a characteristic that a similar degree of insolation is repeatedly incident in the same space and in the same time zone except on cloudy days. Accordingly, if the solar radiation pattern of a space is identified, the air conditioner may be controlled using the same rules for the corresponding space to cancel the effect of solar radiation.

The air conditioner according to the exemplary embodiment of the present disclosure may enable uniform and effective air conditioning in both the first space 100 and the second space 200 even in the situation shown in FIG. 1 .

2 shows a block diagram of an air conditioner according to an embodiment of the present disclosure.

The indoor unit 120 of the air conditioner controlled based on the amount of insolation according to the embodiment of the present disclosure includes the memory 121 for storing commands and codes, and the indoor unit 120 of the air conditioner until the set temperature is reached. Various information related to the operation of the air conditioner including the load measuring unit 122 for measuring the load to be processed, the time checking unit 123 for checking the current time of the place where the indoor unit 120 is installed, and the indoor temperature of the sensor unit 124 for detecting , the setting unit 125 for setting the air conditioner operating conditions including the set temperature, the wireless communication module 126 for communicating with an external server or user terminal, and the air conditioner It may include a control unit 129 that communicates with the components and controls the operation of the air conditioner.

The indoor unit 120 of the air conditioner may support object intelligence communication (internet of things (IoT), internet of everything (IoE), internet of small things (IoST), etc.), and M2M (machine to machine) communication, D2D (device to device) communication and the like may be supported.

In addition, the indoor unit 120 of the air conditioner is the indoor unit of the air conditioner using big data, artificial intelligence (AI) algorithm and/or machine learning algorithm in a 5G environment connected for the Internet of Things. 120) may determine the characteristics of the installed space (insolation amount, insolation time, degree of temperature change according to solar radiation, etc.).

The controller 129 of the air conditioner may include one or more processors, and the one or more processors may include all kinds of devices capable of processing data, for example, an MCU. Here, the 'processor' may refer to a data processing device embedded in hardware, for example, having a physically structured circuit to perform a function expressed as a code or an instruction included in a program.

As an example of the data processing device embedded in the hardware as described above, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated (ASIC) circuit) and a processing device such as a field programmable gate array (FPGA), but the scope of the present disclosure is not limited thereto.

Memory 121 may include one or more non-transitory storage media such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, and the like. The memory 121 may store data and codes or instructions that, when executed by the processors, cause the air conditioner to perform operations.

Also, the air conditioner 120 may receive commands from the user including the user interface 140 , and may transmit output information to the user. The user interface 140 may include various input means such as a keyboard, a mouse, a touch screen, a microphone, a camera, and a remote control, and various output means such as a monitor, a speaker, and a display.

The load measuring unit 122 may measure the load processed by the indoor unit 120 to achieve a set temperature for a preset period (such as a week or a month) after the air conditioner is initially installed. Here, the load may be determined using information such as power consumed by the indoor unit 120 to achieve the set temperature.

The data about the load measured by the load measuring unit 122 enables estimation of the characteristics of the space in which the indoor unit 120 is installed.

For example, if the load measured for an indoor unit for a week starts to increase from 12 pm, peaks at 2 pm, and shows a high load until 4 pm, solar radiation starts at 12 pm in the space where the indoor unit is installed. It can be estimated that the incident is until 4 pm and the maximum insolation is incident at 2 pm.

The control unit 129 may be configured to extract the effect of radiant heat on the space in which the indoor unit 120 is installed based on the data on the load measured by the load measuring unit 122 . Matters related to this will be described in more detail with reference to FIG. 3 .

The time check unit 123 checks the current time of the place where the indoor unit 120 is installed to determine whether the current time belongs to a time zone in which the space in which the indoor unit 120 is installed is greatly affected by solar radiation.

The sensor unit 124 may include various sensors such as an indoor temperature sensor for measuring the indoor temperature, an indoor unit temperature sensor for measuring the inside temperature of the indoor unit 120 , and a hygrometer for measuring indoor humidity.

The setting unit 125 may set various parameters for operating conditions of the air conditioner, such as the rotation speed of the blowing fan 127 and the direction of the discharge vane 128 , including a set temperature targeted by the air conditioner.

The wireless communication module 126 may communicate with an external server or a user terminal, and may collect information such as external horizontal surface insolation, sunrise time, sunset time, and weather for each region from an external server such as a meteorological office server.

Also, the wireless communication module 126 may transmit information related to the operation of the air conditioner to the user terminal and may receive a command related to the operation of the air conditioner from the user terminal.

The control unit 129 determines and controls most operations of the air conditioner, and in the air conditioner according to the embodiment of the present disclosure, solar radiation characteristics of a place where the indoor unit 120 is installed based on the load processed by the indoor unit 120 . can be judged

In addition, the control unit 129 is configured to determine the solar time of the space in which the indoor unit 120 is located according to the determined solar characteristics, and adjust the set temperature using a set temperature determination method different from the other times within the solar time. can be

Through the configuration as described above, the air conditioner according to the present embodiment determines the installation location of the indoor unit, extracts a time period when the influence of insolation is high for the indoor unit installed in a space with a lot of solar heat, and considers not only the air temperature but also the radiant heat. By controlling the air conditioner by calculating a comfortable set temperature based on the index, it is possible to increase the comfort satisfaction rate within the air conditioning time with minimum energy consumption.

3 is a view for explaining the effect of radiant heat on the load of the indoor unit of the air conditioner according to an embodiment of the present disclosure.

The load processed by the indoor unit 120 may be roughly divided into several types. _{First, there is a heat loss (Q CON} ) by the outer wall, an inner wall, a window, etc., and there is also _{an amount of heat (Q IH} ) due to an internal invention coming from a user and an installation device inside the space where the indoor unit 120 is installed.

The above two amounts of heat belong to a load that is constantly and constantly generated during the air conditioning time with the user. In addition, in the case of a window where sunlight enters, radiant heat (Q _SUN ) may be generated due to incident solar radiation, and there may be irregular loads caused by the user's entry/exit or window opening/closing activity.

_{In order to extract the effect of radiant heat (Q SUN} ) from the load of the indoor unit 120 , _{first, Q IH} and Q _CON , which are constant and continuously generated heat quantities, may be excluded. On the other hand, Q _CON can be standardized by dividing by delta T (temperature difference value) of the indoor air temperature and the outdoor air temperature obtained from the outdoor unit every hour.

In addition, Q _IH can be standardized by dividing by the rated capacity of the indoor unit.

Meanwhile, in order to extract the effect of radiant heat from the data on the load of the indoor unit, a value (Normalized Q) obtained by normalizing the load measured for each indoor unit to the indoor unit capacity and the current indoor/outdoor temperature difference may be calculated.

In addition, if a certain peak is seen at a certain time every day of the observed days by looking at the time-wise variation of the calculated Normailized Q value, it can be determined that the indoor unit is installed in the place where the highest solar radiation occurs at that time.

The peak shape of the load may be grouped based on a clustering algorithm using pre-collected indoor unit data to match the location where the indoor unit is installed.

For example, according to the peak shape of the load, the processor of the indoor unit may determine that the indoor unit is disposed at one of positions such as a window facing east, a window facing west, and the center of the interior.

Graphs indicating the daily change amount of Normalized Q at positions that can be representative can be described in more detail in FIG. 6 .

The solar radiation type of the installation location of the indoor unit indicated by the load graph of the indoor unit to be measured may be determined based on the change pattern of each graph in FIG. 6 .

4 is a flowchart illustrating a method of controlling an air conditioner according to an exemplary embodiment of the present disclosure.

The air conditioner control method of FIG. 4 is performed during use, and in order to use the air conditioner, it is necessary to initially set the air conditioner.

After the user installs the air conditioner, the user may start the initial setting of the air conditioner. Through the initial setting operation, the type of insolation amount of the place where the indoor unit 120 of the air conditioner is installed may be determined.

At the time of initial setting, the processor of the indoor unit 120 may measure the load processed by the indoor unit 120 of the air conditioner to reach the set indoor temperature for a predetermined period of time and record the measured load in the memory 121 .

The processor of the indoor unit 120 may extract the effect of radiant heat based on data related to the load recorded for a certain period of time. Extraction of radiant heat can be achieved by calculating a Normalized Q value as described above.

The processor of the indoor unit 120 may determine the insolation time of the space in which the indoor unit 120 is located based on the extracted information on the influence of radiant heat. _{For example, if Q SUN} equal to or greater than a predetermined value exists only in a specific time period every day in the data related to the load of the indoor unit 120 , the processor may determine that the specific time period is a time zone affected by solar radiation.

As another method, the processor of the indoor unit 120 may determine the solar type of the space in which the indoor unit is installed by inputting the recorded load data into the first learning model.

The solar radiation time of the space in which the indoor unit 120 is installed may be determined according to the determined solar radiation type.

Here, the first learning model may be a neural network model trained in advance to determine which solar radiation type the corresponding space belongs to among predetermined solar radiation types by inputting a load for each time period processed for temperature control of a certain space.

For example, the first learning model is trained in a supervised learning method through data on the load of the indoor unit in 11 representative spaces labeled with the solar type, and when the load data of the indoor unit is inputted, the space in which the indoor unit is installed among the 11 solar types. It may be a neural network model that can output where the solar type of

In another embodiment, the processor of the indoor unit 120 may determine the solar radiation time of the space in which the indoor unit 120 is installed by inputting the recorded load data into the second learning model.

Here, the second learning model may be a neural network model trained in advance to estimate a time period in which solar radiation is incident to a corresponding space by inputting a load for each time period processed for temperature control of a predetermined space.

For example, the second learning model is trained in a supervised learning method through data about the loads of a plurality of indoor units labeled with solar time, and when the load data of the indoor units is input, when is the insolation time that affects the space where the indoor units are installed? It may be a neural network model that can be output.

Through the initial setting of the above-described method, the solar time (eg, 12:00 to 4:00) of the space in which the indoor unit 120 is installed may be determined.

Thereafter, when the air conditioner starts to operate ( S100 ), the processor of the air conditioner may determine a current time section through the time check unit 123 ( S110 ).

The processor of the indoor unit 120 may determine whether the current time period is the period of the solar radiation time determined in the above initial setting, that is, whether the air conditioner is conditionally operated ( S120 ).

If the current time interval belongs to the conditional operation time (eg, between 12 o'clock and 4 o'clock), the processor of the indoor unit 120 uses a comfort index including the effect of radiant heat, unlike in a time other than the solar time, using the The set temperature can be adjusted.

In order to consider radiant heat, if the air conditioner has a radiant temperature sensor, the radiant temperature measured through the radiant temperature sensor can be used. If the radiant temperature sensor is not provided, the current indoor air temperature is used based on the following equation. The radiant temperature can be estimated.

Equation 1 for estimating the Mean Radian Temperature (MRT) is as follows, which is a temperature based on data measured from buildings in Seoul.

Here, T _air is the current indoor air temperature. The unit of I _sol is MJ/m ² , and it is information that can be obtained from the Meteorological Agency, etc. with the amount of insolation on the external horizontal plane, and can also be predicted through data measured by an outdoor unit.

PMV (Predicted Mean Vote) is the most commonly used comfort index. It is an index indicating comfort based on air temperature, radiant temperature, humidity, airflow, occupant clothing, and activity. It has a value between -3 and 3, and 0 is It represents the most comfortable state.

In general, PMV has a complicated calculation formula that includes humidity or airflow values, but here, a simple formula that can obtain PMV with the following Equation 2 is provided in order to explain the control formula as simply as possible.

According to Equation 2, a current PMV value in consideration of radiant heat may be calculated (S130).

It is determined whether the PMV is 0.5 or 0.8 or more according to the energy mode (S140), so that only the blowing operation is performed without changing the temperature (S150), or a set temperature to be changed can be calculated (S160).

The set temperature may be calculated through Equation 3 below using the difference between the current PMV and the target PMV (for example, it may be set to 0 in the case of prioritizing comfort performance, 0.5 in the case of prioritizing energy saving).

The processor of the indoor unit 120 may control the operation of the air conditioner by applying a set temperature adjusted in consideration of radiant heat ( S170 ).

Meanwhile, the PMV may also reflect wind speed and humidity, and accordingly, the rotation speed of the indoor unit fan may be adjusted or dehumidification or humidification control may be separately performed.

When time elapses and it is time for the next section (S180), the flowchart of FIG. 4 may be repeated again.

In the present disclosure, it is possible to control the air conditioner using the set temperature adjusted using the comfort index that can consider radiant heat, without using the set temperature in the general situation as above, within the time period where the influence of solar radiation is determined to be large. can

Meanwhile, in the above, the air conditioner is operated at the set temperature adjusted by reflecting the amount of solar radiation based on the current time, but the load due to the solar radiation may be reflected in advance.

In this case, receive the solar radiation forecast after one hour from the network connected to the outside, or obtain the predicted value for the next hour's solar radiation by using the solar radiation information obtained from the outdoor unit so that the air conditioner can preemptively respond to the effects of solar radiation. can do.

5 illustrates load graphs for each solar radiation type referenced to determine a solar radiation type of a space in which an indoor unit of the air conditioner is installed according to an embodiment of the present disclosure.

FIG. 5 shows the daily variation of Normalized Q based on data acquired from 18 sites across the country, and 11 graphs clustered from data from 18 sites across the country.

According to the peak shape of the Normalized Q value for each cluster, the group receiving sunlight in the morning (a, c, e, f, i, j), the group receiving solar radiation in the afternoon (d, k), and the peak of radiant heat all day do not occur. It can be divided into groups (b, g, h) that do not

If these clusters are used, the normalized Q value is obtained from the load data of the indoor unit for a certain period measured in the field, and by checking which group the indoor unit belongs to, it is determined whether the indoor unit is in the location where the solar radiation is incident, and when the solar radiation is incident. can judge

Such clustering may be performed through unsupervised learning, and by classification according to clustering, it is possible to determine which group the space in which the indoor unit to be measured is installed belongs to in advance.

Meanwhile, as in the above description, the method of controlling the air conditioner based on the amount of insolation may use a neural network model, which will be briefly described with reference to FIG. 6 .

6 is a diagram for describing a neural network model for determining a characteristic of a space in which an indoor unit of an air conditioner is installed according to an embodiment of the present disclosure.

In the neural network model, input data goes through layers consisting of an input layer, a hidden layer, and an output layer, and output data comes out. Various types of input data and output data are set in controlling the air conditioner based on the amount of insolation according to an embodiment of the present disclosure Thus, a neural network model can be used.

For example, the input data may be used by selecting at least some of indoor unit operation data, hourly indoor temperature, hourly processing load, and hourly indoor solar radiation.

The neural network model may be configured differently depending on what value is to be output as output data, and in controlling the air conditioner based on the amount of insolation according to the embodiment of the present disclosure, the indoor unit installation location, the comfort temperature for each hour, or whether the conditional operation is performed You can make it come out as an output value.

The memory 121 of the air conditioner may store a neural network model to which artificial intelligence technology is applied. For example, the neural network model to which artificial intelligence technology is applied may be combined with convolutional neural networks, adversarial generative neural networks, or other types of machine learning models. It may be a variety of learning models such as

Here, artificial intelligence (AI) is a field of computer engineering and information technology that studies how computers can do the thinking, learning, and self-development that can be done with human intelligence. It means being able to imitate intelligent behavior.

Also, AI does not exist by itself, but has many direct and indirect connections with other fields of computer science. In particular, in modern times, attempts are being made to introduce artificial intelligence elements in various fields of information technology and use them to solve problems in that field.

Machine learning is a branch of artificial intelligence, a field of study that gives computers the ability to learn without an explicit program.

Specifically, machine learning can be said to be a technology that studies and builds a system and an algorithm for learning based on empirical data, making predictions, and improving its own performance. Machine learning algorithms build specific models to make predictions or decisions based on input data, rather than executing strictly set static program instructions.

The term 'machine learning' may be used interchangeably with the term 'machine learning'.

With regard to how to classify data in machine learning, many machine learning algorithms have been developed. Decision trees, Bayesian networks, support vector machines (SVMs), and artificial neural networks (ANNs) are representative examples.

Decision tree is an analysis method that performs classification and prediction by charting decision rules in a tree structure.

The Bayesian network is a model that expresses the probabilistic relationship (conditional independence) between multiple variables in a graph structure. Bayesian networks are suitable for data mining through unsupervised learning.

The support vector machine is a model of supervised learning for pattern recognition and data analysis, and is mainly used for classification and regression analysis.

An artificial neural network is an information processing system in which a number of neurons called nodes or processing elements are connected in the form of a layer structure by modeling the operating principle of biological neurons and the connection relationship between neurons.

An artificial neural network is a model used in machine learning, a statistical learning algorithm inspired by neural networks in biology (especially the brain in the central nervous system of animals) in machine learning and cognitive science.

Specifically, the artificial neural network may refer to an overall model having problem-solving ability by changing the bonding strength of synapses through learning in which artificial neurons (nodes) formed a network by combining synapses.

The term artificial neural network may be used interchangeably with the term neural network.

The artificial neural network may include a plurality of layers, and each of the layers may include a plurality of neurons. Also, the artificial neural network may include neurons and synapses connecting neurons.

In general, artificial neural networks calculate the output value from the following three factors: (1) the connection pattern between neurons in different layers (2) the learning process that updates the weight of the connection (3) the weighted sum of the input received from the previous layer It can be defined by the activation function it creates.

The artificial neural network may include network models such as Deep Neural Network (DNN), Recurrent Neural Network (RNN), Bidirectional Recurrent Deep Neural Network (BRDNN), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN). , but not limited thereto.

In this specification, the term 'layer' may be used interchangeably with the term 'layer'.

Artificial neural networks are divided into single-layer neural networks and multi-layer neural networks according to the number of layers.

A typical single-layer neural network consists of an input layer and an output layer.

In addition, a general multilayer neural network consists of an input layer, one or more hidden layers, and an output layer.

The input layer is a layer that receives external data. The number of neurons in the input layer is the same as the number of input variables, and the hidden layer is located between the input layer and the output layer, receives a signal from the input layer, extracts characteristics, and transmits it to the output layer do. The output layer receives a signal from the hidden layer and outputs an output value based on the received signal. The input signal between neurons is multiplied by each connection strength (weight) and then summed. If the sum is greater than the threshold of the neuron, the neuron is activated and the output value obtained through the activation function is output.

Meanwhile, a deep neural network including a plurality of hidden layers between an input layer and an output layer may be a representative artificial neural network that implements deep learning, which is a type of machine learning technology.

Meanwhile, the term 'deep learning' may be used interchangeably with the term 'deep learning'.

The artificial neural network may be trained using training data. Here, learning refers to a process of determining parameters of an artificial neural network using learning data to achieve the purpose of classifying, regressing, or clustering input data. can As a representative example of parameters of an artificial neural network, a weight applied to a synapse or a bias applied to a neuron may be mentioned.

The artificial neural network learned by the training data may classify or cluster the input data according to a pattern of the input data.

Meanwhile, an artificial neural network trained using training data may be referred to as a training model in the present specification.

The following describes the learning method of the artificial neural network.

Learning methods of artificial neural networks can be broadly classified into supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.

Supervised learning is a method of machine learning for inferring a function from training data.

And among these inferred functions, outputting a continuous value is called regression, and predicting and outputting a class of an input vector can be called classification.

In supervised learning, an artificial neural network is trained in a state in which a label for training data is given.

Here, the label may mean a correct answer (or a result value) that the artificial neural network should infer when training data is input to the artificial neural network.

In the present specification, when training data is input, the correct answer (or result value) that the artificial neural network must infer is called a label or labeling data.

Also, in the present specification, setting a label on the training data for learning of the artificial neural network is called labeling the labeling data on the training data.

In this case, the training data and the label corresponding to the training data) constitute one training set, and may be input to the artificial neural network in the form of a training set.

On the other hand, training data represents a plurality of features, and labeling the training data may mean that the features represented by the training data are labeled. In this case, the training data may represent the features of the input object in a vector form.

The artificial neural network may infer a function for the relationship between the training data and the labeling data by using the training data and the labeling data. In addition, parameters of the artificial neural network may be determined (optimized) through evaluation of the function inferred from the artificial neural network.

Unsupervised learning is a type of machine learning where no labels are given to training data.

Specifically, the unsupervised learning may be a learning method for learning the artificial neural network to find and classify patterns in the training data itself, rather than the association between the training data and the labels corresponding to the training data.

Examples of unsupervised learning include clustering or independent component analysis.

In this specification, the term 'clustering' may be used interchangeably with the term 'clustering'.

Examples of artificial neural networks using unsupervised learning include a generative adversarial network (GAN) and an autoencoder (AE).

A generative adversarial neural network is a machine learning method in which two different artificial intelligences, a generator and a discriminator, compete to improve performance.

In this case, the generator is a model that creates new data, and can generate new data based on the original data.

In addition, the discriminator is a model for recognizing a pattern of data, and may play a role of discriminating whether input data is original data or new data generated by the generator.

And the generator learns by receiving the data that did not deceive the discriminator, and the discriminator can learn by receiving the deceived data from the generator. Accordingly, the generator can evolve to deceive the discriminator as best as possible, and the discriminator can evolve to distinguish the original data and the data generated by the generator well.

An autoencoder is a neural network that aims to reproduce the input itself as an output.

The auto-encoder includes an input layer, at least one hidden layer and an output layer.

In this case, since the number of nodes in the hidden layer is smaller than the number of nodes in the input layer, the dimension of data is reduced, and thus compression or encoding is performed.

Also, the data output from the hidden layer goes into the output layer. In this case, since the number of nodes in the output layer is greater than the number of nodes in the hidden layer, the dimension of data increases, and thus decompression or decoding is performed.

On the other hand, the auto-encoder controls the neuron's connection strength through learning, so that the input data is expressed as hidden layer data. The hidden layer expresses information with fewer neurons than the input layer, and being able to reproduce the input data as an output may mean that the hidden layer found and expressed hidden patterns from the input data.

Semi-supervised learning is a type of machine learning, and may refer to a learning method using both labeled and unlabeled training data.

As one of the techniques of semi-supervised learning, there is a technique of inferring a label of unlabeled training data and then performing learning using the inferred label. This technique can be useful when the cost of labeling is large. can

Reinforcement learning is the theory that, given the environment in which the agent can decide what action to take at every moment, it can find the best way through experience without data.

Reinforcement learning can be mainly performed by Markov Decision Process (MDP).

To explain the Markov decision process, first, an environment is given in which the information necessary for the agent to take the next action is given, secondly, how the agent behaves in that environment is defined, and thirdly, the agent is rewarded ( It gives a reward and defines a penalty point for failing to do so, and fourthly, the optimal policy is derived by repeating experiences until the future reward reaches the highest point.

The structure of an artificial neural network is specified by the model configuration, activation function, loss function or cost function, learning algorithm, optimization algorithm, etc., and hyperparameters are pre-trained. It is set, and then, a model parameter is set through learning and the content can be specified.

For example, factors determining the structure of the artificial neural network may include the number of hidden layers, the number of hidden nodes included in each hidden layer, an input feature vector, a target feature vector, and the like.

Hyperparameters include several parameters that must be initially set for learning, such as initial values of model parameters. And, the model parameter includes several parameters to be determined through learning.

For example, the hyperparameter may include an initial weight value between nodes, an initial bias value between nodes, a mini-batch size, a number of learning iterations, a learning rate, and the like. In addition, the model parameters may include inter-node weights, inter-node biases, and the like.

The loss function may be used as an index (reference) for determining the optimal model parameter in the learning process of the artificial neural network. In artificial neural networks, learning refers to the process of manipulating model parameters to reduce the loss function, and the purpose of learning can be seen to determine the model parameters that minimize the loss function.

The loss function may mainly use a mean squared error (MSE) or a cross entropy error (CEE), but the present disclosure is not limited thereto.

The cross-entropy error can be used when the correct answer label is one-hot encoded. One-hot encoding is an encoding method in which the correct label value is set to 1 only for neurons corresponding to the correct answer, and the correct answer label value is set to 0 for neurons that do not have the correct answer.

In machine learning or deep learning, a learning optimization algorithm can be used to minimize the loss function, and learning optimization algorithms include Gradient Descent (GD), Stochastic Gradient Descent (SGD), and Momentum. ), Nesterov Accelerate Gradient (NAG), Adagrad, AdaDelta, RMSProp, Adam, and Nadam.

Gradient descent is a technique that adjusts model parameters in the direction of reducing the loss function value by considering the gradient of the loss function in the current state.

The direction in which the model parameter is adjusted is referred to as a step direction, and the size to be adjusted is referred to as a step size.

In this case, the step size may mean a learning rate.

In the gradient descent method, a gradient may be obtained by partial differentiation of the loss function into each model parameter, and the model parameters may be updated by changing the learning rate in the obtained gradient direction.

The stochastic gradient descent method is a technique in which the frequency of gradient descent is increased by dividing the training data into mini-batch and performing gradient descent for each mini-batch.

Adagrad, AdaDelta, and RMSProp are techniques to increase optimization accuracy by adjusting the step size in SGD. In SGD, momentum and NAG are techniques to increase optimization accuracy by adjusting the step direction. Adam is a technique to increase optimization accuracy by adjusting the step size and step direction by combining momentum and RMSProp. Nadam is a technique to increase optimization accuracy by adjusting the step size and step direction by combining NAG and RMSProp.

The learning speed and accuracy of an artificial neural network have a characteristic that it largely depends on hyperparameters as well as the structure of the artificial neural network and the type of learning optimization algorithm. Therefore, in order to obtain a good learning model, it is important not only to determine an appropriate artificial neural network structure and learning algorithm, but also to set appropriate hyperparameters.

Typically, hyperparameters are experimentally set to various values to train an artificial neural network, and as a result of learning, they are set to optimal values that provide stable learning speed and accuracy.

The embodiment according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded in a computer-readable medium. In this case, the medium includes a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as CD-ROM and DVD, a magneto-optical medium such as a floppy disk, and a ROM. , RAM, flash memory, and the like, hardware devices specially configured to store and execute program instructions.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and used by those skilled in the computer software field. Examples of the computer program may include high-level language codes that can be executed by a computer using an interpreter as well as machine language codes such as those generated by a compiler.

In the specification of the present invention (especially in the claims), the use of the term "above" and similar referential terms may be used in both the singular and the plural. In addition, when a range is described in the present invention, each individual value constituting the range is described in the detailed description of the invention as including the invention to which individual values belonging to the range are applied (unless there is a description to the contrary). same as

The steps constituting the method according to the present invention may be performed in an appropriate order, unless there is an explicit order or description to the contrary. The present invention is not necessarily limited to the order in which the steps are described. The use of all examples or exemplary terms (eg, etc.) in the present invention is merely for the purpose of describing the present invention in detail, and unless defined by the claims, the scope of the present invention is limited by the examples or exemplary terminology. it's not going to be In addition, those skilled in the art will recognize that various modifications, combinations, and changes may be made in accordance with design conditions and factors within the scope of the appended claims or their equivalents.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the spirit of the present invention is not limited to the scope of the scope of the present invention. will be said to belong to

Claims (20)

An air conditioner controlled based on insolation, comprising:
a setting unit for setting an air conditioner operating condition including a set temperature;
a load measuring unit for measuring a load processed by the indoor unit of the air conditioner until a set temperature is reached;
a time check unit for checking a current time of a place where the indoor unit is installed; and
a control unit communicating with the setting unit, the load measuring unit, and the time check unit and controlling the operation of the air conditioner;
The control unit is
In order to reach the set temperature for a predetermined period, a solar time of the space in which the indoor unit is located is determined based on the load processed by the indoor unit, and within the solar time, a set temperature determination method different from other times is used. configured to adjust the set temperature;
air conditioner.
The method of claim 1,
The control unit is
extracting an effect of radiant heat based on data about a load processed by the indoor unit measured for the predetermined period, and determining a solar time of a space in which the indoor unit is located based on the extracted influence of radiant heat;
The effect of the radiant heat is calculated by excluding the amount of heat caused by internal heat generation of the space and the amount of heat lost through outer sheath conduction of the space from the load measured for the predetermined period of time,
air conditioner.
3. The method of claim 2,
The amount of heat lost in the sheath conduction is a value standardized based on a difference value between an air temperature of a room in which the indoor unit is located and an outdoor air temperature obtained from an outdoor unit of the air conditioner;
air conditioner.
3. The method of claim 2,
The amount of heat generated by the internal heating is a value standardized based on the rated capacity of the indoor unit,
How to control the air conditioner.
The method of claim 1,
The control unit is
and input data about the processing load measured for the predetermined period to a first learning model to determine a solar type of the space, and to determine a solar time of the space according to the determined solar type,
The first learning model is a neural network model trained in advance to determine which solar radiation type the space belongs to among predetermined solar radiation types by inputting a load for each time period processed for temperature control of a certain space.
air conditioner.
The method of claim 1,
The control unit is
determining the solar time of the space by inputting data about the processing load measured for the predetermined period to a second learning model;
The second learning model is a neural network model trained in advance to estimate the time period when solar radiation is incident in the space by inputting a load for each time period processed for temperature control of a certain space,
air conditioner.
The method of claim 1,
The method of determining the set temperature is,
It is a method of calculating an optimum temperature for optimizing a comfort index based on the radiation temperature of a space in which the indoor unit is located and adjusting the set temperature to the optimum temperature
air conditioner.
8. The method of claim 7,
Further comprising a communication unit for communicating with an external weather server,
The radiation temperature is estimated based on the measured indoor temperature and the external horizontal plane insolation obtained from the external weather server,
air conditioner.
8. The method of claim 7,
wherein the comfort index is a Predicted Mean Vote (PMV), and the comfort index is optimized when a value is 0,
air conditioner.
An air conditioner controlled based on insolation, comprising:
memory for storing instructions and code;
one or more processors coupled to the memory;
The memory, when executed by the processor, causes the processor to:
Measure and record the load processed by the indoor unit of the air conditioner to reach the set indoor temperature for a predetermined period,
extracting the effect of radiant heat based on the data about the load recorded for the predetermined period,
determining a solar time of a space in which the indoor unit is located based on the information on the effect of the extracted radiant heat;
Adjust the set temperature using the comfort index including the effect of radiant heat within the solar time,
storing a code causing the air conditioner to be controlled according to the adjusted set temperature;
air conditioner.
A method of controlling an air conditioner based on insolation, comprising:
measuring and recording a load processed by an indoor unit of the air conditioner to reach a set indoor temperature for a predetermined period;
extracting the effect of radiant heat based on the data on the load recorded for the predetermined period;
determining a solar radiation time of a space in which the indoor unit is located based on the extracted information on the influence of radiant heat;
adjusting a set temperature using a comfort index including the effect of radiant heat within the solar time; and
Including the step of controlling the air conditioner according to the adjusted set temperature,
How to control the air conditioner.
12. The method of claim 11,
The step of extracting the effect of the radiant heat,
excluding the amount of heat due to internal heat generation of the space and the amount of heat lost through outer sheath conduction of the space from the processing load measured for the predetermined period of time,
How to control the air conditioner.
13. The method of claim 12,
The amount of heat lost in the sheath conduction is a value standardized based on a difference value between an air temperature of a room in which the indoor unit is located and an outdoor air temperature obtained from an outdoor unit of the air conditioner;
How to control the air conditioner.
13. The method of claim 12,
The amount of heat generated by the internal heating is a value standardized based on the rated capacity of the indoor unit,
How to control the air conditioner.
12. The method of claim 11,
The step of determining the insolation time is,
determining the solar radiation type of the space by inputting the recorded data on the load into a first learning model; and
determining a solar radiation time of the space according to the solar radiation type;
The first learning model is a neural network model trained in advance to determine which solar radiation type the space belongs to among predetermined solar radiation types by inputting a load for each time period processed for temperature control of a certain space.
How to control the air conditioner.
12. The method of claim 11,
The step of determining the insolation time is,
determining the solar time of the space by inputting the data on the recorded load into a second learning model,
The second learning model is a neural network model trained in advance to estimate the time period when solar radiation is incident in the space by inputting a load for each time period processed for temperature control of a certain space,
How to control the air conditioner.
12. The method of claim 11,
The step of adjusting the set temperature is,
calculating an optimum temperature for optimizing the comfort index based on the radiant temperature of the space in which the indoor unit is located; and
Comprising the step of adjusting the set temperature to the optimum temperature,
How to control the air conditioner.
18. The method of claim 17,
Calculating the optimum temperature comprises:
obtaining an external horizontal plane insolation from an external weather server; and
Including the step of estimating the radiation temperature based on the measured indoor temperature and the external horizontal plane insolation,
How to control the air conditioner.
12. The method of claim 11,
The step of extracting the effect of the radiant heat,
calculating a leveled load value obtained by leveling the load measured by the indoor unit using the indoor unit capacity and the indoor/outdoor temperature difference during measurement; and
monitoring the change over time of the load value;
How to control the air conditioner.
A computer-readable recording medium having stored thereon a computer program configured to cause the computer to execute the method of any one of claims 11 to 19 when executed by a computer.

Images